Search Results

Emily's Care Nourish Test System (Model 1) quantitatively measures the concentration of protein, fat (triglycerides), and carbohydrates (lactose) in human milk. It also provides calculated values for calories (energy). These measurements, in conjunction with other clinical assessments, may be used to aid in the nutritional management of newborns, including preterm, and infants.

This device is intended for use in healthcare by trained healthcare personnel at point of care or clinical laboratory settings.

The device is for prescription use only.

The Emily's Care Nourish Test System (Model 1) is an in vitro diagnostic device that consists of the following:

• 1. iPhone models 12 mini. 12 pro. 12 pro max. 13. 13 pro max, 14 or 14 pro max running iOS 16 or 17
• 2. Free Emily's Care app to be downloaded on the iPhone app store
• 3. Single-use test strips, in a desiccant-lined vial
• 4. Single-use reference card to place the test strip on to be read
• 5. Pipettes and tubes to collect milk
• 6. Lightbox

The provided text is a 510(k) summary from the FDA for the Emily's Care Nourish Test System (Model 1). It primarily focuses on the regulatory aspects of device clearance rather than a detailed study report on acceptance criteria and performance. Therefore, I cannot provide a complete answer to all parts of your request based solely on the provided text.

Specifically, the document does not contain:

• A table of acceptance criteria and reported device performance (only ranges are given for measuring various components).
• Details on sample sizes used for the test set, data provenance, or details about training sets.
• Information on the number or qualifications of experts, adjudication methods, or MRMC comparative effectiveness studies.
• Information on standalone algorithm performance or the type of ground truth used beyond stating that the device measures "macronutrients."

However, I can extract the following information relevant to your request based on the provided text:

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

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics. It indicates acceptable measuring ranges for the macronutrients, which can be seen as implicit acceptance criteria for the device's measurement capabilities.

The document states that "The Emily's Care Nourish Test System underwent bench testing to evaluate its performance characteristics, including precision, accuracy (bias), linearity, sensitivity, and interference." While these are the types of performance characteristics evaluated, the specific acceptance criteria and the numerical results are not provided in this summary.

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

This information is not provided in the given text.

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)

This information is not provided in the given text.

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

This information is not provided in the given text.

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

This information is not provided in the given text, and it's generally not applicable to this type of IVD device which measures macronutrients, rather than an AI-assisted diagnostic imaging device for human readers.

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

The device is described as an "in vitro diagnostic device" that quantitatively measures macronutrients using an iPhone running an app, single-use test strips, a reference card, pipettes, tubes, and a lightbox. This implies a "standalone" measurement system in the sense that the device itself performs the measurement and calculation, but it is explicitly intended for "use in healthcare by trained healthcare personnel." Therefore, it's not an "algorithm-only" performance study in the sense of AI-driven image analysis without human interaction, but rather a system performance. No separate "standalone" study is specifically detailed, as the entire system's performance is intended for the test.

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

The document states the device "quantitatively measures the concentration of protein, fat (triglycerides), and carbohydrates (lactose) in human milk." For such a device, ground truth would typically be established by reference laboratory methods (e.g., gold-standard chemical assays or spectroscopy) that are highly accurate for measuring these macronutrients in breast milk. The text does not explicitly state which specific "gold standard" methods were used as ground truth for comparison.

8. The sample size for the training set

This information is not provided in the given text. Given the device uses a colorimetric principle with an iPhone camera, it would likely involve some form of calibration or training data for the image analysis algorithm, but specifics are absent.

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

This information is not provided in the given text.

Ask a specific question about this device

The Miris Human Milk Analyzer (HMA) quantitatively measures the concentration of fat, protein, and carbohydrate in human milk. The Miris HMA also provides calculated values for total solids and energy. These measurements, in conjunction with other clinical assessments, may be used to aid in the nutritional management of newborns, including preterm, and infants. This device is intended for use in healthcare by trained healthcare personnel at clinical laboratories. The Miris HMA is also intended for use by personnel trained in the use of the device at Human Milk Banking Association of North America (HMBANA) accredited human milk banks, for the purpose of labeling milk donations and in the processing of milk donations.

The Miris Human Milk Analyzer (HMA) includes a mid-infrared (mid-IR) spectroscopy system and a man-machine interface (MMI). The user is guided by the interactive MMI, via the screen, through the measurement process by use of the six-button controlled menu system. Milk samples are injected into the measuring unit (cuvette) via the instrument inlet using a syringe (sample volume 3 mL), excess sample and waste exiting via the outlet.

The device consists of the following components and accessories: an instrument casing with sample inlet and outlet holding a measurement unit and electronics mainboard, with AC/DC adapter, syringes for injection of sample, zero-setting solution, quality control solutions, and cleaning agent, waste container (not provided by the manufacturer), and outlet tubes.

The Miris Human Milk Analyzer (HMA) is a medical device that quantitatively measures the concentration of fat, protein, and carbohydrate in human milk. It also provides calculated values for total solids and energy, which can be used alongside other clinical assessments to aid in the nutritional management of newborns and infants. The device is intended for use by trained healthcare personnel in clinical laboratories and by personnel in Human Milk Banking Association of North America (HMBANA) accredited human milk banks.

Here's an analysis of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document details various performance characteristics. Below is a table summarizing the acceptance criteria and the device's reported performance where available and explicitly stated. For some categories, the acceptance criteria are implied by the "acceptable" or "met all expected performance" statements as explicit numerical criteria are not always provided.

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

• Precision Study (Test Set 1):

  • Sample Size:
    • Main site (E): 5 human milk samples.
    • Secondary sites (F, G): 5 human milk samples (same as main site).
  • Data Provenance: The study was performed at three US human donor milk bank sites in February and March 2022. These were:
    • Mothers' Milk Bank (San José, USA) - Main site (E)
    • Mid-Atlantic Mothers' Milk Bank 'Three Rivers' (Pittsburgh, USA) - Secondary site (F)
    • The New York Milk Bank, Inc., (New York, USA) - Secondary site (G)
  • Nature of Data: Prospective, as it involved actively testing samples with the device at the specified sites.

• Linearity Study (Test Set 2):

  • Sample Size: Not explicitly stated as a number of distinct samples for the new linearity study. However, the study evaluated the linear range for Fat, CP, TP, CHO, TS, and E over specified intervals.
  • Data Provenance: Not explicitly stated, but it's a new study undertaken for this 510(k) submission, implying prospective data generation.

• Trueness, Method Comparison Testing (Test Set 3):

  • Sample Size: 112 human milk samples (plus 1 extra sample for replacement if needed).
  • Data Provenance: Not explicitly stated where the samples originated from, but the study compared Miris HMA analysis to biochemical standard methods. The study was conducted following CLSI EP09c guideline, implying a rigorous, likely prospective, assessment.

• Detection Capability, Interference, and Carry Over: For these studies, the document states "Data concerning the Miris HMA... were included in DEN180007." This indicates the data was retrospective (from the predicate device's submission). The sample sizes are not detailed in this section for those previous studies.

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

This information is not provided in the document. For the Miris HMA, the "ground truth" for macronutrient content is established by biochemical standard methods, not expert consensus. The experts involved would likely be laboratory technicians or specialists trained in performing these reference methods.

4. Adjudication Method for the Test Set

Adjudication methods (like 2+1, 3+1 for resolving disagreements) are typically used in studies involving human interpretation of results, especially for imaging or diagnostic decision-making.

For the Miris HMA, the ground truth is established by objective biochemical standard methods and precise measurements, not by subjective human interpretation that would require an adjudication process. Therefore, an adjudication method as commonly understood in expert review is not applicable and not mentioned.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done

No, an MRMC comparative effectiveness study was not done.

MRMC studies typically compare the diagnostic accuracy of multiple readers interpreting medical cases, often with and without AI assistance, to measure the "effect size" of AI improvement. The Miris HMA is an automated analytical device that provides quantitative measurements, not an AI interpretation system requiring human readers. Therefore, this type of study design is not relevant to this device.

6. If a Standalone Study (Algorithm Only Without Human-in-the-Loop Performance) was done

Yes, the Miris HMA performance studies are essentially standalone.

The device itself is an automated analyzer. The precision, linearity, and method comparison studies evaluate the device's output (measurements of fat, protein, carbohydrate, total solids, and energy) without direct human intervention in the measurement process itself beyond operating the machine and preparing samples. The "ground truth" is established by independent, objective laboratory reference methods. The device's performance is assessed purely on how accurately and precisely it measures the macronutrients compared to these reference methods.

7. The Type of Ground Truth Used

The ground truth used for the Miris HMA performance studies (Trueness/Method Comparison) was based on biochemical standard methods:

• Fat: Röse Gottlieb (ISO 1211)
• Crude Protein: Kjeldahl (ISO 8968-1)
• True Protein: Kjeldahl crude protein * 0.8
• Total CHO (Carbohydrate): Calculated by difference from values obtained by comparative methods.
• Total Solids (TS): Drying oven (ISO 6731)
• Energy: Bomb calorimetry (ISO 1928)

These are recognized, validated laboratory reference methods for analyzing macronutrients in human milk.

8. The Sample Size for the Training Set

The document does not explicitly state the sample size used for the training set of the Miris HMA. The device uses mid-infrared spectroscopy with an internal calibration. While calibration involves a set of reference samples, the term "training set" is more commonly associated with machine learning or AI models. Given that the device is based on Beer's law (absorbance proportional to concentration) and an internal calibration, the training set would refer to the samples and methods used to establish and validate this internal calibration curve. This information is not detailed in the provided summary.

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

Similar to point 8, the specific details of how the ground truth for the training set (i.e., the samples used for the device's internal calibration) were established are not provided. However, it is highly probable that the ground truth for these calibration samples would have been established using the same (or similar) biochemical standard methods as described for the Trueness/Method Comparison study (Röse Gottlieb, Kjeldahl, Drying oven, Bomb calorimetry, etc.), as these are the gold-standard methods for determining macronutrient content in milk.

Ask a specific question about this device

The Miris Human Milk Analyzer (HMA) quantitatively measures the concentration of fat, carbohydrate, and protein in human milk. The Miris HMA also provides calculated values for total solids and energy. These measurements, in conjunction with other clinical assessments, may be used to aid in the nutritional management of newborns, including preterm, and infants. This device is intended for use in healthcare by trained healthcare personnel at clinical laboratories.

The Miris Human Milk Analyzer (HMA) is a system for the quantitative measurement of fat, protein, and total carbohydrate content in human milk. The measurements of fat, protein and carbohydrate are also used in calculating the total solids and the energy content of human milk samples. The HMA unit includes a mid-infrared (mid-IR) spectroscopy system and a user interface. The user is guided by the interactive interface, via the screen, through the measurement process by use of the six-button controlled menu system. Milk samples (3 mL) are injected into the measuring unit (cuvette) via the instrument inlet using a syringe, with excess sample and waste exiting via the outlet.

The HMA device is comprised of a sample cuvette, hardware consisting of a mainboard and central processing unit (CPU) board, a display, touch button, fan, case, and consumables. The hardware consists of a mainboard with a CPU-board, detector board, and emitter board.

Here's a breakdown of the acceptance criteria and the study details for the Miris Human Milk Analyzer, based on the provided document:

Acceptance Criteria and Device Performance

The acceptance criteria are generally implied by the various performance studies conducted and the statements regarding the device's suitability for its intended use. The performance characteristics sections (L.1 and L.2) provide the reported device performance.

Study Details for Miris Human Milk Analyzer

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

   • Precision Studies:
     • Site 1: Minimum of 3 milk samples, 80 measurements per sample (20 days, 2 runs/day, 2 replicates/run).
     • Sites 2 & 3: Milk samples (number not specified, but at least 4-5 based on table rows), 30 measurements per sample (5 days, 2 runs/day, 3 replicates/run).
     • Provenance: "Native human milk samples." No specific country of origin is mentioned, but it's implied to be retrospective as samples are collected and then tested.
   • Linearity Studies: Minimum of 12 samples of known relative concentration. Provenance not specified.
   • Detection Limit Studies:
     • LoB: 4 blank samples, 60 measurements (5 days, 3 replicates/day/sample).
     • LoD & LoQ: 7 milk samples with low fat, and 7 samples with low protein/carbohydrate levels, 105 replicates per variable (5 days, 3 replicates/day/sample). Provenance not specified.
   • Analytical Specificity (Interference) Studies: 2 milk sample pools. Provenance not specified.
   • Accuracy (Method Comparison): 112 native human milk samples. Provenance not specified; implied retrospective.
   • Energy Accuracy (Bomb Calorimetry): (b)(4) native human milk samples. Provenance not specified.

2. 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):

   • No information is provided about experts establishing ground truth. Instead, reference laboratory methods were used. The document states: "The Miris Human Milk Analyzer is traceable to certified reference materials and validated chemical methods. The validation of these chemical methods was reviewed and found to be acceptable." For the accuracy studies, "validated comparative chemical methods" and a "validated bomb calorimetric method" were used.

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

   • There was no mention of an adjudication method in the context of expert review. For the method comparison studies, the reference method results were often a "mean of the triplicates results."

4. 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:

   • No MRMC comparative effectiveness study was conducted. This device is an analyzer for macronutrient composition, not an AI-assisted diagnostic device for human readers.

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

   • Yes, this entire evaluation describes the performance of the device in a standalone capacity. It quantitatively measures analytes in human milk directly, without human interpretation of raw data for results. The results are then used by healthcare providers.

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

   • The ground truth was established by validated chemical reference methods and certified reference materials. For energy, a validated bomb calorimetric method was used.

7. The sample size for the training set:

   • The document states that the instrument is "calibrated at the manufacturer site" using "(b)(4) calibration samples designed to cover the instrument calibration range." The specific number of samples beyond this redacted information is not provided.

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

   • For the training (calibration) set, "The calibration samples are prepared, and values are assigned using validated methods." This implies that the ground truth for calibration samples is also established using reference chemical methods, similar to the method comparison studies.

Ask a specific question about this device