Search Results

Manufacturer

Date Cleared

2023-07-07

(219 days)

Product Code

Regulation Number

Type

Panel

Reference & Predicate Devices

K213230

Intended Use

The T3 Platform™ software features the T3 Data Aggregation & Visualization software module version 5.0 and the T3 Risk Analytics Engine software module version 9.0.

To remotely consult regarding a patient's status, and
To remotely review other standard or critical near real-time patient data in order to aid in clinical decisions and deliver patient care in a timely manner.

The T3 Data Aggregation & Visualization software module can display numeric physiologic data captured by other medical devices:

· Airway flow, volume, and pressure
· Arterial blood pressure (invasive and non-invasive, systolic, diastolic, and mean)
Bispectral index (BIS, signal quality index, suppression ratio) .
Cardiac Index
Cardiac output .
Central venous pressure .
. Cerebral perfusion pressure
End-tidal CO2 .
· Heart rate
Heart rate variability .
Intracranial pressure .
. Left atrium pressure
Oxygen saturation (intravascular, regional, SpO2) .
Premature ventricular counted beats .
Pulmonary artery pressure (systolic, diastolic, and mean) .
Pulse pressure variation
· Pulse Rate
· Respiratory rate
Right atrium pressure .
Temperature (rectal, esophageal, tympanic, blood, core, nasopharyngeal, skin)
· Umbilical arterial pressure (systolic, diastolic, and mean)

The T3 Data Aggregation & Visualization software module can display laboratory measurements including arterial and venous blood gases, complete blood count, and lactic acid. T3 Data Aggregation & Visualization software module can display information captured by the T3 Risk Analytics Engine software module.

The T3 Risk Analytics Engine software module calculates four indices: the IDO2 Index™ for inadequate delivery of oxygen, the IVCO2 Index™ for inadequate ventilation of carbon dioxide, the ACD Index™ for acidemia, and the HLA Index™ for hyperlactatemia.

The IDO2 Index™ is indicated for use by health care professionals with post-surgical patients 0 to 12 years of age and weighing 2 kg or more under intensive care. The IDO2 Index™ is derived by mathematical manipulations of the physiologic data and laboratory measurements received by the T3 Data Aggregation & Visualization software module. When the IDO2 Index™ is increasing, it means that there is an increasing risk of inadequate oxygen delivery and attention should be brought to the patient. The IDO2 Index™ presents partial quantitative information about the patient's cardiovascular condition, and no therapy or drugs can be administered based solely on the interpretation statements.

The IVCO2 Index™ is indicated for use by health care professionals with invasively ventilated patients 0 to 12 years of age under intensive care. The IVCO2 Index™ is derived by mathematical manipulations of the physiologic data and laboratory measurements received by the T3 Data Aggregation and Visualization software module. When the IVCO2 Index™ is increasing, it means that there is an increasing risk of inadequate carbon dioxide ventilation and attention should be brought to the patient. The IVCO2 Index™ presents partial quantitative information about the patient's respiratory condition, and no therapy or drugs can be administered based solely on the interpretation statements.

The ACD Index™ is indicated for use by health care professionals with invasively ventilated patients 0 to 12 years of age and weighing 2 kg or more under intensive care. The ACD Index™ is derived by mathematical manipulations of the physiologic data and laboratory measurements received by the T3 Data Aggregation and Visualization software module. When the ACD Index™ is increasing, it means that there is an increasing risk of acidemia and attention should be brought to the patient. The ACD Index™ presents partial quantitative information about the patient's respiratory condition, and no therapy or drugs can be administered based solely on the interpretation statements.

The HLA Index™ is indicated for use by health care professionals with post-surgical patients 0 to 12 years of age and weighing 2 kg or more under intensive care. The HLA Index™ is derived by mathematical manipulations of the physiologic data and laboratory measurements received by the T3 Data Aggregation & Visualization software module. When the HLA Index™ is increasing, it means that there is an increasing risk of hyperlactatemia and attention should be brought to the patient. The HLA Index™ presents partial quantitative information about the patient's cardiovascular condition, and no therapy or drugs can be administered based solely on the interpretation statements.

Device Description

The Tracking, Trajectory, Trigger (73) intensive care unit software solution allows clinicians and quality improvement teams in the ICU to aggregate data from multiple sources, store it in a database for analysis, and view the streaming data. System features include:

Adjunctive status indicators ●
Customizable display of physiologic parameters over the entire patient stay
. Configurable annotation
Web-based visualization that may be used on any standard browser
Minimal IT footprint ●
Software-only solution no new bedside hardware required ●
Highly reliable and robust operation
. Auditable data storage

AI/ML Overview

The T3 Platform™ software calculates four indices: the IDO2 Index™ for inadequate delivery of oxygen, the IVCO2 Index™ for inadequate ventilation of carbon dioxide, the ACD Index™ for acidemia, and the HLA Index™ for hyperlactatemia. The document specifies that studies were performed to validate the IVCO2 Index.

Here's an analysis of the acceptance criteria and study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document explicitly states that the acceptance criteria for the IVCO2 Index™ are: discriminatory power, range utilization, resolution/limitation, and robustness. It is stated that "All results met the same acceptance criteria as the predicate device".

However, specific quantitative values for these criteria (e.g., a specific threshold for discriminatory power, or a defined range utilization percentage) and the exact performance metrics obtained are not provided in the given text. The document confirms that the device met these criteria without detailing the quantitative results of the performance.

2. Sample Size Used for the Test Set and Data Provenance

Test Set 1 (Neonatal ICU patients):
- Sample Size: 180 patients, contributing 1108 PaCO2 measurements from arterial blood gases.
- Data Provenance: Retrospective, obtained from two Level IV regional NICUs in the US.
Test Set 2 (Non-NICU patients):
- Sample Size: 2090 patients, contributing 29,841 PaCO2 measurements from arterial blood gases.
- Data Provenance: Retrospective, from clinical sites in the US.
- Demographics: 42% neonates, 32% infants, and 26% children. 46% female and 54% male.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications

The document does not specify the number of experts or their qualifications used to establish the ground truth for the test set. It mentions "PaCO2 measurements from arterial blood gases," which implies that the ground truth was based on laboratory measurements rather than expert review.

4. Adjudication Method for the Test Set

The document does not mention an adjudication method for the test set. Given that the ground truth appears to be objective laboratory measurements (PaCO2 from arterial blood gases) and not subjective expert interpretations, a traditional adjudication process (like 2+1 or 3+1) would not be applicable or necessary.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No MRMC comparative effectiveness study was mentioned. The study described focuses on the device's performance against objective physiological measurements, not on its impact on human reader performance.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

Yes, a standalone performance study was done. The IVCO2 Index™ was "retrospectively computed on all de-identified patients" and "evaluated against the same acceptance criteria as the predicate device." This indicates an algorithm-only evaluation, without human-in-the-loop assistance.

7. Type of Ground Truth Used

The ground truth used was objective physiological data/laboratory measurements, specifically PaCO2 measurements from arterial blood gases.

8. Sample Size for the Training Set

The document mentions "Development test sets are used to evaluate the impact of the development changes during the development process." However, it does not specify the sample size for the training set(s) used to develop the IVCO2 Index™ model. It only provides details for the validation sets.

9. How the Ground Truth for the Training Set Was Established

The document states that the "adjunctive status indicators are produced by a model-based approach. The model-based approach is designed based on principles of physiology with parameters chosen to reflect those specified in the medical literature." It does not explicitly detail how ground truth was established for the training data beyond implying it was based on physiological principles and medical literature, and presumably also included patient data similar to the validation sets.

Ask a Question

Ask a specific question about this device

K Number

K213423

Device Name

Manufacturer

Etiometry. Inc.

Date Cleared

2023-01-06

(443 days)

Product Code

Regulation Number

Type

Panel

Reference & Predicate Devices

K213230

Intended Use

The T3 Platform™ software features the T3 Data Aggregation & Visualization software module version 5.0 and the T3 Adult Risk Analytics Engine software module version 1.0.

. To remotely consult regarding a patient's status, and
To remotely review other standard or critical near real-time patient data in order to aid in . clinical decisions and deliver patient care in a timely manner.

The T3 Data Aggregation & Visualization software module can display numeric physiologic data captured by other medical devices:

· Airway flow, volume, and pressure
· Arterial blood pressure (invasive and non-invasive, systolic, diastolic, and mean)
· Bispectral index (BIS, signal quality index, suppression ratio)
· Cardiac Index
. Cardiac output
Central venous pressure .
. Cerebral perfusion pressure
· End-tidal CO2
· Heart rate
· Heart rate variability
Intracranial pressure .
. Left atrium pressure
Oxygen saturation (intravascular, regional, SpO2) .
· Premature ventricular counted beats
· Pulmonary artery pressure (systolic, diastolic, and mean)
· Pulse pressure variation
· Pulse Rate
· Respiratory rate
· Right atrium pressure
· Temperature (rectal, esophageal, tympanic, blood, core, nasopharyngeal, skin)
· Umbilical arterial pressure (systolic, diastolic, and mean)

The T3 Data Aggregation & Visualization software module can display laboratory measurements including arterial and venous blood gases, complete blood count, and lactic acid.

The T3 Data Aggregation & Visualization software module can display information captured by the T3 Adult Risk Analytics Engine software module.

The T3 Adult Risk Analytics Engine software module calculates the Adult IDO2 Index for inadequate delivery of oxygen. The Adult IDO2 Index is indicated for use by health care professionals with post-surgical patients 18 years of age or older under intensive care and not on Mechanical Circulatory Support. The Adult IDO2 Index is derived by mathematical manipulations of the physiologic data and laboratory measurements received by the T3 Data Aggregation & Visualization software module. When the Adult IDO2 Index is increasing, it means that there is an increasing risk of madequate oxygen delivery and attention should be brought to the patient. The Adult IDO2 Index presents partial quantitative information about the patient's cardiovascular condition, and no therapy or drugs can be administered based solely on the interpretation statements.

Device Description

· Customizable display of physiologic parameters over entire patient stay
Configurable annotation
Web-based visualization that may be used on any standard browser
Minimal IT footprint
Software-only solution no new bedside hardware required
Highly reliable and robust operation
Auditable data storage

AI/ML Overview

Here's a breakdown of the acceptance criteria and study details for the T3 Platform™ software:

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criteria	Reported Device Performance
Discriminatory Power	Met acceptance criteria
Range Utilization	Met acceptance criteria
Resolution/Limitation	Met acceptance criteria
Robustness	Met acceptance criteria

2. Sample Size and Data Provenance for Test Set

Sample Size: 4251 mixed venous oxygen saturation measurements from 634 patients.
Data Provenance: Clinical data from different clinical sites in the US (retrospective). The data were obtained by the T3 Platform software and were de-identified.

3. Number of Experts and Qualifications for Ground Truth Establishment (Test Set)

This information is not explicitly provided in the document. The document states that the Adult IDO2 Index was "retrospectively computed on all de-identified patients" and "evaluated against the same acceptance criteria as the supportive predicate device," implying an objective ground truth related to mixed venous oxygen saturation, but not explicitly stating an expert consensus process for the test set.

4. Adjudication Method for Test Set

This information is not explicitly provided in the document. The evaluation was against objective acceptance criteria and not described as involving human adjudication.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

A multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly mentioned for this device. The study focused on the standalone performance of the Adult IDO2 Index against established acceptance criteria.

6. Standalone Performance Study

Yes, a standalone study was done. The Adult IDO2 Index algorithm's performance was validated using clinical datasets.

7. Type of Ground Truth Used

The ground truth used was based on mixed venous oxygen saturation measurements, a physiological parameter that the Adult IDO2 Index aims to reflect (likelihood of inadequate delivery of oxygen, specifically defined as mixed venous oxygen saturation below a threshold of 50%).

8. Sample Size for Training Set

The document does not explicitly state the sample size used for the training set. It mentions that the Adult Risk Analytics Engine version 1.0 employs the "same model of human physiology as the one utilized in Risk Analytics Engine version 8.0 cleared under K213230 for the computation of the IDO2 index in pediatric patients (0 to 12 years of age), however, the physiology model has been modified to extend the age-based parameterization." This suggests that a previous model was adapted, but details of the original or updated training data size are not provided.

9. How Ground Truth for Training Set Was Established

The document does not explicitly describe how the ground truth for the training set was established. It states that the Adult Risk Analytics Engine version 1.0 "employs the same model of human physiology" as its predecessor, which was "modified to extend the age-based parameterization." This implies the model was developed based on physiological principles and likely validated against clinical data that included mixed venous oxygen saturation measurements. However, the specific process for establishing ground truth during the training phase is not detailed.

Ask a Question

Ask a specific question about this device

K Number

K213230

Device Name

T3 Platform Software

Manufacturer

Date Cleared

2022-06-22

(266 days)

Product Code

Regulation Number

Type

Panel

Reference & Predicate Devices

K202306

Intended Use

The T3 Platform™ software features the T3 Data Aggregation & Visualization software module version 5.0 and the T3 Risk Analytics Engine software module version 8.0.

To remotely consult regarding a patient's status, and
To remotely review other standard or critical near real-time patient data in order to aid in clinical decisions and deliver patient care in a timely manner.

The T3 Data Aggregation & Visualization software module can display numeric physiologic data captured by other medical devices:

Airway flow, volume, and pressure
Arterial blood pressure (invasive and non-invasive, systolic, diastolic, and mean)
Bispectral index (BIS, signal quality index, suppression ratio) .
Cardiac Index
. Cardiac output
Central venous pressure .
. Cerebral perfusion pressure
End-tidal CO2 .
· Heart rate
Heart rate variability .
Intracranial pressure .
. Left atrium pressure
Oxygen saturation (intravascular, regional, SpO2) .
Premature ventricular counted beats .
· Pulmonary artery pressure (systolic, diastolic, and mean)
Pulse pressure variation
· Pulse Rate
· Respiratory rate
Right atrium pressure .
Temperature (rectal, esophageal, tympanic, blood, core, nasopharyngeal, skin)
· Umbilical arterial pressure (systolic, diastolic, and mean)

The IVCO2 Index™ is indicated for use by health care professionals with invasively ventilated patients 0 to 12 years of age and weighing 2 kg or more under intensive care. The IVCO2 Index™ is derived by mathematical manipulations of the physiologic data and laboratory measurements received by the T3 Data Aggregation and Visualization software module. When the IVCO2 Index™ is increasing, it means that there is an increasing risk of inadequate carbon dioxide ventilation and attention should be brought to the IVCO2 Index™ presents partial quantitative information about the patient's respiratory condition, and no therapy or drugs can be administered based solely on the internets.

The HLA Index™ is indicated for use by health care professionals with post-surgical patients 0 to 12 years of age and weighing 2 kg or more under intensive care. The HLA Index™ is derived by mathematical manipulations of the physiologic data and laboratory measurements received by the T3 Data Aggregation & Visualization software module. When the HLA Index™ is increasing, it means that there is an increasing risk of hyperlactaternia and attention should be brought to the patient. The HLA Index™ presents partial quantitative information about the patient's cardiovascular condition, and no therapy or drugs can be administered based solely on the interpretation statements.

Device Description

Adjunctive status indicators
Customizable display of physiologic parameters over entire patient stay
Configurable annotation
Web-based visualization that may be used on any standard browser
Minimal IT footprint
Software-only solution no new bedside hardware required
Highly reliable and robust operation
Auditable data storage

AI/ML Overview

Here's an analysis of the acceptance criteria and study proving the device meets those criteria, based on the provided text:

Device: T3 Platform™ software (specifically the T3 Risk Analytics Engine software module version 8.0, which calculates the IDO2 Index™, IVCO2 Index™, ACD Index™, and HLA Index™).

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are broadly defined as "discriminatory power, range utilization, resolution/limitation, and robustness." While specific numerical thresholds for these criteria are not provided in the document, the conclusion states that "All results met acceptance criteria for discriminatory power, range utilization, resolution/limitation, and robustness."

Acceptance Criteria	Reported Device Performance
Discriminatory Power	Met acceptance criteria (all indices)
Range Utilization	Met acceptance criteria (all indices)
Resolution/Limitation	Met acceptance criteria (all indices)
Robustness	Met acceptance criteria (all indices)

2. Sample Size Used for the Test Set and Data Provenance

The document provides sample sizes for the validation of the new indices (ACD and HLA Indexes):

HLA Index Validation: 58,168 whole blood lactate measurements from 3,496 patients.
ACD Index Validation: 24,431 arterial blood pH measurements from 1,858 patients.

Data Provenance:

Country of Origin: United States (data from eleven different clinical sites in the US).
Retrospective or Prospective: Retrospectively computed on all de-identified patients.

3. Number of Experts Used to Establish Ground Truth and Qualifications

The document does not specify the number of experts or their qualifications used to establish the ground truth for the test set. It states that the indices are "derived by mathematical manipulations of the physiologic data and laboratory measurements" and that the "underlying physiology model" for the indices has been updated. The ground truth for the ACD Index is defined as "arterial pH less than 7.25" and for the HLA Index as "whole blood lactate level concentration above 4 mmol / L." These appear to be objective thresholds based on laboratory measurements rather than expert consensus on interpretations of images or complex clinical states.

4. Adjudication Method for the Test Set

No adjudication method (e.g., 2+1, 3+1) is mentioned or appears to be relevant given the nature of the ground truth (objective laboratory measurements).

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No MRMC study was done, as the device is a risk analytics engine providing calculated indices, not an imaging AI designed to assist human readers in interpreting medical images. The primary use is for "remotely consult regarding a patient's status" and "remotely review other standard or critical near real-time patient data in order to aid in clinical decisions and deliver patient care." The indices provide "partial quantitative information" and "no therapy or drugs can be administered based solely on the interpretation statements." Furthermore, the warnings state: "Do not rely on the T3 Platform software as the sole source of patient status information." This indicates an adjunctive role rather than one where human interpretation is directly assisted in a comparative effectiveness study.

6. Standalone (Algorithm Only) Performance Study

Yes, the validation of the ACD Index and HLA Index appears to be a standalone (algorithm only) performance study against objective ground truth derived from laboratory measurements. The indices were "retrospectively computed on all de-identified patients" and evaluated against the defined acceptance criteria.

7. Type of Ground Truth Used

The ground truth used is primarily outcomes data / objective laboratory measurements.

For the ACD Index: Arterial blood pH measurements, with acidemia defined as arterial pH less than 7.25.
For the HLA Index: Whole blood lactate measurements, with hyperlactatemia defined as whole blood lactate level concentration above 4 mmol/L.

8. Sample Size for the Training Set

The document does not explicitly state the sample size for a dedicated "training set." It mentions that the "approach is designed based on principles of physiology, and parameters are chosen to reflect those specified in the medical literature and employed development testing data sets and validation sets." It distinguishes between "Development testing sets" (used to evaluate impact of changes during development) and "Validation sets" (used after development is complete). The sample sizes provided (3,496 patients for HLA, 1,858 patients for ACD) are for the validation sets. The size of the "development testing sets" is not specified.

9. How Ground Truth for the Training Set Was Established

The document implies that the model's development and parameter choices were guided by "principles of physiology" and "medical literature," which would have formed the basis for the ground truth during the development ("training") phase. For the actual performance testing, the ground truth was established by objective laboratory measurements (arterial pH and whole blood lactate levels) with pre-defined thresholds for acidemia and hyperlactatemia. The details of how ground truth was precisely established for the "development testing data sets" are not explicitly detailed, but it would logically follow the same principles of using objective physiological and laboratory data.

Ask a Question

Ask a specific question about this device

K Number

K202306

Device Name

Manufacturer

Date Cleared

2020-11-25

(103 days)

Product Code

Regulation Number

Type

Panel

Reference & Predicate Devices

K190273

Intended Use

The T3 Data Aggregation & Visualization software module is intended for the recording and display of multiple physiological parameters of the adult, pediatric, and neonatal patients from supported bedside devices. The software module is not intended for alarm notification or waveform display, nor is it intended to control any of the independent bedside devices to which it is connected. The software module is intended to be used by healthcare professionals for the following purposes: To remotely consult regarding a patient's status, and To remotely review other standard or critical near real-time patient data in order to aid in clinical decisions and deliver patient care in a timely manner.

The T3 Data Aggregation & Visualization software module can display numeric physiologic data captured by other medical devices: Airway flow, volume, and pressure Arterial blood pressure (invasive and non-invasive, systolic, diastolic, and mean) Bispectral index (BIS, signal quality index, suppression ratio) Cardiac Index Cardiac output Central venous pressure Cerebral perfusion pressure End-tidal CO2 Heart rate Heart rate variability Intracranial pressure Left atrium pressure Oxygen saturation (intravascular, regional, SpO2) Premature ventricular counted beats Pulmonary artery pressure (systolic, diastolic, and mean) Pulse pressure variation Pulse Rate Respiratory rate Right atrium pressure Temperature (rectal, esophageal, tympanic, blood, core, nasopharyngeal, skin) Umbilical arterial pressure (systolic, diastolic, and mean)

The T3 Data Aggregation & Visualization software module can display laboratory measurements including arterial and venous blood gases, complete blood count, and lactic acid.

T3 Data Aggregation & Visualization software module can display information captured by the T3 Risk Analytics Engine software module.

The T3 Risk Analytics Engine software module calculates two indices: the IDO2 Index™ for inadequate delivery of oxygen and the IVCO2 Index™ for inadequate ventilation of carbon dioxide.

IDO2 Index™ is indicated for use by health care professionals with post-surgical patients aged zero days to twelve years weighing 2 kg or more under intensive care. IDO2 Index™ is derived by mathematical manipulations of the physiologic data and laboratory measurements received by the T3 Data Aggregation & Visualization software module, version 5.0 or higher. When the IDO2 Index™ is increasing, it means that there is an increasing risk of inadequate oxygen delivery and attention should be brought to the IDO2 Index™ presents partial quantitative information about the patient's cardiovascular condition, and no therapy or drugs can be administered based solely on the interpretation statements.

IVCO2 Index™ is indicated for use by health care professionals with invasively ventilated patients aged 29 days to 12 years weighing 2 kg or more under intensive care. IVCO2 Index™ is derived by mathematical manipulations of the physiologic data and laboratory measurements received by the T3 Data Aggregation and Visualization software module, version 5.0 or higher. When the IVCO2 Index™ is increasing, it means that there is an increasing risk of inadequate carbon dioxide ventilation and attention should be brought to the IVCO2 Index™ presents partial quantitative information about the patient's respiratory condition, and no therapy or drugs can be administered based solely on the interpretation statements.

Device Description

The Tracking, Trajectory, Trigger (T3) intensive care unit software solution allows clinicians and quality improvement teams in the ICU to aggregate data from multiple sources, store it in a database for analysis, and view the streaming data. System features include: Customizable display of physiologic parameters over entire patient stay, Configurable annotation, Web-based visualization that may be used on any standard browser, Minimal IT footprint, Software-only solution - no new bedside hardware required, Highly reliable and robust operation, Auditable data storage.

AI/ML Overview

The provided text is a 510(k) summary for the Etiometry T3 Platform™ software. It describes the device, its intended use, and a comparison to a predicate device, focusing on changes made since the prior clearance. However, it does not contain the detailed acceptance criteria or the specifics of a study proving the device meets those criteria, especially in the context of an AI/ML device.

The document states: "The changes to the algorithm were validated using clinical data sets. The software verification and validation testing were conducted for the subject device, and documentation was provided in accordance with FDA's 'Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices', May 11, 2005." This indicates that some validation was performed, but the specific metrics, methodologies, and results that would constitute "acceptance criteria" and "detailed performance study" for an AI/ML algorithm are not included in this publicly available summary.

The device includes an "T3 Risk Analytics Engine software module" which calculates two indices: the IDO2 Index™ and the IVCO2 Index™. These are described as being derived by "mathematical manipulations of the physiologic data and laboratory measurements" and they provide "partial quantitative information about the patient's cardiovascular condition" or "respiratory condition." While these are algorithmic calculations, the document does not present them as a typical AI/ML system that would require a ground truth study with human expert readers for "acceptance criteria" based on metrics like sensitivity, specificity, or AUC, as is common for diagnostic AI.

Therefore,Based on the provided text, I cannot extract the specific information requested in your prompt regarding acceptance criteria and a study that proves the device meets them, especially in the context of AI/ML performance. The document focuses on showing substantial equivalence to a predicate device via comparative technological characteristics and a general statement of software verification and validation. It does not contain the detailed breakdown of the
AI/ML specific performance study as requested.

Here's a breakdown of why each point cannot be robustly addressed from the text:

A table of acceptance criteria and the reported device performance: Not provided. The document states "The performance of the IDO2 Index™ was evaluated with and without regional oximetry to confirm the utility of the measurement as an input," but no specific performance metrics or acceptance criteria are listed.
Sample sizes used for the test set and the data provenance: Not mentioned. It only states "validated using clinical data sets."
Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not mentioned. The ground truth method is not explicitly detailed beyond the indices being "derived by mathematical manipulations of the physiologic data and laboratory measurements."
Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not mentioned.
If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: Not mentioned. The IDO2 and IVCO2 indices are described as providing "partial quantitative information" and not something on which therapy or drugs can be administered solely. There is no indication of a human-in-the-loop study to demonstrate improvement.
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The indices are calculated by the software ("algorithm only"), but the performance metrics for these calculations (e.g., accuracy against a gold standard for the derived "risk") are not presented.
The type of ground truth used (expert consensus, pathology, outcomes data, etc.): The indices are mathematically derived from physiological data and lab measurements. The "ground truth" for these indices would likely be the accurate calculation based on these inputs, or potentially a correlation with actual patient outcomes (though no such correlation study is detailed here). The text mentions the indices represent "increasing risk of inadequate oxygen delivery" or "inadequate carbon dioxide ventilation," but how this "risk" itself is ground-truthed is not explained.
The sample size for the training set: Not mentioned.
How the ground truth for the training set was established: Not mentioned.

In summary, the provided FDA 510(k) summary focuses on demonstrating substantial equivalence based on the device's intended use and technological characteristics compared to a previously cleared predicate and generalized statements of V&V. It does not provide the specific performance study details, particularly those related to acceptance criteria, ground truth establishment, and reader studies that are typically associated with AI/ML devices making diagnostic assertions.

Ask a Question

Ask a specific question about this device

K Number

K190273

Device Name

Manufacturer

Date Cleared

2019-12-08

(303 days)

Product Code

Regulation Number

Type

Panel

Reference & Predicate Devices

K163065

Intended Use

The T3 Data Aggregation & Visualization software module is intended for the recording and display of multiple physiological parameters of the adult, pediatric, and neonatal patients from supported bedside devices. The software module is not intended for alarm notification or waveform display, nor is it intended to control any of the independent bedside devices to which it is connected. The software module is intended to be used by healthcare professionals for the following purposes:
· To remotely consult regarding a patient's status, and
• To remotely review other standard or critical near real-time patient data in order to aid in clinical decisions and deliver patient care in a timely manner.

The T3 Data Aggregation & Visualization software module can display numeric physiologic data captured by other medical devices:

· Airway flow, volume, and pressure
· Arterial blood pressure (invasive and non-invasive, systolic, diastolic, and mean)
· Bispectral index (BIS, signal quality index, suppression ratio)
Cardiac Index
Cardiac output
Central venous pressure
· Cerebral perfusion pressure
· End-tidal CO2
· Heart rate
· Heart rate variability
· Intracranial pressure
Left atrium pressure
· Oxygen saturation (intravascular, regional, SpO2)
· Premature ventricular counted beats
· Pulmonary artery pressure (systolic, diastolic, and mean)
· Pulse pressure variation
· Pulse Rate
· Respiratory rate
· Right atrium pressure
· Temperature (rectal, esophageal, tympanic, blood, core, nasopharyngeal, skin)
· Umbilical arterial pressure (systolic, diastolic, and mean)

The T3 Data Aggregation & Visualization software module can display laboratory measurements including arterial and venous blood gases, complete blood count, and lactic acid.

The T3 Data Aggregation & Visualization software module can display information captured by the T3 Risk Analytics Engine software module.

The T3 Risk Analytics Engine software module calculates two indices: the IDO2 Index™ for inadequate delivery of oxygen and the IVCO2 Index™ for inadequate ventilation of carbon dioxide.

IDO2 Index™ is indicated for use by health care professionals with post-surgical patients aged zero days to twelve years weighing 2 kg or more under intensive care. IDO2 Index™ is derived by mathematical manipulations of the physiologic data and laboratory measurements received by the T3 Data Aggregation & Visualization software module, version 3.3 or higher. When the IDO2 Index™ is elevated. it means that there is an increased risk of inadequate oxygen delivery and attention should be brought to the IDO2 Index™ presents partial quantitative information about the patient's cardiovascular condition, and no therapy or drugs can be administered based solely on the interpretation statements.

IVCO2 Index™ is indicated for use by health care professionals with invasively ventilated patients aged 29 days to 12 years weighing 2 kg or more under intensive care. IVCO2 Index™ is derived by mathematical manipulations of the physiologic data and laboratory measurements received by the T3 Data Aggregation and Visualization software module, version 3.3 or higher. When the IVCO2 Index™ is increasing, it means that there is an increasing risk of inadequate carbon dioxide ventilation and attention should be brought to the patient.

Device Description

Customizable display of physiologic parameters over entire patient stay
Configurable annotation
Web-based visualization that may be used on any standard browser ●
. Minimal IT footprint
Software-only solution no new bedside hardware required .
. Highly reliable and robust operation
Auditable data storage

This release of the T3 Platform Software contains the following software module changes:

T3 Risk Analytics Engine software module version 5.0

IVCO2 Index™. The subject device is a modification of the T3 Platform software clearance under K163065 that expands the Indications for Use for inadequate ventilation of carbon dioxide index (IVCO2 Index™). The IVCO2 Index™ calculates a patient status index. This is a measure of the likelihood that an arterial blood gas measurement of carbon dioxide would indicate a partial pressure greater than 50 mmHg.
Minor changes to maintain the performance of the IDO2 Index™ when external factors exist. Minor changes to the IDO2 Index™ have been made to maintain the specified performance of the IDO2 Index™ when variations in external factors exist. Specifically, these included changes in the initialization routine to ensure that the algorithm converges to stable behavior within the required time window, and changes in the artifact rejection logic of noninvasive blood pressure measurements to ensure that these measurements are not ignored when only minimum data is available thus providing required minimum data performance.

T3 Data Aggregation & Visualization software module version 3.3

Index Displayed on Census View. IDO2 Index™ and the IVCO2 Index™ are not displayed on the Census View and the requirement was removed.
Blackout. To mitigate potential misuse of active patient monitoring with Persistent Displays in the ICU, the IDO2 Index™ and the IVCO2 Index™ are blacked out in the near-real-time, a warning label is placed above the Index, and a user is prompted to acknowledge warnings when selecting an Index to be graphed.
Measure synonyms. Certain measures, while not identical to each other, are nevertheless closely related and can be thought of as "synonyms" for each other. For example, "Temp" (Generic Temperature), "Tairwy" (Airway Temperature), "Tesoph" (Esophogeal Temperature), and "Ttymp" (Tympanic Temperature) are all measures of the patient's temperature. In this example, the measure synonym feature would allow T3 Data Aggregation & Visualization software module to continuously report a value for "Temperature" based on whatever values were being received for Temp, Tairwy, Tesoph and/or Ttymp. The raw (source) variables continue to be available to be seen or graphed. In addition, this feature includes an "explain" function that allows the clinician to examine measure synonyms to see the source of the displayed data value at each moment in time.
Respiratory View. T3 Data Aggregation & Visualization software module now includes a screen that displays measures and laboratory results related to the patient's respiratory system. This predefined arrangement, accessed by clicking on the "Respiratory" tab beside the previously released "Hemodynamic" view, saves the clinician the time and effort of graphing these laboratory data and measures in order to understand the status and trend of the patient's respiratory system. The respiratory view includes Smart Visualization Groups that show measures and labs related to respiratory rate, ventilation pressure, respiratory volume, oxygenation, and ventilation.
Placement of IDO2 at the top of the Patient View. In the T3 Data Aggregation & Visualization software module, the display canvas for IDO2 Index™ has been moved to the top of the Patient View.
Current measure value is shown on the graph instead of the legend. When the user positions the mouse cursor in the central graph area, T3 Data Aggregation & Visualization software module displays the value of all graphed measures for the time corresponding to the cursor location. Previous releases of T3 Data Aggregation & Visualization software module displayed this information on the legend (the label for each measure or laboratory result that is shown to the left of the graph area). This release of T3 Data Aggregation & Visualization software module instead shows the value beside a light vertical line that is drawn at the mouse cursor position. This moves the information closer to the user's focus of attention (the mouse cursor).
Ability to receive and merge multiple data interfaces of the same type. T3 Data Aggregation & Visualization software module currently receives three types of data interfaces: patient registration (ADT), laboratory results, and physiometric data. This release allows T3 Data Aggregation & Visualization software module to receive and merge data interfaces of the same type coming from two or more sources. For example, a physiometric data interface for beds from a particular floor of the hospital can now be merged with a separate physiometric data interface with beds from a different floor or unit. This feature allows clinicians to view collections of beds that correspond to patient care trajectories such as the operating room and recovery unit, or intensive care and step-down unit.
Ability to receive data through SQL relational database query. Previous releases of T3 Data Aggregation & Visualization software module received data exclusively through HL7-based data interfaces. However, depending on a hospital's IT infrastructure, data from peripheral devices like ventilators may be sent to the hospital electronic medical record but not broadcast through an HL7 data interface. This release of T3 Data Aggregation & Visualization software module retains its HL7 functionality, but also supplements it with the ability to simultaneously receive other data through periodic SQL relational database queries. (SQL, structured query language, is the ANSI standard language for relational database management systems). For example, T3 Data Aggregation & Visualization software module can query a hospital database periodically to read validated ventilator values that are not otherwise transmitted through HL7 data interfaces, while simultaneously receiving device and lab data through HL7.
Support for an expanded number of beds. This release of T3 Platform software of T3 web server to support up to 128 intensive-care beds. Previously an instance of T3 web server could only support 30 intensive-care beds. The server-side hardware requirements have been modified to request additional hard disk space for T3 web server to support more beds.

AI/ML Overview

The T3 Platform software (T3 Data Aggregation & Visualization software module version 3.3 and T3 Risk Analytics Engine software module version 5.0) was evaluated for its IVCO2 Index™ for inadequate ventilation of carbon dioxide.

1. Table of Acceptance Criteria and Reported Device Performance (Focus on IVCO2 Index™):

The document does not explicitly state quantitative acceptance criteria for the IVCO2 Index™ performance. However, it states the index's ability to "correctly discriminate the physiologic state of inadequate ventilation of carbon dioxide though its whole range" and its robustness "against different data availability" was validated. The reported performance is that the validation study demonstrated this ability.

Acceptance Criteria (Inferred from study description)	Reported Device Performance
Ability to correctly discriminate the physiologic state of inadequate ventilation of carbon dioxide through its whole range.	The IVCO2 Index™ was validated retrospectively on clinical data and demonstrated its ability to correctly discriminate the physiologic state of inadequate ventilation of carbon dioxide through its whole range.
Robustness against different data availability.	The IVCO2 Index™ was validated retrospectively on clinical data and demonstrated its robustness against different data availability.

2. Sample Size and Data Provenance for Test Set:

Sample Size: 951 patients.
Data Provenance: The data was clinical data gathered in the intended patient population, implying it's from a healthcare setting. The document does not specify a country of origin. The study was retrospective.

3. Number of Experts and Qualifications for Ground Truth:

The document does not specify the number or qualifications of experts used to establish the ground truth.

4. Adjudication Method for Test Set:

The document does not describe an adjudication method for the test set.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not reported in this document. The focus of the validation was on the algorithm's standalone performance against a clinical gold standard.

6. Standalone Performance Study:

Yes, a standalone study of the algorithm's performance (without human-in-the-loop) was done. The IVCO2 Index™ was retrospectively computed on patient data and validated against a gold standard.

7. Type of Ground Truth Used:

The ground truth used was arterial blood gases.

8. Sample Size for Training Set:

The document does not specify a separate sample size for a training set. The descriptions focus on the validation study using clinical data.

9. How Ground Truth for Training Set Was Established:

The document does not provide information on how ground truth was established for a training set, as a specific training set size is not mentioned. For the validation set, the ground truth was established using arterial blood gases.

Ask a Question

Ask a specific question about this device

K Number

K163065

Device Name

Manufacturer

ETIOMETRY, INC.

Date Cleared

2017-05-26

(205 days)

Product Code

Regulation Number

Type

Panel

Reference & Predicate Devices

K152258

Intended Use

The T3 Software is intended for the recording and display of multiple physiological parameters of adult, pediatric and neonatal patients from supported bedside devices. T3 is not intended for alarm notification or waveform display, nor is it intended to control any of the independent bedside devices to which it is connected. T3 is intended to be used by healthcare professionals for the following purposes:

To remotely consult regarding a patient's status, and
To remotely review other standard or critical near real-time patient data in order to aid in clinical decisions and deliver patient care in a timely manner.

T3 can display numeric physiologic data captured by other medical devices:

Airway flow, volume and pressure
Arterial blood pressure (invasive and non-invasive, systolic, diastolic, and mean)
Bispectral index (BIS, signal quality index, suppression ratio)
Cardiac Index
Cardiac output
Central venous pressure
Cerebral perfusion pressure
End-tidal CO2
Heart rate
Heart rate variability
Intracranial pressure
Left atrium pressure
Oxygen saturation (intravascular, regional, SpO2)
Premature ventricular counted beats
Pulmonary artery pressure (systolic, diastolic, and mean)
Pulse pressure variation
Pulse Rate
Respiratory rate
Right atrium pressure
Temperature (rectal, esophageal, tympanic, blood, core, nasopharyngeal, skin)
Umbilical arterial pressure (systolic, diastolic, and mean)

It can also display laboratory measurements including arterial and venous blood gases, complete blood count, and lactic acid.

T3 includes a Patient Risk Analytics Engine that calculates an index (the Inadequate Oxygen Delivery Index) that is indicated for use by health care professionals with postsurgical patients aged zero days to twelve years weighing 2 kg or more under intensive care. The Inadequate Oxygen Delivery Index is derived by mathematical manipulations of the physiologic data and laboratory measurements received by T3. When the index is elevated, it means that there is increased risk of inadequate oxygen delivery and attention should be brought to the patient. The index presents partial quantitative information about the patient's cardiovascular condition, and no therapy or drugs can be administered based solely on the interpretation statements.

Device Description

Customizable display of physiologic parameters over entire patient stay.
Configurable annotation.
Web-based visualization that may be used on any standard browser.
Minimal IT footprint.
Software-only solution no new bedside hardware required.
Highly reliable and robust operation.
Auditable data storage.

The subject device is a modification of the T3 Software that expands the Indications for Use for the Inadequate Oxygen Delivery Index (IDO2) from patients aged 0 - 28 days to patients aged zero days to twelve years. The IDO2 Index is derived by mathematical manipulations of the physiologic data and laboratory measurements received by T3. This index provides an interpretation of how different the patient's physiologic measures are from normality.

In addition to the expansion in the Indications of Use for the IDO2 Index, T3 release 3.0 contains the following changes:

1. In previous T3 versions, the Inadequate Oxygen Delivery Index is documented as having the following limitation.
  The index will not be displayed if the following minimum measurements are not available:
a. Heart rate from ECG or pulse at a minimum of once every 30 seconds
b. SpO2 from pulse oximetry at a minimum of once every 30 seconds
c. Blood Pressure (mean/diastolic/systolic) at a minimum of once every 10 minutes
This limitation has been changed to the following:
The index will not be displayed if the following minimum measurements are not available:
a. Heart rate from ECG or pulse at a minimum of once every 60 seconds
b. SpO2 from pulse oximetry at a minimum of once every 10 minutes
c. Blood Pressure (mean/diastolic/systolic) at a minimum of once every 10 minutes
The minimum requirement for Heart Rate data has changed from 30 seconds to 60 seconds, and the minimum requirement for SpO2 has changed from 30 seconds to 10 minutes.
1. In previous T3 versions, the software model used to calculate IDO2 had age independent parameters and did not include a number of potentially useful model relationships. In the updated model, parameters are now dependent on patient age. Also, new model states and relationships have been implemented to improve the performance.
1. In previous T3 versions, the calibration logic for IDO2 utilized the probability distribution of patient states to determine whether or not to display a given IDO2 value. The new calibration logic is simply time based, waiting 5 minutes to display IDO2 values for a new patient. In addition, if the algorithm is re-initialized for any reason, it will undergo an additional 5 minutes of calibration after the re-initialization.
1. The IDO2 labeling contains a list of required and optional algorithm inputs. One required input is SpO2. Previous releases of T3 accepted SpO2 captured by the patient monitor and reported with any of three different labels: "SpO2" (defined as "SpO2 from pulse oximeter"), "SpO2 l" (defined as "arterial oxygen saturation left"), and "SpO2 r" (defined as "arterial oxygen saturation right"). This release of T3 adds SpO2 as reported with two other labels: "SpO2 pr" (defined as "pre-ductal SpO2") and "SpO2 po" (defined as "post-ductal SpO2").
1. T3 version 3.0 also includes the following User Interface changes:
a. A new user interface mode that displays the data originating from a single bed location, even as new patients are transferred into that location. The benefit of this change is that the T3 user is never auto-logged off due to inactivity. Instead, T3 displays either the view of the patient data or a dialog stating that no data is being received for the bed. The mode is suitable for a bedside display, and saves clinicians the time and effort of logging in and navigating to that patient's data each time they want to use T3. To mitigate possible clinician confusion about which patient the data is for, T3 only displays data for one patient at a time - the current patient. Furthermore, the patient's name, medical record number and date of birth are displayed on the screen.
b. Views: These are predefined arrangements of labs and measures. Views are accessed through a tabbed display. The first instance of the View functionality is the Hemodynamic View, which presents information about the patient's hemodynamic system. Views save clinicians the time and effort to drag meaningful labs and measures to the central graph area in order to display them.
c. Smart Visualization Groups: These are collections of measures and laboratory results that are graphed together as a single unit. T3 is able to insert shading, vertical lines and other visual cues to emphasize relationships in the data. For example, in the Blood Pressure group, the area between systolic and diastolic pressure is shaded. The shading represents "pulse pressure," a standard measure of the force the heart generates each time it contracts. The shading allows the clinician to see increases or decreases in pulse pressure, in addition to the systolic and diastolic blood pressure values from which pulse pressure is calculated.
d. When T3 displays a measure it inserts the starting and ending values for the period of time being graphed on the left and right edges of the canvas. It inserts the maximum and minimum values for the measure in circles at the point in time when they occur. If two or more of these values would overlap on the graph, T3 omits all but one of them for clarity. Likewise, if one of these values would obscure the graphic icon for a laboratory result, T3 omits it so the laboratory result is shown.
e. Night Mode. There are now application-wide configuration settings that specify when "night time" starts and ends. For example, night time can be defined to start at 7PM and end at 7AM - or whatever times are desired. When T3 runs "at night," the application recognizes that it is night based on the system clock, and automatically uses a dark background. This reduces the amount of ambient light that the T3 monitor emits. When it runs during the day, T3 similarly recognizes that it is day and automatically uses a light background. It is possible for individual users to manually override the night mode function. On the patient view screen, T3 adds buttons that let the user manually control night mode. There is a sunshine button that lightens the background, and a moon button that darkens the background. A lock button locks in the user's selection of day or night.
f. If T3 receives data for a patient measure whose unit of measure is different from what was previously received for that patient and measure, it now displays a temporary warning banner at the top of the display that is automatically dismissed after ten seconds. Previously, T3 displayed the warning, but required the user to dismiss it by clicking on it. In many situations, needing to click to dismiss the warning was inconvenient or impractical. An example of this functionality is if T3 is receiving mean airway pressure for a patient. The monitor may report values in "millibars" then switch to "cmH2O." Both are commonly accepted ways of measuring airway pressure. In this case, the warning will say "Measure mnAWp has inconsistent unit codes. T3 is expecting units of mbar, but received data points with units of cmH2O. Those data points will not be displayed."
g. The dialog showing additional details for a lab value is now invoked by clicking anywhere on the lab icon. Previously it was invoked by hovering the mouse cursor over the exact data point for the lab value. The new functionality is more forgiving if the mouse cursor is slightly misplaced, and is less susceptible to displaying unwanted tooltips when the user moves the mouse cursor around the screen.
1. Typically, a clinician enters the patient's medical record number (MRN) into the bedside monitor. The physio interface sent to T3 from that monitor then includes the MRN and bed location along with the data values for the patient. T3 now supports an alternate workflow where the hospital's Admit, Discharge and Transfer (ADT) interface is used as the definitive source of patient identity and location information. The physio interface contains bed location along with the data values for the patient, but T3 derives the MRN by matching the bed location sent in the physio interface with the bed location / MRN pairing sent in the ADT interface. In order to recover from a situation where an ADT message is not delivered to T3 for some reason, or T3 processes it incorrectly, there is also a user interface in T3 that allows an administrator to explicitly specify the MRN for the patient occupying a bed location. This has the same effect as an ADT message associating a patient with a bed location.
1. T3 can now send an informational email to one or more configured email addresses when it detects that data is being received from a bed location without an associated patient medical record number, or when it detects that data is simultaneously being received from multiple bed locations with the same associated MRN. The recipient of the email can then investigate and correct the problem. The email does not contain protected health information; instead it specifies the bed locations where the issue occurs.
1. The T3 labeling lists a series of clinical calculations that can be configured upon clinician demand. These clinical calculations are simple algebraic formulas that accept raw parameters and output a single result. An example is Pulse Width which is equal to Systolic blood pressure minus Diastolic blood pressure. This release of T3 adds the following calculations to the list that may be requested by clinicians:
  | Label | Name | Formula |
  |---|---|---|
  | P/F | P/F Ratio | PaO2 / FiO2 |
  | S/F | S/F Ratio | SpO2 / FiO2 |
  | OI | Oxygenation Index | (FiO2 * Mean Airway Pressure * 100) / PaO2 |
  | OSI | Oxygen Saturation Index | (FiO2 * Mean Airway Pressure * 100) / SpO2 |

AI/ML Overview

Here is a summary of the acceptance criteria and the study that proves the device meets the acceptance criteria, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with numerical targets and corresponding device performance metrics for the T3 Software (Version 3.0). Instead, it focuses on demonstrating substantial equivalence to its predicate device (T3 Software Version 2.0) and supporting the expanded Indications for Use of the Inadequate Oxygen Delivery Index (IDO2).

The key "performance" aspect discussed is the validation of the IDO2 Index in the expanded patient population.

Acceptance Criteria (Implied)	Reported Device Performance
IDO2 Index Correlation to Patient Status Change	The validation study results using clinical data gathered in the intended patient population demonstrate the IDO2 Index included in the subject device correlates with changes in the patient's physical status. (Specific metrics of correlation, such as sensitivity, specificity, AUC, or other statistical measures, are not provided in this summary document.)
Software Verification and Validation	"Software verification and validation testing was conducted for the subject device, and documentation was provided in accordance with FDA's 'Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices', May 11, 2005. The results of this testing demonstrate the safety and effectiveness of the subject T3 software product (Ver. 3.0) is comparable to that of the predicate T3 software products (Ver. 2.0.1)." (No specific test results or metrics are given).
Equivalence in Design, Features, and Functionality to Predicate	"The T3 Software has equivalent design, features and functionality as the predicate T3 Software with few exceptions and these exceptions do not affect the safety or effectiveness of the system." (Changes include expanded age range for IDO2, modified calculation parameters for IDO2, changes to minimum measurement requirements for IDO2 display, and various UI/workflow enhancements. These are deemed not to raise new safety/effectiveness concerns).

2. Sample Size Used for the Test Set and Data Provenance

Sample Size: Clinical data from 1504 patients were used for the validation study.
Data Provenance: The data was described as "clinical data gathered in the intended patient population" and covered "the expanded patient age range." The country of origin is not specified, but it's typically assumed to be U.S. clinical data for FDA submissions unless otherwise stated. The document doesn't specify if the data was retrospective or prospective, but clinical validation studies often leverage retrospective data for initial submissions unless a specific prospective trial is mentioned.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications

The document does not provide information on the number of experts used or their qualifications to establish ground truth for the test set. It mentions the "IDO2 Index ... correlates with changes in the patient's physical status," implying that some form of clinical assessment or patient outcome served as the ground truth, but the specifics of its establishment are not detailed.

4. Adjudication Method for the Test Set

The document does not specify any adjudication method (e.g., 2+1, 3+1, none) used for establishing ground truth or evaluating the device's performance.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size

The document does not indicate that an MRMC comparative effectiveness study was done to assess how much human readers improve with AI vs. without AI assistance. The T3 Software, particularly the IDO2 Index, is described as an index that "presents partial quantitative information about the patient's cardiovascular condition" to aid healthcare professionals in clinical decisions, but not as an AI-assisted diagnostic tool requiring reader performance comparison.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

Yes, a form of standalone performance assessment was conducted for the IDO2 Index. The validation study "using clinical data" to demonstrate correlation with "changes in the patient's physical status" against a ground truth (even if unspecified in detail) is a standalone evaluation of the algorithm's output. The device itself (T3 Software) is also described as a "Software-only solution."

7. The Type of Ground Truth Used

The ground truth implicitly used for the IDO2 Index validation is related to "changes in the patient's physical status." This likely refers to clinically relevant changes as observed by healthcare professionals, or potentially outcomes data, but the specific nature (e.g., expert consensus on patient status, objective physiological changes, or adverse events) is not explicitly defined in this summary.

8. The Sample Size for the Training Set

The document does not provide information about the sample size used for the training set of the T3 Software or the IDO2 algorithm. It only mentions the 1504 patients for the validation study.

9. How the Ground Truth for the Training Set Was Established

The document does not provide information on how the ground truth for the training set was established, as the training set details are not included in this summary.

Ask a Question

Ask a specific question about this device

K Number

K152258

Device Name

K142732,K151715,K081140,K110953

Manufacturer

ETIOMETRY, INC.

Date Cleared

2016-03-31

(233 days)

Product Code

Regulation Number

Type

Panel

Reference & Predicate Devices

Intended Use

To remotely consult regarding a patient's status, and
To remotely review other standard or critical near real-time patient data in order to aid in clinical decisions and deliver patient care in a timely manner.
T3 can display numeric physiologic data captured by other medical devices:
Airway flow, volume and pressure
Arterial blood pressure (invasive and non-invasive, systolic, diastolic, and mean)
Bispectral index (BIS, signal quality index, suppression ratio)
Cardiac Index
Cardiac output
Central venous pressure
Cerebral perfusion pressure
End-tidal CO2
Heart rate
Heart rate variability
Intracranial pressure
Left atrium pressure
Oxygen saturation (intravascular, regional, SpO2)
Premature ventricular counted beats
Pulmonary artery pressure (systolic, diastolic, and mean)
Pulse pressure variation
Pulse Rate
Respiratory rate
Right atrium pressure
Temperature (rectal, esophageal, tympanic, blood, core, nasopharyngeal, skin)
Umbilical arterial pressure (systolic, diastolic, and mean)
It can also display laboratory measurements including arterial and venous blood count, and lactic acid.
T3 includes a Patient Risk Analytics Engine that calculates an index (the Inadequate Oxygen Delivery Index) that is indicated for use by health care professionals with post-surgical neonatal patients weighing 2 kg or more under intensive care. The Inadequate Oxygen Delivery Index is derived by mathematical manipulations of the physiologic data and laboratory measurements received by T3. When the index is elevated, it means that there is increased risk of inadequate oxygen delivery and attention should be brought to the index presents partial quantitative information about the patient's cardiovascular condition, and no therapy or drugs can be administered based solely on the interpretation statements.
WARNING: T3 Software is not an active patient monitoring system. It is intended to supplement and not replace any part of the hospital's device monitoring. Do not rely on the T3 Software Solution as the sole source of patient status information.

Device Description

Customizable display of physiologic parameters over entire patient stay.
Configurable annotation
Web-based visualization that may be used on any standard browser
Minimal IT footprint
Software-only solution no new bedside hardware required
Highly reliable and robust operation.
Auditable data storage.
The subject device is a modification of the T3 Software that includes Risk Analytics Engine that computes an Inadequate Oxygen Delivery Index (IDO2). The IDO2 Index is derived by mathematical manipulations of the physiologic data and laboratory measurements received by T3. This index provides an interpretation of how different the patient's physiologic measures are from normality.

AI/ML Overview

The provided text describes the T3 Software, version 2.0.1, which includes a Patient Risk Analytics Engine calculating an Inadequate Oxygen Delivery Index (IDO2). The document is a 510(k) summary, making it a submission to the FDA for market clearance, stating that the new version is substantially equivalent to previous versions and other predicate devices.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based only on the provided text:

1. A table of acceptance criteria and the reported device performance

The document does not explicitly present specific, quantitative acceptance criteria for the IDO2 Index. Instead, it relies on demonstrating that the device's software functions as intended and that the IDO2 Index correlates with changes in physical status, similar to a predicate device.

Acceptance Criteria (Implicit from document)	Reported Device Performance
Software Functionality: The software records and displays multiple physiological parameters accurately from supported bedside devices.	"Software verification and validation testing was conducted for the subject device... The results of this testing demonstrate the safety and effectiveness of the subject T3 software product (Ver. 2.0.1) is comparable to that of the predicate T3 software products (Ver. 1.9)." (Implies successful operation and comparable accuracy to predicate for data display and recording)
IDO2 Index Calculation & Interpretation: The Patient Risk Analytics Engine calculates the IDO2 Index correctly based on mathematical manipulations, and when elevated, indicates an "increased risk of inadequate oxygen delivery." (Accuracy of calculation and qualitative interpretation)	"The Inadequate Oxygen Delivery Index is derived by mathematical manipulations of the physiologic data and laboratory measurements received by T3. When the index is elevated, it means that there is increased risk of inadequate oxygen delivery..." (The document states how it's derived and what an elevated index means, implying it performs this function as designed.)
Clinical Correlation of IDO2 Index: The IDO2 Index correlates with changes in the patient's physical status.	"Additionally, validation study results using clinical data gathered in the intended patient population demonstrate the IDO2 Index included in the subject device correlates with changes in the patient's physical status, as does the Visensia Index." (Directly states correlation observed in a validation study.)
Safety and Effectiveness: The device is safe and effective and raises no new questions of safety or effectiveness compared to predicate devices.	"The results of this testing demonstrate the safety and effectiveness of the subject T3 software product (Ver. 2.0.1) is comparable to that of the predicate T3 software products (Ver. 1.9) and the Visensia device." and "No new questions of safety or effectiveness are raised as a result of the differences when compared to the predicate device and the data provided in the submission show that the subject device is substantially equivalent to the legally-marketed predicate devices."

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document states: "Additionally, validation study results using clinical data gathered in the intended patient population demonstrate the IDO2 Index included in the subject device correlates with changes in the patient's physical status, as does the Visensia Index."

Sample Size: The sample size for the "validation study" is not specified in the provided text.
Data Provenance: The country of origin of the data is not specified. The text only mentions "clinical data gathered in the intended patient population." It is also not specified if the data was retrospective or prospective.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

The document does not provide any information regarding the number of experts used or their qualifications for establishing ground truth in the validation study. The ground truth refers to "changes in the patient's physical status," but how this was determined by experts is not detailed.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

The document does not specify any adjudication method used for the test set.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

The document does not describe a multi-reader multi-case (MRMC) comparative effectiveness study. The study focused on the correlation of the IDO2 Index with patient physical status. There is no mention of human readers or their improvement with or without AI assistance. The device is intended to aid clinical decisions and provide quantitative information, but not in a comparative effectiveness study involving human interpretation.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

Yes, the validation study appears to be a standalone performance study of the algorithm. The statement "validation study results... demonstrate the IDO2 Index... correlates with changes in the patient's physical status" indicates an evaluation of the algorithm's output (the IDO2 Index) against an independent measure of patient status, without involving human-in-the-loop performance measurement.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

The ground truth used is "changes in the patient's physical status." The specific method for determining "changes in the patient's physical status" (e.g., expert consensus, specific clinical criteria, or other outcomes data) is not detailed in the provided text.

8. The sample size for the training set

The document does not specify a separate "training set" or its sample size. The description focuses on the validation of the IDO2 Index, which implies the algorithm's parameters were already established.

9. How the ground truth for the training set was established

Since a "training set" is not mentioned, the document does not provide information on how ground truth for any training set was established. The IDO2 Index is described as being "derived by mathematical manipulations of the physiologic data and laboratory measurements," suggesting a formulaic or rule-based derivation rather than a machine learning model trained on labeled data in the context usually implied by "training set ground truth."

Ask a Question

Ask a specific question about this device

K Number

K151715

Device Name

Manufacturer

Date Cleared

2015-10-29

(126 days)

Product Code

Regulation Number

Type

Panel

Reference & Predicate Devices

K142732

Intended Use

· To remotely consult regarding a patient's status, and
· To remotely review other standard or critical near real-time patient data in order to aid in clinical decisions and deliver patient care in a timely manner.

T3 can display numeric physiologic data captured by other medical devices:

· Airway flow, volume and pressure
· Arterial blood pressure (invasive and non-invasive, systolic, diastolic, and mean)
· Bispectral index (BIS, signal quality index, suppression ratio)
Cardiac Index
Cardiac output
Central venous pressure
· Cerebral perfusion pressure
· End-tidal CO2
· Heart rate
· Heart rate variability
· Intracranial pressure
· Left atrium pressure
· Oxygen saturation (intravascular, regional, SpO2)
· Premature ventricular counted beats
· Pulmonary artery pressure (systolic, diastolic, and mean)
· Pulse pressure variation
Pulse Rate
· Respiratory rate
· Right atrium pressure
· Temperature (rectal, esophageal, tympanic, blood, core, nasopharyngeal, skin)
· Umbilical arterial pressure (systolic, diastolic, and mean)

It can also display laboratory measurements including arterial and venous blood count, and lactic acid.

WARNING: T3 Software is not an active patient monitoring system. It is intended to supplement and not replace any part of the hospital's device monitoring. Do not rely on the T3 Software Solution as the sole source of patient status information.

Device Description

Customizable display of physiologic parameters over entire patient stay ●
Configurable annotation .
Web-based visualization that may be used on any standard browser ●
. Minimal IT footprint
Software-only solution no new bedside hardware required .
Highly reliable and robust operation
Auditable data storage .

The T3 Software is intended for the display and recording of multiple physiological parameters of adult, pediatric and neonatal patients. T3 is not intended for alarm notification, nor is it intended to control any of the independent bedside devices to which it is connected

The T3 software can display user-defined, derived measures. These measures include the percentage of time within a time period that a particular variable is above or below a threshold. The user can configure the time period, threshold, and label of the resulting derived measure for ease of use considerations, only.

The T3 Software is not an active patient monitoring system. It is intended to supplement and not replace any part of the hospital's device monitoring.

T3 has a web architecture consisting of a user interface that runs in a browser, and a central web server. The T3 server, a set of cooperating web services written in Java, processes data as it is received, caches it in memory, and writes out copies of the data to a relational database and to the file system. In this manner, the data is available to the user interface to be visualized by the end user - a clinician.

Clinicians access the T3 user interface in a web browser. T3 runs in current browsers that support HTML5, Javascript and web sockets, such as Chrome, Firefox, Safari and Internet Explorer. The clinicians may be in the hospital, or may be outside the hospital accessing T3 over a Virtual Private Network (VPN). Clinicians use T3 in addition to the physiometric devices themselves and other information sources such as the electronic medical record to monitor the patient's condition.

AI/ML Overview

The provided document is a 510(k) premarket notification for the Etiometry T3 Software Version 1.9. It outlines the device's indications for use and compares its technological characteristics to a predicate device. However, it explicitly states that clinical testing was not required for this submission.

Therefore, the document does not contain a study that proves the device meets specific acceptance criteria in terms of clinical performance. Instead, its substantial equivalence is based on software verification and validation, and comparison to a predicate device.

Given that no clinical study was conducted as part of this submission, I cannot provide the requested information about acceptance criteria, sample sizes, expert involvement, adjudication methods, MRMC studies, standalone performance, or ground truth details.

The document states:

"Software verification and validation testing has been conducted for T3 Software and documentation has been provided in accordance with FDA 's "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices", May 11, 2005."
"Clinical testing was not required."

This indicates that the "performance data" referred to in Section VII primarily pertains to software V&V, ensuring the software performs as designed and intended, rather than proving clinical efficacy or diagnostic accuracy against a clinical ground truth.

If you have other documents that describe clinical performance studies for this device, please provide them.

Ask a Question

Ask a specific question about this device

K Number

K142732

Device Name

Manufacturer