System Architecture of a European Platform for Health Policy Decision Making: MIDAS.

Background: Healthcare data is a rich yet underutilized resource due to its disconnected, heterogeneous nature. A means of connecting healthcare data and integrating it with additional open and social data in a secure way can support the monumental challenge policy-makers face in safely accessing all relevant data to assist in managing the health and wellbeing of all. The goal of this study was to develop a novel health data platform within the MIDAS (Meaningful Integration of Data Analytics and Services) project, that harnesses the potential of latent healthcare data in combination with open and social data to support evidence-based health policy decision-making in a privacy-preserving manner. Methods: The MIDAS platform was developed in an iterative and collaborative way with close involvement of academia, industry, healthcare staff and policy-makers, to solve tasks including data storage, data harmonization, data analytics and visualizations, and open and social data analytics. The platform has been piloted and tested by health departments in four European countries, each focusing on different region-specific health challenges and related data sources. Results: A novel health data platform solving the needs of Public Health decision-makers was successfully implemented within the four pilot regions connecting heterogeneous healthcare datasets and open datasets and turning large amounts of previously isolated data into actionable information allowing for evidence-based health policy-making and risk stratification through the application and visualization of advanced analytics. Conclusions: The MIDAS platform delivers a secure, effective and integrated solution to deal with health data, providing support for health policy decision-making, planning of public health activities and the implementation of the Health in All Policies approach. The platform has proven transferable, sustainable and scalable across policies, data and regions.

Discovering and comparing types of general practitioner practices using geolocational features and prescribing behaviours by means of K-means clustering.

Traditionally General Practitioner (GP) practices have been labelled as being in Rural, Urban or Semi-Rural areas with no statistical method of identifying which practices fall into each category. The main aim of this study is to investigate whether location and other characteristics can provide a tautology to identify different types of GP practice and compare the prescribing behaviours associated with the different practice types. To achieve this monthly open source prescription data were analysed by practice considering location, practice size, population density and deprivation rankings. One year's data was subjected to k-means clustering with the results showing that only two different types of GP practice can be classified that are dependent on location characteristics in Northern Ireland. Traditional labels did not describe the two classifications fully and new classifications of Metropolitan and Non-Metropolitan were used. Whilst prescribing patterns were generally similar, it was found that Metropolitan practices generally had higher prescribing rates than Non-Metropolitan practices. Examining prescribing behaviours in accordance with British National Formulary (BNF) categories (known as chapters) showed that Chapter 4 (Central Nervous System) was responsible for most of the difference in prescribing levels. Within Chapter 4 higher prescribing levels were attributable to Analgesic and Antidepressant prescribing. The clusters were finally examined regarding the level of deprivation experienced in the area in which the practice was located. This showed that the Metropolitan cluster, having higher prescription rates, also had a higher proportion of practices located in highly deprived areas making deprivation a contributing factor.

Identifying Key Predictors of Cognitive Dysfunction in Older People Using Supervised Machine Learning Techniques: Observational Study.

BACKGROUND: Machine learning techniques, specifically classification algorithms, may be effective to help understand key health, nutritional, and environmental factors associated with cognitive function in aging populations. OBJECTIVE: This study aims to use classification techniques to identify the key patient predictors that are considered most important in the classification of poorer cognitive performance, which is an early risk factor for dementia. METHODS: Data were used from the Trinity-Ulster and Department of Agriculture study, which included detailed information on sociodemographic, clinical, biochemical, nutritional, and lifestyle factors in 5186 older adults recruited from the Republic of Ireland and Northern Ireland, a proportion of whom (987/5186, 19.03%) were followed up 5-7 years later for reassessment. Cognitive function at both time points was assessed using a battery of tests, including the Repeatable Battery for the Assessment of Neuropsychological Status (RBANS), with a score <70 classed as poorer cognitive performance. This study trained 3 classifiers-decision trees, Naïve Bayes, and random forests-to classify the RBANS score and to identify key health, nutritional, and environmental predictors of cognitive performance and cognitive decline over the follow-up period. It assessed their performance, taking note of the variables that were deemed important for the optimized classifiers for their computational diagnostics. RESULTS: In the classification of a low RBANS score (<70), our models performed well (F1 score range 0.73-0.93), all highlighting the individual's score from the Timed Up and Go (TUG) test, the age at which the participant stopped education, and whether or not the participant's family reported memory concerns to be of key importance. The classification models performed well in classifying a greater rate of decline in the RBANS score (F1 score range 0.66-0.85), also indicating the TUG score to be of key importance, followed by blood indicators: plasma homocysteine, vitamin B6 biomarker (plasma pyridoxal-5-phosphate), and glycated hemoglobin. CONCLUSIONS: The results suggest that it may be possible for a health care professional to make an initial evaluation, with a high level of confidence, of the potential for cognitive dysfunction using only a few short, noninvasive questions, thus providing a quick, efficient, and noninvasive way to help them decide whether or not a patient requires a full cognitive evaluation. This approach has the potential benefits of making time and cost savings for health service providers and avoiding stress created through unnecessary cognitive assessments in low-risk patients.

Reliability of Supervised Machine Learning Using Synthetic Data in Health Care: Model to Preserve Privacy for Data Sharing.

BACKGROUND: The exploitation of synthetic data in health care is at an early stage. Synthetic data could unlock the potential within health care datasets that are too sensitive for release. Several synthetic data generators have been developed to date; however, studies evaluating their efficacy and generalizability are scarce. OBJECTIVE: This work sets out to understand the difference in performance of supervised machine learning models trained on synthetic data compared with those trained on real data. METHODS: A total of 19 open health datasets were selected for experimental work. Synthetic data were generated using three synthetic data generators that apply classification and regression trees, parametric, and Bayesian network approaches. Real and synthetic data were used (separately) to train five supervised machine learning models: stochastic gradient descent, decision tree, k-nearest neighbors, random forest, and support vector machine. Models were tested only on real data to determine whether a model developed by training on synthetic data can used to accurately classify new, real examples. The impact of statistical disclosure control on model performance was also assessed. RESULTS: A total of 92% of models trained on synthetic data have lower accuracy than those trained on real data. Tree-based models trained on synthetic data have deviations in accuracy from models trained on real data of 0.177 (18%) to 0.193 (19%), while other models have lower deviations of 0.058 (6%) to 0.072 (7%). The winning classifier when trained and tested on real data versus models trained on synthetic data and tested on real data is the same in 26% (5/19) of cases for classification and regression tree and parametric synthetic data and in 21% (4/19) of cases for Bayesian network-generated synthetic data. Tree-based models perform best with real data and are the winning classifier in 95% (18/19) of cases. This is not the case for models trained on synthetic data. When tree-based models are not considered, the winning classifier for real and synthetic data is matched in 74% (14/19), 53% (10/19), and 68% (13/19) of cases for classification and regression tree, parametric, and Bayesian network synthetic data, respectively. Statistical disclosure control methods did not have a notable impact on data utility. CONCLUSIONS: The results of this study are promising with small decreases in accuracy observed in models trained with synthetic data compared with models trained with real data, where both are tested on real data. Such deviations are expected and manageable. Tree-based classifiers have some sensitivity to synthetic data, and the underlying cause requires further investigation. This study highlights the potential of synthetic data and the need for further evaluation of their robustness. Synthetic data must ensure individual privacy and data utility are preserved in order to instill confidence in health care departments when using such data to inform policy decision-making.