Hossein Estiri1,2,3, Zachary H Strasser1,2,3, Shawn N Murphy1,2,3. 1. Harvard Medical School, Boston, Massachusetts, USA. 2. Massachusetts General Hospital, Boston, Massachusetts, USA. 3. Mass General Brigham, Boston, Massachusetts, USA.
Abstract
OBJECTIVE: High-throughput electronic phenotyping algorithms can accelerate translational research using data from electronic health record (EHR) systems. The temporal information buried in EHRs is often underutilized in developing computational phenotypic definitions. This study aims to develop a high-throughput phenotyping method, leveraging temporal sequential patterns from EHRs. MATERIALS AND METHODS: We develop a representation mining algorithm to extract 5 classes of representations from EHR diagnosis and medication records: the aggregated vector of the records (aggregated vector representation), the standard sequential patterns (sequential pattern mining), the transitive sequential patterns (transitive sequential pattern mining), and 2 hybrid classes. Using EHR data on 10 phenotypes from the Mass General Brigham Biobank, we train and validate phenotyping algorithms. RESULTS: Phenotyping with temporal sequences resulted in a superior classification performance across all 10 phenotypes compared with the standard representations in electronic phenotyping. The high-throughput algorithm's classification performance was superior or similar to the performance of previously published electronic phenotyping algorithms. We characterize and evaluate the top transitive sequences of diagnosis records paired with the records of risk factors, symptoms, complications, medications, or vaccinations. DISCUSSION: The proposed high-throughput phenotyping approach enables seamless discovery of sequential record combinations that may be difficult to assume from raw EHR data. Transitive sequences offer more accurate characterization of the phenotype, compared with its individual components, and reflect the actual lived experiences of the patients with that particular disease. CONCLUSION: Sequential data representations provide a precise mechanism for incorporating raw EHR records into downstream machine learning. Our approach starts with user interpretability and works backward to the technology.
OBJECTIVE: High-throughput electronic phenotyping algorithms can accelerate translational research using data from electronic health record (EHR) systems. The temporal information buried in EHRs is often underutilized in developing computational phenotypic definitions. This study aims to develop a high-throughput phenotyping method, leveraging temporal sequential patterns from EHRs. MATERIALS AND METHODS: We develop a representation mining algorithm to extract 5 classes of representations from EHR diagnosis and medication records: the aggregated vector of the records (aggregated vector representation), the standard sequential patterns (sequential pattern mining), the transitive sequential patterns (transitive sequential pattern mining), and 2 hybrid classes. Using EHR data on 10 phenotypes from the Mass General Brigham Biobank, we train and validate phenotyping algorithms. RESULTS: Phenotyping with temporal sequences resulted in a superior classification performance across all 10 phenotypes compared with the standard representations in electronic phenotyping. The high-throughput algorithm's classification performance was superior or similar to the performance of previously published electronic phenotyping algorithms. We characterize and evaluate the top transitive sequences of diagnosis records paired with the records of risk factors, symptoms, complications, medications, or vaccinations. DISCUSSION: The proposed high-throughput phenotyping approach enables seamless discovery of sequential record combinations that may be difficult to assume from raw EHR data. Transitive sequences offer more accurate characterization of the phenotype, compared with its individual components, and reflect the actual lived experiences of the patients with that particular disease. CONCLUSION: Sequential data representations provide a precise mechanism for incorporating raw EHR records into downstream machine learning. Our approach starts with user interpretability and works backward to the technology.
Authors: Sheng Yu; Katherine P Liao; Stanley Y Shaw; Vivian S Gainer; Susanne E Churchill; Peter Szolovits; Shawn N Murphy; Isaac S Kohane; Tianxi Cai Journal: J Am Med Inform Assoc Date: 2015-04-29 Impact factor: 4.497
Authors: Abel N Kho; Jennifer A Pacheco; Peggy L Peissig; Luke Rasmussen; Katherine M Newton; Noah Weston; Paul K Crane; Jyotishman Pathak; Christopher G Chute; Suzette J Bielinski; Iftikhar J Kullo; Rongling Li; Teri A Manolio; Rex L Chisholm; Joshua C Denny Journal: Sci Transl Med Date: 2011-04-20 Impact factor: 17.956
Authors: Tao Zheng; Wei Xie; Liling Xu; Xiaoying He; Ya Zhang; Mingrong You; Gong Yang; You Chen Journal: Int J Med Inform Date: 2016-10-01 Impact factor: 4.046
Authors: Catherine A McCarty; Rex L Chisholm; Christopher G Chute; Iftikhar J Kullo; Gail P Jarvik; Eric B Larson; Rongling Li; Daniel R Masys; Marylyn D Ritchie; Dan M Roden; Jeffery P Struewing; Wendy A Wolf Journal: BMC Med Genomics Date: 2011-01-26 Impact factor: 3.063
Authors: Sheng Yu; Abhishek Chakrabortty; Katherine P Liao; Tianrun Cai; Ashwin N Ananthakrishnan; Vivian S Gainer; Susanne E Churchill; Peter Szolovits; Shawn N Murphy; Isaac S Kohane; Tianxi Cai Journal: J Am Med Inform Assoc Date: 2017-04-01 Impact factor: 4.497
Authors: Hossein Estiri; Zachary H Strasser; Gabriel A Brat; Yevgeniy R Semenov; Chirag J Patel; Shawn N Murphy Journal: BMC Med Date: 2021-09-27 Impact factor: 11.150