Predictive models to assess risk of type 2 diabetes, hypertension and comorbidity: machine-learning algorithms and validation using national health data from Kuwait—a cohort study

Abstract

ObjectiveWe build classification models and risk assessment tools for diabetes, hypertension and comorbidity using machine-learning algorithms on data from Kuwait. We model the increased proneness in diabetic patients to develop hypertension and vice versa. We ascertain the importance of ethnicity (and natives vs expatriate migrants) and of using regional data in risk assessment.DesignRetrospective cohort study. Four machine-learning techniques were used: logistic regression, k-nearest neighbours (k-NN), multifactor dimensionality reduction and support vector machines. The study uses fivefold cross validation to obtain generalisation accuracies and errors.SettingKuwait Health Network (KHN) that integrates data from primary health centres and hospitals in Kuwait.Participants270 172 hospital visitors (of which, 89 858 are diabetic, 58 745 hypertensive and 30 522 comorbid) comprising Kuwaiti natives, Asian and Arab expatriates.Outcome measuresIncident type 2 diabetes, hypertension and comorbidity.ResultsClassification accuracies of >85% (for diabetes) and >90% (for hypertension) are achieved using only simple non-laboratory-based parameters. Risk assessment tools based on k-NN classification models are able to assign ‘high’ risk to 75% of diabetic patients and to 94% of hypertensive patients. Only 5% of diabetic patients are seen assigned ‘low’ risk. Asian-specific models and assessments perform even better. Pathological conditions of diabetes in the general population or in hypertensive population and those of hypertension are modelled. Two-stage aggregate classification models and risk assessment tools, built combining both the component models on diabetes (or on hypertension), perform better than individual models.ConclusionsData on diabetes, hypertension and comorbidity from the cosmopolitan State of Kuwait are available for the first time. This enabled us to apply four different case–control models to assess risks. These tools aid in the preliminary non-intrusive assessment of the population. Ethnicity is seen significant to the predictive models. Risk assessments need to be developed using regional data as we demonstrate the applicability of the American Diabetes Association online calculator on data from Kuwait.

Mining comorbidity patterns using retrospective analysis of big collection of outpatient records

“…Machine learning (ML) is the basic technology used in such studies. For instance, four ML techniques (logistic regression, k-nearest neighbors, multifactor dimensionality reduction and support vector machines) were applied to assess risks for diabetes, hypertension and their comorbidity in a cohort of 270,172 hospital visitors (89,858 diabetic, 58,745 hypertensive and 30,522 comorbid patients) in Kuwait, with accuracy > 85% (for diabetes) and > 90% (for hypertension) [10]. An original approach for predicting a comorbid medical condition incidence and progression of medical conditions, using self-posted data available on patient-oriented social media sites, is presented in [11].…”

13. From telemedicine to modeling and proactive medicine

“…Among the computational methods used for developing models of disease progression and therapy effects, the following principal groups of methods can be distinguished: -regression methods [10,17,24,25] -supervised learning methods [10,12,15,17] -unsupervised learning methods [11,13] -Markov Decision Process (MDP)-based methods [16,23] -Monte-Carlo methods [18] The first group of methods, i.e. regression-based prediction, roughly speaking relies on fitting a multidimensional function h(x), called a hypothesis, onto a given dataset, so that its values are as close as possible to the values in the dataset within a specific function form.…”

“…The function found can then be used either to predict future values (in this case time is one of the function's dimensions) or to classify patterns. From the medical modeling viewpoint, the first approach takes place when a disease's progress or a therapy response is simulated [17,24,25], whereas the second case mainly refers to CAD software [10].…”

“…arterial hypertension [12,13], coronary artery disease [14,15] or pulmonary hypertension [16] -metabolic diseases, e.g. diabetes [17] -neoplasms [5] -AIDS [18] These models allow for automatic extraction of selected aspects or features that are supportive to physicians in making decisions regarding the applied therapy. Such models are particularly useful in case of chronic diseases (e.g.…”

Diagnosis of Diabetes by Applying Data Mining Classification Techniques

“…Farran et al [16] used non-laboratory attributed to classify the diabetes by applying 4 data mining models that were logistic regression, k-nearest neighbors (k-NN), multifactor dimensionality reduction and Support Vector Machines (SVM). They achieved an accuracy of 85% for diabetic patients.…”