5 papers
Censored Flow Matching for Synthetic Time-to-Event Generation
Jianbin Tan, Xingran Chen, Kevin He +3
Generating time-to-event data is increasingly important in survival analysis, but it remains statistically challenging because event times are often censored and thus prevent flexi…
The Epidemiology of Artificial Intelligence
Harsh Parikh, Tyler McCormick, Emily Johnson +3
Artificial intelligence (AI) systems increasingly shape how people access health information, make medical decisions, and receive care -- yet epidemiology lacks frameworks for meas…
Prediction-based Inference in Electronic Health Record (EHR)-linked Biobanks with Clinically Informative Outcomes
Xingran Chen, Cheng-Han Yang, Zhenke Wu +1
Electronic health record (EHR)-linked biobank data hold tremendous promise for large-scale discoveries via genome-wide association study (GWAS) on diverse phenotypic traits and bio…
Data (in)equities in data science: Dissecting systemic and systematic biases in pulse oximetry
Lillian Rountree, Harsh Parikh, Bhramar Mukherjee
Data equity is an emerging framework for responsible data science. However, its core concepts, including fairness, representativeness, and information bias, remain largely abstract…
A Unified Framework for Inference with General Missingness Patterns and Machine Learning Imputation
Xingran Chen, Tyler McCormick, Bhramar Mukherjee +1
Predictions from machine learning (ML) models are increasingly used to impute missing data, but their naive use risks biased inference. Existing methods provide valid inference wit…