A comparative data analytic approach to construct a risk trade-off for cardiac patients’ re-admissions

Abstract

Purpose The purpose of this paper is to formulate a framework to construct a patient-specific risk score and therefore to classify these patients into various risk groups that can be used as a decision support mechanism by the medical decision makers to augment their decision-making process, allowing them to optimally use the limited resources available. Design/methodology/approach A conventional statistical model (logistic regression) and two machine learning-based (i.e. artificial neural networks (ANNs) and support vector machines) data mining models were employed by also using five-fold cross-validation in the classification phase. In order to overcome the data imbalance problem, random undersampling technique was utilized. After constructing the patient-specific risk score, k-means clustering algorithm was employed to group these patients into risk groups. Findings Results showed that the ANN model achieved the best results with an area under the curve score of 0.867, while the sensitivity and specificity were 0.715 and 0.892, respectively. Also, the construction of patient-specific risk scores offer useful insights to the medical experts, by helping them find a trade-off between risks, costs and resources. Originality/value The study contributes to the existing body of knowledge by constructing a framework that can be utilized to determine the risk level of the targeted patient, by employing data mining-based predictive approach.

Predicting hotel reviews from sentiment: a multinomial classification framework

“…Hence, if a particular text piece embodies more pre-arranged “positive” terms than “negative” ones, that specific portion of text would be considered as “positive” and vice versa. The second broad category is known as Machine Learning or ML, a subset of artificial intelligence that has been rigorously applied for text analytics, as well as other domains including healthcare analytics and financial analytics (Dag et al , 2017; Topuz et al , 2018; Kibis, 2017; Simsek et al , 2020; Nasir et al , 2019; Yucel et al , 2021). ML approaches effectively categorize text data into binary/multinomial classes via supervised learning through labelled past data.…”

A joint weighting and modified weighted aggregated sum product assessment‐based methodology for the measurement of patient satisfaction: Evidence from Indian healthcare

“…Ortiz‐Barrios et al (2017) propose a hybrid analytic decision‐making preference model to evaluate the preparation of an emergency department for a disaster situation. Nasir et al (2019) devise an aggregated logistic regression, artificial neural network, support vector machines, and k‐means clustering algorithm‐based methodology to determine the risk scores of the cardiac patients and classify them into different groups. In the context of federal university hospitals of Brazil, Peixoto et al (2018) incorporate the principal component analysis and clusters analysis to determine the crucial factors of the performance improvement.…”

Research Trends on Machine Learning in Construction Management: A Scientometric Analysis

“…Machine learning may assist project stakeholders to decrease risk by identifying risks, measuring their impact, and using predictive analytics. Therefore, many studies were undertaken to apply machine learning to predict and assess risks of construction projects [8][9][10][11][12][13][14][15][16][17][18]. For example, the study of [13] used machine learning to address the soft-margin support vector machines for supervised machine learning classification using n-fold cross-validation.…”