Search

Clinical investigators, health professionals and managers are often interested in developing criteria for clustering patients into clinically meaningful groups according to their expected length of stay. In this paper, we propose two novel types of survival trees; phase-type survival trees and mixed distribution survival trees, which extend previous work on exponential survival trees. The trees are used to cluster the patients with respect to length of stay where partitioning is based on covariates such as gender, age at the time of admission and primary diagnosis code. Likelihood ratio tests are used to determine optimal partitions. The approach is illustrated using nationwide data available from the English Hospital Episode Statistics (HES) database on stroke-related patients, aged 65 years and over, who were discharged from English hospitals over a 1-year period. [ABSTRACT FROM AUTHOR]

Background: Little is known about the burden of parkinsonism and Parkinson's disease (PD) in Latin America. Better understanding of health service use and clinical outcomes in PD is needed to improve its prognosis. Objective: The aim of the study was to estimate the burden of parkinsonism and PD in six Latin American countries. Methods: 12,865 participants aged 65 years and older from the 10/66 population-based cohort study were analysed. Baseline assessments were conducted in 2003–2007 and followed-up 4 years later. Parkinsonism and PD were defined using current clinical criteria or self-reported diagnosis. Logistic regression models assessed the association between parkinsonism/PD with baseline health service use (community-based care or hospitalisation in the last 3 months) and Cox proportional hazards regression models with incident dependency (subjective assessment by interviewer based on informant interview) and mortality. Separate analyses for each country were combined via fixed effect meta-analysis. Results: At baseline, the prevalence of parkinsonism and PD was 7.9% (n = 934) and 2.6% (n = 317), respectively. Only parkinsonism was associated with hospital admission at baseline (OR 1.89, 95% CI 1.30–2.74). Among 7,296 participants without dependency at baseline, parkinsonism (HR 2.34, 95% CI 1.81–3.03) and PD (2.10, 1.37–3.24) were associated with incident dependency. Among 10,315 participants with vital status, parkinsonism (1.73, 1.50–1.99) and PD (1.38, 1.07–1.78) were associated with mortality. The Higgins I2 tests showed low to moderate levels of heterogeneity across countries. Conclusions: Our findings show that older people with parkinsonism or PD living in Latin America have higher risks of developing dependency and mortality but may have limited access to health services. [ABSTRACT FROM AUTHOR]

Healthcare has seen many advances in sensor technology, but with recent improvements in networks and the addition of the Internet of Things, it is even more promising. Current solutions to managing healthcare data with cloud computing may be unreliable at the most critical moments. High response latency, large volumes of data, and security are the main issues of this approach. The promising solution is fog computing, which offers an immediate response resistant to disconnections and ways to process big data using real-time analytics and artificial intelligence (AI). However, fog computing has not yet matured and there are still many challenges. This article presents for a computer scientist a systematic review of the literature on fog computing in healthcare. Articles published in six years are analysed from the service, software, hardware, information technologies and mobility with autonomy perspectives. The contribution of this study includes an analysis of recent trends, focus areas and benefits of the use of AI techniques in fog computing e-health applications. [ABSTRACT FROM AUTHOR]

Due to the increasing importance of evaluating the quality of health care services using the patient-centred approach, this study aimed to propose a novel framework by combining the SERVQUAL model and multi-attribute decision-making (MADM) methods using interval-valued triangular fuzzy numbers (IVTFN). In this study, after an initial overview of related work and expert opinions, a list of the most important dimensions and indicators for measuring the quality of health care services was extracted and localized. Then, to determine the importance of each of the identified factors, one of MADM's acceptable methods called step-wise weight assessment ratio analysis (SWARA) was used. Then, in order to use the developed framework for comparing different health centres and ranking them, after collecting evaluation data in the form of linguistic variables, another practical method in the field of MADM has been used, namely, Additive Ratio Assessment (ARAS) method. The dimensions and sub-dimensions identified are, on the one hand, appropriate to the conditions of the case study and, on the other hand, the findings from the implementation show that among the dimensions of health service quality, responsiveness and then reliability has the highest rank in this case. Also, the use of IVTFN, on the one hand, eliminates the problems related to the use of Likert scale in other quality assessment methods and, on the other hand, reduces the possibility of facing imperfect knowledge of data which is a common problem in the field of qualitative evaluations. Utilizing the results of this study can significantly help decision makers in their choice of strategies to improve service quality. Furthermore, improving the quality of services can play an important role in promoting the competitiveness and performance of health care providers by increasing patient satisfaction with the services received. Also, as a side effect, the developed framework can be used to compare the performance of different hospitals and health centres, as well as their ranking. [ABSTRACT FROM AUTHOR]

Blockchain is gaining traction for improving the security of healthcare applications, however, it does not become a silver bullet as various security threats are observed in blockchain-based applications. Moreover, when performing the security risk management (SRM) of blockchain-based applications, there are conceptual ambiguities and semantic gaps that hinder from treating the security threats effectively. To address these issues, we present a blockchain-based healthcare security ontology (HealthOnt) that offers coherent and formal information models to treat security threats of traditional and blockchain-based applications. We evaluate the ontology by performing the SRM of a back-pain patient's healthcare application case. The results show that HealthOnt can support the iterative process of SRM and can be continually updated when new security threats, vulnerabilities, or countermeasures emerge. In addition, the HealthOnt may assist in the modelling and analysis of real-world situations while addressing important security concerns from the perspective of stakeholders. This work can help blockchain developers, practitioners, and other associated stakeholders to develop secure blockchain-based healthcare applications in the early stages. [ABSTRACT FROM AUTHOR]