Bringing big data analytics closer to practice: A methodological explanation and demonstration of classification algorithms. Issue 1 (March 2019)

• Record Type: Journal Article
• Authors: Ben-Assuli, Ofir; Heart, Tsipi; Shlomo, Nir; Klempfner, Robert
• Is Part Of: Health policy and technology. Volume 8:Issue 1(2019)
• Page Start: 7
• Page End: 13
• Publication Date: 2019-03
• Subjects: Congestive heart failure -- Machine learning -- Logistic regression -- Boosted decision tree -- Support vector machine -- Neural network; Medical policy -- Periodicals; Medical technology -- Periodicals; Medical policy; Medical technology; Health Policy -- Periodicals; Biomedical Technology -- Periodicals; Technology Assessment, Biomedical -- Periodicals; Periodicals; 362.105
• DOI: 10.1016/j.hlpt.2018.12.003
• Languages: English
• ISSNs: 2211-8837

Abstract

Highlights: Our objective is to encourage policy makers to allocate more resources to ○ Health IT projects that will provide extensive, integrated health data, critical for more accurate big data analyses. ○ Projects that clarify and simplify big data analytics so it can be used by practitioners and decision makers. To this end, we methodologically explain the principles and wisdom of several commonly used machine-learning algorithms. This is a step toward bringing big data analytics closer to the points of decision-making, making it more understandable by non-experts. We demonstrate the use of these algorithms on a large, comprehensive data set of Congestive Heart Failure patients. The results outperform previous works and support our call for policy makers to allocate resources first to establish comprehensive, integrated health IT systems, and second, to projects aimed at simplifying machine-learning analytics. Abstract: Background: Big data analytics are becoming more prevalent due to the recent availability of health data. Yet in spite of evidence supporting the potential contribution of big data analytics to health policy makers and care providers, these tools are still too complex to be routinely used. Further, access to comprehensive datasets required for more accurate results is complex and costly. Consequently, big data analytics are mostly used by researchers and experts who are far removed from actual clinical practice. Hence, policy makers should allocate resources to encourage studies that clarify and simplify big data analytics so it can be used by non-experts (e.g., clinicians, practitioners and decision-makers who may not have advanced computer skills). It is also important to fund data collection and integration from various health IT, a pre-condition for any big data analytics project. Objectives: To methodologically clarify the rationale and logic behind several analytics algorithms to help non-expert users employ big data analytics by understanding how to implement relatively easy to use platforms as Azure ML. Methods: We demonstrate the predictive power of four known algorithms and compare their accuracy in predicting early mortality of Congestive Heart Failure (CHF) patients. Results: The results of our models outperform those reported in the literature, attesting to the strength of some of the models, and the utility of comprehensive data. Conclusions: The results support our call to policy makers to allocate resources to establishing comprehensive, integrated health IT systems, and to projects aimed at simplifying ML analytics.