Karandeep Singh1,2, Rebecca A Betensky3, Adam Wright4,5, Gary C Curhan5,6,7, David W Bates4,5,8, Sushrut S Waikar5,6. 1. Division of Learning and Knowledge Systems, Department of Learning Health Sciences and kdpsingh@umich.edu. 2. Division of Nephrology, Department of Internal Medicine, University of Michigan Medical School, Ann Arbor, Michigan; Departments of. 3. Biostatistics. 4. Division of General Internal Medicine, Department of Medicine and. 5. Department of Medicine, Harvard Medical School, Boston, Massachusetts. 6. Division of Renal Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts; and. 7. Epidemiology, and. 8. Health Policy and Management, Harvard T.H. Chan School of Public Health, Boston, Massachusetts.
Abstract
BACKGROUND AND OBJECTIVES: Identifying predictors of kidney disease progression is critical toward the development of strategies to prevent kidney failure. Clinical notes provide a unique opportunity for big data approaches to identify novel risk factors for disease. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: We used natural language processing tools to extract concepts from the preceding year's clinical notes among patients newly referred to a tertiary care center's outpatient nephrology clinics and retrospectively evaluated these concepts as predictors for the subsequent development of ESRD using proportional subdistribution hazards (competing risk) regression. The primary outcome was time to ESRD, accounting for a competing risk of death. We identified predictors from univariate and multivariate (adjusting for Tangri linear predictor) models using a 5% threshold for false discovery rate (q value <0.05). We included all patients seen by an adult outpatient nephrologist between January 1, 2004 and June 18, 2014 and excluded patients seen only by transplant nephrology, with preexisting ESRD, with fewer than five clinical notes, with no follow-up, or with no baseline creatinine values. RESULTS: Among the 4013 patients selected in the final study cohort, we identified 960 concepts in the unadjusted analysis and 885 concepts in the adjusted analysis. Novel predictors identified included high-dose ascorbic acid (adjusted hazard ratio, 5.48; 95% confidence interval, 2.80 to 10.70; q<0.001) and fast food (adjusted hazard ratio, 4.34; 95% confidence interval, 2.55 to 7.40; q<0.001). CONCLUSIONS: Novel predictors of human disease may be identified using an unbiased approach to analyze text from the electronic health record.
BACKGROUND AND OBJECTIVES: Identifying predictors of kidney disease progression is critical toward the development of strategies to prevent kidney failure. Clinical notes provide a unique opportunity for big data approaches to identify novel risk factors for disease. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: We used natural language processing tools to extract concepts from the preceding year's clinical notes among patients newly referred to a tertiary care center's outpatient nephrology clinics and retrospectively evaluated these concepts as predictors for the subsequent development of ESRD using proportional subdistribution hazards (competing risk) regression. The primary outcome was time to ESRD, accounting for a competing risk of death. We identified predictors from univariate and multivariate (adjusting for Tangri linear predictor) models using a 5% threshold for false discovery rate (q value <0.05). We included all patients seen by an adult outpatient nephrologist between January 1, 2004 and June 18, 2014 and excluded patients seen only by transplant nephrology, with preexisting ESRD, with fewer than five clinical notes, with no follow-up, or with no baseline creatinine values. RESULTS: Among the 4013 patients selected in the final study cohort, we identified 960 concepts in the unadjusted analysis and 885 concepts in the adjusted analysis. Novel predictors identified included high-dose ascorbic acid (adjusted hazard ratio, 5.48; 95% confidence interval, 2.80 to 10.70; q<0.001) and fast food (adjusted hazard ratio, 4.34; 95% confidence interval, 2.55 to 7.40; q<0.001). CONCLUSIONS: Novel predictors of human disease may be identified using an unbiased approach to analyze text from the electronic health record.
Authors: H M Perry; J P Miller; J R Fornoff; J D Baty; M P Sambhi; G Rutan; D W Moskowitz; S E Carmody Journal: Hypertension Date: 1995-04 Impact factor: 10.190
Authors: Lili Chan; Kelly Beers; Amy A Yau; Kinsuk Chauhan; Áine Duffy; Kumardeep Chaudhary; Neha Debnath; Aparna Saha; Pattharawin Pattharanitima; Judy Cho; Peter Kotanko; Alex Federman; Steven G Coca; Tielman Van Vleck; Girish N Nadkarni Journal: Kidney Int Date: 2019-11-09 Impact factor: 10.612
Authors: V G Vinod Vydiswaran; Daniel M Romero; Xinyan Zhao; Deahan Yu; Iris Gomez-Lopez; Jin Xiu Lu; Bradley E Iott; Ana Baylin; Erica C Jansen; Philippa Clarke; Veronica J Berrocal; Robert Goodspeed; Tiffany C Veinot Journal: J Am Med Inform Assoc Date: 2020-02-01 Impact factor: 4.497
Authors: Juan Zhao; Monika E Grabowska; Vern Eric Kerchberger; Joshua C Smith; H Nur Eken; QiPing Feng; Josh F Peterson; S Trent Rosenbloom; Kevin B Johnson; Wei-Qi Wei Journal: J Biomed Inform Date: 2021-03-25 Impact factor: 8.000