{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/predicting-pregnancy-using-large-scale-data","title":"Predicting pregnancy using large-scale data from a women's health tracking mobile application","arxiv_id":"1812.02222","date":"2018-12-05","proceeding":null,"authors":["Bo Liu","Shuyang Shi","Yongshang Wu","Daniel Thomas","Laura Symul","Emma Pierson","Jure Leskovec"],"abstract":"Predicting pregnancy has been a fundamental problem in women's health for\nmore than 50 years. Previous datasets have been collected via carefully curated\nmedical studies, but the recent growth of women's health tracking mobile apps\noffers potential for reaching a much broader population. However, the\nfeasibility of predicting pregnancy from mobile health tracking data is\nunclear. Here we develop four models -- a logistic regression model, and 3 LSTM\nmodels -- to predict a woman's probability of becoming pregnant using data from\na women's health tracking app, Clue by BioWink GmbH. Evaluating our models on a\ndataset of 79 million logs from 65,276 women with ground truth pregnancy test\ndata, we show that our predicted pregnancy probabilities meaningfully stratify\nwomen: women in the top 10% of predicted probabilities have a 89% chance of\nbecoming pregnant over 6 menstrual cycles, as compared to a 27% chance for\nwomen in the bottom 10%. We develop a technique for extracting interpretable\ntime trends from our deep learning models, and show these trends are consistent\nwith previous fertility research. Our findings illustrate the potential that\nwomen's health tracking data offers for predicting pregnancy on a broader\npopulation; we conclude by discussing the steps needed to fulfill this\npotential.","url_abs":"http://arxiv.org/abs/1812.02222v2","url_pdf":"http://arxiv.org/pdf/1812.02222v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"predicting-pregnancy-using-large-scale-data","repo_url":"https://github.com/AndyYSWoo/pregnancy-prediction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[{"method_slug":"logistic-regression","method_name":"Logistic Regression"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}