Literature DB >> 31323204

Machine Learning-Based Predictive Modeling of Surgical Intervention in Glaucoma Using Systemic Data From Electronic Health Records.

Sally L Baxter1, Charles Marks2, Tsung-Ting Kuo3, Lucila Ohno-Machado4, Robert N Weinreb5.   

Abstract

PURPOSE: To predict the need for surgical intervention in patients with primary open-angle glaucoma (POAG) using systemic data in electronic health records (EHRs).
DESIGN: Development and evaluation of machine learning models.
METHODS: Structured EHR data of 385 POAG patients from a single academic institution were incorporated into models using multivariable logistic regression, random forests, and artificial neural networks. Leave-one-out cross-validation was performed. Mean area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, and Youden index were calculated for each model to evaluate performance. Systemic variables driving predictions were identified and interpreted.
RESULTS: Multivariable logistic regression was most effective at discriminating patients with progressive disease requiring surgery, with an AUC of 0.67. Higher mean systolic blood pressure was associated with significantly increased odds of needing glaucoma surgery (odds ratio [OR] = 1.09, P < .001). Ophthalmic medications (OR = 0.28, P < .001), non-opioid analgesic medications (OR = 0.21, P = .002), anti-hyperlipidemic medications (OR = 0.39, P = .004), macrolide antibiotics (OR = 0.40, P = .03), and calcium blockers (OR = 0.43, P = .03) were associated with decreased odds of needing glaucoma surgery.
CONCLUSIONS: Existing systemic data in the EHR has some predictive value in identifying POAG patients at risk of progression to surgical intervention, even in the absence of eye-specific data. Blood pressure-related metrics and certain medication classes emerged as predictors of glaucoma progression. This approach provides an opportunity for future development of automated risk prediction within the EHR based on systemic data to assist with clinical decision-making. Published by Elsevier Inc.

Entities:  

Mesh:

Year:  2019        PMID: 31323204      PMCID: PMC6888922          DOI: 10.1016/j.ajo.2019.07.005

Source DB:  PubMed          Journal:  Am J Ophthalmol        ISSN: 0002-9394            Impact factor:   5.258


  44 in total

1.  A marked fall in nocturnal blood pressure is associated with the stage of primary open-angle glaucoma in patients with arterial hypertension.

Authors:  Beata Krasińska; Małgorzata Karolczak-Kulesza; Zbigniew Krasiński; Katarzyna Pawlaczyk-Gabriel; Arkadiusz Niklas; Jerzy Głuszek; Andrzej Tykarski
Journal:  Blood Press       Date:  2010-12-07       Impact factor: 2.835

2.  Association of Statin Use and High Serum Cholesterol Levels With Risk of Primary Open-Angle Glaucoma.

Authors:  Jae H Kang; Tahani Boumenna; Joshua D Stein; Anthony Khawaja; Bernard A Rosner; Janey L Wiggs; Louis R Pasquale
Journal:  JAMA Ophthalmol       Date:  2019-07-01       Impact factor: 7.389

3.  Factors associated with optic disc hemorrhages in glaucoma.

Authors:  Adael S Soares; Paul H Artes; Pantelis Andreou; Raymond P Leblanc; Balwantray C Chauhan; Marcelo T Nicolela
Journal:  Ophthalmology       Date:  2004-09       Impact factor: 12.079

4.  Comparison of glaucomatous progression between untreated patients with normal-tension glaucoma and patients with therapeutically reduced intraocular pressures. Collaborative Normal-Tension Glaucoma Study Group.

Authors: 
Journal:  Am J Ophthalmol       Date:  1998-10       Impact factor: 5.258

5.  Open-angle glaucoma and systemic hypertension: the blue mountains eye study.

Authors:  Paul Mitchell; Anne J Lee; Elena Rochtchina; Jie Jin Wang
Journal:  J Glaucoma       Date:  2004-08       Impact factor: 2.503

6.  Therapeutic potentials of aspirin in glaucomatous optic neuropathy.

Authors:  Abbas Attarzadeh; Hamid Hosseini; Sarah Nowroozizadeh
Journal:  Med Hypotheses       Date:  2006-03-09       Impact factor: 1.538

Review 7.  Disc hemorrhages in the glaucomas.

Authors:  S M Drance
Journal:  Surv Ophthalmol       Date:  1989 Mar-Apr       Impact factor: 6.048

8.  Limitations of Bayesian Leave-One-Out Cross-Validation for Model Selection.

Authors:  Quentin F Gronau; Eric-Jan Wagenmakers
Journal:  Comput Brain Behav       Date:  2018-09-27

Review 9.  21st century glaucoma care.

Authors:  Harry A Quigley
Journal:  Eye (Lond)       Date:  2018-10-10       Impact factor: 3.775

10.  The revival of the Gini importance?

Authors:  Stefano Nembrini; Inke R König; Marvin N Wright
Journal:  Bioinformatics       Date:  2018-11-01       Impact factor: 6.937

View more
  10 in total

1.  Predictive Modeling of Long-Term Glaucoma Progression Based on Initial Ophthalmic Data and Optic Nerve Head Characteristics.

Authors:  Eun Ji Lee; Tae-Woo Kim; Jeong-Ah Kim; Seung Hyen Lee; Hyunjoong Kim
Journal:  Transl Vis Sci Technol       Date:  2022-10-03       Impact factor: 3.048

2.  Evaluating machine learning classifiers for glaucoma referral decision support in primary care settings.

Authors:  Omkar G Kaskar; Elaine Wells-Gray; David Fleischman; Landon Grace
Journal:  Sci Rep       Date:  2022-05-20       Impact factor: 4.996

3.  Special Commentary: Using Clinical Decision Support Systems to Bring Predictive Models to the Glaucoma Clinic.

Authors:  Brian C Stagg; Joshua D Stein; Felipe A Medeiros; Barbara Wirostko; Alan Crandall; M Elizabeth Hartnett; Mollie Cummins; Alan Morris; Rachel Hess; Kensaku Kawamoto
Journal:  Ophthalmol Glaucoma       Date:  2020-08-15

4.  Development and evaluation of novel ophthalmology domain-specific neural word embeddings to predict visual prognosis.

Authors:  Sophia Wang; Benjamin Tseng; Tina Hernandez-Boussard
Journal:  Int J Med Inform       Date:  2021-04-16       Impact factor: 4.730

5.  Predictive Analytics for Glaucoma Using Data From the All of Us Research Program.

Authors:  Sally L Baxter; Bharanidharan Radha Saseendrakumar; Paulina Paul; Jihoon Kim; Luca Bonomi; Tsung-Ting Kuo; Roxana Loperena; Francis Ratsimbazafy; Eric Boerwinkle; Mine Cicek; Cheryl R Clark; Elizabeth Cohn; Kelly Gebo; Kelsey Mayo; Stephen Mockrin; Sheri D Schully; Andrea Ramirez; Lucila Ohno-Machado
Journal:  Am J Ophthalmol       Date:  2021-01-23       Impact factor: 5.488

Review 6.  Applications of Artificial Intelligence to Electronic Health Record Data in Ophthalmology.

Authors:  Wei-Chun Lin; Jimmy S Chen; Michael F Chiang; Michelle R Hribar
Journal:  Transl Vis Sci Technol       Date:  2020-02-27       Impact factor: 3.283

7.  Systematic literature review of machine learning methods used in the analysis of real-world data for patient-provider decision making.

Authors:  Alan Brnabic; Lisa M Hess
Journal:  BMC Med Inform Decis Mak       Date:  2021-02-15       Impact factor: 2.796

8.  Predicting Glaucoma Progression Requiring Surgery Using Clinical Free-Text Notes and Transfer Learning With Transformers.

Authors:  Wendeng Hu; Sophia Y Wang
Journal:  Transl Vis Sci Technol       Date:  2022-03-02       Impact factor: 3.283

9.  Deep Learning Approaches for Predicting Glaucoma Progression Using Electronic Health Records and Natural Language Processing.

Authors:  Sophia Y Wang; Benjamin Tseng; Tina Hernandez-Boussard
Journal:  Ophthalmol Sci       Date:  2022-02-12

10.  Development of the Integrated Glaucoma Risk Index.

Authors:  Sejong Oh; Kyong Jin Cho; Seong-Jae Kim
Journal:  Diagnostics (Basel)       Date:  2022-03-17
  10 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.