Chronic kidney disease (CKD) is one of the leading medical ailments in developing countries. Due to the limited healthcare infrastructure and the lack of trained human resources, the CKD problem aggravates if it is not addressed in its earlier stages. In this regard, the role of machine learning-based automated diagnosis systems plays a vital role to deal with the CKD problem. In most of the studies conducted on the automated CKD decision modeling, the main emphasis is given to enhancing the predictive accuracy of the system. In this study, we focus on the applicability challenges of automated decision systems taking CKD diagnosis as a case study within the purview of developing countries. In this regard, we propose a cost-sensitive ensemble feature ranking method that takes a more realistic approach to group-based feature selection. Two candidate solutions are proposed for group-based feature selection to meet different objectives. Subsequently, both the candidate solutions are combined into a consolidated solution. It is pertinent to note that it is one of the first studies in which cost-sensitive ensemble feature ranking for non-overlapping groups is successfully demonstrated to achieve the stated objectives i.e. low-cost and high-accuracy solution. Based on an extensive set of experiments, we demonstrate that a cost-effective and accurate solution for the CKD problem can be obtained. The experimentation includes 7 well-known classification algorithms and 8 comparative feature selection methods to show the efficacy of the proposed approach. It is concluded that the applicability of the automated CKD systems can be enhanced by including the cost consideration into the objective space of the solution formulation. Therefore, a trade-off solution can be obtained that is cost-effective and yet accurate enough to serve as a CKD screening system.

Automated medical diagnosis is one of the important machine learning applications in the domain of healthcare. In this regard, most of the approaches primarily focus on optimizing the accuracy of classification models. In this research, we argue that, unlike general-purpose classification problems, medical applications, such as chronic kidney disease (CKD) diagnosis, require special treatment. In the case of CKD, apart from model performance, other factors such as the cost of data acquisition may also be taken into account to enhance the applicability of the automated diagnosis system. In this research, we proposed two techniques for cost-sensitive feature ranking. An ensemble of decision tree models is employed in both the techniques for computing the worth of a feature in the CKD dataset. An automatic threshold selection heuristic is also introduced which is based on the intersection of features’ worth and their accumulated cost. A set of experiments are conducted to evaluate the efficacy of the proposed techniques on both tree-based and non tree-based classification models. The proposed approaches were also evaluated against several comparative techniques. Furthermore, it is demonstrated that the proposed techniques select around 1/4th of the original CKD features while reducing the cost by a factor of 7.42 of the original feature set. Based on the extensive experimentation, it is concluded that the proposed techniques employing feature-cost interaction heuristic tend to select feature subsets that are both useful and cost-effective.

Clinical decision support systems (CDSSs) represent the latest technological transformation in healthcare for assisting clinicians in complex decision-making. Several CDSSs are proposed to deal with a range of clinical tasks such as disease diagnosis, prescription management, and medication ordering. Although a small number of CDSSs have focused on treatment selection, areas such as medication selection and dosing selection remained under-researched. In this regard, this study represents one of the first studies in which a CDSS is proposed for clinicians who manage patients with end-stage renal disease undergoing maintenance hemodialysis, almost all of whom have some manifestation of chronic kidney disease–mineral and bone disorder (CKD–MBD). The primary objective of the system is to aid clinicians in dosage prescription by levering medical domain knowledge as well existing practices. The proposed CDSS is evaluated with a real-world hemodialysis patient dataset acquired from Kyung Hee University Hospital, South Korea. Our evaluation demonstrates overall high compliance based on the concordance metric between the proposed CKD–MBD CDSS recommendations and the routine clinical practice. The concordance rate of overall medication dosing selection is 78.27%. Furthermore, the usability aspects of the system are also evaluated through the User Experience Questionnaire method to highlight the appealing aspects of the system for clinicians. The overall user experience dimension scores for pragmatic, hedonic, and attractiveness are 1.53, 1.48, and 1.41, respectively. A service reliability for the Cronbach’s alpha coefficient greater than 0.7 is achieved using the proposed system, whereas a dependability coefficient of the value 0.84 reveals a significant effect.

Clinical Practice Guidelines (CPGs) aim to optimize patient care by assisting physicians during the decision-making process. However, guideline adherence is highly affected by its unstructured format and aggregation of background information with disease-specific information. The objective of our study is to extract disease-specific information from CPG for enhancing its adherence ratio. In this research, we propose a semi-automatic mechanism for extracting disease-specific information from CPGs using pattern-matching techniques. We apply supervised and unsupervised machine-learning algorithms on CPG to extract a list of salient terms contributing to distinguishing recommendation sentences (RS) from non-recommendation sentences (NRS). Simultaneously, a group of experts also analyzes the same CPG and extract the initial patterns “Heuristic Patterns” using a group decision-making method, nominal group technique (NGT). We provide the list of salient terms to the experts and ask them to refine their extracted patterns. The experts refine patterns considering the provided salient terms. The extracted heuristic patterns depend on specific terms and suffer from the specialization problem due to synonymy and polysemy. Therefore, we generalize the heuristic patterns to part-of-speech (POS) patterns and unified medical language system (UMLS) patterns, which make the proposed method generalize for all types of CPGs. We evaluated the initial extracted patterns on asthma, rhinosinusitis, and hypertension guidelines with the accuracy of 76.92%, 84.63%, and 89.16%, respectively. The accuracy increased to 78.89%, 85.32%, and 92.07% with refined machine-learning assistive patterns, respectively. Our system assists physicians by locating disease-specific information in the CPGs, which enhances the physicians’ performance and reduces CPG processing time. Additionally, it is beneficial in CPGs content annotation.

In the era of digital well-being, smart gadgets are the unobtrusive sources of acquiring information. A variety of personalized wellness applications support self-quantification based recommendations to provide wellness status for achieving personalized targets. However, these applications are unable to promote the induction of new healthy habits and thus are not too much effective for long term as users tend to loose their interest. Thus, we have proposed a methodology for User-Centric Adaptive Intervention based on behavior change theory for maintaining end-users’ interest. The methodology consists of four steps: (1) quantification of behavior based on contributing factors governed by expert-driven rules; (2) behavior-context based mapping for the identification of behavior status of the user; (3) selection of appropriate way of intervention to get fruitful outcomes; and finally (4) feedback based evaluation on the basis of recorded activities and questionnaires for satisfaction. A comprehensive healthy behavior index-based quantification supports the machine learning-based prediction model for behavior-context mapping. Furthermore, the evaluation is performed through implicit and explicit feedback analysis along with the accuracy of the behavior-context prediction model through multiple scenarios to cover comprehensive situations. The ensemble classifier suggests the accuracy of 98.02% for the behavior-context prediction model, which is higher than the other classifiers. The gain in behavior change is drawn from implicit feedback, which depicts that behavior context-based methods have improved the adaptation in behavior at a steady pace for the long term. The explicit feedback from 99 end-users of wellness application based on the proposed methodology obtained Good and Desired status for widely used System Usability Score and AttrakDiff tools respectively.