(268 days)
Natural Cycles is a stand-alone software application, intended for women 18 years and older, to monitor their fertility. Natural Cycles can be used for preventing a pregnancy (contraception) or planning a pregnancy (conception).
Natural Cycles is an over-the-counter web and mobile-based standalone software application that monitors a woman's menstrual cycle using information entered by the user and informs the user about her past, current and future fertility status. The following information is used by the Natural Cycles software:
- daily body temperature measurements
- information about the user's menstruation cycle (i.e., start date, number of days)
- optional ovulation or pregnancy test results
A proprietary algorithm evaluates the data and returns the user's fertility status.
Natural Cycles is available in three modes: Contraception, and Pregnancy. For Contraception mode, the device provides predictions of "not fertile," shown as green days, and "use protection," shown as red days, that allow 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.
In addition to measuring daily basal body temperature with an oral thermometer with two decimal points, the device allows automatic temperature input from the Oura ring, a wearable temperature monitor.
Natural Cycles can be used by women 18 years and older. Women who have been on hormonal birth control within 60 days prior to using Natural Cycles have a higher risk of becoming preqnant when compared to women who have not been on hormonal birth control within the 12 months prior to using the device may not be right for women who have a medical condition where pregnancy would be associated with a significant risk to the mother or the fetus.
Here's a breakdown of the acceptance criteria and study proving the device meets them, based on the provided FDA 510(k) summary for Natural Cycles (K202897):
1. Table of Acceptance Criteria and Reported Device Performance
The primary purpose of this 510(k) submission was to add the Oura ring as a new temperature input method for the Natural Cycles algorithm. Therefore, the acceptance criteria and performance data revolve around demonstrating that this new input method does not negatively impact the algorithm's contraceptive effectiveness.
| Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|
| Algorithm Performance Equivalence: The Natural Cycles algorithm, when using Oura ring temperature input, must maintain its ability to accurately identify ovulation and determine fertility status for contraception, comparable to using oral thermometer input, without increasing the risk of unintended pregnancy. | "the Natural Cycles algorithm was able to identify that ovulation had occurred, which was confirmed in the study by comparison to the 87 positive LH test results." (This indicates the core function of identifying ovulation was maintained). "Compared to the two-decimal place oral thermometer, the Natural Cycles algorithm provides additional 1.6 green days (not fertile) in the luteal phase of the menstrual cycle when the input temperature was from the Oura ring, without increasing the risk of unintended pregnancy." (This directly addresses the equivalence in contraceptive effectiveness by showing more "green days" without higher pregnancy risk, implying no decrease in safety/effectiveness). |
| Usability/Human Factors (Implicit for integration): The integration of Oura ring data should be seamless and not introduce new usability issues that compromise safety or effectiveness. (While not explicitly stated as a criterion, it's generally an underlying expectation for new input methods). | "Human factors testing in DEN170052 was used to support that device users could safely use the device." (This refers to prior human factors testing for the predicate device, implying that the general usability of Natural Cycles for temperature input was already established, and the Oura integration implicitly rode on this). The study design, with participants being "experienced users of both Natural Cycles and entering their daily temperature using an oral thermometer but did not have experience using the Oura ring with Natural Cycles," suggests that the focus was on the data integration, not on the fundamental usability of the app itself. |
| Software Compliance & Cybersecurity: The software handling Oura ring data must conform to regulatory standards. | "- Software documentation provided in accordance with the 2005 FDA guidance document Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices to support device software with a major level of concern. |
- Cybersecurity information provided in accordance with the 2014 FDA guidance document ● Content of Premarket Submissions for Management of Cybersecurity in Medical Devices." (These directly state compliance with relevant software and cybersecurity guidelines.) |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: 40 women.
- Data Provenance:
- Country of Origin: The majority (38) of the women were located in Sweden, with one each in the US and Switzerland.
- Retrospective or Prospective: Prospective. The study involved current data collection from participants wearing the Oura ring and using an oral thermometer over multiple menstrual cycles.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Experts
The document does not mention the use of human experts to establish ground truth for this specific clinical study. The ground truth for identifying ovulation was established by:
- Objective Physiological Markers: Luteinizing Hormone (LH) tests. Participants were asked to record the results of LH tests.
- Algorithmic Confirmation: The Natural Cycles algorithm's determination of ovulation.
The study aimed to compare the algorithm's performance with two different temperature inputs (oral thermometer vs. Oura ring) against an objective biological marker (LH tests).
4. Adjudication Method for the Test Set
No explicit adjudication method is described, as the ground truth was based on LH test results and the algorithm's determination, rather than subjective expert interpretations.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done
No, an MRMC comparative effectiveness study was not done. This study focused on comparing the performance of the algorithm with different data inputs (Oura ring vs. oral thermometer) in determining fertility status, using LH tests for validation. It did not involve multiple human readers assessing cases with and without AI assistance.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
Yes, a standalone study was done. The study "was conducted to compare the daily temperatures generated by a wearable temperature monitor, the Oura ring, to a two decimal place oral thermometer for use by the NaturalCycles algorithm." The outcome measured was the algorithm's ability to identify ovulation and determine fertility status based on these inputs, and how the "green days" (not fertile) differed, without increasing the risk of unintended pregnancy. The human "in the loop" was the user providing the temperature data, but the performance being assessed was the algorithm's interpretation of that data.
7. The Type of Ground Truth Used
The primary ground truth used was:
- Luteinizing Hormone (LH) Test Results: Used to confirm ovulation occurrence (87 positive LH test results were submitted).
- Implied Clinical Outcome (Contraceptive Effectiveness): The statement "without increasing the risk of unintended pregnancy" refers to the overall clinical effectiveness as proven by prior studies of the Natural Cycles algorithm itself (likely referenced in the predicate device’s submission DEN170052), which this study aimed to maintain.
8. The Sample Size for the Training Set
The document does not specify the sample size for the training set for the Natural Cycles algorithm. It states, "There have been no changes to how the Natural Cycles algorithm determines the daily fertility status," implying the core algorithm was trained and validated prior to this submission (likely as part of the predicate device DEN170052). This submission focuses on validating a new input source for an existing, unchanged algorithm.
9. How the Ground Truth for the Training Set Was Established
Since the document does not provide details on the training set, it does not specify how its ground truth was established. However, for a fertility tracking algorithm, the ground truth for training would typically involve:
- Large datasets of menstrual cycles: Including daily basal body temperature, menstruation dates, and confirmed ovulation dates.
- Confirmation of ovulation: Often through methods like ultrasound, blood hormone levels (e.g., progesterone for luteal phase confirmation), and LH tests.
- Pregnancy outcomes: For contraceptive effectiveness studies.
The detailed methods for the original algorithm's training and ground truth establishment would be found in the 510(k) submission for the predicate device, DEN170052. This current submission (K202897) is an update validating a new data input source for an already cleared and validated algorithm.
§ 884.5370 Software application for contraception.
(a)
Identification. A software application for contraception is a device that provides user-specific fertility information for preventing a pregnancy. This device includes an algorithm that performs analysis of patient-specific data (e.g., temperature, menstrual cycle dates) to distinguish between fertile and non-fertile days, then provides patient-specific recommendations related to contraception.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Clinical performance testing must demonstrate the contraceptive effectiveness of the software in the intended use population.
(2) Human factors performance evaluation must be provided to demonstrate that the intended users can self-identify that they are in the intended use population and can correctly use the application, based solely on reading the directions for use for contraception.
(3) Software verification, validation, and hazard analysis must be performed. Documentation must include the following:
(i) A cybersecurity vulnerability and management process to assure software functionality; and
(ii) A description of the technical parameters of the software, including the algorithm used to determine fertility status and alerts for user inputs outside of expected ranges.
(4) Labeling must include:
(i) The following warnings and precautions:
(A) A statement that no contraceptive method is 100% effective.
(B) A statement that another form of contraception (or abstinence) must be used on days specified by the application.
(C) Statements of any factors that may affect the accuracy of the contraceptive information.
(D) A warning that the application cannot protect against sexually transmitted infections.
(ii) Hardware platform and operating system requirements.
(iii) Instructions identifying and explaining how to use the software application, including required user inputs and how to interpret the application outputs.
(iv) A summary of the clinical validation study and results, including effectiveness of the application as a stand-alone contraceptive and how this effectiveness compares to other forms of legally marketed contraceptives.