Search Results

The ABL90 FLEX analyzer is an in vitro diagnostic, portable, automated analyzer that quantitatively measures neonatal bilirubin in heparinized capillary, venous and arterial whole blood.
The ABL90 FLEX analyzer is intended for use by trained technologists, nurses, physicians and therapists.
It is intended for use in a laboratory environment, near patient or point-of-care setting.
These tests are only performed under a physician's order.
Bilirubin measurements on the ABL90 FLEX analyzer are intended to aid in assessing the risk of kernicterus in neonates.

ABL90 FLEX PLUS:
The ABL90 FLEX PLUS analyzer is an in vitro diagnostic, portable, automated analyzer that quantitatively measures neonatal bilirubin in heparinized capillary, venous and arterial whole blood.
The ABL90 FLEX PLUS analyzer is intended for use by trained technologists, nurses, physicians and therapists.
It is intended for use in a laboratory environment, near patient or point-of-care setting.
These tests are only performed under a physician's order.
Bilirubin measurements on the ABL90 FLEX PLUS analyzer are intended to aid in assessing the risk of kernicterus in neonates.

The ABL90 FLEX and ABL90 FLEX PLUS analyzers are two models of the same portable, automated system intended for in vitro testing of samples of whole blood for the parameters pH, pO-, pCO3, potassium, sodium, calcium, chloride, glucose, lactate, neonatal bilirubin, and co-oximetry parameters (total hemoglobin, oxygen saturation, and the hemoglobin fractions FO-Hb, FCOHb, FMetHb, FHHb and FHbF).
The manufacturer of the ABL90 FLEX and ABL90 FLEX PLUS is Radiometer Medical ApS.
The ABL90 FLEX and ABL90 FLEX PLUS consist of an instrument with a sensor cassette and a solution pack as the main accessories. Multiple models of sensor cassettes are available.
The various sensor cassette models for different parameter combinations. For each parameter combination, models allowing for different test load are available.
The solution pack is available in two models differing in the number of tests available.
Technology:
The ABL 90 FLEX and ABL90 FLEX PLUS electrochemical sensors are miniaturized, manufactured by film technology and integrated in a common sensor cassette. Likewise, the ABL90 FLEX and ABL90 FLEX PLUS optical oxygen sensor is integrated in the sensor cassette. A 256-pixel array spectrophotometer is used for the co-oximetry parameters and bilirubin.
Clinical Utility ctBil:
For newborns up to an age of one month the method's reportable range covers the entire reference range. Neonatal Bilirubin test is intended for use to aid in assessing the risk of kernicterus in newborns.

The provided document is a 510(k) Premarket Notification from the FDA regarding the ABL90 FLEX and ABL90 FLEX PLUS devices for measuring neonatal bilirubin. It primarily focuses on demonstrating substantial equivalence to a predicate device, rather than defining and proving acceptance criteria as typically done for novel AI/ML medical devices.

Therefore, many of the requested points related to acceptance criteria, ground truth establishment, expert consensus, MRMC studies, and training sets are not applicable to this type of submission. This 510(k) is for an in-vitro diagnostic device that measures a chemical parameter (bilirubin) using established spectrophotometric technology, not an AI/ML-driven diagnostic or image analysis tool. The "performance" being evaluated is the analytical performance (accuracy, precision, linearity) of the device against a known predicate and reference methods, not the diagnostic performance of an algorithm.

However, I can extract the relevant information from the document that pertains to its performance evaluation.

Overview of Device Performance Evaluation (Not AI/ML focused)

The ABL90 FLEX and ABL90 FLEX PLUS analyzers are in vitro diagnostic devices designed to quantitatively measure neonatal bilirubin in heparinized capillary, venous, and arterial whole blood. The submission aims to extend the indicated sample types for neonatal bilirubin measurement to include arterial and venous whole blood, leveraging performance data already established for capillary whole blood in a previous 510(k) (K132691).

The core of the performance study for this specific submission is demonstrating method comparison (correlation) against a predicate device (ABL800 FLEX or ABL835 FLEX, which is part of the ABL800 FLEX family) for the new sample types.

Relevant Performance Information and Analysis (from the provided document):

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

   • Acceptance Criteria: Not explicitly stated as pass/fail thresholds in this document for the method comparison study. The goal is to demonstrate "substantial equivalence" based on the correlation characteristics (slope, intercept, R-squared) to the predicate device. The implicit acceptance is that the correlation is strong (R-squared close to 1) and the linear relationship is close to y=x (slope close to 1, intercept close to 0), indicating comparable performance to the predicate. The FDA's determination of substantial equivalence implies these criteria were met.

   • Reported Device Performance (from Table 1: Neonatal bilirubin linear regression data for ABL90 FLEX measurements compared to ABL835 FLEX measurements):

     Parameter	Units	Slope	Intercept (mg/dL)	R²	Sy.x (mg/dL)
     ctBil All (combined samples)	mg/dL	0.97	-0.38	1.00	0.60
     ctBil Arterial All	mg/dL	0.98	-0.54	0.97	0.53
     ctBil Venous All	mg/dL	0.98	-0.32	0.98	0.62
     ctBil site 1	mg/dL	0.96	-0.18	1.00	0.57
     ctBil site 2	mg/dL	0.98	-0.71	1.00	0.58

   Interpretation: The R-squared values are very high (0.97 to 1.00), indicating a very strong linear correlation between the ABL90 FLEX and the predicate ABL835 FLEX. The slopes are close to 1 (0.96-0.98) and intercepts are close to 0 (-0.18 to -0.71 mg/dL), suggesting good agreement (i.e., minimal proportional or constant bias) between the new device and the predicate.

2. Sample size used for the test set and the data provenance:

   • Test Set Sample Sizes:
     • 44 arterial blood samples
     • 42 venous blood samples
     • 17 spiked cord blood samples
     • Total N = 103 samples (44 arterial + 42 venous + 17 spiked)
   • Data Provenance: The study was conducted at "two point-of-care sites." The document does not specify the country of origin of the data. It is a prospective method comparison study where new measurements were taken for the purpose of this submission.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Not applicable in the context of an AI/ML algorithm. For this in vitro diagnostic device, the "ground truth" for the method comparison is the measurement obtained from the predicate device (ABL835 FLEX), which is itself a validated diagnostic instrument. This is an analytical performance study, not a diagnostic performance study relying on expert interpretation.

4. Adjudication method for the test set:

   • Not applicable. This study involves direct quantitative measurements of a chemical analyte, not qualitative assessments or interpretations that would require adjudication.

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:

   • Not applicable. This is an in vitro diagnostic device measuring a chemical substance, not an AI-assisted diagnostic tool that would involve human readers interpreting images or data.

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

   • This is inherently a "standalone" device in its measurement function. The device itself performs the measurement and provides a numerical output. Human involvement is in operating the device and interpreting the numerical result in a clinical context, but not in assisting an algorithm to produce the measurement.

7. The type of ground truth used:

   • The "ground truth" (or reference method for comparison) was measurements obtained from another legally marketed device (predicate device, ABL835 FLEX), which is widely considered a reliable method for bilirubin measurement. For in vitro diagnostics, this is a standard approach to demonstrating substantial equivalence – showing comparable performance to an established method.

8. The sample size for the training set:

   • Not applicable. This device uses established spectrophotometric technology and is not an AI/ML device that requires a training set in the conventional sense. The "training" here would be the design and calibration of the instrument based on chemical and optical principles.

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

   • Not applicable. As above, no training set in the AI/ML sense.

Ask a specific question about this device

The ABL90 FLEX analyzer is an in vitro diagnostic, portable, automated analyzer that quantitatively measures neonatal bilirubin in heparinised capillary whole blood. The ABL90 FLEX analyzer is intended for use by trained technologists, nurses, physicians and therapists. It is intended for use in a laboratory environment, near patient or point-of-care setting. These tests are only performed under a physician's order. Bilirubin measurements on the ABL90 FLEX analyzer are intended to aid in assessing the risk of kernicterus in neonates.

The ABL90 FLEX is a portable, automated system intended for in vitro testing of samples of whole blood for the parameters pH, pO2, pCO2, potassium, sodium, chloride, glucose, lactate, neonatal bilirubin and co-oximetry parameters (total hemoglobin, oxygen saturation, and the hemoglobin fractions FO2Hb, FCOHb, FMetHb, FHHb and FHbF). The ABL90 FLEX consists of an instrument with a sensor cassette and a solution pack as the main accessories. Multiple models of sensor cassettes are available. The various sensor cassette models for different parameter combinations. For each parameter combination, models allowing for different test load are available. The solution pack is available in one model. The ABL 90 FLEX electrochemical sensors are miniaturized, manufactured by film technology and integrated in a common sensor cassette. Likewise, the ABL90 FLEX optical oxygen sensor is integrated in the sensor cassette. A 256-pixel array spectrophotometer is used for the co-oximetry parameters and bilirubin.

Here's a breakdown of the acceptance criteria and study information for the ABL90 FLEX device, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance:

• Capillary mode: Total %CV from 1.4% to 3.8%
• Syringe mode: Total %CV from 1.3% to 4.6%
  Spiked Adult Whole Blood (1-day pooled):
• Capillary mode: Total %CV from 1.6% to 14.0%
• Syringe mode: Total %CV from 1.0% to 8.7%
  Spiked Adult Whole Blood & Cord Blood (1-day lab):
• Capillary mode: Total %CV from 1.1% to 7.7% for adult, 0.9% to 7.4% for cord. |
  | Method Comparison (vs. Predicate ABL800 FLEX) | Good correlation with the predicate device and very good agreement between the two modes. | Syringe mode (pooled): Slope = 0.9903 (95% CI: 0.975-1.005), Intercept = 0.6574, R² = 0.9878
  Capillary mode (pooled): Slope = 0.9760 (95% CI: 0.961-0.991), Intercept = 0.7741, R² = 0.9861 |
  | Linearity | Linear over the entire measuring range and fulfills requirements for allowable error due to non-linearity. | Linear (first order) over the entire measuring range. R² = 0.9996 for Bilirubin: ABL90 vs. Sample Conc. |
  | Interference (Non-Significant) |

Ask a specific question about this device

The Jaundice Meter (JM-105) is a non-invasive transcutaneous bilirubinometer. It measures yellowness of subcutaneous tissue in newborn infants. The unit pro-vides a visual digital measurement that has been shown to correlate with serum bilirubin in newborn infants.

The device is intended for use in hospitals, clinics or doctor's offices under a physicians supervision / direction to assist clinicians in monitoring of newborn infants. The device is not intended as a standalone for diagnosis of hyperbilirubinemia. It is to be used in conjunction with other clinical signs and laboratory measurements.

Newborn infants whose JM-105 Jaundice Meter test results are indicative of hy-perbilirybinemia should be evaluated by their physician(s) for appropriate patient management. Specific neonatal patient Bilirubin levels should be confirmed by other methods, such as serum bilirubin, prior to treatment determinations.

The JM 105 is a prescription medical device

• The JM 105 is not intended for home use.
  The JM 105 may only be used at the sternum measurement site for Physician's office applications.

The Jaundice Meter is a non-invasive transcutaneous bilirubinometer. It measures yellowness of subcutaneous tissue in newborn infants. The unit provides a visual digital measurement that has been shown to correlate with serum bilirubin in newborn infants.

The JM-105 is a portable, hand held, battery powered device that includes a docking station with a built in reading checker. The JM-105 batteries can be charged using a battery charger or an optional USB cable.

The basic functionality including measurement of the JM-105 is equivalent to the JM-103. The display of the JM-105 has been improved (larger screen, touchscreen) and data storage and transmission functionality was added. The measuring probe, hardware, and software used to process the measurements are identical and therefore use the same measuring principle. The JM-103 and JM-105 determines the yellowness of subcutaneous tissue by using two optical paths to measure the optical density difference at two wavelengths. The measuring principle is further described in the "Principles of Operations" section of the Instructions for Use.

In addition to the features offered with the JM-103, the JM-105 provides the following.

• Internal memory up to 100 patient files
• Data transfer via HL7
• Easily mark & ID babies that need special attention with patient flagging
• Cost-efficient screening

There are no sterile or single-use components or accessories for the JM-105.

Here's an analysis of the acceptance criteria and study information for the Draeger Medical Systems Jaundice Meter JM-105, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

Notes on Acceptance Criteria: The document primarily refers to the JM-103's performance criteria as the basis for substantial equivalence for the JM-105, stating that the measuring principle and core functionality are identical. The accuracy mentioned is specifically for infants > 35 weeks gestation.

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

• Hospital Studies (JM-103):

  • Sample Size: Not explicitly stated as a number of patients or measurements. The document mentions "All patients meeting the above criteria were included in the study."
  • Data Provenance: Not explicitly stated, but the context of an FDA submission for a US market device generally implies studies either conducted in or accepted by the US regulatory framework. It's retrospective inference, as the studies were performed previously for the predicate JM-103.
  • Retrospective/Prospective: The initial studies for the JM-103 would have been prospective, as new data was collected to demonstrate performance. The JM-105 relies on this previously collected data.

• Doctor's Office Studies (JM-103):

  • Sample Size: Not explicitly stated as a number of patients or measurements.
  • Data Provenance: Not explicitly stated, but implies clinical sites (doctor's offices) where the device was intended for use.
  • Retrospective/Prospective: Same as hospital studies, likely prospective for the JM-103, now serving as retrospective for JM-105.

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

• Number of Experts: Not explicitly stated.
• Qualifications of Experts: Not explicitly stated. The ground truth method (serum bilirubin) implies that clinical laboratory professionals would be involved in generating the comparison data, and physicians would be involved in determining the need for serum bilirubin tests.

4. Adjudication Method for the Test Set

• No specific adjudication method (e.g., 2+1, 3+1) is mentioned or implied for either the transcutaneous bilirubin readings or the serum bilirubin ground truth. The comparison is directly between the device measurement and the laboratory measurement.

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

• No MRMC comparative effectiveness study is mentioned. The device, a Jaundice Meter, provides a direct measurement and is not an imaging or diagnostic AI requiring human interpretation or assistance for its primary function. Its use is to assist clinicians in monitoring, not to replace their diagnostic decision-making or enhance their reading of complex medical images. Therefore, the concept of "human readers improve with AI vs without AI assistance" does not directly apply in this context.

6. Standalone Performance Study (Algorithm only without human-in-the-loop performance)

• Yes, the clinical performance data described for the JM-103 (and relied upon for the JM-105) is a standalone performance study. The device provides a direct measurement (transcutaneous bilirubin), which is then compared against the established ground truth (serum bilirubin). There is no "human-in-the-loop" interaction for interpreting the device's reading itself; the reading is digital and absolute. The clinicians then use this reading in conjunction with other clinical signs.

7. Type of Ground Truth Used

• Ground Truth: Laboratory measured total serum bilirubin (TSB).

8. Sample Size for the Training Set

• The document does not describe a "training set" in the context of an AI/ML algorithm. The JM-103/JM-105 is a device based on an optical measurement principle, not a machine learning model that undergoes a training phase. Its internal parameters would be set during design and calibration, not through iterative training on a dataset in the modern AI sense.

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

• As noted above, there is no mention of a "training set" for an AI/ML algorithm. The device's measurement principle (optical density difference at two wavelengths) is based on established biophysical principles, not an AI model that learns from data.

Ask a specific question about this device

The neonatal bilirubin test used on RAPIDPoint® 405 systems is an in vitro diagnostic test for the determination of total neonatal bilirubin (nBili) concentration in the whole blood of newborn infants. Measurement of nBili aids in assessing the risk of kernicterus. This test is intended for use in point of care or laboratory settings.

Neonatal Bilirubin (nBili) is a new parameter offered on the RAPIDPoint 405 (RP405) blood gas system. The RP405 system is a point of care and laboratory testing blood gas analyzer and currently measures a variety of parameters that have been previously cleared. Enabling the nBili measurement is accomplished through software design changes introduced in Software Version 3.7. No hardware or mechanical changes were needed.

Here's a breakdown of the acceptance criteria and study information for the Siemens RAPIDPoint® 405 System Neonatal Bilirubin (nBili) Test, based on the provided 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Approximately 200 samples (combining internal and external evaluations).
• Data Provenance:
  • Internal Evaluation: Unconjugated bilirubin in oxygenated cord whole blood (mimics neonatal samples). This suggests laboratory-controlled samples, likely prepared in a laboratory setting.
  • External Evaluation: Intended use neonatal whole blood samples from multiple point-of-care sites. This indicates prospective, real-world clinical samples collected from neonates within various healthcare facilities.

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

The document does not specify the number of experts used or their qualifications for establishing ground truth. The ground truth was established by comparison to the predicate devices.

4. Adjudication Method for the Test Set

The document does not describe an adjudication method for the test set. Performance was assessed by comparing the device's measurements directly to those of the predicate devices.

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

No, a Multi Reader Multi Case (MRMC) comparative effectiveness study was not done. This device is an automated in vitro diagnostic system for measuring bilirubin, not an imaging device requiring interpretation by human readers. Therefore, the concept of "human readers improve with AI vs without AI assistance" does not apply here.

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

Yes, a standalone study was done. The "Assessment of Performance" section describes the device's performance in measuring nBili directly, without human intervention in the measurement process itself. The system uses "iterative least squares analysis" and "correction for hematocrit to produce nBili results," indicating an automated algorithm.

7. Type of Ground Truth Used

The ground truth used was comparison to a predicate device. Specifically, "Specimens were evaluated against the RAPIDLab 1245 and 1265 predicate devices." This means the measurements from the RAPIDPoint® 405 System were compared against the established measurements from the legally marketed and previously cleared predicate devices to demonstrate substantial equivalence.

8. Sample Size for the Training Set

The document does not provide information on a separate training set or its sample size. This type of 510(k) submission for an in vitro diagnostic device, especially one involving a software update to an existing platform for a new parameter, often focuses on validation against a predicate rather than detailed machine learning model training data.

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

Since no independent training set or machine learning model training details are described, the document does not explain how ground truth for a training set was established. The focus is on demonstrating clinical performance and substantial equivalence.

Ask a specific question about this device

The neonatal bilirubin test intended use on the Rapidlab 1245 and Rapidlab 1265 analyzers is an in vitro diagnostic test for the determination of total neonatal bilirubin (nBili) concentration in the whole blood of newborn infants. Measurement of nBili aids in assessing the risk of kernicterus.

Neonatal Bilirubin (nBili) is a new parameter enabled on models 1245 and 1265 of the Rapidlab® 1200 blood gas family of instruments. It is intended as an in vitro diagnostic test for the determination of total neonatal Bilirubin (nBili) concentration in the whole blood of newborn infants. Enabling the nBill measurement is accomplished through software design changes introduced in Rapidlab Software Version 2.1. No hardware /mechanical changes were needed.

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

Acceptance Criteria and Device Performance for Neonatal Bilirubin (nBili) on Rapidlab® 1200 Blood Gas Systems

1. Table of Acceptance Criteria and Reported Device Performance:

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

• Sample Size: 2,241 samples.
• Data Provenance: The samples were described as "unconjugated bilirubin in oxygenated whole blood (neonatal type samples)". The text does not explicitly state the country of origin or if the data was retrospective or prospective, but the nature of the samples suggests clinical relevance to neonates. It was an "internal evaluation study."

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

The document does not provide information on the number of experts, their qualifications, or their role in establishing the ground truth if a gold standard method was used. The study primarily compares the device's measurement against predicate devices, rather than an expert human interpretation.

4. Adjudication Method for the Test Set:

Not applicable. The study involved instrumental measurements, not human interpretation that would require adjudication.

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

No, an MRMC comparative effectiveness study was not done. The device measures a biochemical marker (bilirubin concentration) rather than interpreting medical images or clinical observations that would typically involve human readers. The study compared the device's performance against predicate devices.

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

Yes, a standalone study was performed. The "nBili internal evaluation study" assessed the performance of the Rapidlab 1245 and 1265 in measuring neonatal bilirubin concentrations. This device, being a diagnostic instrument (blood gas system), inherently operates in a standalone manner to provide quantitative results. The human involvement is in operating the device and interpreting its output, not in performing the measurement itself.

7. Type of Ground Truth Used:

The ground truth for the test set was established by comparing the Rapidlab 1200 systems' nBili measurements against "predicate devices" (Radiometer ABL735 and ABL800 FLEX). The study aimed to demonstrate "substantial equivalence" to these established devices across the reporting range. Therefore, the ground truth was effectively the measurements obtained from these predicate devices.

8. Sample Size for the Training Set:

The document does not provide information about a separate training set or its sample size. The focus is on the performance of the device's software, which "was enabled through software changes." The 2,241 samples appear to be for validation/testing, not for training a machine learning model. This suggests that the "software changes" were likely based on established physiological models or signal processing algorithms, rather than iterative machine learning training.

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

Not applicable, as no explicit training set for a machine learning model is mentioned. The device's measurement technology relies on "multiple wavelength spectrophotometry (CO-oximetry)" and "iterative least squares analysis" to determine bilirubin values, which are then "corrected for hematocrit." This description points to a deterministic algorithm based on scientific principles and calibration, rather than a system trained on data with established ground truth.

Ask a specific question about this device

The Jaundice Meter (JM-103) is a non-invasive transcutaneous bilirubinometer. It measures yellowness of subcutaneous tissue as a shown to correlate with serum bilirubin in newborn infants. The device is intended for use in hospitals, clinics or doctor's offices under a physician's direction to assist clinicians in monitoring of newborn infants. The device is not intended as a standalone for diagnosis of hyperbilirubinemia. The device is intended to be used in conjunction with other clinical signs and laboratory measurements. Newborn infants whose JM-103 Jaundice Meter test results are indicative of hyperbilliubinemia should be evaluated by their physician(s) for appropriate patient management. JM-103 test results should be confirmed by other methods, such as serum bilirubin, prior to treatment determinations. The JM 103 is a prescription Medical Device. The JM 103 is not intended for home use. The JM 103 may only be used at the sternum measurement site for Physician's office applications.

The JM-103 Jaundice Meter is designed to provide a transcutaneous measurement of bilirubin displayed in Mg/dl or umol/L. This measurement is intended as a screening tool to determine when a serum bilirubin measurement should be taken, or, sequential bilirubin measurements over time to provide indication of change. This device is not intended for determinations of whether treatment is indicated. The determination of treatment must be based on a serum bilirubin measurement.

The provided text does not contain detailed information about acceptance criteria or a study proving the device meets those criteria. The document is a 510(k) summary for the Draeger Air Shields Infant Care Inc. Minolta Draeger Air Shields JM 103 Jaundice Meter. It primarily focuses on demonstrating substantial equivalence to a predicate device (K021622 JM 103 Jaundice Meter) and provides an "Indications for Use Statement."

Here's an analysis based on the absence of the requested information:

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

• Information not provided. The document does not specify any quantitative acceptance criteria or report specific performance metrics from a study conducted for this 510(k) submission. It states "No modification to hardware, software, or procedures for use were implemented for this submission on the JM 103 Device previously cleared by the FDA as a medical device," implying that performance was established during the predicate device's clearance.

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

• Information not provided. No details are given about a test set sample size or its provenance.

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)

• Information not provided. The document does not mention the use of experts or ground truth establishment for a test set.

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

• Information not provided. There is no mention of adjudication methods.

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

• Not applicable. The device is a Jaundice Meter, a non-AI diagnostic tool for transcutaneous bilirubin measurement, not an AI-assisted imaging device or system. No MRMC study would be relevant in this context.

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

• Not applicable. The JM 103 is a standalone device in that it provides a measurement directly. However, it's explicitly stated that it's "not intended as a standalone for diagnosis" and its results "should be confirmed by other methods, such as serum bilirubin, prior to treatment determinations." This indicates it's a screening tool that operates independently but requires human medical interpretation and follow-up. Since it's not an AI algorithm, "algorithm only" performance is not a relevant concept here.

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

• Information not provided for this submission. The document states the device "has been shown to correlate with serum bilirubin in newborn infants." This implies that the ground truth for its initial development and validation (likely for the predicate device) would have been serum bilirubin measurements, which are established clinical standards for diagnosing hyperbilirubinemia.

8. The sample size for the training set

• Information not provided. The device is not an AI/machine learning device, so the concept of a "training set" in that context does not apply.

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

• Information not provided. As above, the concept of a training set is not applicable.

Summary based on the provided text:

The submission for the JM 103 Jaundice Meter is a 510(k) for a device that had "No modification to hardware, software, or procedures for use" from a previously cleared device. Therefore, the core performance characteristics and "acceptance criteria" are presumed to have been met by the predicate device (K021622 JM 103 Jaundice Meter). This 510(k) is about demonstrating substantial equivalence rather than presenting new performance data from clinical studies. The device's function is to provide a transcutaneous bilirubin measurement that correlates with serum bilirubin, acting as a screening tool, not a definitive diagnostic or treatment determination device.

Ask a specific question about this device

The Roche Diagnostics OMNI S Analyzer is a fully automated critical care analyzer intended to be used for the measurement of pH, PO2, PCO2, sodium, potassium, ionized calcium, chloride, hematocrit, glucose, lactate, urca/BUN, bilirubin, total hemoglobin, oxygen saturation, oxyhemoglobin, deoxyhemoglobin, carboxyhemoglobin and methemoglobin in samples of whole blood, serum, plasma and aqueous solutions as appropriate.

The Roche Diagnostics OMNI S Analyzer is a fully automated critical care analyzer intended to be used for the measurement of pH, PO2, PCO2, sodium, potassium, ionized calcium, chloride, hematocrit, glucose, lactate, urea/BUN, bilirubin. hemoglobin, oxygen saturation, oxyhemoglobin, total deoxyhemoglobin, carboxyhemoglobin and methemoglobin in samples of whole blood, serum, plasma and aqueous solutions as appropriate.

The provided text describes a 510(k) submission for a bilirubin assay rather than a medical device or AI algorithm with performance metrics like sensitivity, specificity, or AUC. The document focuses on establishing substantial equivalence to predicate devices for regulatory clearance, not on demonstrating performance against clinical acceptance criteria in the way an AI diagnostic would.

Therefore, many of the requested categories for AI device studies (e.g., sample size of test set, number of experts, adjudication method, MRMC studies, standalone performance, training set details) are not applicable or cannot be extracted from this type of regulatory submission. The document primarily discusses method comparison studies with existing commercial assays.

Here's an attempt to answer the questions based only on the provided text, highlighting the limitations:

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

The document does not explicitly state quantitative "acceptance criteria" for the bilirubin assay in terms of diagnostic performance (e.g., sensitivity, specificity, or accuracy targets). Instead, it discusses "acceptable performance" through method comparison studies with 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, "The bilirubin parameter for use on the OMNI S Analyzer was compared to several legally marketed analyzers in the method comparison studies." However, it does not specify the sample size for these method comparison studies or the data provenance (country of origin, retrospective/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)

Not applicable. For laboratory assays like this, "ground truth" is typically established by reference methods or validated predicate devices, not by expert interpretation in the same way as imaging diagnostics. The text does not mention any human experts establishing ground truth for the test set.

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

Not applicable. Adjudication methods are typically used in imaging or clinical studies where subjective human interpretation needs to be reconciled. For a bilirubin assay, results are quantitative measurements, and reconciliation would involve comparing numerical values, not subjective interpretations. The text does not mention any adjudication method.

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

Not applicable. This is a laboratory assay for measuring a biomarker, not an AI-assisted diagnostic device that would involve human readers or image interpretation.

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

This refers to a standalone device, which is what the OMNI S Analyzer with the bilirubin assay is. It operates without human interpretation of results in the diagnostic pipeline beyond reading the numerical output. The entire development process would inherently evaluate its standalone performance by comparing its results to predicate devices.

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

The "ground truth" for this bilirubin assay is established by comparison to results obtained from legally marketed predicate bilirubin assays on other analyzers (Roche Hitachi Analyzers, Radiometer ABL735, Beckman LX®20 System, Kodak Vitros System). These predicate devices are considered the "truth" for establishing equivalence.

8. The sample size for the training set

Not applicable. This is a chemical assay, not an AI algorithm. There is no concept of a "training set" in the context of developing this type of device.

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

Not applicable, as there is no training set for this type of device.

Ask a specific question about this device

The Jaundice Meter (JM-103) is a non-invasive transcutaneous bilirubinometer. It measures yellowness of subcutaneous tissue in newborn infants and displays a measured value which has been shown to correlate with serum bilirubin. The device is for use in the hospital to assist clinicians in monitoring the status of newborn infants for the development of hyperbilirubinemia. The device is not intended as a standalone for diagnosis of hyperbilirubinemia. It is to be used in conjunction with other clinical signs and laboratory measurements. Newborn infants whose Jaundice Meter (JM 103) test results are indicative of hyperbilirubinemia are evaluated by their doctor(s) for appropriate patient management. Bilirubin levels should be confirmed by other methods, such as serum bilirubin, prior to treatment determinations. This device is not intended for home use. This is a prescription device.

The JM 103 Jaundice Meter is designed to provide a non-invasive measurement of the yellowness of subcutaneous tissue. This measurement is converted to an estimated bilirubin concentration and displayed in units of mg/dL or umole/L. This measurement is taken using a dual path optical system. The measurements from each path are then subtracted to minimize the impact of skin pigmentation. The software in the device then computes the estimated bilirubin concentration based on an established correlation coefficient.

Acceptance Criteria and Study for Minolta Hill-Rom Air Shields JM 103 Jaundice Meter

This document outlines the acceptance criteria for the Minolta Hill-Rom Air Shields JM 103 Jaundice Meter and details the clinical study performed to demonstrate its performance.

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly state pre-defined acceptance criteria in terms of specific thresholds for correlation coefficient (r) or standard deviation (SD). However, the clinical study's results (correlation and SD) serve as the device's demonstrated performance, indicating what was considered acceptable by the FDA for market clearance. The predicate device (JM 102) itself is the benchmark for "substantial equivalence."

Note: The acceptance criteria are "implied" because the document focuses on demonstrating correlation and performance, rather than setting a pass/fail threshold. The FDA's clearance indicates that these demonstrated performance metrics were deemed substantially equivalent to the predicate device.

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

• Sample Size:
  • Site A: 513 (for both forehead and sternum measurements per patient, presumably)
  • Site B: 100 (for both forehead and sternum measurements per patient, presumably)
  • Total: 613 patients across two sites.
• Data Provenance: The study was a prospective clinical assessment performed at two study sites. The specific country of origin is not explicitly stated, but given the manufacturer (Hill-Rom Air Shields, Hatboro, PA) and the FDA submission, it is highly probable the studies were conducted in the United States.

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

The document does not provide details on the number of experts or their qualifications for establishing the ground truth. It states that the JM 103 estimated bilirubin concentration was correlated with total serum bilirubin concentration. This indicates that the ground truth was derived from laboratory measurements of total serum bilirubin, which is a standard and objective clinical assay, rather than expert consensus on transcutaneous measurements. Therefore, direct "experts" for ground truth establishment in the traditional sense (e.g., radiologists assessing images) would not be applicable here.

4. Adjudication Method for the Test Set

Since the ground truth was established by total serum bilirubin (TSB) laboratory measurements, an adjudication method (like 2+1 or 3+1 for expert review) is not applicable or mentioned. TSB results are quantitative and typically considered definitive for bilirubin levels in this context.

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

There is no indication of an MRMC comparative effectiveness study being performed. The study aimed to establish the correlation between the JM 103 device and serum bilirubin, not to compare human reader performance with and without AI assistance. The JM 103 is a measurement device, not an AI-assisted diagnostic tool that aids human interpretation.

6. Standalone (Algorithm Only) Performance Study

Yes, a standalone performance study was done. The clinical assessment directly demonstrates the performance of the JM 103 device (algorithm only, as it's a physical device with embedded software) in correlating its transcutaneous bilirubin measurements with total serum bilirubin (ground truth). The reported "r" and "SD" values represent this standalone performance. The device is intended to assist clinicians, but its correlation and accuracy are assessed independently of human interpretation of its raw output.

7. Type of Ground Truth Used

The type of ground truth used was laboratory measurements of Total Serum Bilirubin (TSB). This is a direct, objective biochemical measurement of bilirubin concentration in the blood, considered the clinical standard for establishing bilirubin levels.

8. Sample Size for the Training Set

The document does not specify a separate training set or its sample size. The clinical assessment described appears to be the primary dataset used to demonstrate the device's performance and correlation. It's possible the "established correlation coefficient" mentioned in the device description refers to internal data or previous models (e.g., from the JM 102), but this is not detailed. The provided study focuses on validation/performance assessment of the device as a whole. Without a clear indication of a distinct training phase/set, it's assumed the device's underlying algorithm was potentially developed using other data, but the performance reported relates to the final product on the described clinical study population.

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

As a separate "training set" is not explicitly mentioned or detailed, the method for establishing its ground truth cannot be determined from the provided text. If the "established correlation coefficient" refers to the model built into the device, it would likely have been established through a similar process of correlating transcutaneous measurements with laboratory-confirmed total serum bilirubin (TSB).

Ask a specific question about this device

Ask a specific question about this device

Ask a specific question about this device