Tao Zheng1, Wei Xie2, Liling Xu3, Xiaoying He4, Ya Zhang5, Mingrong You6, Gong Yang6, You Chen7. 1. Institute of Image Communication and Networking, Shanghai Jiao Tong University, Shanghai, China; Tongren Hospital Shanghai Jiao Tong University, Shanghai, China. 2. Department of Electrical Engineering & Computer Science, Vanderbilt University, Nashville, TN, USA. 3. Tongren Hospital Shanghai Jiao Tong University, Shanghai, China. 4. Department of Endocrinology, the First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, China. 5. Institute of Image Communication and Networking, Shanghai Jiao Tong University, Shanghai, China. 6. Division of Epidemiology, Vanderbilt University, Nashville, TN, USA. 7. Department of Biomedical Informatics, Vanderbilt University, Nashville, TN, USA. Electronic address: you.chen@vanderbilt.edu.
Abstract
OBJECTIVE: To discover diverse genotype-phenotype associations affiliated with Type 2 Diabetes Mellitus (T2DM) via genome-wide association study (GWAS) and phenome-wide association study (PheWAS), more cases (T2DM subjects) and controls (subjects without T2DM) are required to be identified (e.g., via Electronic Health Records (EHR)). However, existing expert based identification algorithms often suffer in a low recall rate and could miss a large number of valuable samples under conservative filtering standards. The goal of this work is to develop a semi-automated framework based on machine learning as a pilot study to liberalize filtering criteria to improve recall rate with a keeping of low false positive rate. MATERIALS AND METHODS: We propose a data informed framework for identifying subjects with and without T2DM from EHR via feature engineering and machine learning. We evaluate and contrast the identification performance of widely-used machine learning models within our framework, including k-Nearest-Neighbors, Naïve Bayes, Decision Tree, Random Forest, Support Vector Machine and Logistic Regression. Our framework was conducted on 300 patient samples (161 cases, 60 controls and 79 unconfirmed subjects), randomly selected from 23,281 diabetes related cohort retrieved from a regional distributed EHR repository ranging from 2012 to 2014. RESULTS: We apply top-performing machine learning algorithms on the engineered features. We benchmark and contrast the accuracy, precision, AUC, sensitivity and specificity of classification models against the state-of-the-art expert algorithm for identification of T2DM subjects. Our results indicate that the framework achieved high identification performances (∼0.98 in average AUC), which are much higher than the state-of-the-art algorithm (0.71 in AUC). DISCUSSION: Expert algorithm-based identification of T2DM subjects from EHR is often hampered by the high missing rates due to their conservative selection criteria. Our framework leverages machine learning and feature engineering to loosen such selection criteria to achieve a high identification rate of cases and controls. CONCLUSIONS: Our proposed framework demonstrates a more accurate and efficient approach for identifying subjects with and without T2DM from EHR. Copyright Â
OBJECTIVE: To discover diverse genotype-phenotype associations affiliated with Type 2 Diabetes Mellitus (T2DM) via genome-wide association study (GWAS) and phenome-wide association study (PheWAS), more cases (T2DM subjects) and controls (subjects without T2DM) are required to be identified (e.g., via Electronic Health Records (EHR)). However, existing expert based identification algorithms often suffer in a low recall rate and could miss a large number of valuable samples under conservative filtering standards. The goal of this work is to develop a semi-automated framework based on machine learning as a pilot study to liberalize filtering criteria to improve recall rate with a keeping of low false positive rate. MATERIALS AND METHODS: We propose a data informed framework for identifying subjects with and without T2DM from EHR via feature engineering and machine learning. We evaluate and contrast the identification performance of widely-used machine learning models within our framework, including k-Nearest-Neighbors, Naïve Bayes, Decision Tree, Random Forest, Support Vector Machine and Logistic Regression. Our framework was conducted on 300 patient samples (161 cases, 60 controls and 79 unconfirmed subjects), randomly selected from 23,281 diabetes related cohort retrieved from a regional distributed EHR repository ranging from 2012 to 2014. RESULTS: We apply top-performing machine learning algorithms on the engineered features. We benchmark and contrast the accuracy, precision, AUC, sensitivity and specificity of classification models against the state-of-the-art expert algorithm for identification of T2DM subjects. Our results indicate that the framework achieved high identification performances (∼0.98 in average AUC), which are much higher than the state-of-the-art algorithm (0.71 in AUC). DISCUSSION: Expert algorithm-based identification of T2DM subjects from EHR is often hampered by the high missing rates due to their conservative selection criteria. Our framework leverages machine learning and feature engineering to loosen such selection criteria to achieve a high identification rate of cases and controls. CONCLUSIONS: Our proposed framework demonstrates a more accurate and efficient approach for identifying subjects with and without T2DM from EHR. Copyright Â
Authors: Wei Xie; Murat Kantarcioglu; William S Bush; Dana Crawford; Joshua C Denny; Raymond Heatherly; Bradley A Malin Journal: Bioinformatics Date: 2014-08-21 Impact factor: 6.937
Authors: Theodora S Brisimi; Tingting Xu; Taiyao Wang; Wuyang Dai; Ioannis Ch Paschalidis Journal: Stat Methods Med Res Date: 2018-11-25 Impact factor: 3.021
Authors: Partho P Sengupta; Sirish Shrestha; Béatrice Berthon; Emmanuel Messas; Erwan Donal; Geoffrey H Tison; James K Min; Jan D'hooge; Jens-Uwe Voigt; Joel Dudley; Johan W Verjans; Khader Shameer; Kipp Johnson; Lasse Lovstakken; Mahdi Tabassian; Marco Piccirilli; Mathieu Pernot; Naveena Yanamala; Nicolas Duchateau; Nobuyuki Kagiyama; Olivier Bernard; Piotr Slomka; Rahul Deo; Rima Arnaout Journal: JACC Cardiovasc Imaging Date: 2020-09
Authors: José S Enriquez; Yan Chu; Shivanand Pudakalakatti; Kang Lin Hsieh; Duncan Salmon; Prasanta Dutta; Niki Zacharias Millward; Eugene Lurie; Steven Millward; Florencia McAllister; Anirban Maitra; Subrata Sen; Ann Killary; Jian Zhang; Xiaoqian Jiang; Pratip K Bhattacharya; Shayan Shams Journal: JMIR Med Inform Date: 2021-06-17