diabetestalk.net

Diabetes Risk Prediction Using Machine Learning Prospect And Challenges

Risk Prediction Using Genome-wide Association Studies On Type 2 Diabetes

Risk Prediction Using Genome-wide Association Studies On Type 2 Diabetes

Risk Prediction Using Genome-Wide Association Studies on Type 2 Diabetes Choi, Bae, and Park: Risk Prediction Using Genome-Wide Association Studies on Type 2 Diabetes Special Issue: Recent Statistical Challenges in High Dimensional Omics Data Genomics & Informatics 2016; 14(4): 138-148. 1Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul 08826, Korea. 2Department of Statistics, Seoul National University, Seoul 08826, Korea. Corresponding author: Tel: +82-2-880-8924, Fax: +82-2-883-6144, [email protected] Received November 10, 2016 Revised December 05, 2016 Accepted December 05, 2016 Copyright 2016 by the Korea Genome Organization It is identical to the Creative Commons Attribution Non-Commercial License ( ). The success of genome-wide association studies (GWASs) has enabled us to improve risk assessment and provide novel genetic variants for diagnosis, prevention, and treatment. However, most variants discovered by GWASs have been reported to have very small effect sizes on complex human diseases, which has been a big hurdle in building risk prediction models. Recently, many statistical approaches based on penalized regression have been developed to solve the large p and small n problem. In this report, we evaluated the performance of several statistical methods for predicting a binary trait: stepwise logistic regression (SLR), least absolute shrinkage and selection operator (LASSO), and Elastic-Net (EN). We first built a prediction model by combining variable selection and prediction methods for type 2 diabetes using Affymetrix Genome-Wide Human SNP Array 5.0 from the Korean Association Resource project. We assessed the risk prediction performance using area under the receiver operating characteristic curve (AUC) for the internal and ex Continue reading >>

Predictive Analytics

Predictive Analytics

This article needs additional citations for verification . Please help improve this article by adding citations to reliable sources . Unsourced material may be challenged and removed. ( Learn how and when to remove this template message ) Predictive analytics encompasses a variety of statistical techniques from predictive modelling , machine learning , and data mining that analyze current and historical facts to make predictions about future or otherwise unknown events. [1] [2] In business, predictive models exploit patterns found in historical and transactional data to identify risks and opportunities. Models capture relationships among many factors to allow assessment of risk or potential associated with a particular set of conditions, guiding decision making for candidate transactions. [3] The defining functional effect of these technical approaches is that predictive analytics provides a predictive score (probability) for each individual (customer, employee, healthcare patient, product SKU, vehicle, component, machine, or other organizational unit) in order to determine, inform, or influence organizational processes that pertain across large numbers of individuals, such as in marketing, credit risk assessment, fraud detection, manufacturing, healthcare, and government operations including law enforcement. Predictive analytics is used in actuarial science , [4] marketing , [5] financial services , [6] insurance , telecommunications , [7] retail , [8] travel , [9] mobility , [10] healthcare , [11] child protection , [12] [13] pharmaceuticals , [14] capacity planning [ citation needed ] and other fields. One of the best-known applications is credit scoring , [1] which is used throughout financial services . Scoring models process a customer's credit history , loan app Continue reading >>

2018 Ai Predictions | Thomson Reuters

2018 Ai Predictions | Thomson Reuters

The below excerpt of a sonnet titled Gate was written by a machine. And be very careful crossing the streets. How fair an entrance breaks the way to love! Just then a light flashed from the cliff above. The fields near the house were invisible. From the big apple tree down near the pond. Specifically, an award-winning AI system , built by Thomson Reuters technologists in our Center for AI and Cognitive Computing . While public interest and media narratives around artificial intelligence (AI) have ebbed and flowed over the past couple decades, the conversation has been heating back up in recent years, due to advancing consumer technology and the need to process and understand ever increasing amounts of data. That buzz will likely continue into 2018 and beyond as new products and services built on AI seep into many aspects of our lives be it in the home, on the commute, in the workplace, or elsewhere. At times an oversaturated topic, the term AI has become shorthand for several specific technologies including cognitive computing, machine learning, natural language processing, and data analytics, among others. To move beyond the hype and look to the immediate future, we asked 10 Thomson Reuters technologists and innovators to make their AI predictions for the year ahead. AI brings a new set of rules to knowledge work In the information industry and at Thomson Reuters, AI and machine learning are already driving innovation and transformation. They are embedded in how we sift through large volumes of data and content and how we enhance, organize, connect, and deliver content and information. They are the engines underlying many of our products and services. Vice President, R&D and Head of the Center for AI and Cognitive Computing When things go digital, they start following Continue reading >>

Machine Intelligence

Machine Intelligence

Research at Google is at the forefront of innovation in Machine Intelligence, with active research exploring virtually all aspects of machine learning, including deep learning and more classical algorithms. Exploring theory as well as application, much of our work on language, speech, translation, visual processing, ranking and prediction relies on Machine Intelligence. In all of those tasks and many others, we gather large volumes of direct or indirect evidence of relationships of interest, applying learning algorithms to understand and generalize. Machine Intelligence at Google raises deep scientific and engineering challenges, allowing us to contribute to the broader academic research community through technical talks and publications in major conferences and journals. Contrary to much of current theory and practice, the statistics of the data we observe shifts rapidly, the features of interest change as well, and the volume of data often requires enormous computation capacity. When learning systems are placed at the core of interactive services in a fast changing and sometimes adversarial environment, combinations of techniques including deep learning and statistical models need to be combined with ideas from control and game theory.

Genetic Screening For The Risk Of Type 2 Diabetes

Genetic Screening For The Risk Of Type 2 Diabetes

The prevalence and incidence of type 2 diabetes, representing >90% of all cases of diabetes, are increasing rapidly throughout the world. The International Diabetes Federation has estimated that the number of people with diabetes is expected to rise from 366 million in 2011 to 552 million by 2030 if no urgent action is taken. Furthermore, as many as 183 million people are unaware that they have diabetes (www.idf.org). Therefore, the identification of individuals at high risk of developing diabetes is of great importance and interest for investigators and health care providers. Type 2 diabetes is a complex disorder resulting from an interaction between genes and environment. Several risk factors for type 2 diabetes have been identified, including age, sex, obesity and central obesity, low physical activity, smoking, diet including low amount of fiber and high amount of saturated fat, ethnicity, family history, history of gestational diabetes mellitus, history of the nondiabetic elevation of fasting or 2-h glucose, elevated blood pressure, dyslipidemia, and different drug treatments (diuretics, unselected β-blockers, etc.) (1–3). There is also ample evidence that type 2 diabetes has a strong genetic basis. The concordance of type 2 diabetes in monozygotic twins is ~70% compared with 20–30% in dizygotic twins (4). The lifetime risk of developing the disease is ~40% in offspring of one parent with type 2 diabetes, greater if the mother is affected (5), and approaching 70% if both parents have diabetes. In prospective studies, we have demonstrated that first-degree family history is associated with twofold increased risk of future type 2 diabetes (1,6). The challenge has been to find genetic markers that explain the excess risk associated with family history of diabetes Continue reading >>

Deep Patient: An Unsupervised Representation To Predict The Future Of Patients From The Electronic Health Records

Deep Patient: An Unsupervised Representation To Predict The Future Of Patients From The Electronic Health Records

Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records Scientific Reports volume 6, Articlenumber:26094 (2016) Secondary use of electronic health records (EHRs) promises to advance clinical research and better inform clinical decision making. Challenges in summarizing and representing patient data prevent widespread practice of predictive modeling using EHRs. Here we present a novel unsupervised deep feature learning method to derive a general-purpose patient representation from EHR data that facilitates clinical predictive modeling. In particular, a three-layer stack of denoising autoencoders was used to capture hierarchical regularities and dependencies in the aggregated EHRs of about 700,000 patients from the Mount Sinai data warehouse. The result is a representation we name deep patient. We evaluated this representation as broadly predictive of health states by assessing the probability of patients to develop various diseases. We performed evaluation using 76,214 test patients comprising 78 diseases from diverse clinical domains and temporal windows. Our results significantly outperformed those achieved using representations based on raw EHR data and alternative feature learning strategies. Prediction performance for severe diabetes, schizophrenia, and various cancers were among the top performing. These findings indicate that deep learning applied to EHRs can derive patient representations that offer improved clinical predictions, and could provide a machine learning framework for augmenting clinical decision systems. A primary goal of precision medicine is to develop quantitative models for patients that can be used to predict health status, as well as to help prevent disease or disability. In this contex Continue reading >>

Predicting Two-year Survival Versus Non-survival After First Myocardial Infarction Using Machine Learning And Swedish National Register Data

Predicting Two-year Survival Versus Non-survival After First Myocardial Infarction Using Machine Learning And Swedish National Register Data

BMC Medical Informatics and Decision Making Machine learning algorithms hold potential for improved prediction of all-cause mortality in cardiovascular patients, yet have not previously been developed with high-quality population data. This study compared four popular machine learning algorithms trained on unselected, nation-wide population data from Sweden to solve the binary classification problem of predicting survival versus non-survival 2years after first myocardial infarction (MI). This prospective national registry study for prognostic accuracy validation of predictive models used data from 51,943 complete first MI cases as registered during 6years (20062011) in the national quality register SWEDEHEART/RIKS-HIA (90% coverage of all MIs in Sweden) with follow-up in the Cause of Death register (> 99% coverage). Primary outcome was AUROC (C-statistic) performance of each model on the untouched test set (40% of cases) after model development on the training set (60% of cases) with the full (39) predictor set. Model AUROCs were bootstrapped and compared, correcting the P-values for multiple comparisons with the Bonferroni method. Secondary outcomes were derived when varying sample size (1100% of total) and predictor sets (39, 10, and 5) for each model. Analyses were repeated on 79,869 completed cases after multivariable imputation of predictors. A Support Vector Machine with a radial basis kernel developed on 39 predictors had the highest complete cases performance on the test set (AUROC=0.845, PPV=0.280, NPV=0.966) outperforming Boosted C5.0 (0.845 vs. 0.841, P=0.028) but not significantly higher than Logistic Regression or Random Forest. Models converged to the point of algorithm indifference with increased sample size and predictors. Using the top five predictors Continue reading >>

Risk Estimation And Risk Prediction Using Machine-learning Methods

Risk Estimation And Risk Prediction Using Machine-learning Methods

Risk estimation and risk prediction using machine-learning methods Jochen Kruppa , Andreas Ziegler , and Inke R. Knig Institut fr Medizininsche Biometrie und Statistik, Universitt zu Lbeck, Universittsklinikum Schleswig-Holstein, Campus Lbeck, Maria-Goeppert-Str. 1, 23562 Lbeck, Germany Institut fr Medizininsche Biometrie und Statistik, Universitt zu Lbeck, Universittsklinikum Schleswig-Holstein, Campus Lbeck, Maria-Goeppert-Str. 1, 23562 Lbeck, Germany Institut fr Medizininsche Biometrie und Statistik, Universitt zu Lbeck, Universittsklinikum Schleswig-Holstein, Campus Lbeck, Maria-Goeppert-Str. 1, 23562 Lbeck, Germany Institut fr Medizininsche Biometrie und Statistik, Universitt zu Lbeck, Universittsklinikum Schleswig-Holstein, Campus Lbeck, Maria-Goeppert-Str. 1, 23562 Lbeck, Germany Inke R. Knig, Phone: +49-451-500/5580, Fax: +49-451-500/2999, Email: [email protected]ekni . Received 2012 Feb 28; Accepted 2012 Jun 14. This article has been cited by other articles in PMC. After an association between genetic variants and a phenotype has been established, further study goals comprise the classification of patients according to disease risk or the estimation of disease probability. To accomplish this, different statistical methods are required, and specifically machine-learning approaches may offer advantages over classical techniques. In this paper, we describe methods for the construction and evaluation of classification and probability estimation rules. We review the use of machine-learning approaches in this context and explain some of the machine-learning algorithms in detail. Finally, we illustrate the methodology through application to a genome-wide association analysis on rheumatoid arthritis. The online version of this article (doi:10.1007/s00439-012 Continue reading >>

Diabetes Risk Prediction Using Machine Learning: Prospect And Challenges

Diabetes Risk Prediction Using Machine Learning: Prospect And Challenges

Diabetes risk prediction using machine learning: prospect and challenges Postdoctoral Fellow, University of Texas MD Anderson Cancer Center, Houston, USA Shankaracharya. Postdoctoral Fellow, University of Texas MD Anderson Cancer Center, Houston, USA; [Tel] - 17134976813; E-mail: [email protected] Shankaracharya. Diabetes risk prediction using machine learning: prospect and challenges (2017) Bioinfo Proteom Img Anal 3(2):194- 195. 2017 Shankaracharya. This is an Open access article distributed under the terms of Creative Commons Attribution 4.0 International License. According to first WHO Global report on diabetes published on world health day April 7, 2016, the number of adults living with diabetes has almost increased four times since 1980 to 422 million. It caused about 1.5 million deaths in 2012. This threatening numbers necessitates the development of effective and accurate diagnosis tools that may reach to the table of clinicians. Diabetes diagnosis is based on various epidemiological and genetic factors. Epidemiological risk factors include smoking status, dietary habits, physical activities, BMI etc. whereas genetic factors are the inherited causative genes from parents. Hence it is very necessary to consider all factors collectively to get the accurate prediction and diagnosis of the disease. Many factors including lack of experience or fatigue of an expert may lead to incorrect diagnosis. Therefore computational approach may provide a strong alternative for diabetes prediction and diagnosis. These computational tools may help clinicians to make accurate diagnosis. Also, it will help individuals to get acquainted about their health status and future possible diabetic condition so that they can get chance to adopt better lifestyle to prevent the d Continue reading >>

Genetic Variants And Their Interactions In Disease Risk Prediction Machine Learning And Network Perspectives

Genetic Variants And Their Interactions In Disease Risk Prediction Machine Learning And Network Perspectives

Received 2012 October 5; Accepted 2013 February 11. Copyright 2013 Okser et al.; licensee BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License ( ), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. This article has been cited by other articles in PMC. A central challenge in systems biology and medical genetics is to understand how interactions among genetic loci contribute to complex phenotypic traits and human diseases. While most studies have so far relied on statistical modeling and association testing procedures, machine learning and predictive modeling approaches are increasingly being applied to mining genotype-phenotype relationships, also among those associations that do not necessarily meet statistical significance at the level of individual variants, yet still contributing to the combined predictive power at the level of variant panels. Network-based analysis of genetic variants and their interaction partners is another emerging trend by which to explore how sub-network level features contribute to complex disease processes and related phenotypes. In this review, we describe the basic concepts and algorithms behind machine learning-based genetic feature selection approaches, their potential benefits and limitations in genome-wide setting, and how physical or genetic interaction networks could be used as a priori information for providing improved predictive power and mechanistic insights into the disease networks. These developments are geared toward explaining a part of the missing heritability, and when combined with individual genomic profiling, such systems medicine approaches may also provide a principled means f Continue reading >>

Machine Learning Approaches To The Social Determinants Of Health In The Health And Retirement Study - Sciencedirect

Machine Learning Approaches To The Social Determinants Of Health In The Health And Retirement Study - Sciencedirect

Machine learning approaches to the social determinants of health in the health and retirement study Author links open overlay panel BenjaminSeligmana Big data methods may aid understanding of social determinants of health. Neural networks outperform other methods in prediction and variance explained. No individual machine learning method was readily interpretable. Variables in common among machine learning methods suggest core social determinants. Social and economic factors are important predictors of health and of recognized importance for health systems. However, machine learning, used elsewhere in the biomedical literature, has not been extensively applied to study relationships between society and health. We investigate how machine learning may add to our understanding of social determinants of health using data from the Health and Retirement Study. A linear regression of age and gender, and a parsimonious theory-based regression additionally incorporating income, wealth, and education, were used to predict systolic blood pressure, body mass index, waist circumference, and telomere length. Prediction, fit, and interpretability were compared across four machine learning methods: linear regression, penalized regressions, random forests, and neural networks. All models had poor out-of-sample prediction. Most machine learning models performed similarly to the simpler models. However, neural networks greatly outperformed the three other methods. Neural networks also had good fit to the data (R2 between 0.40.6, versus <0.3 for all others). Across machine learning models, nine variables were frequently selected or highly weighted as predictors: dental visits, current smoking, self-rated health, serial-seven subtractions, probability of receiving an inheritance, probabili Continue reading >>

Scanning Retinas For Heart Disease With Ai Prediction

Scanning Retinas For Heart Disease With Ai Prediction

Scanning Retinas for Heart Disease with AI Prediction Stephan Cunningham Artificial Intelligence Researchers have devised a deep-learning algorithm that uses AI prediction techniques to forecast cardiovascular risk based on scans of patients retinas. A team of researchers from Google, Verily Life Sciences and the Stanford School of Medicine trained their deep-learning algorithm using data from 284,335 patients. The algorithms were able to predict cardiovascular (CV) issues with surprisingly high accuracy for patients by looking for risk factors including diabetes, smoking, and high blood pressure. Based on the scans, the algorithm could differentiate the retinal images of smokers versus non-smokers with 71 percent accuracy, Google noted in a blog post . Although doctors can tell whether patients have acute high blood pressure by looking at their retinal images, the algorithm can actually predict systolic blood pressure levels for every patient. In addition to predicting the various risk factors (age, gender, smoking, blood pressure, etc) from retinal images, our algorithm was fairly accurate at predicting the risk of a CV event directly, Google stated. Our algorithm used the entire image to quantify the association between the image and the risk of heart attack or stroke. Given the retinal image of one patient who (up to 5 years) later experienced a major CV event (such as a heart attack) and the image of another patient who did not, our algorithm could pick out the patient who had the CV event 70 percent of the time. This performance approaches the accuracy of other CV risk calculators that require a blood draw to measure cholesterol. Even more significantly, the researchers have been able to observe how the algorithm was able to make AI predictions. By doing this, th Continue reading >>

[full Text] Hard-to-heal Diabetes-related Foot Ulcers: Current Challenges And Futu | Cwcmr

[full Text] Hard-to-heal Diabetes-related Foot Ulcers: Current Challenges And Futu | Cwcmr

Editor who approved publication: Professor Marco Romanelli Video abstract presented by Vanessa Nube. Vanessa Nube,1 Georgina Frank,1 Jessica White,1 Sarah Stubbs,1 Sara Nannery,2 Louise Pfrunder,2 Stephen M Twigg,3 Susan V McLennan4 1Department of Podiatry, Sydney Local Health District, Camperdown, NSW, Australia; 2Diabetes Centre High Risk Foot Service, Royal Prince Alfred Hospital, Camperdown, NSW, Australia; 3Discipline of Medicine, Sydney Medical School, University of Sydney, Camperdown, Sydney, NSW, Australia; 4Department of Endocrinology, Royal Prince Alfred Hospital, Camperdown, Sydney, NSW, Australia Abstract: Diabetes-related foot ulceration is a frequent cause for hospital admission and the leading cause of nontraumatic lower limb amputation, placing a high burden on the health system, patient, and their families. Considerable advances in treatments and the establishment of specialized services and teams have improved healing rates and reduced unnecessary amputations. However, amputation rates remain high in some areas, with unacceptable variations within countries yet to be resolved. Specific risk factors including infection, ischemia, ulcer size, depth, and duration as well as probing to bone (or osteomyelitis), location of ulcer, sensory loss, deformity (and high plantar pressure), advanced age, number of ulcers present, and renal disease are associated with poor outcome and delayed healing. To assist in prediction of difficult-to-heal ulcers, more than 13 classification systems have been developed. Ulcer depth (or size), infection, and ischemia are the most common risk factors identified. High-quality treatment protocols and guidelines exist to facilitate best practice in the standard of care. Under these conditions, 66%77% of foot ulcers will heal. The r Continue reading >>

How Machine Learning Could Revolutionize Medicine

How Machine Learning Could Revolutionize Medicine

octors will one day be able to more accurately predict how long patients with fatal diseases will live. Medical systems will learn how to save money by skipping expensive and unnecessary tests. Radiologists will be replaced by computer algorithms. These are just some of the realities patients and doctors should prepare for as machine learning enters the world of medicine, according to Dr. Ziad Obermeyer, an assistant professor at Harvard Medical School, and Dr. Ezekiel Emanuel of the University of Pennsylvania, who recently coauthored an article in the New England Journal of Medicine on the topic. But what exactly is machine learning? And how will medical systems make use of it? Obermeyer, who is also an emergency physician at Bostons Brigham and Womens Hospital, spoke with STAT to provide some answers. This discussion has been edited and condensed. Watson goes to Asia: Hospitals use supercomputer for cancer treatment How is machine learning different than, say, artificial intelligence? The traditional approach to solving problems with technology is to give the computer some rules and apply brute computing force. With machine learning, you dont actually give machines rules. You give them data and ask them to learn the rules. We can point this very powerful tool at a medical problem and say, Im going to show you a bunch of people who had heart attacks, and a bunch who didnt. Go learn how to tell them apart. Then, once the algorithm has seen a million patients and what happened to them, you can show it information about a new patient and let it predict whether he might be at imminent risk for a heart attack. These algorithms are extraordinarily good at telling the difference. What we need to know more is, what are the rules the machine is learning, and how did it arrive Continue reading >>

Jmir-guidelines For Developing And Reporting Machine Learning Predictive Models In Biomedical Research: A Multidisciplinary View | Luo | Journal Of Medical Internet Research

Jmir-guidelines For Developing And Reporting Machine Learning Predictive Models In Biomedical Research: A Multidisciplinary View | Luo | Journal Of Medical Internet Research

The Karma system is currently undergoing maintenance (Monday, January 29, 2018). The maintenance period has been extended to 8PM EST. Karma Credits will not be available for redeeming during maintenance. Preprints (earlier versions) of this paper are available at , first published Apr 12, 2016. This paper is in the following e-collection/theme issue: 1Centre for Pattern Recognition and Data Analytics, School of Information Technology, Deakin University, Geelong, Australia 3Philips Research, Briarcliff Manor, NY, United States 4Japan Advanced Institute of Science and Technology, Nomi, Japan Centre for Pattern Recognition and Data Analytics Background: As more and more researchers are turning to big data for new opportunities of biomedical discoveries, machine learning models, as the backbone of big data analysis, are mentioned more often in biomedical journals. However, owing to the inherent complexity of machine learning methods, they are prone to misuse. Because of the flexibility in specifying machine learning models, the results are often insufficiently reported in research articles, hindering reliable assessment of model validity and consistent interpretation of model outputs. Objective: To attain a set of guidelines on the use of machine learning predictive models within clinical settings to make sure the models are correctly applied and sufficiently reported so that true discoveries can be distinguished from random coincidence. Methods: A multidisciplinary panel of machine learning experts, clinicians, and traditional statisticians were interviewed, using an iterative process in accordance with the Delphi method. Results: The process produced a set of guidelines that consists of (1) a list of reporting items to be included in a research article and (2) a set of p Continue reading >>

More in diabetes