± HEALTH In our modern society, digital devices, social media platforms, and artificial intelligence (AI) tools have b…+ CLIMATE The growing complexity of electric vehicle charging station (EVCS) operations—driven by grid constraints, ren…± HEALTH Objectives This study aim to develop, compare and internally validate machine-learning models for predicting…+ HEALTH Diabetes management faces a number of obstacles, such as fragmented healthcare data, privacy concerns, poor e…− SCIENCE Background Craniofacial soft tissue thickness (CFSTT) is a critical parameter in forensic facial reconstructi…+ HEALTH Background Technological innovation in total joint arthroplasty (TJA) has largely focused on intraoperative p…± HEALTH Infective endocarditis (IE) continues to be an often fatal condition despite improvements in cardiac surgical…± HEALTH Purpose of review Systemic sclerosis-associated interstitial lung disease (SSc-ILD) is the leading cause of d…
TruaceTracing the truth around AIFriday, September 11, 2026
Subscribe
Health·G Space·Evidence-backed gain·Published 2026-09-09

Causal adiposity and clinical validation of regional fat distribution in PMOS: a multi-modal analysis integrating GBD 2021, Mendelian randomization, and machine learning

Abstract: Background Polyendocrine metabolic ovarian syndrome (PMOS), previously named polycystic ovary syndrome (PCOS), is the most common endocrine disorder among women of reproductive age and a leading cause of anovulatory infertility. However, the evolving global burden of PMOS and the role of adiposity, particularly regional fat distribution, remain incompletely understood. We integrated global epidemiological analysis, genetic causal inference, and clinical prediction modeling to investigate the burden and adiposity…

TRV-2026-1034Peer-reviewedPermanent record — cite & verify
Causal adiposity and clinical validation of regional fat distribution in PMOS: a multi-modal analysis integrating GBD 2021, Mendelian randomization, and machine learning

"Cmglee Cambridge Cancer Research" by Cmglee is licensed under CC BY-SA 3.0. To view a copy of this license, visit https://creativecommons.org/licenses/by-sa/3.0/.

The quick read

Using GBD 2021 data, Mendelian randomization, and a clinical cohort, the study quantified global PMOS burden and tested adiposity as a causal determinant, then built machine-learning models from body-composition measures to predict PMOS, with XGBoost reaching AUC 0.701 and SHAP highlighting left-leg and trunk fat mass.

The convergence of population burden, genetic evidence, and ML prediction suggests body-composition phenotypes beyond BMI matter for PMOS risk and infertility, but predictive performance was modest and validation was internal only, leaving uncertainty about clinical utility across diverse populations and settings.

Main points
  • GBD 2021 analysis estimated PMOS affected approximately 69.5 million women globally in 2021 with age-standardized prevalence 1,757.8 per 100,000.
  • Two-sample Mendelian randomization linked adiposity traits to PMOS, including body mass index OR 2.60 and left-leg fat mass OR 3.44, while fat-free mass showed no significant association.
  • Clinical ML cohort used detailed body-composition measurements to train models, with XGBoost outperforming others and SHAP used to interpret predictions.
Gain

XGBoost model predicted PMOS status from detailed body-composition measures with AUC 0.701 in testing, with SHAP highlighting regional fat masses as top predictors.

The rundown

Researchers combined GBD 2021 epidemiology, two-sample Mendelian randomization for overall and regional adiposity, and a clinical cohort with detailed body-composition data to train ML models for PMOS.

GBD results showed highest modeled incidence in the 10-14-year age group and about 12.5 million infertility cases attributable to PMOS worldwide, while MR found trunk fat mass OR 2.54 and body fat percentage OR 3.32 as risk factors.

Sources

Reader signal

How should this claim be treated?

The debate