Analyzing the Performance of Feature Selection on Regression Problems: A Case Study on Older Adults’ Functional Profile

Abstract

Healthcare systems are capable of collecting a significant number of patient health-related parameters. Analyzing them to find the reasons that cause a given disease is challenging. Feature Selection techniques have been used to address this issue-reducing these parameters to a smaller set with the most "determinant" information. However, existing proposals usually focus on classification problems-aimed to detect whether a person is or is not suffering from an illness or from a finite set of illnesses. However, there are many situations in which health professionals need a numerical assessment to quantify the severity of an illness, thus dealing with a regression problem instead. Proposals using Feature Selection here are very limited. This paper examines several Feature Selection techniques to gauge their applicability to the regression-type problems, comparing these techniques by applying them to a real-life scenario on the functional profiles of older adults. Data from 829 functional profiles assessments in 49 residential homes were used in this study. The number of features was reduced from 31 to 25-with a correlation between inputs and outputs of 0.99 according to the R 2 score and a Mean Square Error (MSE) of 0.11-or to 14 features-with a correlation of 0.98 and MSE of 5.73.

The Effectiveness of Nursing Rehabilitation Interventions on Self-Care for Older Adults with Respiratory Disorders: A Systematic Review with Meta-Analysis

“…The mentioned studies observed the importance of continuous monitoring, family involvement, and peer support in promoting self-care in chronic diseases. Based on our screening of the scientific evidence produced in the national context (in Portugal), several authors have addressed this subject and corroborate these findings by stating that these interventions contribute to the empowerment of patients, increase health literacy and emotional support, and provide a better understanding of the disease, resulting in better self-care outcomes and overall well-being [46][47][48][49][50].…”

“…The outcome indicator symptom control involves health education interventions on inhaler therapy [9] and coughing techniques [9,14], breathing control techniques for dyspnea/anxiety relief [8,13,14], and non-pharmacological techniques for symptom control and relief [9,43]. Several studies agree with these findings, suggesting self-care as an outcome sensitive to rehabilitation care, with a positive impact on promoting health and well-being by increasing people's skills and abilities through aptitude training or adaptive strategies, in which rehabilitation care plays a decisive role [46][47][48][49][50]52]. According to Wang et al [9], empowering patients to self-manage their disease by providing knowledge about pathophysiology, therapeutic administration techniques, and pharmacological and nonpharmacological strategies for symptom relief reduces patients' recurring visits to emergency departments during symptom exacerbation because patients and their families are equipped with disease control and management expertise.…”

Analyzing Wet-Neuromorphic Computing Using Bacterial Gene Regulatory Neural Networks

“…Mathematical regression has been widely used in data mining applications [38], [39] for many years. Therefore, one key contribution of this study is the GRNN's expression behaviour that matches regression problems, which will be analyzed in this section.…”