2 Hits in 1.3 sec

SAMGEP: A Novel Method for Prediction of Phenotype Event Times Using the Electronic Health Record [article]

Yuri Ahuja, Chuan Hong, Zongqi Xia, Tianxi Cai
2021 medRxiv   pre-print
Objective: While there exist numerous methods to predict binary phenotypes using electronic health record (EHR) data, few exist for prediction of phenotype event times, or equivalently phenotype state  ...  Methods: SAMGEP broadly consists of four steps: (i) assemble time-evolving EHR features predictive of the target phenotype event, (ii) optimize weights for combining raw features and feature embeddings  ...  Since the ultimate objective of SAMGEP is to predict the precise timings of phenotype events over the course of a patient's observed record, as well as the time to first event for survival analysis, we  ... 
doi:10.1101/2021.03.07.21253096 fatcat:ahl3si5y65fajjtkyw6rqtqa5a

Semi-supervised Calibration of Risk with Noisy Event Times (SCORNET) Using Electronic Health Record Data [article]

Yuri Ahuja, Liang Liang, Sicong Huang, Tianxi Cai
2021 bioRxiv   pre-print
Leveraging large-scale electronic health record (EHR) data to estimate survival curves for clinical events can enable more powerful risk estimation and comparative effectiveness research.  ...  However, use of EHR data is hindered by a lack of direct event times observations.  ...  Acknowledgements The authors declare no conflicts of interest. References  ... 
doi:10.1101/2021.01.08.425976 fatcat:7j7vkvbbfzaerp6o5wmjeyo5ri