(160 days)
The YO™ Home Sperm Test is a smartphone based home test which provides a qualitative assessment of motile sperm concentration (MSC) in human semen. MSC is one aspect of a male semen examination. The YO™ Home Sperm Test does not provide a comprehensive evaluation of a male's fertility status and is intended for over-the-counter, in vitro use only.
YO™ is an over-the-counter device that provides a qualitative assessment of motile sperm concentration (MSC) in human semen. Results are reported as "LOW MSC RANGE" or "MODERATE/NORMAL MSC RANGE," requiring no user interpretation. The YO™ software application is downloaded onto the users' own smartphone and on-screen menus and instructions are shown on the phone's display so that the user is taken through the process step by step. The YO™ kit (purchased on the website) provides all the supplies necessary to evaluate two semen samples: two semen collection cups, two vials of liquefying powder (chymotrypsin), two pipettes for sample aspiration, two fixed coverslip slides for sample testing, one QC slide, and one YOT™ Clip that attaches to the smartphone and houses the fixed coverslip slide.
Here's a breakdown of the acceptance criteria and study details for the YO™ Home Sperm Test, based on the provided document:
Acceptance Criteria and Reported Device Performance
| Criteria | Acceptance Metric | Reported Performance (iPhone and Galaxy Combined) |
|---|---|---|
| Reproducibility/Repeatability (Non-clinical) | %CV 90% | PPA = 93.5% (iPhone & Galaxy combined) |
| NPA = 96.7% (iPhone & Galaxy combined) | ||
| Clinical Agreement (Lay User vs. SQA-V) | PPA and NPA > 90% | PPA = 95.3% |
| NPA = 96.1% | ||
| Clinical Agreement (Lay User vs. Trained User) | PPA and NPA > 90% | PPA = 96.7% |
| NPA = 98.7% | ||
| Clinical Agreement (Trained User vs. SQA-V) | PPA and NPA > 90% | PPA = 97.6% |
| NPA = 97.0% | ||
| Usability/Comprehension (Clinical) | High satisfaction and good comprehension of labeling | Over 81% rated directions as "Very clear and easy to follow" for all 5 questions. |
Note: The acceptance criteria for the non-clinical and clinical studies are implicitly derived from the reported performance, as the document states that the results "exceeded 90%" and indicate the system is "safe and effective for its intended use."
Study Details
1. Sample sizes used for the test set and the data provenance:
- Reproducibility/Repeatability (Non-clinical): At least 60 subjects per site (two sites, one internal and one external). Samples were grouped into three MSC categories (Positive 8 M/mL), with approximately 20 samples per group. 480 measurements per site were performed. Data provenance is implied to be laboratory-generated samples at the internal (MES) and external (Ruppin College) sites. It is retrospective in the sense that laboratory-prepared samples were used to control specific variables.
- Detection Limit (Non-clinical): Four semen samples prepared to represent four MSC levels (0 M/mL, 2-3 M/mL, 5-6 M/mL, 8-9 M/mL), assayed in duplicate. Data provenance similar to reproducibility study.
- Analytical Specificity (Non-clinical): Three "LOW MSC RANGE" and three "MODERATE/NORMAL MSC RANGE" semen samples, each split into aliquots for various contaminants and controls. A separate study used three "LOW" and three "MODERATE/NORMAL" MSC samples for urine and saliva interference. Data provenance similar to reproducibility study.
- MSC Cut-off Trial (Non-clinical): 100 fresh human semen samples (approximately 50/50 split above and below 6 M/mL MSC cutoff). 10% were prepared samples to better represent samples close to the cutoff. Data provenance similar to reproducibility study.
- Clinical Study (Test Set): 316 samples across three clinical sites (one in Israel, two in the US). These were prospective samples from male subjects.
2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Non-clinical studies: The ground truth for MSC values in non-clinical studies (Reproducibility, Detection Limit, Analytical Specificity, MSC Cut-off) was established using the SQA-V sperm analyzer, which is a legally marketed predicate device cleared under K021746. No specific number of experts is mentioned as directly establishing these ground truths, but the SQA-V is an established laboratory-based instrument.
- Clinical Study: The ground truth for the clinical study was established by two SQA-V systems (predicate device), with their results averaged. While not explicitly stated as "experts," the SQA-V is an established clinical laboratory method used by trained professionals to determine semen parameters. Additionally, "trained health care professionals (HCPs, trained users)" who performed a separate YO™ test served as a comparison point for the lay user results.
3. Adjudication method for the test set:
- For non-clinical studies (MSC Cut-off Trial): The SQA-V generated numerical MSC data, which was then converted to qualitative results ("LOW MSC RANGE" or "MODERATE/NORMAL MSC RANGE") based on the 6 M/mL cutoff. This essentially serves as the adjudicator.
- For clinical studies: The SQA-V results (averaged from two systems and then converted to qualitative categories) served as the comparator/ground truth against which both lay user YO™ results and trained user YO™ results were compared. There was no explicit "adjudication" in the sense of multiple human experts reviewing discrepancies; instead, the SQA-V was the reference standard.
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:
- This was not an MRMC comparative effectiveness study in the traditional sense of evaluating human reader improvement with AI assistance. The YO™ Home Sperm Test is designed for standalone over-the-counter use by lay users, with the device itself providing the qualitative assessment.
- The study did compare lay users' performance with the device against a laboratory reference (SQA-V) and against trained users with the device. This assesses the device's accuracy when used by its target demographic. No "human reader improvement with AI vs without AI" effect size can be determined from this study design as there is no "without AI" human reading component.
5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance was done for internal validation and non-clinical studies. The non-clinical studies (Reproducibility, Detection Limit, Analytical Specificity, MSC Cut-off Trial) assessed the YO™ system (device and algorithm) against the SQA-V without explicit human interpretation being part of the YO™ device's output. The YO™ device outputs "LOW MSC RANGE" or "MODERATE/NORMAL MSC RANGE" directly.
- The clinical study primarily focused on the device's performance with a human user interaction (lay users following instructions). However, the underlying technology performing the sperm analysis and classification into MSC ranges is the standalone algorithm of the YO™ device.
6. The type of ground truth used:
- Predominantly expert consensus via a legally marketed predicate device (SQA-V). For all quantitative evaluations, the SQA-V sperm analyzer served as the gold standard. The SQA-V itself is an instrument used by trained professionals and provides objective measurements, which are then categorized based on WHO guidelines.
7. The sample size for the training set:
- The document does not explicitly state the sample size used for the training set for the YO™ device's algorithm. The non-clinical and clinical studies described are performance validation studies, not algorithm training studies.
8. How the ground truth for the training set was established:
- Since the training set size is not provided, the method for establishing its ground truth is also not explicitly stated in this document. However, given that the SQA-V is used as the comparative method for all validation, it is highly probable that similar laboratory-based, SQA-V derived measurements and classifications would have been used to establish the ground truth for any training data.
§ 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.”