A team of researchers from the National Institute of Health Data Science at Peking University and the Department of Clinical Epidemiology and Biostatistics at Peking University People's Hospital conducted a systematic review on methods for handling missing data in electronic health records (EHRs). Missing data pose significant challenges in medical research, potentially leading to biased results and reduced statistical power. This review, which analyzed 46 studies published between 2010 and 2024, compared traditional statistical techniques, such as Multiple Imputation by Chained Equations (MICE), with advanced machine learning approaches, including Generative Adversarial Networks (GANs) and k-Nearest Neighbors (KNN).

The findings revealed that machine learning methods, especially GAN-based and time-series imputation techniques like CATSI, often outperformed traditional statistical methods in addressing missing data across diverse datasets. However, no single method was universally optimal, highlighting the need for standardized benchmarks to evaluate the performance of these methodologies under various scenarios. The research team aims to develop such benchmarks and create protocols for reliable missing data handling, ensuring more robust and reproducible outcomes in healthcare studies.

Women who develop bacterial vaginosis (BV) often later acquire chlamydia, a common and potentially serious sexually transmitted bacterial infection. Now, researchers at Albert Einstein College of Medicine, Roswell Park Comprehensive Cancer Center, and the Icahn School of Medicine at Mount Sinai have found that BV actually consists of two subtypes—one of which significantly increases the risk of developing chlamydia infections. The findings were made in a population of young Black and Hispanic women, who are disproportionately affected by both BV and chlamydia, but are historically understudied. The study, one of the largest and most comprehensive of its kind, was published online today in the journal Cell.