Search Results
Found 1 results
510(k) Data Aggregation
(444 days)
Clue Birth Control is a software application for women ages 18 - 45 years old, to monitor their fertility and prevent pregnancy. Clue Birth Control is suitable for women with predictable 20 - 40 day cycles, who have not recently used hormonal birth control.
Clue Birth Control is a feature of the Clue period tracker mobile application. Clue Birth Control's proprietary algorithm uses period start date information entered by the user to provide predictions of "high risk days" and "low risk days" for becoming pregnant based on a Fertility Awareness Based Method (FABM) of contraception. Identification of high risk days allows the user to determine the days on which her risk of conception is highest, and then make choices about either abstaining from sex or using a barrier method of contraception to prevent pregnancy.
To use Clue Birth Control, users go through an onboarding process from within the Clue app, during which they are asked to provide information that will determine whether they meet the Clue Birth Control use criteria. Clue Birth Control can only be used by women who are between 18 and 45 years old and their last 12 cycles were between 20 and 40 days and the difference between the lengths of the shortest and longest cycles is less than or equal to 9 days. In addition, users must have had at least three cycles (four periods) after stopping hormonal birth control (HBC) or since the end of a pregnancy.
Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The FDA clearance document doesn't explicitly list specific numerical acceptance criteria (e.g., "Pearl Index must be less than X"). Instead, the document focuses on demonstrating substantial equivalence to a predicate device and meeting the regulatory requirements for preventing pregnancy. However, the study provides performance metrics (Pearl Indices) which serve as the basis for demonstrating effectiveness.
| Acceptance Criteria (Implied) | Reported Device Performance (Clue Birth Control) |
|---|---|
| Contraception Effectiveness: Demonstrate acceptable levels of pregnancy prevention. | Perfect-use Pearl Index: 0.8 (0.8 out of 100 women using the app perfectly for one year will get pregnant). |
| Typical-use Pearl Index: 5.2 (95% CI: 3.4-7.7) (5.2 out of 100 women get pregnant during one year of use due to all possible reasons). | |
| User Comprehension and Safety: Users must understand the device's outputs and eligibility criteria to use it safely and effectively. | Human factors testing demonstrated that device users could safely use the device, focusing on onboarding (eligibility and risk), data input, and understanding messaging (high risk, low risk, ineligible). |
| Software Quality and Security: Adherence to FDA guidance for medical device software and cybersecurity. | Software documentation provided in accordance with the 2005 FDA guidance document "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." |
| Cybersecurity information provided in accordance with the 2014 FDA guidance document "Content of Premarket Submissions for Management of Cybersecurity in Medical Devices." | |
| Substantial Equivalence: Demonstrate that the device is as safe and effective as a legally marketed predicate device.** | Comparison of intended use and technological characteristics, combined with performance data, concluded that Clue Birth Control is as safe and effective as the predicate device (Natural Cycles: DEN170052) for its intended use population. |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: 718 women
- Data Provenance: Prospective clinical trial, conducted in the United States, at the Institute for Reproductive Health at Georgetown University.
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 or qualifications of experts used to establish ground truth for pregnancy outcomes. However, for a clinical trial assessing contraceptive effectiveness, the "ground truth" for pregnancy is typically based on confirmed clinical pregnancy outcomes (e.g., positive pregnancy tests, medical confirmation). It's implied that medical professionals were involved in confirming these outcomes, but specific details on their expertise are not provided.
4. Adjudication Method for the Test Set
The document does not explicitly describe an adjudication method for the test set regarding conflicting diagnoses or interpretations. For pregnancy outcomes, it's generally a binary and verifiable event. The mention of "worst-case Pearl Index" (assuming pregnancies for all 'possibly pregnant' users lost to follow-up) suggests a conservative approach to handling uncertainty, but this isn't an adjudication method in the traditional sense of expert review for ambiguous 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, a Multi Reader Multi Case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance was not done. This study is a standalone clinical trial of the device's effectiveness as a contraceptive method. The device's output is "high risk" or "low risk" days, not an interpretation of medical images or data that would typically involve human "readers."
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes, the clinical efficacy trial described ("Dynamic Optical Timing (DOT) clinical efficacy trial") assesses the performance of the algorithm itself, without human interpretation of its outputs beyond the user's decision to act on the "high risk" or "low risk" days. The Pearl Index measures the effectiveness of the method, which includes the algorithm's predictions and the user's adherence to the advice. The "perfect-use" Pearl Index specifically isolates the method's inherent failure rate.
7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)
The ground truth used was outcomes data, specifically confirmed pregnancies (or lack thereof) over a period of 13 cycles.
8. The Sample Size for the Training Set
The document does not specify the sample size for the training set used to develop the Clue Birth Control algorithm. The clinical trial described is for validation of the algorithm's efficacy.
9. How the Ground Truth for the Training Set Was Established
The document does not specify how the ground truth for the training set was established, as details about the algorithm's development are not provided.
Ask a specific question about this device
Page 1 of 1