Purpose: This review aims to summarize and evaluate the most accurate machine-learning algorithm used to predict ischemic heart disease. Methods: This systematic review was performed following PRISMA guidelines. A comprehensive search was carried out using multiple databases such as Science Direct, PubMed\ MEDLINE, CINAHL, and IEEE explore. Results: Thirteen articles published between 2017 to 2021 were eligible for inclusion. Three themes were extracted: the commonly used algorithm to predict ischemic heart disease, the accuracy of algorithms to predict ischemic heart disease, and the clinical outcomes to improve the quality of care. All methods have utilized supervised and unsupervised machine-learning. Conclusion: Applying machine-learning is expected to assist clinicians in interpreting patients’ data and implementing optimal algorithms for their datasets. Furthermore, machine-learning can build evidence-based that support health care providers to manage individual situations who need invasive procedures such as catheterizations.

Purpose This study aims to assess the quality of life (QOL) and the related factors in patients post-stroke in Jordan. Design/methodology/approach Prospective, the cross-sectional study recruited 100 participants with stroke from three public hospitals from December 1, 2021 to February 1, 2022. Patients with stroke were interviewed to fill the stroke-specific quality of life questionnaire. Findings Forty-five per cent of the participants were male. More than half of the participants (53%) were married, and the average age of the participants was 63.6 (SD =3.8). Most of the participants had an ischemic stroke (86%) with an affected left side (65%). The overall QOL of the participants was leveling at (M = 123.5, SD = 45.2), which is a moderate level. It was found statistical significance differences among participants according to gender, type of stroke, affected side and presence of comorbidities (Table 1). Research limitations/implications There were some limitations in this study. First, this study was based on mild to moderate Jordanian stroke survivors and did not include critically ill stroke survivors; the QOL critically ill stroke survivors may differ, which could affect the generalizability of data among all stroke survivors. Second, this study is prospective, and this type of study is prone to bias that could influence the reliability of the results. It is recommended to conduct a mixed-method study to reveal an in-depth understanding of the associated factors with QOL, to ensure reliability and to reflect a better view of the Jordanian population. Practical implications To sum up, there is a reduction in the level of QOL among stroke survivors; hence, it is crucial to focus on detecting factors contributing to reducing the QOL and taking individual differences between sexes, type and location of the stroke, and comorbidities into consideration to develop a treatment plan that enhances the QOL and well-being for survivors of stroke. Social implications Taking individual differences between sexes, type and location of the stroke and comorbidities into consideration to develop a treatment plan that enhances the QOL and well-being of survivors of stroke. Originality/value The findings of this study bring a strong insight toward assessing the main factors indicating a decrease QOL among stroke survivors.

Background: Diabetes is an endocrine chronic condition with a high prevalence rate among the population that needs a complex management process. However, many advanced health care technologies were evolving to help patients to achieve their centered care and self-management using real-time proactive techniques through interactive systems to detect early complications and prevent them. the purpose of the current review is to assess the findings of literature reviews of the main interventions that used a real-time partially automated interactive systems to interpret patient’s data including biological information, exercise, and dietary content calculated from a message sent by the patient and respond with actionable findings, helping patients to achieve diabetes self-management. Methods: PubMed\ MEDLINE, CINAHL, Google Scholar, and Research Gate were used to search the literature for studies published between the periods 2015 to 2021. Results: Eleven articles were included in the literature review. The retrieved studies approved the significant effect of achieving diabetic self-management by utilizing Information Technology [IT] with the Natural Language Processing [NLP] methods by sending a real-time, partially automated interactive system to interpret patient's biological information, physical activity, and dietary content calculated using a message sent by patients to achieve their self-management. Conclusion: Improved blood glucose levels, glycemic control, better readings of blood pressure, and lifestyle improvement including dietary intake and physical activity were offered using continuous real-time massages to improve their health outcomes.

No abstract