Identifying Women at Risk for Polycystic Ovary Syndrome Using a Mobile Health App: Virtual Tool Functionality Assessment
Open accessPublished version of a preprint
Abstract
Background: Polycystic ovary syndrome (PCOS) is an endocrine disrupting disorder affecting about 10% of reproductive-aged women. PCOS diagnosis may be delayed several years and may require multiple physicians, resulting in lost time for risk-reducing interventions. Menstrual tracking apps are a potential tool to alert women of their risk while also prompting evaluation from a medical professional. Objective: The primary objective of this study was to develop and pilot test the irregular cycle feature, a predictive model that generated a PCOS risk score, in the menstrual tracking app, Clue. The secondary objectives were to run the model using virtual test subjects, create a quantitative risk score, compare the feature’s risk score with that of a physician, and determine the sensitivity and specificity of the model before empirical testing on human subjects. Methods: A literature review was conducted to generate a list of signs and symptoms of PCOS, termed variables. Variables were then assigned a probability and built into a Bayesian network. Questions were created based on these variables. A total of 9 virtual test subjects were identified using self-reported menstrual cycles and answers to the feature’s questions. Upon completion of the questionnaire, a Result Screen and Doctor’s Report summarizing the probability of having PCOS was displayed. This provided information about PCOS and data to facilitate diagnosis by a medical professional. To assess the accuracy of the feature, the same set of 9 virtual test subjects was assigned probabilities by the feature and the physician, who served as the gold standard. The feature recommended individuals with a score greater than or equal to 25% to follow-up with a physician. Differences between the feature and physician scores were evaluated using a t test and a Pearson correlation coefficient in 8 of the 9 virtual test subjects. A second iteration was conducted to assess the feature’s probability capabilities. Results: The irregular cycle feature’s first iteration produced 1 false-positive compared with the physician score and had an absolute mean difference of 15.5% (SD 15.1%) among the virtual test subjects. The second iteration had 2 false positives compared with the physician score and had an absolute mean difference of 18.8% (SD 13.6%). The feature overpredicted the virtual test subjects’ risk of PCOS compared with the physician. However, a significant positive correlation existed between the feature and physician score (Pearson correlation coefficient=0.82; P=.01). The second iteration performed worse, with a Pearson correlation coefficient of 0.73 (P=.03). Conclusions: The first iteration of the feature outperformed the second and better predicted the probability of PCOS. Although further research is needed with a more robust sample size, this pilot study indicates the potential value for developing a screening tool to prompt high-risk subjects to seek evaluation by a medical professional.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Nine included studies mention the use of machine learning.
“Nine included studies mention the use of machine learning [63,64,65,66,67,76,87,88,89] (Supplementary File S3).”
From Polycystic Ovary Syndrome and the Internet of Things: A Scoping Review (2024) · cites this paper as [67]
The Methods (Creating the Framework; page unavailable) describe a Bayesian-network model used to generate PCOS risk scores, supporting this paper’s inclusion as a study of an algorithmic prediction tool. They say the network’s probabilities were manually encoded, however, and our copy does not explicitly mention machine learning. This source also cannot establish the citing paper’s count of nine included studies. (LLM, conf=0.81)
Experimental — accuracy not yet measuredOne study developed a prediction model capable of generating a PCOS risk score and tested it by analyzing data from the irregular cycle feature of the app Clue, with the model showing a higher probability of prediction when compared to assessment by a clinician.
“One study developed a prediction model capable of generating a PCOS risk score and tested it by analyzing data from the irregular cycle feature of the app Clue, with the model showing a higher probability of prediction when compared to assessment by a clinician [67].”
From Polycystic Ovary Syndrome and the Internet of Things: A Scoping Review (2024) · cites this paper as [67]
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measuredThe majority of machine learning studies originated from India (n = 5), while three originated from the USA, and one from New Zealand.
“The majority of these studies originated from India (n = 5) [63,64,65,66,88], while three originated from the USA (n = 3) [67,87,89], and one from New Zealand [76].”
From Polycystic Ovary Syndrome and the Internet of Things: A Scoping Review (2024) · cites this paper as [67]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
(2004) · Fertility and Sterility · doi:10.1016/j.fertnstert.2003.10.004 · Cited by 9,050 · see citing works
The Rotterdam ESHRE/ASRM-sponsored PCOS consensus workshop group (2004) · Human Reproduction · doi:10.1093/humrep/deh098 · Cited by 6,138 · see citing works
Azziz, R., Carmina, E., Dewailly, D., Diamanti-Kandarakis, E., Escobar-Morreale, H. F., Futterweit, W., Janssen, O. E., Legro, R. S., Norman, R. J., Taylor, A. E., et al. (2009) · Fertility and Sterility · doi:10.1016/j.fertnstert.2008.06.035 · Cited by 2,132 · see citing works
Health App Use Among US Mobile Phone Owners: A National Survey
Krebs, P., & Duncan, D. T. (2015) · JMIR mHealth and uHealth · doi:10.2196/mhealth.4924 · Cited by 1,274 · see citing works
Yildiz, B. O., Bozdag, G., Yapici, Z., Esinler, I., & Yarali, H. (2012) · Human Reproduction · doi:10.1093/humrep/des232 · Cited by 704 · see citing works
Azziz, R., Marin, C., Hoq, L., Badamgarav, E., & Song, P. (2005) · The Journal of Clinical Endocrinology & Metabolism · doi:10.1210/jc.2005-0628 · Cited by 537 · see citing works
Gibson-Helm, M., Teede, H., Dunaif, A., & Dokras, A. (2016) · The Journal of Clinical Endocrinology & Metabolism · doi:10.1210/jc.2016-2963 · Cited by 428 · cited 1× · see citing works
“By providing more information about PCOS and giving users feedback based on information they have collected, the research team predicts that this feature will provide important information to those at high risk of the disease and potentially shorten the time for diagnosis [22,23].”
BackgroundThe FIGO recommendations on terminologies and definitions for normal and abnormal uterine bleeding
Fraser, I., Critchley, H., Broder, M., & Munro, M. (2011) · Seminars in Reproductive Medicine · doi:10.1055/s-0031-1287662 · Cited by 384 · see citing works
Examining menstrual tracking to inform the design of personal informatics tools
Epstein, D. A., Lee, N. B., Kang, J. H., Agapie, E., Schroeder, J., Pina, L. R., Fogarty, J., Kientz, J. A., & Munson, S. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025635 · Cited by 346 · see citing works
Health Care Utilization and Costs by Metabolic Syndrome Risk Factors
Boudreau, D. M., Malone, D. C., Raebel, M. A., Fishman, P. A., Nichols, G. A., Feldstein, A. C., Boscoe, A. N., Ben-Joseph, R. H., Magid, D. J., & Okamoto, L. J. (2009) · Metabolic Syndrome and Related Disorders · doi:10.1089/met.2008.0070 · Cited by 225 · see citing works
Kononowicz, A. A., Zary, N., Edelbring, S., Corral, J., & Hege, I. (2015) · BMC Medical Education · doi:10.1186/s12909-015-0296-3 · Cited by 203 · see citing works
Diagnosis of hyperandrogenism: clinical criteria
Yıldız, B. O. (2006) · Best Practice & Research Clinical Endocrinology & Metabolism · doi:10.1016/j.beem.2006.02.004 · Cited by 126 · see citing works
Smartphone Medical Applications for Women’s Health: What Is the Evidence-Base and Feedback?
Derbyshire, E. J., & Dancey, D. (2013) · International Journal of Telemedicine and Applications · doi:10.1155/2013/782074 · Cited by 99 · see citing works
The quantified patient: a patient participatory culture
Appelboom, G., LoPresti, M. A., Reginster, J., Connolly, E. S., & Dumont, E. P. L. (2014) · Current Medical Research and Opinion · doi:10.1185/03007995.2014.954032 · Cited by 56 · see citing works
Defining epidemics in computer simulation models: How do definitions influence conclusions?
Orbann, C., Sattenspiel, L., Miller, E. L., & Dimka, J. (2016) · Epidemics · doi:10.1016/j.epidem.2016.12.001 · Cited by 52 · see citing works
Electronic versus paper instruments for daily data collection
Johannes, C. B., Woods, J., Crawford, S., Cochran, H. L., Tran, D., & Schuth, B. (2000) · Annals of Epidemiology · doi:10.1016/s1047-2797(00)00141-1 · Cited by 41 · see citing works
Ask PCOS: identifying need to inform evidence-based app development for polycystic ovary syndrome
Xu, R., Gilbert, E., Kuczynska-Burggraf, M., Tan, B., Teede, H., Vincent, A., Gibson-Helm, M., & Boyle, J. (2018) · Seminars in Reproductive Medicine · doi:10.1055/s-0038-1667187 · Cited by 32 · see citing works
Aliferis, C., & Cooper, G. F. (1994) · Elsevier eBooks · doi:10.1016/b978-1-55860-332-5.50006-7 · Cited by 29 · see citing works
The Ovulation and Menstruation Study Report on Cognitive Testing of Survey Instrument, July 5, 2017
Mahalingaiah, S. (2020) · Harvard Dataverse · doi:10.7910/dvn/j0cl9o · Cited by 2 · see citing works
Self-citationComputer Simulation Model to Train Medical Personnel on Glucose Clamp Procedures
Maghoul, P., Boulet, B., Tardif, A., & Haidar, A. (2017) · Canadian Journal of Diabetes · doi:10.1016/j.jcjd.2017.08.004 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Barrera, F. J., Brown, E. D. L., Rojo, A., Obeso, J., Plata, H., Lincango, E. P., Terry, N., Rodríguez-Gutiérrez, R., Hall, J. E., & Shekhar, S. (2023) · Frontiers in Endocrinology · doi:10.3389/fendo.2023.1106625 · Cited by 91 · see citing works
Artificial intelligence in polycystic ovarian syndrome management: past, present, and future
Wang, J., Chen, R., Long, H., He, J., Tang, M., Su, M., Deng, R., Chen, Y., Ni, R., Zhao, S., et al. (2025) · La radiologia medica · doi:10.1007/s11547-025-02032-9 · Cited by 26 · see citing works
Survey analysis of quantitative and qualitative menstrual cycle tracking technologies
Stujenske, T. M., Mu, Q., Pérez Capotosto, M., & Bouchard, T. P. (2023) · Medicina · doi:10.3390/medicina59091509 · Cited by 22 · see citing works
Polycystic Ovary Syndrome Monitoring using Machine Learning
Vasavi, R. R., Priscilla Prathibha, S., Valiveti, H., Maringanti, S., & Parsa, A. (2023) · 2023 International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT) · doi:10.1109/idciot56793.2023.10052781 · Cited by 15 · see citing works
Polycystic Ovary Syndrome and the Internet of Things: A Scoping Review
Graca, S., Alloh, F., Lagojda, L., Dallaway, A., Kyrou, I., Randeva, H. S., & Kite, C. (2024) · Healthcare · doi:10.3390/healthcare12161671 · Cited by 14 · see citing works
“Most of the videos (n = 133, 67.2”
BackgroundInfluentialPeven, K., Wickham, A. P., Wilks, O., Kaplan, Y. C., Marhol, A., Ahmed, S., Bamford, R., Cunningham, A. C., Prentice, C., Meczner, A., et al. (2023) · JMIR mHealth and uHealth · doi:10.2196/46718 · Cited by 9 · see citing works
Polycystic ovary syndrome and related inflammation in radiomics; relationship with patient outcome
Zheng, C.-Y., Yu, Y., & Bai, X. (2023) · Seminars in Cell and Developmental Biology · doi:10.1016/j.semcdb.2023.02.013 · Cited by 9 · see citing works
Wright, P. J., Burts, C., Harmon, C., & Corbett, C. F. (2025) · JMIR Infodemiology · doi:10.2196/68469 · Cited by 8 · see citing works
“Women with PCOS report the expectation of an easily accessible and user-friendly platform [23,25,27,28].”
Arabkermani, Z., Barzegari, S., Rouhani, A., Nahavandi, N., Gibreel, O., & Arpacı, İ. (2025) · Journal of Medical Internet Research · doi:10.2196/71118 · Cited by 8 · see citing works
Sacca, L., Lobaina, D., Knopf, E., Burgoa, S., Jimenez, S., Okwaraji, G., Etzel, M., Vardanyan, V., Tharp, M. E., Rao, M., et al. (2024) · Clinics and Practice · doi:10.3390/clinpract14050131 · Cited by 5 · see citing works
Wearable intelligence: can we transform fertility tracking through digital innovation?
Ali, Z. E., Ammar, O. F., Liperis, G., Sharma, K., Hall, J., Grace, B., & Fraire-Zamora, J. J. (2025) · Human Reproduction · doi:10.1093/humrep/deaf148 · Cited by 4 · see citing works
Adnan, T., Li, H., Peer, K., Peebles, E., James, K. E., & Mahalingaiah, S. (2023) · Journal of Medical Internet Research · doi:10.2196/42164 · Cited by 4 · see citing works
Self-citationVemulavada, S., Karthikvatsan, S., Babu, A., Kadalmani, B., Devi, T. R., Sasipraba, T., Manikkam, R., Parthasarathy, K., & Balaji, V. H. (2024) · Springer eBooks · doi:10.1007/978-981-97-1777-4_9 · Cited by 3 · see citing works
Ramaiyer, M. S., Sabeh, M. E., Zhu, J., Shea, A. A., Segev, D. L., Yenokyan, G., & Borahay, M. A. (2024) · Vaccine X · doi:10.1016/j.jvacx.2024.100501 · Cited by 2 · see citing works
Hou, J., Duan, Y., Zhao, W., Sun, Q., & Wang, J. (2026) · Frontiers in Endocrinology · doi:10.3389/fendo.2026.1760541 · Cited by 1 · see citing works
Femtech: Marktpotenziale genderspezifischer Versorgung
Korte, L. (2023) · Springer eBooks · doi:10.1007/978-3-658-41781-9_50
Leveraging AI Models/Tools for Human Fertility
Santosh, K., & Roy, D. G. (2025) · Studies in computational intelligence · doi:10.1007/978-981-95-1248-5_4
HERCYCLE: AI and Doctor guided Health for Women dealing with PCOD/PCOS
Dhanyaja, P., Nisna Haneefa, K., M, G. K., M, N. N., S, R. P., & Anjali, B. (2026) · International Conference on Networking and Communications (ICNWC) · doi:10.1109/icnwc68145.2026.11518502
- Authors
- Rodriguez, E. M., Thomas, D., Druet, A., Vlajic-Wheeler, M., Lane, K. J., & Mahalingaiah, S.
- Affiliations
- Boston University (US)
- Corresponding author
- Mahalingaiah, Shruthi
- ORCID
- Venue
- JMIR Formative Research
- Publisher
- JMIR Publications Inc.
- Published
- 2020-05-14
- Volume
- 4
- Issue
- 5
- Pages
- e15094
- ISSN
- 2561-326X (ISSN-L)
- PMC
- PMC7256750
- OpenAlex
- W3012954192
- Cited by
- 18
- References
- 20
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 4 · 2023: 7
- FWCI
- 1.83
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- JMIR Formative Research (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- OpenBU (Boston University) (submittedVersion)
- Topics
- Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
- Health Sciences › Medicine › Reproductive Medicine › Ovarian function and disorders
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- polycystic ovary syndrome, menstrual tracking apps, clues, mobile health, Bayesian networks, menstrual irregularity, PCOS symptoms, physician comparison, risk score, delayed diagnosis, women's health technology, sensitivity and specificity
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
