Characterization of Polycystic Ovary Syndrome Among Flo App Users Around the World
Bibliographic record
Abstract
Abstract Background: Polycystic ovary syndrome (PCOS) is a complex and multi-faceted endocrine disorder that affects 5-20% of women. Literature is limited regarding potentially differing PCOS phenotypes among women around the world. Therefore, we used Flo app technology to understand the multifaceted characteristics of PCOS across several countries and identify contributing risk factors to the development of this condition.Methods: Flo is a widely used female health and wellbeing app with period tracking functionality that provides a globally representative and medically unbiased perspective on PCOS symptomatology. A chatbot dialog on PCOS was subsequently administered on the Flo application (app) to users from 142 countries (with at least 100 respondents) who have the app running in English during September-October 2019.Results: For analyses, we selected the five countries with the greatest number of respondents: US (n=243,238), UK (n=68,325), India (n=40,092), Philippines (n=35,131), and Australia (n=29,926). Bloating was the most frequently reported symptom among PCOS-positive women and appeared to be the main predictor of PCOS in our model (odds ratio 3·76 [95% CI 3·60-3·94]; p<0·0001). Additional top predictors of PCOS are high blood cholesterol and glucose levels. As BMI increased, the percentage of women who reported a physician-confirmed PCOS diagnosis also increased. However, women in India did not follow this trend.Conclusions: Our findings are based on the largest known PCOS dataset and indicate that symptoms are more complex than previously understood. The most frequently reported symptoms (bloating, facial hirsutism, irregular cycles, hyperpigmentation, and baldness) are broader than those included in the Rotterdam criteria. Future work should reevaluate and refine the criteria utilized in PCOS diagnosis.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".