(176 days)
The YO Home Sperm Test (YO 3.0) is a smartphone-based test for semen analysis performed by lay users.
The parameters reported by the YO Home Sperm Test (YO 3.0) are:
-
Total Sperm Concentration / Sperm Concentration, M/mL
-
Total Motile / Motility (PR + Non Progressive [NP]), %
-
Progressive Motility (PR), % (combines Rapidly and Slowly Progressive, %)
-
Motile Sperm Concentration (MSC), M/mL
-
Progressively Motile Sperm Concentration (PMSC), M/mL (combines Rapidly and Slowly Motile Sperm Concentration, M/mL)
The YO Home Sperm Test (YO 3.0) does not provide a comprehensive evaluation of a male's fertility status and is intended for in vitro, over the counter only.
The YO Home Sperm Test (YO 3.0) is a smartphone-based test for semen analysis performed by lay users.
The parameters reported by the YO Home Sperm Test (YO 3.0) are:
-
- Total Sperm Concentration / Sperm Concentration, M/mL
-
- Total Motile / Motility (PR + NP), %
-
- Progressive Motility (PR), % (combines Rapidly and Slowly Progressive, %)
-
- Motile Sperm Concentration (MSC), M/mL
-
- Proqressively Motile Sperm Concentration (PMSC), M/mL (combines Rapidly and Slowly Motile Sperm Concentration, M/mL)
The YO Home Sperm Test (YO 3.0) utilizes proprietary algorithms to both conduct semen analysis, and present and store the results and videos on the user's smartphone and in the YO application ("app") is downloaded onto the user's own smartphone (iPhone/Android) and is controlled by the user through a proprietary graphical interface (GUI). The GUI quides the user through the process step by step on the App's screen and operates with the YO device.
The YO kit provides the supplies necessary to test up to six semen collection cups, pipettes for sample aspiration, fixed coverslip slides, liquefaction powder and a YO device that connects via WiFi to a smartphone and houses the YO slide. The YO software app guides the user through the sample preparation and testing process step-by-step with mandatory confirmation by the user of each completed step. The app also operates the YO device's camera and processor to provide a semen video.
The plastic YO device contains a fixed coverslip slide insertion channel, magnification lens, lens holder, WiFi camera and an LED that lights up the optical path. The YO software captures a video in HD (high definition) mode and implements a unique software algorithm to identify sperm and analyze the light fluctuations resulting from sperm movement to report semen values. The algorithm recognizes when the YO autofocus function has the best image and then defines the optimal area of the video for analysis.
When YO reports any semen value below the cut-off for normal, YO recommends performing an additional test with a new sample and to seek medical advice. YO cut-offs are based on WHO 6th ed. reference values for semen parameters, statistical modeling, and expert publications. The user is not required to perform any interpretation of the test results and YO does not review, verify, or interpret the video provided to the operator. The user can only observe and archive his test results and sperm video. YO does not provide a comprehensive evaluation of a male's fertility status and is intended for over-thecounter ), for in vitro use only.
The YO software quides the user through the testing process step by step on the smartphone's screen and operates in conjunction with the: YO device, smartphone's built-in camera, flash, and man-machine interface to report and store the results of 5 sperm parameters and a video of the user's semen samples. After analyzing the operator's semen video, the YO software reports both the quantitative results and an explanation about the 5 Semen parameters which are visually presented in the YO app directly following testing. In addition, the operator's sperm video is also presented in the test results section directly following the testing phase of the app.
Here's a summary of the acceptance criteria and the study proving the device meets those criteria, based on the provided text:
Device: YO Home Sperm Test (YO 3.0)
1. Table of Acceptance Criteria and Reported Device Performance:
| Parameter | Acceptance Criteria (from analytical studies) | Reported Device Performance (from clinical study vs. SQA-V) |
|---|---|---|
| Analytical Performance | ||
| Within-run Repeatability (%CV) | 0.9 | R > 0.9 (claim met) |
| Linearity (Slope) | 1.0 +/- 0.2 | Slope > 1.0 +/- 0.2 (claim met, from text) |
| Interference (Percent difference) | Within 15% of controls | Within 15% of controls |
| Clinical Performance (vs. SQA-V) | (Implied good correlation and user comprehension) | |
| Sperm Concentration (M/mL) | Intercept: 2.29 (95% CI: 1.29 to 3.25) | |
| Slope: 0.86 (95% CI: 0.82 to 0.91) | ||
| Correlation (r): 0.93 (95% CI: 0.92 to 0.95) | ||
| Motility, % | Intercept: 0.00 (95% CI: 0.00 to 3.00) | |
| Slope: 1.05 (95% CI: 1.00 to 1.11) | ||
| Correlation (r): 0.90 (95% CI: 0.88 to 0.92) | ||
| Progressive Motility, % | Intercept: -0.47 (95% CI: -2.78 to 0.00) | |
| Slope: 1.24 (95% CI: 1.16 to 1.31) | ||
| Correlation (r): 0.88 (95% CI: 0.85 to 0.90) | ||
| Motile Sperm Concentration (M/mL) | Intercept: 1.84 (95% CI: 1.50 to 2.20) | |
| Slope: 0.92 (95% CI: 0.88 to 0.95) | ||
| Correlation (r): 0.94 (95% CI: 0.93 to 0.95) | ||
| **Progressively Motile Sperm ** | Intercept: -0.04 (95% CI: -0.44 to 0.00) | |
| Concentration (M/mL) | Slope: 1.03 (95% CI: 0.98 to 1.07) | |
| Correlation (r): 0.94 (95% CI: 0.92 to 0.95) | ||
| User Comprehension (Questionnaire) | High percentage of correct answers (implied) | 87% - 99% correct responses across various questions |
2. Sample size used for the test set and the data provenance:
-
Clinical Study (Method Comparison):
- Sample Size: 309 comparative data sets overall. A minimum of 100 semen samples per site (across 3 US sites).
- Data Provenance: Prospective. Conducted at three US sites, with lay users recruited to analyze their own samples or female users testing donor samples.
-
Analytical Studies (Precision, LoD/LoQ, Linearity, Interference):
- Sample Size for Precision (user repeatability): Approximately 20 users per site (3 sites), testing samples in triplicate.
- Sample Size for Precision (professional user reproducibility): 15-30 native semen samples per site (3 sites), representing 3 levels, 2 reps per sample, 4 time points, 3 YO devices (total 360 measurements, 24 results per sample).
- Sample Size for LoD/LoQ: Two samples (blank and low concentration), 5 YO3 devices, 2 lots of slides, 2 operators. Each level assayed 12 times on each device (60 results per level).
- Sample Size for Linearity: Semen samples prepared at ten concentration intervals (low to high). Tested in three YO devices per concentration level.
- Sample Size for Interference: Two concentration levels of semen samples and 11 potentially interfering substances.
- Data Provenance: In-house analytical studies. Semen samples collected following WHO 6th ed. manual guidance from consented donors. Analyzed in a blinded fashion on SQA-iO and SQA-V.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Clinical Study Ground Truth: The comparator device was the SQA-V sperm quality analyzer operated by TRAINED OPERATORS. The text does not specify the number or detailed qualifications of these "trained operators" beyond that.
- Analytical Studies Ground Truth: The text mentions "comparative device, SQA-V" and for LoD/LoQ, confirmation of concentration by "manual microscope." For training ground truth, it implies the use of the SQA-iO and SQA-V, as well as WHO 6th ed. guidelines.
4. Adjudication method for the test set:
- The text describes a "method comparison study" where "Each semen sample was tested in singleton in a blinded fashion by each method using split aliquots." This indicates a direct comparison to a reference standard (SQA-V) rather than an expert consensus adjudication of specific cases.
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:
- No MRMC comparative effectiveness study was done.
- This device is designed for lay users (Over-The-Counter) and the study compares the device's performance to a professional laboratory device (SQA-V), not human readers with and without AI assistance. The "lay users" are the primary operators of the YO device, and their performance with the device is what's being evaluated against the SQA-V.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- The analytical (bench) studies (Precision, LoD/LoQ, Linearity, Interference) assess the device's technical performance characteristics, which is essentially the "algorithm without human-in-the-loop" once the sample is loaded. However, the overall device function requires human interaction for sample preparation and device operation as instructed by the app.
- The clinical validation specifically compares the algorithm's performance when operated by intended lay users against results from the comparator device (SQA-V) operated by trained operators. So, while the underlying algorithm's accuracy is foundational, the clinical study explicitly includes human-in-the-loop for the test device.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Clinical Study: The ground truth was established by comparison to a legally marketed predicate device, the SQA-V sperm quality analyzer, operated by trained professionals.
- Analytical Studies:
- Precision, Linearity, Interference: Comparison against the SQA-V comparator device.
- LoD/LoQ: Manual microscope verification for blank and low concentration samples.
8. The sample size for the training set:
- The document does not explicitly state the sample size used for the training set for the YO Home Sperm Test (YO 3.0) algorithms. It describes the data used for analytical validation and clinical validation, but not the development/training phase.
9. How the ground truth for the training set was established:
- The document does not detail how the ground truth for the training set was established. It states that the device "utilizes proprietary algorithms" and implements a "unique software algorithm to identify sperm and analyze the light fluctuations resulting from sperm movement." It also mentions "YO cut-offs are based on WHO 6th ed. reference values for semen parameters, statistical modeling, and expert publications." This implies the algorithms were developed and refined using data aligned with WHO standards and likely validated against reference methods like the SQA-V, but the specifics of the training data development are not provided.
§ 864.5220 Automated differential cell counter.
(a)
Identification. An automated differential cell counter is a device used to identify one or more of the formed elements of the blood. The device may also have the capability to flag, count, or classify immature or abnormal hematopoietic cells of the blood, bone marrow, or other body fluids. These devices may combine an electronic particle counting method, optical method, or a flow cytometric method utilizing monoclonal CD (cluster designation) markers. The device includes accessory CD markers.(b)
Classification. Class II (special controls). The special control for this device is the FDA document entitled “Class II Special Controls Guidance Document: Premarket Notifications for Automated Differential Cell Counters for Immature or Abnormal Blood Cells; Final Guidance for Industry and FDA.”