K234088 · Lactation Lab, Inc. · QEI · May 3, 2024 · Clinical Chemistry
Device Facts
Record ID
K234088
Device Name
Emily's Care Nourish Test System (Model 1)
Applicant
Lactation Lab, Inc.
Product Code
QEI · Clinical Chemistry
Decision Date
May 3, 2024
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1493
Device Class
Class 2
Attributes
Software as a Medical Device, Real-World Evidence, Pediatric
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K234088 · May 3, 2024
Emily's Care Nourish Test System (Model 1)
Lactation Lab, Inc.
Published clinical literature (meta-analyses of human milk macronutrient composition)
The sponsor utilized meta-analysis data from peer-reviewed literature to define expected reference ranges for fat, protein, lactose, and calories in human milk for both term and preterm infants, providing clinical context for the device's measurements.
Meta-analysis; Reference ranges; Human milk composition; Clinical literature
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Meta-analysis of macronutrient composition of term and preterm human milk; Systematic review and meta-analysis; Follow-up/Duration: Various time points (Day 1-3 to Week 10-12)
Term (37-42 weeks) and preterm (<37 weeks) human milk samples; Number of Sites: Not applicable
Not applicable for this study
Concentration of fat, protein, lactose, and calories
Indications for Use
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.
Device Story
System uses enzyme-based test strips with three reagent pads to measure fat, protein, and lactose in human breast milk; colorimetric reaction occurs on pads; iPhone camera acts as spectrometer; Emily’s Care mobile app guides user, scans strip, interprets color changes, and calculates caloric content; used at point-of-care or clinical labs by trained healthcare personnel; results aid clinicians in nutritional management and growth monitoring of newborns; not for use with fortified milk or infant formula.
Clinical Evidence
Bench testing only. Precision evaluated per CLSI EP05-A3 (N=84 at site A; N=20 at sites B-F). Linearity evaluated across reportable ranges (R2 0.997-0.998). Interference testing per CLSI EP07 identified specific substances (e.g., folic acid, hemoglobin) causing bias. Method comparison against Miris HMA (N=113-115) showed strong correlation (R2 0.953-0.978). No clinical trials performed.
Technological Characteristics
Enzyme-based test strips with three reagent pads; colorimetric sensing; iPhone camera as spectrometer; mobile app for image processing and calculation; requires dedicated iPhone (12-14 series) running iOS 16/17; lightbox accessory; standalone system; non-sterile.
Indications for Use
Indicated for quantitative measurement of protein, fat, and carbohydrates in human milk to aid nutritional management of newborns, including preterm infants, in clinical or point-of-care settings by trained healthcare personnel.
Regulatory Classification
Identification
A breast milk macronutrients test system is a device intended to quantitatively measure fat, protein, and total carbohydrate content in human breast milk. These measurements, in conjunction with other clinical assessments, may be used to aid in the nutritional management of infants.
Special Controls
A breast milk macronutrient test system must comply with the following special controls:
*Classification.* Class II (special controls). The special controls for this device are:(1) Design verification and validation must include the following:
(i) An appropriate traceability plan, as determined by FDA, to minimize the risk of drift in the breast milk macronutrient test system results over time.
(ii) Data that demonstrate appropriate precision, as determined by FDA, of the breast milk macronutrients test system. Precision studies must include assessment of a minimum of three breast milk specimens containing different concentrations (low, medium, and high levels) of fat, carbohydrates, and protein. Precision data must include breast milk specimen measurements that are collected at a minimum of three laboratory sites.
(iii) Data that demonstrate appropriate measurement accuracy, as determined by FDA, of fat, carbohydrates, and protein in breast milk. Measurement accuracy data must include breast milk specimen measurements that are collected at a minimum of one laboratory site.
(iv) Data from studies appropriate, as determined by FDA, to demonstrate that the device is free from significant interference from substances that could be present in human milk, including hemoglobin, and medications that are used by breastfeeding subjects.
(2) The labeling required under § 809.10 of this chapter must include a limiting statement indicating that the results should be used only as an aid in the nutritional management of infants and not as the sole basis for making nutrition decisions.
{0}
FDA U.S. FOOD & DRUG ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY AND INSTRUMENT
## I Background Information:
A 510(k) Number
K234088
B Applicant
Lactation Lab Inc.
C Proprietary and Established Names
Emily's Care Nourish Test System (Model 1)
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| QEI | Class II | 21 CFR 862.1493 - Breast Milk Macronutrients Test System | CH - Clinical Chemistry |
## II Submission/Device Overview:
A Purpose for Submission:
New device
B Measurand:
Fat, lactose, and protein in breast milk
C Type of Test:
Quantitative, Colorimetric
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
III Intended Use/Indications for Use:
A Intended Use(s):
See Indications for Use below.
B Indication(s) for Use:
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.
C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
The Emily's Care Nourish Test System (Model 1) is not the sole basis for nutritional management of the newborn. Use of the Emily's Care Nourish Test System (Model 1) device is intended as part of an overall treatment plan and nutritional measures for newborns. The Emily's Care Nourish Test System (Model 1) is an aid to the healthcare providers’ standard of care assessment of nutritional management of newborns through monitoring of weight gain and growth.
Do not use the Emily's Care Nourish Test System (Model 1) with fortified human milk or infant formula.
Clinicians should follow clinical practice guidelines and standard of care when supplementing or fortifying human breast milk.
D Special Instrument Requirements:
1. iPhone Models 12 mini, 12 Pro, and 12 Pro Max, 13, 13 Pro, 13 Pro Max, 14, and 14 ProMax that run iOS 16 or 17 operating systems. Phones and iOS versions that are not validated for use with the candidate device will be prevented from opening the Emily’s Care App. The sponsor has added a statement to their labeling that the iPhones should be dedicated for use with the app.
2. Emily’s Care mobile iOS application provides guided instructions to use and scan the test strip, interpret the spectrometer readings into concentrations, and displays the final results.
K234088 - Page 2 of 16
{2}
K234088 - Page 3 of 16
## IV Device/System Characteristics:
### A Device Description:
The Emily's Care Nourish Test System (Model 1) is an analytical system designed to measure the concentration of fat, carbohydrates (lactose), and protein in human milk at point of care using an enzyme-based test strip (Macronutrient Breast Milk Test Strip) with three different reagent pads and a smartphone camera with an associated application as a spectrometer. The system is comprised of a dedicated iPhone validated for use with the device (not provided), the Emily’s Care app, test strips, a single use reference card, pipettes and tubes to collect the milk, and a lightbox.
### B Principle of Operation:
The Macronutrient Breast Milk Test Strip is an enzyme-based test strip that contains three separate reagent pads to measure the concentration of fat (triglycerides), carbohydrates (lactose), and total protein in human breast milk. The individual chemical coatings of each reagent pad produce specific enzymatic reactions coupled with a colorimetric dye, resulting in a color change on the test strip paper depending on the concentration of protein, fat (triglycerides) and carbohydrates (lactose) present in the breast milk sample. Calories (kcal/dl) are calculated based on these values. The test strip is placed on a reference card inside a lightbox and is scanned using the built-in functionality of the Emily’s Care mobile application and the phone’s camera.
The mobile application guides the user through the measurement steps and displays the final results.
### C Instrument Description Information:
1. Instrument Name:
Emily's Care Nourish Test System (Model 1)
2. Specimen Identification:
Specimens are identified and entered manually at the time of analysis.
3. Specimen Sampling and Handling:
Fresh specimens can be analyzed with no pretreatment. Samples that were stored refrigerated or frozen must be brought to 68-104°F prior to analysis. Complete instructions on sample handling are provided in the labeling.
4. Calibration:
There is no separate calibration step performed by the user.
{3}
K234088 - Page 4 of 16
5. Quality Control:
Recommendations for the quality control are provided in the labeling.
V Substantial Equivalence Information:
A Predicate Device Name(s):
Miris Human Milk Analyzer
B Predicate 510(k) Number(s):
DEN180007
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K234088 | DEN180007 |
| --- | --- | --- |
| Device Trade Name | Emily’s Care Nourish Test System (Model 1) | Miris Human Milk Analyzer |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | Quantitatively measures the concentration of fat, carbohydrates, and protein in human milk and provides calculated values for calories (energy). These measurements are used in conjunction with other clinical assessments, to aid in the nutritional management of newborns, including preterm, and infants. | Same |
| Sample type | Human Breast Milk | Same |
| General Device Characteristic Differences | | |
| Test System | Emily Care’s app run on an iPhone with a Lightbox | Miris Human Milk Analyzer |
| Measuring Range | Fat: 0.6 – 6.0 g/dL | Fat: 0.6 - 6.0 g/dL |
| | | Crude Protein: 0.8 – 3.0 g/dL |
| | Protein: 0.6 – 2.4 g/dL | True Protein: 0.6 – 2.4 g/dL |
| | Lactate: 4.5 – 9.5 g/dL | Carbohydrates: 6.6 – 8.7 g/dL |
| Testing Environment | Point-of-Care settings by trained professionals. | Clinical laboratory settings by trained professionals. |
| Sampling Method | Test strip dipped in breastmilk sample | Breastmilk samples are injected into the measuring |
{4}
K234088 - Page 5 of 16
| Device & Predicate Device(s): | K234088 | DEN180007 |
| --- | --- | --- |
| | | unit via the instrument inlet using a syringe |
| Principle of Operation | Spectrophotometry | Mid-infrared (mid-IR) transmission spectroscopy |
## VI Standards/Guidance Documents Referenced:
Clinical & Laboratory Standards Institute (CLSI) EP05-A3: Evaluation of Precision of Qualitative Measurement Methods Procedures; Approved Guideline – Third Edition
CLSI EP07 3rd Edition: Interference Testing in Clinical Chemistry
CLSI EP17-A2: Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures
Special Controls: 21 CFR 862.1493 Breast milk macronutrients test system special controls
## VII Performance Characteristics (if/when applicable):
### A Analytical Performance:
#### 1. Precision/Reproducibility:
The precision of the Emily’s Care Nourish Test System (Model 1) for measuring fat, protein, and lactose was evaluated following the CLSI EP05-A3 guideline. A precision study was conducted at site A by testing five milk samples on two devices by two operators over 21 different days, with duplicate measurements per run and two runs per day for a total of 84 measurements per sample.
Additional precision studies were conducted at sites B, C, D, E, and F (point-of-care sites and operators), where milk samples were analyzed using two devices by two operators over five days with duplicate measurements per run and two runs per day for a total of 20 measurements per sample.
| Protein | | | | Repeatability (within-run variation | | Intermediate Precision (within-lab variation) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Site | Sample | N | Mean (g/dL) | SD | CV% | SD | CV% |
| | | | | (g/dL) | | (g/dL) | |
| Site A | 1 | 84 | 0.9 | 0.05 | 5.6 | 0.05 | 5.6 |
| | 2 | 84 | 1.2 | 0.05 | 4.1 | 0.06 | 5.0 |
| | 3 | 84 | 0.6 | 0.03 | 4.9 | 0.03 | 4.9 |
{5}
| Protein | | | | Repeatability (within-run variation | | Intermediate Precision (within-lab variation) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Site B | 4 | 20 | 0.8 | 0.05 | 6.3 | 0.06 | 7.5 |
| | 5 | 20 | 0.9 | 0.06 | 6.7 | 0.06 | 6.7 |
| | 6 | 20 | 1.7 | 0.06 | 3.5 | 0.09 | 5.0 |
| | 7 | 20 | 1.1 | 0.07 | 6.4 | 0.08 | 7.3 |
| | 8 | 20 | 1.2 | 0.04 | 3.3 | 0.04 | 3.3 |
| Site C | 4 | 20 | 0.8 | 0.06 | 7.5 | 0.08 | 10.0 |
| | 5 | 20 | 0.9 | 0.05 | 5.6 | 0.06 | 6.7 |
| | 6 | 20 | 1.7 | 0.06 | 3.5 | 0.06 | 3.5 |
| | 7 | 20 | 1.1 | 0.05 | 4.5 | 0.06 | 5.5 |
| | 8 | 20 | 1.2 | 0.05 | 4.2 | 0.06 | 5.0 |
| Protein | | | | Repeatability (within-run variation | | Intermediate Precision (within-lab variation) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Site D | 4 | 20 | 0.8 | 0.04 | 5.0 | 0.04 | 5.0 |
| | 5 | 20 | 0.9 | 0.05 | 5.6 | 0.06 | 6.7 |
| | 6 | 20 | 1.7 | 0.07 | 4.1 | 0.07 | 4.1 |
| | 7 | 20 | 1.1 | 0.05 | 4.5 | 0.06 | 5.5 |
| | 8 | 20 | 1.2 | 0.05 | 4.2 | 0.06 | 5.0 |
| Site E | 9 | 20 | 0.6 | 0.04 | 7.2 | 0.05 | 7.5 |
| | 10 | 20 | 0.9 | 0.03 | 3.8 | 0.05 | 6.5 |
| | 11 | 20 | 1.2 | 0.04 | 3.7 | 0.07 | 5.6 |
| Site F | 9 | 20 | 0.6 | 0.03 | 5.1 | 0.04 | 7.2 |
| | 10 | 20 | 0.9 | 0.05 | 5.8 | 0.05 | 6.4 |
| | 11 | 20 | 1.2 | 0.04 | 3.8 | 0.07 | 5.4 |
| Fat | | | | Repeatability (within-run variation | | Intermediate Precision (within-lab variation) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Site | Sample | N | Mean (g/dL) | SD | CV% | SD | CV% |
| | | | | (g/dL) | | (g/dL) | |
| Site A | 1 | 84 | 2.3 | 0.08 | 3.5 | 0.09 | 4.0 |
| | 2 | 84 | 3.1 | 0.15 | 4.9 | 0.16 | 5.2 |
| | 3 | 84 | 5.7 | 0.14 | 2.5 | 0.15 | 2.6 |
| Site B | 4 | 20 | 1.0 | 0.08 | 8.0 | 0.11 | 11.0 |
| | 5 | 20 | 1.2 | 0.08 | 6.7 | 0.11 | 9.2 |
K234088 - Page 6 of 16
{6}
| Fat | | | | Repeatability (within-run variation | | Intermediate Precision (within-lab variation) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | 6 | 20 | 3.1 | 0.10 | 3.2 | 0.12 | 3.9 |
| | 7 | 20 | 4.0 | 0.14 | 3.5 | 0.18 | 4.5 |
| | 8 | 20 | 4.5 | 0.20 | 4.4 | 0.22 | 4.9 |
| Site C | 4 | 20 | 1.0 | 0.05 | 5.0 | 0.08 | 8.0 |
| | 5 | 20 | 1.2 | 0.07 | 5.8 | 0.09 | 7.5 |
| | 6 | 20 | 3.1 | 0.09 | 2.9 | 0.09 | 2.9 |
| | 7 | 20 | 4.0 | 0.19 | 4.8 | 0.20 | 5.0 |
| | 8 | 20 | 4.6 | 0.25 | 5.4 | 0.27 | 5.9 |
| Site D | 4 | 20 | 1.0 | 0.06 | 6.0 | 0.07 | 7.0 |
| | 5 | 20 | 1.2 | 0.11 | 9.2 | 0.11 | 9.2 |
| | 6 | 20 | 3.1 | 0.16 | 5.2 | 0.17 | 5.6 |
| | 7 | 20 | 3.9 | 0.12 | 3.1 | 0.12 | 3.1 |
| | 8 | 20 | 4.5 | 0.18 | 4.0 | 0.19 | 4.2 |
| Fat | | | | Repeatability (within-run variation | | Intermediate Precision (within-lab variation) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Site E | 9 | 20 | 2.2 | 0.10 | 4.6 | 0.15 | 6.8 |
| | 10 | 20 | 3.1 | 0.05 | 1.7 | 0.13 | 4.2 |
| | 11 | 20 | 5.8 | 0.20 | 3.5 | 0.21 | 3.6 |
| Site F | 9 | 20 | 2.3 | 0.10 | 4.3 | 0.18 | 8.1 |
| | 10 | 20 | 3.1 | 0.08 | 2.6 | 0.16 | 5.1 |
| | 11 | 20 | 5.8 | 0.13 | 2.2 | 0.13 | 2.2 |
| Lactose | | | | Repeatability (within-run variation | | Intermediate Precision (within-lab variation) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Site | Sample | N | Mean (g/dL) | SD | CV% | SD | CV% |
| | | | | (g/dL) | | (g/dL) | |
| Site A | 1 | 84 | 5.8 | 0.20 | 3.5 | 0.21 | 3.6 |
| | 2 | 84 | 7.4 | 0.25 | 3.4 | 0.26 | 3.5 |
| | 3 | 84 | 8.6 | 0.32 | 3.7 | 0.32 | 3.7 |
| Site B | 4 | 20 | 7.5 | 0.12 | 1.6 | 0.15 | 2.0 |
| | 5 | 20 | 8.0 | 0.12 | 1.5 | 0.12 | 1.5 |
| | 6 | 20 | 8.1 | 0.16 | 2.0 | 0.20 | 2.5 |
| | 7 | 20 | 8.5 | 0.17 | 2.0 | 0.21 | 2.5 |
| | 8 | 20 | 9.0 | 0.11 | 1.2 | 0.12 | 1.3 |
K234088 - Page 7 of 16
{7}
| Lactose | | | | Repeatability (within-run variation | | Intermediate Precision (within-lab variation) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Site C | 4 | 20 | 7.5 | 0.16 | 2.1 | 0.16 | 2.1 |
| | 5 | 20 | 8.0 | 0.12 | 1.5 | 0.13 | 1.6 |
| | 6 | 20 | 8.2 | 0.18 | 2.2 | 0.18 | 2.2 |
| | 7 | 20 | 8.6 | 0.13 | 1.5 | 0.17 | 2.0 |
| | 8 | 20 | 9.0 | 0.12 | 1.3 | 0.17 | 1.9 |
| Site D | 4 | 20 | 7.5 | 0.12 | 1.6 | 0.13 | 1.7 |
| | 5 | 20 | 8.0 | 0.13 | 1.6 | 0.13 | 1.6 |
| | 6 | 20 | 8.2 | 0.09 | 1.1 | 0.17 | 2.1 |
| | 7 | 20 | 8.5 | 0.16 | 1.9 | 0.23 | 2.7 |
| | 8 | 20 | 9.0 | 0.13 | 1.4 | 0.16 | 1.8 |
| Site E | 9 | 20 | 5.7 | 0.09 | 1.5 | 0.16 | 2.9 |
| | 10 | 20 | 7.5 | 0.21 | 2.8 | 0.22 | 2.9 |
| | 11 | 20 | 8.8 | 0.17 | 1.9 | 0.20 | 2.3 |
| Site F | 9 | 20 | 5.7 | 0.21 | 3.7 | 0.23 | 4.0 |
| | 10 | 20 | 7.6 | 0.17 | 2.3 | 0.22 | 2.9 |
| | 11 | 20 | 8.8 | 0.09 | 1.0 | 0.20 | 2.3 |
# 2. Linearity:
The linearity of the candidate device for the parameters of protein, fat, and lactose was evaluated. Nine levels with fat concentrations spanning the reportable range were analyzed on one device over one day, and each linearity sample was analyzed in duplicate. The observed values were plotted against the expected values and linear regression analysis was performed. The results are provided in the table below.
| Analyte | Concentration Range Tested (g/dL) | R2 | Slope | Intercept |
| --- | --- | --- | --- | --- |
| Protein | 0.2 – 3.2 | 0.998 | 0.996 | 0.0404 |
| Fat | 0.5 – 9.0 | 0.998 | 1.03 | -0.00167 |
| Lactose | 3.5 – 11.1 | 0.997 | 1.03 | -0.0556 |
These results support the claimed measuring range of $0.6 - 2.4\mathrm{g / dL}$ for protein, $0.6 - 6.0\mathrm{g / dL}$ for fat, and $4.5 - 9.5\mathrm{g / dL}$ for lactose.
K234088 - Page 8 of 16
{8}
K234088 - Page 9 of 16
# 3. Analytical Specificity/Interference:
The sponsor performed a study following CLSI EP07 3rd Edition to evaluate whether endogenous or exogenous substances that could be present in breast milk could cause interference with the protein, fat, or lactose measurements of the candidate device.
The study was conducted by spiking six samples of milk with concentrations of fat, protein, or lactate that ranged from high to low for each macronutrient with known concentrations of potentially interfering substances. Each sample was analyzed in duplicate using 3 different test strips. The difference between the test samples and control samples were calculated. Significant interference was defined as a difference >0.1 g/dL for protein, a difference >0.1 g/dL for fat and >0.15 g/dL for carbohydrates (lactose) relative to the reference sample without interferent.
The following substances were found to interfere and the sponsor states in the labeling that milk that may contain any of the substances listed below should not be analyzed with the Emily's Care Nourish Test System (Model 1).
| Interferent Name | Conc at which interference was first observed (mg/L) | Macronutrient(s) Affected |
| --- | --- | --- |
| Hydrocodone | 0.1 | Protein: Positive Bias |
| Folic Acid* | 0.05 | Protein: Positive Bias |
| Gentamicin | 0.15 | Protein: Positive Bias |
| Clindamycin | 0.5 | Protein: Positive Bias |
| Morphine | 0.05 | Protein: Positive Bias |
| Oxycodone | 0.05 | Protein: Positive Bias |
| Hemoglobin | 0.01 | Protein: Positive Bias
Fat: Positive Bias
Lactose: Positive Bias |
| Phenytoin | 0.10 | Protein: Positive Bias |
| Bronopol | 0.01 | Protein: Positive Bias
Fat: Negative Bias |
The compounds and the highest concentration that do not interfere are listed in the table below:
{9}
K234088 - Page 10 of 16
| Drug/Substance Tested | Highest conc tested at which no interference was observed (mg/L) |
| --- | --- |
| Loratadine | 25.0 |
| Diphenhydramine (Tablet) | 125.0 |
| Diphenhydramine (Liquid) | 62.5 |
| Acetaminophen | 81.3 |
| Ibuprofen | 50.0 |
| Naprosyn | 12.5 |
| Diclofenac | 12.5 |
| Spironolactone | 12.5 |
| Zolpidem | 2.5 |
| Citalopram | 2.5 |
| Escitalopram | 1.5 |
| Amoxicillin | 23.0 |
| Ceftriaxone | 20.0 |
| Ciprofloxacin | 100.0 |
| Doxycycline | 100.0 |
| Cefazolin | 25.0 |
| Vancomycin | 120.0 |
| Metronidazole | 125.0 |
| Ampicillin | 50.0 |
| Cephalexin | 50.0 |
| Pseudoephedrine | 20.0 |
| Prednisolone | 20.0 |
| Aspirin | 81.0 |
| Caffeine | 75.0 |
| Progesterone (pill) | 25.0 |
| Methyldopa | 25.0 |
| Sertraline | 25.0 |
| Paroxetine | 25.0 |
| Carbamazepine | 25.0 |
| Metoprolol | 25.0 |
| Propranolol | 25.0 |
| Hydrochlorothiazide | 25.0 |
{10}
*The sponsor added the following limitations to their labeling: Folic acid interferes with this test by causing falsely high protein values. Folic acid is the synthetic (that is, not generally occurring naturally) form of folate that can be used in supplements and in fortified foods and may be used in some infant formulas and fortified milks. Infant formulas and fortified milks should not be used with the Emily Care's Nourish Test System (Model 1). Only human breast milk should be used with this test. The CDC recommends pregnant and lactating mothers take 600 µg of folic acid per day. Breast milk obtained from lactating mothers taking folic acid at 600 µg per day are not likely to have folic acid concentrations in breast milk that will cause interference in this assay.
[1] Cochrane, K.M., Elango, R., Devlin, A.M. et al. Human milk unmetabolized folic acid is increased following supplementation with synthetic folic acid as compared to (6S)-5-methyltetrahydrofolic acid. Sci Rep 13, 11298 (2023).
4. Assay Reportable Range:
Protein: 0.6 – 2.4 g/dL
Fat: 0.6 – 6.0 g/dL
Lactose: 4.5 – 9.5 g/dL
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
The Emily's Care Nourish Test System (Model 1) is traceable to certified reference materials and validated chemical methods. The validation of these chemical methods was reviewed and found to be acceptable. The applicant submitted a detailed traceability assurance plan which was reviewed and found to be acceptable.
6. Detection Limit:
The Limit of blank (LoB), limit of detection (LoD), and limit of quantitation (LoQ) of protein, fat, and lactose on the candidate device was established using a 5-day study protocol per CLSI EP17-A2 guideline.
To evaluate the LoB, triplicate measurements were made on four blank samples over five days for a total of 60 measurements per analyte. The LoB was calculated as the mean of the blank results + 1.64*Standard Deviation (SD).
For the LoD determination, 7 milk samples with low levels of protein, fat and lactose were tested in triplicate over 5 days for a total of 15 measurements per sample. LoD was calculated as LoB + 1.64 *SD pooled.
For the LoQ determination, seven low-concentration samples were tested in triplicate across five days. To determine the LoQ the sponsor plotted a regression line of analyte concentration vs. the expected total error. The concentration at which the total error was 20% for that analyte was chosen as the LoQ.
The LoQ for each of the three analytes is listed in the table below:
K234088 - Page 11 of 16
{11}
| Analyte | Protein g/dL | Fat g/dL | Lactose g/dL |
| --- | --- | --- | --- |
| LoB | 0.10 | 0.07 | 1.02 |
| LoD | 0.23 | 0.21 | 1.19 |
| LoQ | 0.32 | 0.33 | 4.06 |
The sponsor’s labeling specifies that the lowest values that will be reported are 0.6 g/dL for protein and fat, and 4.5 g/dL for lactose. Please see the Assay Reportable Range section above.
7. **Assay Cut-Off:**
Not applicable.
8. **Accuracy (Instrument):**
Not applicable.
9. **Carry-Over and other flex studies:**
The sponsor performed the following flex studies to evaluate the effect of environmental conditions and suboptimal handling of the samples or strips.
- Carry-Over/Bleeding study to evaluate the impact of a color bleeding over onto the adjacent pad of the test strips.
- Dip time study to evaluate whether accurate results could be produced if the user deviated from the recommended dipping time of 2 – 3 seconds.
- Strip Misalignment/Strip Boundary studies to evaluate whether the App can determine when the test strip is misaligned.
- Temperature and humidity study to evaluate the impact of various temperature and humidity scenarios.
- Assay time study (incremental testing time study) to determine the effects of the test strip not being analyzed by the test system within the recommended time window.
The sponsor provided sufficient information to support that the device is adequately robust to conditions that may reasonably be expected in the intended use environment and supports the labeled claims.
B **Comparison Studies:**
1. **Method Comparison with Predicate Device:**
The sponsor performed method comparison studies to determine the bias of the Emily’s Care Nourish Test System (Model 1). The comparator method for fat and protein was the predicate Miris Human Milk Analyzer™. The comparator method for lactose was a validated comparative chemical method. Regression analysis and bias estimations were based on first replicate results for the candidate device. The comparative method included the same
K234088 - Page 12 of 16
{12}
samples analyzed in triplicate. The mean of the triplicates results was used as the comparative values.
Passing-Bablok regression of the data produced the following:
| Analyte | N | Concentration tested | R2 | Slope (95% CI) | Intercept (95% CI) |
| --- | --- | --- | --- | --- | --- |
| Protein | 115 | 0.6 – 2.2 g/dL | 0.953 | 1.000 (1.000,1.000) | 0 (-3.997E-16, 0) |
| Fat | 113* | 0.8 – 6.0 g/dL | 0.970 | 0.9926 (0.9470, 1.000) | 0.02602 (-0.04615, 0.1788) |
| Lactose | 115 | 4.8 – 8.6 g/dL | 0.965 | 1.000 (1.0000, 1.058) | 0.03891 (-0.3447, 0.10000) |
| Calories | 113* | 30 – 90 kcal/dL | 0.978 | 0.9828 0.9565, 1.011 | 1.286 (-0.5307, 2.884) |
*Two samples were excluded as their fat concentrations were outside the claimed measuring range.
The bias at low, medium, and high levels of each analyte was calculated. The results are presented in the table below.
| Analyte | Concentration (g/dL) | Bias (g/dL) | 95% CI |
| --- | --- | --- | --- |
| Fat | 1.0 | 0.0186 | -0.04262, 0.1191 |
| | 2.5 | 0.0074 | -0.04615, 0.10000 |
| | 4.0 | -0.0037 | -0.07101, 0.09047 |
| Protein | 0.8 | 0 | 0.0000, 0.0000 |
| | 1.1 | 0 | 0.0000, 2.2204E-16 |
| | 2.0 | 0 | 0.0000, 8.8818E-16 |
| Lactose | 6.6 | 0.0389 | 0.0000, 0.10000 |
| | 7.5 | 0.0389 | 0.0000, 0.10000 |
| | 8.5 | 0.0389 | 0.0000, 0.1476 |
| Calories | 45 | 0.5184 | -0.1559, 1.2576 |
| | 70 | 0.1108 | -0.4848, 0.7802 |
| | 110 | -0.5412 | -2.0324, 1.0150 |
K234088 - Page 13 of 16
{13}
The sponsor also provided results from a study that demonstrated the accuracy is the same when operated by intended users at POC sites.
2. Matrix Comparison:
Not applicable. The device is designed for use with human breast milk only.
C Clinical Studies:
1. Clinical Sensitivity:
Not applicable
2. Clinical Specificity:
Not applicable
3. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
Not applicable
D Clinical Cut-Off:
Not applicable
E Expected Values/Reference Range:
The sponsor includes the following reference ranges in their labeling: Meta-analysis results of the macronutrient composition of term (37-42 weeks of gestation) human milk [1,2]
| Time after delivery | Fat (g/dl) | | Protein (g/dl) | | Lactose (g/dl) | | Calories (Calculated) (kcal/dl) | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | Mean | SD | Mean | SD | Mean | SD | Mean | SD |
| Day 1-3 | 1.8 | 0.7 | 2.0 | 0.9 | 5.6 | 0.6 | 54* | 8.0 |
| Day 4-7 | 2.6 | 0.8 | 1.6 | 0.3 | 6.0 | 1.0 | 68 | 9.6 |
| Week 2 | 3.0 | 0.9 | 1.3 | 0.2 | 6.2 | 0.6 | 66* | 9.0 |
| Week 3-4 | 3.4 | 0.8 | 1.1 | 0.2 | 6.7 | 0.7 | 70 | 9.3 |
| Week 5-6 | 3.6 | 1.1 | 1.0 | 0.1 | 6.1 | 1.0 | 63* | 7.0 |
| Week 7-9 | 3.4 | 0.8 | 0.9 | 0.1 | 6.5 | 0.5 | 69 | 9.9 |
| Week 10-12 | 3.4 | 0.9 | 1.0 | 0.1 | 6.7 | 0.7 | 68 | 9.0 |
K234088 - Page 14 of 16
{14}
| Time after delivery | Fat (g/dl) | | Protein (g/dl) | | Lactose (g/dl) | | Calories (Calculated) (kcal/dl) | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | Mean | SD | Mean | SD | Mean | SD | Mean | SD |
| Colostrum (day 1-3) | 1.8 | | 2.0 | | 5.6 | | 54 | |
| Mature milk | 3.4 | | 1.0 | | 6.5 | | 63 | |
* Calories/Energy quantified using bomb calorimetry
Meta-analysis results of the macronutrient composition of preterm (<37 weeks of gestation) human milk [1,2]
| Time after delivery | Fat (g/dl) | | Protein (g/dl) | | Lactose (g/dl) | | Calories (Calculated) (kcal/dl) | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | Mean | SD | Mean | SD | Mean | SD | Mean | SD |
| Day 1-3 | 2.2 | 0.9 | 2.7 | 1.5 | 5.1 | 0.7 | 49* | 7.0 |
| Day 4-7 | 3.0 | 1.2 | 1.7 | 0.5 | 6.3 | 1.1 | 65 | 13.0 |
| Week 2 | 3.5 | 1.1 | 1.5 | 0.4 | 5.7 | 0.8 | 70 | 14.0 |
| Week 3-4 | 3.5 | 1.0 | 1.4 | 0.4 | 6.0 | 0.5 | 68 | 8.0 |
| Week 5-6 | 3.2 | -0.8 | 1.1 | 0.2 | 5.8 | 0.6 | 67 | 6.9 |
| Week 7-9 | 3.3 | 0.9 | 1.1 | 0.2 | 6.3 | 0.4 | 66 | 8.9 |
| Week 10-12 | 3.7 | 1.5 | 1.0 | 0.2 | 6.8 | 0.3 | 66 | 14.0 |
| Colostrum (day 1-3) | 2.2 | | 2.7 | | 5.1 | | 49 | |
| Mature milk | 3.3 | | 1.1 | | 6.2 | | 73 | |
* Calories/Energy quantified using bomb calorimetry
Macronutrient composition of donor human milk [4]
| Reference | Fat (g/dl) | | Protein (g/dl) | | Lactose (g/dl) | | Calories (Calculated) (kcal/dl) | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | Mean | Range | Mean | Range | Mean | Range | Mean | Range |
| [4] | 3.2 | 1.2-5.2 | 1.2 | 0.7-1.7 | 7.8 | 6.0-9.6 | 65 | 43-87 |
| [5] | 3.6 | 1.8-8.9 | 0.9 | 0.6-1.4 | 7.2 | 6.4-7.6 | 67 | 50-115 |
K234088 - Page 15 of 16
{15}
K234088 - Page 16 of 16
# References
[1] D. Gidrewicz and T. Fenton. “A systematic review and meta-analysis of the nutrient content of preterm and term breast milk”, BMC Pediatrics 14:216, 2014
[2] K. Wojcik, D. Rechtman, M. Lee, A. Montoya, and E. Medo. “Macronutrient analysis of a nationwide sample of donor breast milk”. J Am Diet Assoc, vol. 109, pp. 137-140, 2009.
[3] K. Michaelsen, L. Skafte, J. Badsberg, and M. Jorgensen. “Variation in macronutrients in human bank milk: Influencing factors and implications for milk banking”. Journal of Pediatric Gastroenterology and Nutrition, vol. 11, pp. 229-239, 1990.
[4] Ballard O, Morrow AL. Human milk composition: nutrients and bioactive factors. Pediatr Clin North Am. 2013 Feb;60(1):49-74. doi: 10.1016/j.pcl.2012.10.002. PMID: 23178060; PMCID: PMC3586783.
[5] Michaelsen KF, Skafte L, Badsberg JH, Jorgensen M. Variation in macronutrients in human bank milk: influencing factors and implications for human milk banking. Journal of pediatric gastroenterology and nutrition. 1990;11(2):229-239
[5] MIRIS HMA User Manual (https://www.mirissolutions.com/support/user-manuals)
## F Other Supportive Instrument Performance Characteristics Data:
Information was provided to support equivalence between the claimed phones.
## VIII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
## IX Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.