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.

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left is the seal of the Department of Health & Human Services. To the right of that is the FDA logo in blue, with the words "U.S. FOOD & DRUG" stacked on top of the word "ADMINISTRATION".

November 25, 2020

Etiometry, Inc. Tim Hanson Director of RA/QA 280 Summer St. 4th Floor Boston, Massachusetts 02210

Re: K202306

Trade/Device Name: T3 Platform software Regulation Number: 21 CFR 870.2300 Regulation Name: Cardiac Monitor (Including Cardiotachometer And Rate Alarm) Regulatory Class: Class II Product Code: MWI, PLB Dated: August 5, 2020 Received: August 14, 2020

Dear Tim Hanson:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part

{1}------------------------------------------------

801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

for LT Stephen Browning Assistant Director DHT2A: Division of Cardiac Electrophysiology, Diagnostics and Monitoring Devices OHT2: Office of Cardiovascular Devices Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K202306

Device Name

The T3 Platform™ software features the T3 Data Aggregation & Visualization software module version 5.0 and the T3 Risk Analytics Engine software module version 6.0.

Indications for Use (Describe)

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 vears

{3}------------------------------------------------

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.

WARNINGS:

Do not use the T3 Platform software as an active patient monitoring system. Do not use the T3 Platform software to replace any part of the hospital's device monitoring. Do not rely on the T3 Platform software as the sole source of patient status information. Do not use the IVCO2 Index as a substitute for arterial blood gases.

Type of Use (Select one or both, as applicable)

Prescription Use (Part 21 CFR 801 Subpart D)

Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{4}------------------------------------------------

Image /page/4/Picture/0 description: The image shows the word "etiometry" in a sans-serif font. The letters are a gradient of blue, with the left side of the word being a darker blue and the right side being a lighter blue. Above the word is a curved line that forms an arc, with a blue triangle at the top of the arc.

October 28, 2020

This 510(k) summary has been prepared in accordance with Title 21 CFR §807.92 and FDA's guidance document, "The 510(k) Program: Evaluating Substantial Equivalence in Premarket Notifications 510(k)" July 28, 2014

4.1 510(k) Submitter

Timothy Hanson, Director of Regulatory Affairs and Quality Assurance 280 Summer St., 4th Floor Boston, MA 02210 Tel: 857.366.9333 ext. 2020 Email: THanson@etiometry.com

4.2 Device

Item	Description
Device Trade Name	T3 Platform™ software (T3 Data Aggregation & Visualization softwaremodule version 5.0 and T3 Risk Analytics Engine software moduleversion 6.0)
Device Common/Usual Name	Data Management Software (without alarms)
Classification Name	Cardiac monitor (including cardiotachometer and rate alarm)
Classification Number	870.2300

{5}------------------------------------------------

Item	Description
Regulatory Class	Class IIThe primary code is MWI: monitor, physiological, patient (withoutarrhythmia detection or alarms).The secondary code is PLB: automated calculation of a summary index(or indices) based on several individual measured vital sign inputs.

4.3 Predicate Device

The T3 Platform™ software featuring the T3 Data Aggregation & Visualization software module version 3.3 and the T3 Risk Analytics Engine software module version 5.0, cleared under K190273.

4.4 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

4.5 Indications for 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 6.0.

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

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

{6}------------------------------------------------

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.

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 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.

WARNINGS:

Do not use the T3 Platform™ software as an active patient monitoring system. ●
. Do not use the T3 Platform™ software to replace any part of the hospital's device monitoring.
Do not rely on the T3 Platform™ software as the sole source of patient status information. ●
Do not use the IVCO2 Index™ as a substitute for arterial blood gases.

{7}------------------------------------------------

4.6 Comparison of Technological Characteristics with the Predicate Device

The subject and predicate T3 Platform™ software have the same Intended Use/Indication for Use. The subject and predicate devices differ with respect to several technological features. (see Table 2).

Feature/Improvement	Description
Addition of data from regional oxygen saturationmonitors as an input for the calculation of theIDO2 Index™	Data from regional oxygen saturation monitors, when available, havebeen added as an input to the Risk Analytics Engine module tofacilitate the detection of inadequate oxygen delivery andrespectively improve the performance of the IDO2 Index™.Specifically, data from regional oximetry are used as a noise proxy ofmixed venous oxygen saturation which the hemodynamic modelinterprets in the context of other physiologic measurements to inferIDO2 value. The performance of the IDO2 Index™ was evaluated withand without regional oximetry to confirm the utility of themeasurement as an input.
Measure Contributions signifying measurementinputs which have the highest contribution to anincrease in the IDO2 Index™ or the IVCO2 Index™	To increase the transparency and understanding of the risk indicescomputed by the platform, the computations have beensupplemented with an external routine which computes how eitherremoving an existing measurement as an input (if the measurementis not in the minimum data set required for the computation of theindex) or setting a measurement to what the algorithms perceive asnominal (if the measurement is part of the minimum data set) affectsthe individual indices. This computing routine enables assessment ofthe "contribution" of each available input in both the IDO2 Index™ orthe IVCO2 Index™. The three measurements with the highestcontribution, i.e. the measurements whose removal or setting tonominal leads to the highest drop in a particular index are thendisplayed as the major contributing measurements at the particulartime instance.
User selectable thresholds for definingInadequate Oxygen Delivery and InadequateVentilation of Carbon Dioxide	The previously cleared version of the software computed the IDO2Index™ and the IVCO2 Index™ as the likelihood of SvO2 < 40% andPaCO2 > 50 mmHg respectively. Using the same computationframework, the current version enables several more thresholds thata clinical user can configure. This facilitates individualizing the indicesbased on patient condition or other clinical considerations.
Modification of minimum data required tocompute IVCO2 Index™	The minimum set for the IVCO2 Index™ to exclude the arterial bloodgases requirement.
Support for encrypted data feeds into theplatform	To improve the cybersecurity of the platform, the softwareintroduces the ability to accept encrypted data feeds from hospitaldata sources.
Display of complete lab panel information	The software introduces a detailed view of a plotted lab result toprovide additional clinical context to the results. This allows cliniciansto both contextualize lab results with physiologic data, but also withother lab results within the panel.
Embedded Standalone Platform Manual	To further ensure labeling availability and distribution, the softwarehas embedded the complete platform manual as part of the release.Users can easy access, consult, and/or download the manual withinthe system.
Feature/Improvement	Description
Addition of Tele-medicine Census view in theexisting User Interface	The User Interface introduces a new feature to facilitate the viewingof the status of all patients in an ICU in a single display, which canserve as a starting point for a more detailed review of individualpatient information. The tool supports interpreting trends forselected variables, understanding the trajectory of patients, andsupporting bedside clinicians in their decision making. For each bedin the ICU, the bed number is displayed along with the last name andage if there is currently a patient in that bed. This tool differs fromthe Census Overview by displaying for each patient the most recentvital signs and algorithm values in tiles containing graphs instead of atable of rows
Integration of Single Sign-on	To facilitate access to the platform, the software has an addedcapability to integrate with an Electronic Medical Record system(EMR). A user can navigate to display T3 patient information from theEMR with a single click, which automatically authenticates them in T3and navigates them to the patient of interest.
Miscellaneous Updates of the HemodynamicModel Employed to Infer the IDO2 Index™	The hemodynamic model powering the IDO2 Index™ has beenupdated by improving specific modeled physiologic effects such asthe adaptable relationship between pulse pressure and strokevolume which now utilizes a logarithmic relationship to facilitatelinear estimation. The updated IDO2 Index™ algorithm was subject tofull performance clinical testing.
Addition of a Retrospective Teaching Census	To facilitate software education and training, the platform introducesthe ability to collate, de-identify, and save a specific patient case in ahospital specific teaching census for use as a training resource.
Repair incorporation of incorrectly labeled SvO2measurements into the algorithm	The software has been modified to reject measurements which maynot correctly be associated with mixed or central venous oxygensaturation. The software classifies venous oxygen saturationmeasurements as either validated or non-validated and incorporatesthe measures under different conditions based on that classification.

{8}------------------------------------------------

Table 2: Summary of Changes

4.7 Performance Data

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. The results of this testing demonstrate that the safety and effectiveness of the subject T3 Platform™ software (subject device) are comparable to that of the predicate T3 Platform™ software (target device).

4.8 Conclusions

Substantial equivalence of the T3 Platform™ software is demonstrated through performance testing. The T3 Platform™ software has the equivalent design, features and functionality as the predicate T3 Platform™ software with few exceptions and these exceptions do not affect the safety or effectiveness of the system.

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 device.

Regulation Number and Section

§ 870.2300 Cardiac monitor (including cardiotachometer and rate alarm).

(a)
Identification. A cardiac monitor (including cardiotachometer and rate alarm) is a device used to measure the heart rate from an analog signal produced by an electrocardiograph, vectorcardiograph, or blood pressure monitor. This device may sound an alarm when the heart rate falls outside preset upper and lower limits.(b)
Classification. Class II (performance standards).