Wenxin Ning1, Stephanie Chan2, Andrew Beam3, Ming Yu1, Alon Geva4, Katherine Liao5, Mary Mullen6, Kenneth D Mandl7, Isaac Kohane3, Tianxi Cai8, Sheng Yu9. 1. Department of Industrial Engineering, Tsinghua University, Beijing, China. 2. Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA. 3. Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA. 4. Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA; Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA, USA; Department of Anesthesia, Harvard Medical School, Boston, MA, USA. 5. Department of Medicine, Division of Rheumatology, Immunology and Allergy, Brigham and Women's Hospital, Boston, MA, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA. 6. Department of Cardiology, Boston Children's Hospital, Boston, MA, USA; Department of Pediatrics, Harvard Medical School, Boston, MA, USA. 7. Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA. 8. Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA. 9. Center for Statistical Science, Tsinghua University, Beijing, China; Department of Industrial Engineering, Tsinghua University, Beijing, China; Institute for Data Science, Tsinghua University, Beijing, China. Electronic address: syu@tsinghua.edu.cn.
Abstract
OBJECTIVE: Phenotyping algorithms can efficiently and accurately identify patients with a specific disease phenotype and construct electronic health records (EHR)-based cohorts for subsequent clinical or genomic studies. Previous studies have introduced unsupervised EHR-based feature selection methods that yielded algorithms with high accuracy. However, those selection methods still require expert intervention to tweak the parameter settings according to the EHR data distribution for each phenotype. To further accelerate the development of phenotyping algorithms, we propose a fully automated and robust unsupervised feature selection method that leverages only publicly available medical knowledge sources, instead of EHR data. METHODS: SEmantics-Driven Feature Extraction (SEDFE) collects medical concepts from online knowledge sources as candidate features and gives them vector-form distributional semantic representations derived with neural word embedding and the Unified Medical Language System Metathesaurus. A number of features that are semantically closest and that sufficiently characterize the target phenotype are determined by a linear decomposition criterion and are selected for the final classification algorithm. RESULTS: SEDFE was compared with the EHR-based SAFE algorithm and domain experts on feature selection for the classification of five phenotypes including coronary artery disease, rheumatoid arthritis, Crohn's disease, ulcerative colitis, and pediatric pulmonary arterial hypertension using both supervised and unsupervised approaches. Algorithms yielded by SEDFE achieved comparable accuracy to those yielded by SAFE and expert-curated features. SEDFE is also robust to the input semantic vectors. CONCLUSION: SEDFE attains satisfying performance in unsupervised feature selection for EHR phenotyping. Both fully automated and EHR-independent, this method promises efficiency and accuracy in developing algorithms for high-throughput phenotyping.
OBJECTIVE: Phenotyping algorithms can efficiently and accurately identify patients with a specific disease phenotype and construct electronic health records (EHR)-based cohorts for subsequent clinical or genomic studies. Previous studies have introduced unsupervised EHR-based feature selection methods that yielded algorithms with high accuracy. However, those selection methods still require expert intervention to tweak the parameter settings according to the EHR data distribution for each phenotype. To further accelerate the development of phenotyping algorithms, we propose a fully automated and robust unsupervised feature selection method that leverages only publicly available medical knowledge sources, instead of EHR data. METHODS: SEmantics-Driven Feature Extraction (SEDFE) collects medical concepts from online knowledge sources as candidate features and gives them vector-form distributional semantic representations derived with neural word embedding and the Unified Medical Language System Metathesaurus. A number of features that are semantically closest and that sufficiently characterize the target phenotype are determined by a linear decomposition criterion and are selected for the final classification algorithm. RESULTS:SEDFE was compared with the EHR-based SAFE algorithm and domain experts on feature selection for the classification of five phenotypes including coronary artery disease, rheumatoid arthritis, Crohn's disease, ulcerative colitis, and pediatric pulmonary arterial hypertension using both supervised and unsupervised approaches. Algorithms yielded by SEDFE achieved comparable accuracy to those yielded by SAFE and expert-curated features. SEDFE is also robust to the input semantic vectors. CONCLUSION:SEDFE attains satisfying performance in unsupervised feature selection for EHR phenotyping. Both fully automated and EHR-independent, this method promises efficiency and accuracy in developing algorithms for high-throughput phenotyping.
Authors: Katherine M Newton; Peggy L Peissig; Abel Ngo Kho; Suzette J Bielinski; Richard L Berg; Vidhu Choudhary; Melissa Basford; Christopher G Chute; Iftikhar J Kullo; Rongling Li; Jennifer A Pacheco; Luke V Rasmussen; Leslie Spangler; Joshua C Denny Journal: J Am Med Inform Assoc Date: 2013-03-26 Impact factor: 4.497
Authors: Joshua C Denny; Lisa Bastarache; Marylyn D Ritchie; Robert J Carroll; Raquel Zink; Jonathan D Mosley; Julie R Field; Jill M Pulley; Andrea H Ramirez; Erica Bowton; Melissa A Basford; David S Carrell; Peggy L Peissig; Abel N Kho; Jennifer A Pacheco; Luke V Rasmussen; David R Crosslin; Paul K Crane; Jyotishman Pathak; Suzette J Bielinski; Sarah A Pendergrass; Hua Xu; Lucia A Hindorff; Rongling Li; Teri A Manolio; Christopher G Chute; Rex L Chisholm; Eric B Larson; Gail P Jarvik; Murray H Brilliant; Catherine A McCarty; Iftikhar J Kullo; Jonathan L Haines; Dana C Crawford; Daniel R Masys; Dan M Roden Journal: Nat Biotechnol Date: 2013-12 Impact factor: 54.908
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: Katherine P Liao; Ashwin N Ananthakrishnan; Vishesh Kumar; Zongqi Xia; Andrew Cagan; Vivian S Gainer; Sergey Goryachev; Pei Chen; Guergana K Savova; Denis Agniel; Susanne Churchill; Jaeyoung Lee; Shawn N Murphy; Robert M Plenge; Peter Szolovits; Isaac Kohane; Stanley Y Shaw; Elizabeth W Karlson; Tianxi Cai Journal: PLoS One Date: 2015-08-24 Impact factor: 3.240
Authors: Katherine P Liao; Tianxi Cai; Guergana K Savova; Shawn N Murphy; Elizabeth W Karlson; Ashwin N Ananthakrishnan; Vivian S Gainer; Stanley Y Shaw; Zongqi Xia; Peter Szolovits; Susanne Churchill; Isaac Kohane Journal: BMJ Date: 2015-04-24
Authors: Griffin M Weber; Tianxi Cai; Isaac S Kohane; Bruce J Aronow; Paul Avillach; Brett K Beaulieu-Jones; Riccardo Bellazzi; Robert L Bradford; Gabriel A Brat; Mario Cannataro; James J Cimino; Noelia García-Barrio; Nils Gehlenborg; Marzyeh Ghassemi; Alba Gutiérrez-Sacristán; David A Hanauer; John H Holmes; Chuan Hong; Jeffrey G Klann; Ne Hooi Will Loh; Yuan Luo; Kenneth D Mandl; Mohamad Daniar; Jason H Moore; Shawn N Murphy; Antoine Neuraz; Kee Yuan Ngiam; Gilbert S Omenn; Nathan Palmer; Lav P Patel; Miguel Pedrera-Jiménez; Piotr Sliz; Andrew M South; Amelia Li Min Tan; Deanne M Taylor; Bradley W Taylor; Carlo Torti; Andrew K Vallejos; Kavishwar B Wagholikar Journal: J Med Internet Res Date: 2021-03-02 Impact factor: 7.076
Authors: Phyllis M Thangaraj; Benjamin R Kummer; Tal Lorberbaum; Mitchell S V Elkind; Nicholas P Tatonetti Journal: BioData Min Date: 2020-12-07 Impact factor: 2.522