scholarly journals Optimized Prediction Models from Fundus Imaging and Genetics for Late Age-Related Macular Degeneration

2021 ◽  
Vol 11 (11) ◽  
pp. 1127
Author(s):  
Arun Govindaiah ◽  
Abdul Baten ◽  
R. Theodore Smith ◽  
Siva Balasubramanian ◽  
Alauddin Bhuiyan
Keyword(s):  
Machine Learning ◽  
Macular Degeneration ◽  
Retinal Image ◽  
Prediction Models ◽  
Retinal Imaging ◽  
Image Data ◽  
Age Related Macular Degeneration ◽  
Learning Models ◽  
Age Related ◽  
Machine Learning Models

Age-related macular degeneration (AMD) is a leading cause of blindness in the developed world. In this study, we compare the performance of retinal fundus images and genetic-information-based machine learning models for the prediction of late AMD. Using data from the Age-related Eye Disease Study, we built machine learning models with various combinations of genetic, socio-demographic/clinical, and retinal image data to predict late AMD using its severity and category in a single visit, in 2, 5, and 10 years. We compared their performance in sensitivity, specificity, accuracy, and unweighted kappa. The 2-year model based on retinal image and socio-demographic (S-D) parameters achieved a sensitivity of 91.34%, specificity of 84.49% while the same for genetic and S-D-parameters-based model was 79.79% and 66.84%. For the 5-year model, the retinal image and S-D-parameters-based model also outperformed the genetic and S-D parameters-based model. The two 10-year models achieved similar sensitivities of 74.24% and 75.79%, respectively, but the retinal image and S-D-parameters-based model was otherwise superior. The retinal-image-based models were not further improved by adding genetic data. Retinal imaging and S-D data can build an excellent machine learning predictor of developing late AMD over 2–5 years; the retinal imaging model appears to be the preferred prognostic tool for efficient patient management.

scholarly journals GWAS-based Machine Learning for Prediction of Age-Related Macular Degeneration Risk

2019 ◽  
Author(s):  
Qi Yan ◽  
Yale Jiang ◽  
Heng Huang ◽  
Anand Swaroop ◽  
Emily Y. Chew ◽  
...  
Keyword(s):  
Machine Learning ◽  
Macular Degeneration ◽  
Genetic Information ◽  
Prediction Models ◽  
Age Related Macular Degeneration ◽  
Accurate Estimation ◽  
Learning Approaches ◽  
Age Related ◽  
Genome Wide ◽  
Normal Controls

ABSTRACTNumerous independent susceptibility variants have been identified for Age-related macular degeneration (AMD) by genome-wide association studies (GWAS). Since advanced AMD is currently incurable, an accurate prediction of a person’s AMD risk using genetic information is desirable for early diagnosis and clinical management. In this study, genotype data of 32,215 Caucasian individuals with age above 50 years from the International AMD Genomics Consortium in dbGAP were used to establish and validate prediction models for AMD risk using four different machine learning approaches: neural network, lasso regression, support vector machine, and random forest. A standard logistic regression model was also considered using a genetic risk score. To identify feature SNPs for AMD prediction models, we selected the genome-wide significant SNPs from GWAS. All methods achieved good performance for predicting normal controls versus advanced AMD cases (AUC=0.81∼0.82 in a separate test dataset) and normal controls versus any AMD (AUC=0.78∼0.79). By applying the state-of-art machine learning approaches on the large AMD GWAS data, the predictive models we established can provide an accurate estimation of an individual’s AMD risk profile across the person’s lifespan based on a comprehensive genetic information.

scholarly journals Age-Related Macular Degeneration, Cardiovascular Disease and Stroke

2021 ◽  
Author(s):  
Gerardo Ledesma-Gil ◽  
Oscar Otero-Marquez ◽  
Sharmina Alauddin ◽  
Yuehong Tong ◽  
Wei Wei ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Risk ◽  
Macular Degeneration ◽  
Severe Aortic Stenosis ◽  
Artery Bypass ◽  
Retinal Imaging ◽  
Vascular Diseases ◽  
Age Related Macular Degeneration ◽  
Age Related ◽  
Soft Drusen

Importance: High-risk vascular diseases (HRVs) may remain undetected until catastrophe ensues. Detection from non-invasive retinal imaging would be highly significant. Objective: To demonstrate that certain lesions of Age-Related Macular Degeneration (AMD) found on retinal imaging correlate with co-existing HRVs. Design: Cross-sectional cohort study. Two years. Retinal image graders blinded to HRV status. Setting: 2 retina referral clinics. Participants: 151 consecutive AMD patients, ages 50-90, 97 females, 54 males, with lesions of soft drusen and/or subretinal drusenoid deposits (SDD). 12 others approached, 10 refused, 2 excluded. Methods: Patients were classified by retinal imaging into SDD (SDD present, +/- drusen) or nonSDD (soft drusen only), and by history into HRV (cardiac pump defect (myocardial infarction (MI), coronary artery bypass grafting (CABG), congestive heart failure (CHF)), valve defect, and carotid stroke) or nonHRV, with serum risk factors and medical histories. Main Outcome Measures: Correlations of HRV with SDD and other covariates (Univariate chi-square and multivariate regression). Performance of Machine Learning predicting HRV. Results: 75 SDD subjects; 76 nonSDD subjects; HRV prevalence 19.2% (29/151). 1. High density lipoprotein (HDL) < 62 mg/Dl was found in 24/29 HRV, 42/122 nonHRV, OR 12.40, 95% Confidence Interval (CI) 5.125-30.014; p= 0.0002. 2. 15 Pump defects, 14/15 SDD, 8 Valve defects, 6/8 SDD (4 severe aortic stenosis), 6 carotid strokes, 5/6 SDD. Total HRVs 29, 25/29 SDD, OR 9.0, 95% CI 2.95-27.46; p= 0.000012. 3. Adjusted multivariate correlations. HRV with SDD (p= 0.000333). SDD and HDL < 62 with HRV (p= 0.000098 and 0.021). 4. Machine Learning prediction of HRVs from SDD status and HDL level: specificity 87.4%, sensitivity 77.4%, accuracy 84.9%; 95% CIs(%) 79.0-93.3, 58.0-90.4, 77.5-90.7, respectively. Conclusions and Relevance: High-risk vascular diseases were accurately identified in a cohort of AMD patients from the presence of characteristic deposits (SDDs) on imaging and HDL levels. The SDDs are directly consequent to inadequate ocular perfusion resulting from the systemic vasculopathies. Further validation in larger cohorts of both vasculopathic and AMD subjects could bring this system into widespread medical practice, to reduce mortality and morbidity from vascular disease, particularly in women, where undiagnosed cardiac disease remains a serious issue.

Machine Learning-based Prediction Models for Diagnosis and Prognosis in Inflammatory Bowel Diseases: A Systematic Review

2021 ◽  
Author(s):  
Nghia H Nguyen ◽  
Dominic Picetti ◽  
Parambir S Dulai ◽  
Vipul Jairath ◽  
William J Sandborn ◽  
...  
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Risk Prediction ◽  
Statistical Models ◽  
Prediction Models ◽  
Risk Of Bias ◽  
Learning Models ◽  
Bowel Diseases ◽  
Inflammatory Bowel ◽  
Machine Learning Models

Abstract Background and Aims There is increasing interest in machine learning-based prediction models in inflammatory bowel diseases (IBD). We synthesized and critically appraised studies comparing machine learning vs. traditional statistical models, using routinely available clinical data for risk prediction in IBD. Methods Through a systematic review till January 1, 2021, we identified cohort studies that derived and/or validated machine learning models, based on routinely collected clinical data in patients with IBD, to predict the risk of harboring or developing adverse clinical outcomes, and reported its predictive performance against a traditional statistical model for the same outcome. We appraised the risk of bias in these studies using the Prediction model Risk of Bias ASsessment (PROBAST) tool. Results We included 13 studies on machine learning-based prediction models in IBD encompassing themes of predicting treatment response to biologics and thiopurines, predicting longitudinal disease activity and complications and outcomes in patients with acute severe ulcerative colitis. The most common machine learnings models used were tree-based algorithms, which are classification approaches achieved through supervised learning. Machine learning models outperformed traditional statistical models in risk prediction. However, most models were at high risk of bias, and only one was externally validated. Conclusions Machine learning-based prediction models based on routinely collected data generally perform better than traditional statistical models in risk prediction in IBD, though frequently have high risk of bias. Future studies examining these approaches are warranted, with special focus on external validation and clinical applicability.

Performance Metrics for the Comparative Analysis of Clinical Risk Prediction Models Employing Machine Learning

2021 ◽  
Author(s):  
Chenxi Huang ◽  
Shu-Xia Li ◽  
César Caraballo ◽  
Frederick A. Masoudi ◽  
John S. Rumsfeld ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Prediction ◽  
Health Care Professionals ◽  
Clinical Decision Making ◽  
Performance Metrics ◽  
Prediction Models ◽  
Learning Models ◽  
Risk Prediction Models ◽  
Clinical Risk ◽  
Machine Learning Models

Background: New methods such as machine learning techniques have been increasingly used to enhance the performance of risk predictions for clinical decision-making. However, commonly reported performance metrics may not be sufficient to capture the advantages of these newly proposed models for their adoption by health care professionals to improve care. Machine learning models often improve risk estimation for certain subpopulations that may be missed by these metrics. Methods and Results: This article addresses the limitations of commonly reported metrics for performance comparison and proposes additional metrics. Our discussions cover metrics related to overall performance, discrimination, calibration, resolution, reclassification, and model implementation. Models for predicting acute kidney injury after percutaneous coronary intervention are used to illustrate the use of these metrics. Conclusions: We demonstrate that commonly reported metrics may not have sufficient sensitivity to identify improvement of machine learning models and propose the use of a comprehensive list of performance metrics for reporting and comparing clinical risk prediction models.

Assessment of CFH and HTRA1 polymorphisms in age-related macular degeneration using classic and machine-learning approaches

2020 ◽  
Vol 41 (6) ◽  
pp. 539-547
Author(s):  
Antonieta Martínez-Velasco ◽  
Andric C. Perez-Ortiz ◽  
Bani Antonio-Aguirre ◽  
Lourdes Martínez-Villaseñor ◽  
Esmeralda Lira-Romero ◽  
...  
Keyword(s):  
Machine Learning ◽  
Macular Degeneration ◽  
Age Related Macular Degeneration ◽  
Learning Approaches ◽  
Age Related

scholarly journals The Relevance of Cataract as a Risk Factor for Age-Related Macular Degeneration: A Machine Learning Approach

2019 ◽  
Vol 9 (24) ◽  
pp. 5550
Author(s):  
Antonieta Martínez-Velasco ◽  
Lourdes Martínez-Villaseñor ◽  
Luis Miralles-Pechuán ◽  
Andric C. Perez-Ortiz ◽  
Juan C. Zenteno ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factor ◽  
Macular Degeneration ◽  
Significant Risk ◽  
Age Related Macular Degeneration ◽  
Supervised Machine Learning ◽  
Current Debate ◽  
Learning Approach ◽  
Age Related ◽  
Machine Learning Approach

Age-related macular degeneration (AMD) is the leading cause of visual dysfunction and irreversible blindness in developed countries and a rising cause in underdeveloped countries. There is a current debate on whether or not cataracts are significant risk factors for AMD development. In particular, research regarding this association is so far inconclusive. For this reason, we aimed to employ here a machine-learning approach to analyze the relevance and importance of cataracts as a risk factor for AMD in a large cohort of Hispanics from Mexico. We conducted a nested case control study of 119 cataract cases and 137 healthy unmatched controls focusing on clinical data from electronic medical records. Additionally, we studied two single nucleotide polymorphisms in the CFH gene previously associated with the disease in various populations as positive control for our method. We next determined the most relevant variables and found the bivariate association between cataracts and AMD. Later, we used supervised machine-learning methods to replicate these findings without bias. To improve the interpretability, we detected the five most relevant features and displayed them using a bar graph and a rule-based tree. Our findings suggest that bilateral cataracts are not a significant risk factor for AMD development among Hispanics from Mexico.

scholarly journals Development of Combined Heavy Rain Damage Prediction Models with Machine Learning

Water ◽  
2019 ◽  
Vol 11 (12) ◽  
pp. 2516 ◽  
Author(s):  
Changhyun Choi ◽  
Jeonghwan Kim ◽  
Jungwook Kim ◽  
Hung Soo Kim
Keyword(s):  
Machine Learning ◽  
Linear Regression ◽  
Prediction Model ◽  
Prediction Models ◽  
Predictive Performance ◽  
Heavy Rain ◽  
Learning Models ◽  
Damage Prediction ◽  
Natural Disaster Management ◽  
Machine Learning Models

Adequate forecasting and preparation for heavy rain can minimize life and property damage. Some studies have been conducted on the heavy rain damage prediction model (HDPM), however, most of their models are limited to the linear regression model that simply explains the linear relation between rainfall data and damage. This study develops the combined heavy rain damage prediction model (CHDPM) where the residual prediction model (RPM) is added to the HDPM. The predictive performance of the CHDPM is analyzed to be 4–14% higher than that of HDPM. Through this, we confirmed that the predictive performance of the model is improved by combining the RPM of the machine learning models to complement the linearity of the HDPM. The results of this study can be used as basic data beneficial for natural disaster management.

Sign in / Sign up

Export Citation Format

Share Document