A Systematic Literature Review on Particle Swarm Optimization Techniques for Medical Diseases Detection

Artificial Intelligence (AI) is the domain of computer science that focuses on the development of machines that operate like humans. In the field of AI, medical disease detection is an instantly growing domain of research. In the past years, numerous endeavours have been made for the improvements of medical disease detection, because the errors and problems in medical disease detection cause serious wrong medical treatment. Meta-heuristic techniques have been frequently utilized for the detection of medical diseases and promise better accuracy of perception and prediction of diseases in the domain of biomedical. Particle Swarm Optimization (PSO) is a swarm-based intelligent stochastic search technique encouraged from the intrinsic manner of bee swarm during the searching of their food source. Consequently, for the versatility of numerical experimentation, PSO has been mostly applied to address the diverse kinds of optimization problems. However, the PSO techniques are frequently adopted for the detection of diseases but there is still a gap in the comparative survey. This paper presents an insight into the diagnosis of medical diseases in health care using various PSO approaches. This study presents to deliver a systematic literature review of current PSO approaches for knowledge discovery in the field of disease detection. The systematic analysis discloses the potential research areas of PSO strategies as well as the research gaps, although, the main goal is to provide the directions for future enhancement and development in this area. This paper gives a systematic survey of this conceptual model for the advanced research, which has been explored in the specified literature to date. This review comprehends the fundamental concepts, theoretical foundations, and conventional application fields. It is predicted that our study will be beneficial for the researchers to review the PSO algorithms in-depth for disease detection. Several challenges that can be undertaken to move the field forward are discussed according to the current state of the PSO strategies in health care.

AEC Classifier: A Tree-Based Classifier with Error Control for Medical Disease Diagnosis and Other Applications

In medical disease diagnosis, the cost of a false negative could greatly outweigh the cost of a false positive. This is because the former could cost a life, whereas the latter may only cause medical costs and stress to the patient. The unique nature of this problem highlights the need of asymmetric error control for binary classification applications. In this domain, traditional machine learning classifiers may not be ideal as they do not provide a way to control the number of false negatives below a certain threshold. This paper proposes a novel tree-based binary classification algorithm that can control the number of false negatives with a mathematical guarantee, based on Neyman–Pearson (NP) Lemma. This classifier is evaluated on the data obtained from different heart studies and it predicts the risk of cardiac disease, not only with comparable accuracy and AUC-ROC score but also with full control over the number of false negatives. The methodology used to construct this classifier can be expanded to many more use cases, not only in medical disease diagnosis but also beyond as shown from analysis on different diverse datasets.

Prioritising Risk Factors for Prescription Drug Overdose among Older Adults in South Korea: A Multi-Method Study

Older adults are vulnerable to drug overdose. We used a multi-method approach to prioritise risk factors for prescription drug overdose among older adults. The study was conducted in two stages. First, risk factors for drug overdose were classified according to importance and changeability through literature review, determined through 2-phase expert surveys. Second, prescription drug overdose cases during 2011–2015 were selected from a national cohort; the prevalence of ‘more important’ or ‘more changeable’ factors determined in stage one was investigated. Scores were assigned according to the Basic Priority Rating Scale formula, reflecting the problem size and seriousness and intervention effectiveness. In the first stage, polypharmacy, old-old age, female sex, chronic disease, psychiatric disease, and low socioeconomic status (SES) were selected as risk factors. In the second stage, 93.9% of cases enrolled had chronic medical disease; 78.3% were using multiple drugs. Low SES was more prevalent than other risk factors. As per the scoring formula, chronic medical disease, polypharmacy, psychiatric disease, low SES, female sex, and old-old age were the most important risk factors in order of priority. Patients with chronic medical disease and those using multiple medications should be prioritised in overdose prevention interventions among older adults.

Physiological changes during pregnancy: a mimic of medical disease and risk to existing ones

During pregnancy; multiple physiological adaptations are encountered. Their aim is to protect and nurture the developing fetus and prepare the mother for labor and delivery. They are mediated by an orchestra of maternal and placental hormones. Some of these changes influence normal biochemical values while others may mimic symptoms of medical disease. It is important to differentiate between normal physiological changes and disease pathology. The present review summarizes the changes in different systems of the body and its metabolism in an attempt to assist clinicians caring for pregnant women during health and disease. Keywords: adaptations, changes, hormones, metabolism, physiology, pregnancy.

ACO_NB-Based Hybrid Prediction Model for Medical Disease Diagnosis

In recent years, a huge increase in the demand of medically related data is reported. Due to this, research in medical disease diagnosis has emerged as one of the most demanding research domains. The research reported in this chapter is based on developing an ACO (ant colony optimization)-based Bayesian hybrid prediction model for medical disease diagnosis. The proposed model is presented in two phases. In the first phase, the authors deal with feature selection by using the application of a nature-inspired algorithm known as ACO. In the second phase, they use the obtained feature subset as input for the naïve Bayes (NB) classifier for enhancing the classification performances over medical domain data sets. They have considered 12 datasets from different organizations for experimental purpose. The experimental analysis advocates the superiority of the presented model in dealing with medical data for disease prediction and diagnosis.