This paper reviews applications of machine learning (ML) predictive models in the diagnosis of chronic diseases. Chronic diseases (CDs) are responsible for a major portion of global health costs. Patients who suffer from these diseases need lifelong treatment. Nowadays, predictive models are frequently applied in the diagnosis and forecasting of these diseases. In this study, we reviewed the state-of-the-art approaches that encompass ML models in the primary diagnosis of CD. This analysis covers 453 papers published between 2015 and 2019, and our document search was conducted from PubMed (Medline), and Cumulative Index to Nursing and Allied Health Literature (CINAHL) libraries. Ultimately, 22 studies were selected to present all modeling methods in a precise way that explains CD diagnosis and usage models of individual pathologies with associated strengths and limitations. Our outcomes suggest that there are no standard methods to determine the best approach in real-time clinical practice since each method has its advantages and disadvantages. Among the methods considered, support vector machines (SVM), logistic regression (LR), clustering were the most commonly used. These models are highly applicable in classification, and diagnosis of CD and are expected to become more important in medical practice in the near future.

Overweight and obesity are key risk factors of cardiovascular disease (CVD). Obesity is currently presented as a pro-inflammatory state with an expansion in the outflow of inflammatory cytokines, such as interleukin-6 (IL-6) and tumor necrosis factor-alpha (TNF-α), alongside the expanded emission of leptin. The present review aimed to evaluate the relationship between obesity and inflammation and their impacts on the development of cardiovascular disease. A literature search was conducted by employing three academic databases, namely PubMed (Medline), Scopus (EMBASE), and the Cumulative Index to Nursing and Allied Health Literature (CINAHL). The search presented 786 items, and by inclusion and exclusion filterers, 59 works were considered for final review. The Newcastle–Ottawa Scale (NOS) method was adopted to conduct quality assessment; 19 papers were further selected based on the quality score. Obesity-related inflammation leads to a low-grade inflammatory state in organisms by upregulating pro-inflammatory markers and downregulating anti-inflammatory cytokines, thereby contributing to cardiovascular disease pathogenesis. Because of inflammatory and infectious symptoms, adipocytes appear to instigate articulation and discharge a few intense stage reactants and carriers of inflammation. Obesity and inflammatory markers are strongly associated, and are important factors in the development of CVD. Hence, weight management can help prevent cardiovascular risks and poor outcomes by inhibiting inflammatory mechanisms.

Background: Internet represents a relevant source of information, but reliability of data that can be obtained by the web is still an unsolved issue. Non-reliable online information may have a relevance, especially in taking decisions related to health problems. Uncertainties on the quality of online health data may have a negative impact on health-related choices of citizens. Objective: This work consisted in a cross-sectional literature review of published papers on online health information. The two main research objectives consisted in the analysis of trends in the use of health web sites and in the quality assessment and reliability levels of web medical sites. Methods: Literature research was made using four digital reference databases, namely PubMed, British Medical Journal, Biomed, and CINAHL. Entries used were “trustworthy of medical information online,” “survey to evaluate medical information online,” “medical information online,” and “habits of web-based health information users”. Analysis included only papers published in English. The Newcastle Ottawa Scale was used to conduct quality checks of selected works. Results: Literature analysis using the above entries resulted in 212 studies. Twenty-four articles in line with study objectives, and user characteristics were selected. People more prone to use the internet for obtaining health information were females, younger people, scholars, and employees. Reliability of different online health sites is an issue taken into account by the majority of people using the internet for obtaining health information and physician assistance could help people to surf more safe health web sites. Conclusions: Limited health information and/or web literacy can cause misunderstandings in evaluating medical data found in the web. An appropriate education plan and evaluation tools could enhance user skills and bring to a more cautious analysis of health information found in the web.

(1) Background: Diabetes is a common chronic disease and a leading cause of death. Early diagnosis gives patients with diabetes the opportunity to improve their dietary habits and lifestyle and manage the disease successfully. Several studies have explored the use of machine learning (ML) techniques to predict and diagnose this disease. In this study, we conducted experiments to predict diabetes in Pima Indian females with particular ML classifiers. (2) Method: A Pima Indian diabetes dataset (PIDD) with 768 female patients was considered for this study. Different data mining operations were performed to a conduct comparative analysis of four different ML classifiers: Naïve Bayes (NB), J48, Logistic Regression (LR), and Random Forest (RF). These models were analyzed by different cross-validation (K = 5, 10, 15, and 20) values, and the performance measurements of accuracy, precision, F-score, recall, and AUC were calculated for each model. (3) Results: LR was found to have the highest accuracy (0.77) for all ‘k’ values. When k = 5, the accuracy of J48, NB, and RF was found to be 0.71, 0.76, and 0.75. For k = 10, the accuracy of J48, NB, and RF was found to be 0.73, 0.76, 0.74, while for k = 15, 20, the accuracy of NB was found to be 0.76. The accuracy of J48 and RF was found to be 0.76 when k = 15, and 0.75 when k = 20. Other parameters, such as precision, f-score, recall, and AUC, were also considered in evaluations to rank the algorithms. (4) Conclusion: The present study on PIDD sought to identify an optimized ML model, using with cross-validation methods. The AUC of LR was 0.83, RF 0.82, and NB 0.81). These three were ranked as the best models for predicting whether a patient is diabetic or not.

Background: Different studies showed that the use of telemedicine is effective in reducing hospital burden, suffering from patients, need of transports, hospital fear, save money and time, and increasing the quality of health care. However, the implementation of telemedicine countenances different challenges in developing countries generally and in Ethiopia, particularly. This review aims to evaluate barriers affecting sustainable telemedicine implementation in Ethiopia. Methods: PubMed (Medline), Google Scholar, Embase, and Scopus databases were searched between July 4, 2020 and July 28, 2020. Studies published between 2005 and June 30, 2020 were considered. Relevant articles were selected by reviewing keywords, titles, and abstracts. Out of 40 articles, 33 articles remained after removing duplicates. We finally analyzed 14 articles from the mentioned databases based on our eligibility criteria and identified different barriers. We followed the preferred reporting items for systematic review and meta-analyses (PRSIMA 2009) checklist for this review. Results: We identified 25 barriers through 14 articles and classified barriers into organizational, users, and staff and programmers' barriers. Accordingly, organizational, users, and staff and programmer barriers were 12 (48%), 7 (28%), and 6 (24%), respectively, with the frequency of occurrence through 14 articles. Cost, awareness, and resistance to change were the most frequently reported barriers among organizational, user, and staff and programmer barriers, respectively. Conclusions: Infrastructure and costs were the most frequently reported barriers, and staff resistance to change was also the critical factor in influencing the sustainable implementation of telemedicine in Ethiopia.

Introduction: Adverse effects on personalized care and outcomes of cardiovascular diseases (CVD) could occur if health systems do not work in an efficient manner. The pandemic caused by COVID-19 has opened new perspectives for the execution and advancement of cardiovascular tests through telemedicine platforms. Objective: This study aimed to analyze the usefulness of telemedical systems for providing personal care in the prevention of CVD. Methods: A systematic review analysis was conducted on the literature available from libraries such as PubMed (Medline), Scopus (Embase), and Cumulative Index to Nursing and Allied Health Literature (CINAHL). Data available in the last 10 years (2011–2020) were also examined by PRISMA guidelines. The selected studies were divided into two categories: (1) benefits of telemedicine in CVD prevention, and (2) recent progress in telemedical services for personalized care of CVD. Results: The literature search produced 587 documents, and 19 articles were considered in this review. Results highlighted that the timely delivery of preventive care for CVD which can be implemented virtually can benefit and modify morbidity and mortality. This could also reduce the pressure on hospitals by decreasing acute CVD occurrence among the general population. The use of these technologies can also help to reduce access to hospitals and other medical devices when not necessary. Conclusions: Telemedicine platforms can be used for regular checkups for CVD and contribute to preventing the occurrence of acute events and more in general the progression of CVD.