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.

No abstract

It is critical to understand human behavior in order to implement effective health-care policies for both developing and industrialized countries. Human behavior issues were studied in Ghana, with a developing economy, and South Korea, with a developed economy. From the survey research in Ghana in 2014, we learned that rural residents are heavily dependent on traditional health care. However, local community residents preferred to talk to medical doctors about their health care when accessible. We also looked into human behavior issues and the unique hospital culture in South Korea that contributed to the Middle East respiratory syndrome coronavirus (MERS-CoV) outbreak in 2015, incorporating human behavior into the SIR (susceptible-infected-recovered) model of infectious disease transmission. Moreover, we closely examined the impacts of human behavior and offered suggestions for the integration of human behavior in health-care policy.

No abstract

Ghana is a developing sub-Saharan country in West Africa and it struggles with delivering health care within the universal health system. The primary barrier to medical care is the lack of access. The government of Ghana subsidizes universal health insurance for all of its citizens, but lacks technology, workforce, and more importantly access to sanitation and clean running water. Access to health care remains a challenge in Ghana, especially in rural areas. In this research, we studied opinion leadership for health care in Ghana using two surveys conducted in May, 2014. Student investigators administered a survey to explore who was identified as the health care opinion leaders by local community members. The respondents were asked to rank seven categories of health care providers by how often they spoke to the health care provider about their health, from most often to least often , including medical doctors, chemical sellers, herbalists, prayer camps, family members, midwives and shrines or voodoo priests. The study surveyed 157 respondents from local community members, including 51 people in cities, 65 people in rural villages and 41 people in Kpanla, a remote isolated island on Lake Volta. Student investigators also gave a self-designating survey to 61 health care providers to measure their health care opinion leadership. The results of these two surveys were consistent. Local community residents preferred to talk to medical doctors about their health care when medical doctors were accessible. Health care providers’ responses to the self-designating opinion leadership survey supported their strong opinion leadership for health care.