Sally L Baxter1, Bharanidharan Radha Saseendrakumar2, Paulina Paul3, Jihoon Kim3, Luca Bonomi3, Tsung-Ting Kuo3, Roxana Loperena4, Francis Ratsimbazafy4, Eric Boerwinkle5, Mine Cicek6, Cheryl R Clark7, Elizabeth Cohn8, Kelly Gebo9, Kelsey Mayo4, Stephen Mockrin10, Sheri D Schully11, Andrea Ramirez12, Lucila Ohno-Machado13. 1. From the Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, (S.L.B., B.R.S.), La Jolla, California; UCSD Health Department of Biomedical Informatics, University of California San Diego, (S.L.B., B.R.S., P.P., J.K., L.B., T.-T.K., L.O.-M.), La Jolla, California. Electronic address: s1baxter@health.ucsd.edu. 2. From the Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, (S.L.B., B.R.S.), La Jolla, California; UCSD Health Department of Biomedical Informatics, University of California San Diego, (S.L.B., B.R.S., P.P., J.K., L.B., T.-T.K., L.O.-M.), La Jolla, California. 3. UCSD Health Department of Biomedical Informatics, University of California San Diego, (S.L.B., B.R.S., P.P., J.K., L.B., T.-T.K., L.O.-M.), La Jolla, California. 4. Vanderbilt Institute for Clinical and Translational Research, Vanderbilt University Medical Center, Nashville, Tennessee (R.L., F.R.). 5. School of Public Health, The University of Texas Health Science Center at Houston, Houston, Texas (E.B.). 6. Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota (M.C.). 7. Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts (C.R.C.). 8. Hunter-Bellevue School of Nursing, Hunter College City University of New York, New York, New York (E.C.). 9. Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, Maryland. 10. Life Sciences Division, Leidos, Inc, Frederick, (S.M.), Maryland. 11. All of Us Research Program, National Institutes of Health, Bethesda (K.M., S.S.), Bethesda, Maryland. 12. Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee (A.R.). 13. UCSD Health Department of Biomedical Informatics, University of California San Diego, (S.L.B., B.R.S., P.P., J.K., L.B., T.-T.K., L.O.-M.), La Jolla, California; Division of Health Services Research and Development, Veterans Affairs San Diego Healthcare System, La Jolla, California (L.O.-M.), USA.
Abstract
PURPOSE: To (1) use All of Us (AoU) data to validate a previously published single-center model predicting the need for surgery among individuals with glaucoma, (2) train new models using AoU data, and (3) share insights regarding this novel data source for ophthalmic research. DESIGN: Development and evaluation of machine learning models. METHODS: Electronic health record data were extracted from AoU for 1,231 adults diagnosed with primary open-angle glaucoma. The single-center model was applied to AoU data for external validation. AoU data were then used to train new models for predicting the need for glaucoma surgery using multivariable logistic regression, artificial neural networks, and random forests. Five-fold cross-validation was performed. Model performance was evaluated based on area under the receiver operating characteristic curve (AUC), accuracy, precision, and recall. RESULTS: The mean (standard deviation) age of the AoU cohort was 69.1 (10.5) years, with 57.3% women and 33.5% black, significantly exceeding representation in the single-center cohort (P = .04 and P < .001, respectively). Of 1,231 participants, 286 (23.2%) needed glaucoma surgery. When applying the single-center model to AoU data, accuracy was 0.69 and AUC was only 0.49. Using AoU data to train new models resulted in superior performance: AUCs ranged from 0.80 (logistic regression) to 0.99 (random forests). CONCLUSIONS: Models trained with national AoU data achieved superior performance compared with using single-center data. Although AoU does not currently include ophthalmic imaging, it offers several strengths over similar big-data sources such as claims data. AoU is a promising new data source for ophthalmic research. Published by Elsevier Inc.
PURPOSE: To (1) use All of Us (AoU) data to validate a previously published single-center model predicting the need for surgery among individuals with glaucoma, (2) train new models using AoU data, and (3) share insights regarding this novel data source for ophthalmic research. DESIGN: Development and evaluation of machine learning models. METHODS: Electronic health record data were extracted from AoU for 1,231 adults diagnosed with primary open-angle glaucoma. The single-center model was applied to AoU data for external validation. AoU data were then used to train new models for predicting the need for glaucoma surgery using multivariable logistic regression, artificial neural networks, and random forests. Five-fold cross-validation was performed. Model performance was evaluated based on area under the receiver operating characteristic curve (AUC), accuracy, precision, and recall. RESULTS: The mean (standard deviation) age of the AoU cohort was 69.1 (10.5) years, with 57.3% women and 33.5% black, significantly exceeding representation in the single-center cohort (P = .04 and P < .001, respectively). Of 1,231 participants, 286 (23.2%) needed glaucoma surgery. When applying the single-center model to AoU data, accuracy was 0.69 and AUC was only 0.49. Using AoU data to train new models resulted in superior performance: AUCs ranged from 0.80 (logistic regression) to 0.99 (random forests). CONCLUSIONS: Models trained with national AoU data achieved superior performance compared with using single-center data. Although AoU does not currently include ophthalmic imaging, it offers several strengths over similar big-data sources such as claims data. AoU is a promising new data source for ophthalmic research. Published by Elsevier Inc.
Authors: Sarah Read-Brown; Michelle R Hribar; Leah G Reznick; Lorinna H Lombardi; Mansi Parikh; Winston D Chamberlain; Steven T Bailey; Jessica B Wallace; Thomas R Yackel; Michael F Chiang Journal: JAMA Ophthalmol Date: 2017-11-01 Impact factor: 7.389
Authors: Hsien-Chang Lin; Joshua D Stein; Bin Nan; David Childers; Paula Anne Newman-Casey; Debra A Thompson; Julia E Richards Journal: JAMA Ophthalmol Date: 2015-08 Impact factor: 7.389
Authors: Jackson T Wright; Jeff D Williamson; Paul K Whelton; Joni K Snyder; Kaycee M Sink; Michael V Rocco; David M Reboussin; Mahboob Rahman; Suzanne Oparil; Cora E Lewis; Paul L Kimmel; Karen C Johnson; David C Goff; Lawrence J Fine; Jeffrey A Cutler; William C Cushman; Alfred K Cheung; Walter T Ambrosius Journal: N Engl J Med Date: 2015-11-09 Impact factor: 91.245
Authors: Cari L Nealon; Christopher W Halladay; Tyler G Kinzy; Piana Simpson; Rachael L Canania; Scott A Anthony; David P Roncone; Lea R Sawicki Rogers; Jenna N Leber; Jacquelyn M Dougherty; Jack M Sullivan; Wen-Chih Wu; Paul B Greenberg; Sudha K Iyengar; Dana C Crawford; Neal S Peachey; Jessica N Cooke Bailey Journal: Ophthalmic Epidemiol Date: 2021-11-25
Authors: Dillon G Pruett; Douglas M Shaw; Hung-Hsin Chen; Lauren E Petty; Hannah G Polikowsky; Shelly Jo Kraft; Robin M Jones; Jennifer E Below Journal: J Fluency Disord Date: 2021-04-15 Impact factor: 2.538