METHODS: The most important climatic factors that contribute to dengue outbreaks were identified in the current work. Correlation analyses were performed in order to determine these factors and these factors were used as input parameters for machine learning models. Top five machine learning classification models (Bayes network (BN) models, support vector machine (SVM), RBF tree, decision table and naive Bayes) were chosen based on past research. The models were then tested and evaluated on the basis of 4-year data (January 2010 to December 2013) collected in Malaysia.
RESULTS: This research has two major contributions. A new risk factor, called the TempeRain factor (TRF), was identified and used as an input parameter for the model of dengue outbreak prediction. Moreover, TRF was applied to demonstrate its strong impact on dengue outbreaks. Experimental results showed that the Bayes Network model with the new meteorological risk factor identified in this study increased accuracy to 92.35% for predicting dengue outbreaks.
CONCLUSIONS: This research explored the factors used in dengue outbreak prediction systems. The major contribution of this study is identifying new significant factors that contribute to dengue outbreak prediction. From the evaluation result, we obtained a significant improvement in the accuracy of a machine learning model for dengue outbreak prediction.
METHOD: This paper is motivated by the gap in the literature, thus proposes an algorithm that measures the strength of the significant features that contribute to heart disease prediction. The study is aimed at predicting heart disease based on the scores of significant features using Weighted Associative Rule Mining.
RESULTS: A set of important feature scores and rules were identified in diagnosing heart disease and cardiologists were consulted to confirm the validity of these rules. The experiments performed on the UCI open dataset, widely used for heart disease research yielded the highest confidence score of 98% in predicting heart disease.
CONCLUSION: This study managed to provide a significant contribution in computing the strength scores with significant predictors in heart disease prediction. From the evaluation results, we obtained important rules and achieved highest confidence score by utilizing the computed strength scores of significant predictors on Weighted Associative Rule Mining in predicting heart disease.
METHODS: A literature review of current studies addressing patients' views on HIE from 2005 was undertaken. Five electronic research databases (Science Direct, PubMed, Web of Science, CINAHL, and Academic Search Premiere) were searched to retrieve articles reporting pros and cons of HIE from patients' opinion.
RESULTS: One hundred and ninety six articles were initially retrieved from the databases. Out of 196, 36 studies met the inclusion criteria and were fully reviewed. Our findings indicate that patient's attitude toward HIE is affected by seven main factors: perceived benefits, perceived concerns, patient characteristics, patient participation level in HIE, type of health information, identity of recipients, and patient preferences regarding consent and features.
CONCLUSIONS: The findings provide useful theoretical implications for research by developing a classification of significant factors and a framework based on the lessons learned from the literature to help guide HIE efforts. Our results also have fundamental practical implications for policy makers, current and potential organizers of HIEs by highlighting the role of patients in the widespread implementation of HIE. The study indicates that new approaches should be applied to completely underline HIE benefits for patients and also address their concerns.
METHODS: After the development of 12 hypotheses, a quantitative, cross-sectional, self-administered survey method was applied to collect data in 9 hospitals in Iran. After the collection of 382 usable questionnaires, the partial least square structural modeling was applied to examine the hypotheses and it was found that 11 hypotheses were empirically supported.
RESULTS: The results suggest that patients' trust in hospitals can significantly predict their perceived security but no significant associations were found between patients' physical protection mechanisms in the hospital and their perceived information security in a hospital. We also found that patients' perceptions about the physical protection mechanism of a hospital can significantly predict their trust in hospitals which is a novel finding by this research.
CONCLUSIONS: The findings imply that hospitals should formulate policies to improve patients' perception about such factors, which ultimately lead to their perceived security.
METHODS: A large hospital-based breast cancer dataset retrieved from the University Malaya Medical Centre, Kuala Lumpur, Malaysia (n = 8066) with diagnosis information between 1993 and 2016 was used in this study. The dataset contained 23 predictor variables and one dependent variable, which referred to the survival status of the patients (alive or dead). In determining the significant prognostic factors of breast cancer survival rate, prediction models were built using decision tree, random forest, neural networks, extreme boost, logistic regression, and support vector machine. Next, the dataset was clustered based on the receptor status of breast cancer patients identified via immunohistochemistry to perform advanced modelling using random forest. Subsequently, the important variables were ranked via variable selection methods in random forest. Finally, decision trees were built and validation was performed using survival analysis.
RESULTS: In terms of both model accuracy and calibration measure, all algorithms produced close outcomes, with the lowest obtained from decision tree (accuracy = 79.8%) and the highest from random forest (accuracy = 82.7%). The important variables identified in this study were cancer stage classification, tumour size, number of total axillary lymph nodes removed, number of positive lymph nodes, types of primary treatment, and methods of diagnosis.
CONCLUSION: Interestingly the various machine learning algorithms used in this study yielded close accuracy hence these methods could be used as alternative predictive tools in the breast cancer survival studies, particularly in the Asian region. The important prognostic factors influencing survival rate of breast cancer identified in this study, which were validated by survival curves, are useful and could be translated into decision support tools in the medical domain.
METHODS: A scoping review was carried out. The Google Play Store and Apple App Store were searched for mobile apps, using search terms derived from the UK Royal College of General Practitioners (RCGP) guideline on GPs' core capabilities and competencies. A manual search was also performed to identify additional apps.
RESULTS: The final analysis included 17 apps from the Google Play Store and Apple App Store, and 21 apps identified by the manual search. mHealth apps were found to have the potential to replace GPs for tasks such as recording medical history and making diagnoses; performing some physical examinations; supporting clinical decision making and management; assisting in urgent, long-term, and disease-specific care; and health promotion. In contrast, mHealth apps were unable to perform medical procedures, appropriately utilise other professionals, and coordinate a team-based approach.
CONCLUSIONS: This scoping review highlights the functions of mHealth apps that can potentially replace GP tasks. Future research should focus on assessing the performance and quality of mHealth apps in comparison with that of real doctors.
RESULT: We tested Naive Bayes, Logistic Regression, KNN, J48, Random Forest, SVM, and Deep Neural Network algorithms to ASD screening dataset and compared the classifiers' based on significant parameters; sensitivity, specificity, accuracy, receiver operating characteristic, area under the curve, and runtime, in predicting ASD occurrences. We also found that most of previous studies focused on classifying health-related dataset while ignoring the missing values which may contribute to significant impacts to the classification result which in turn may impact the life of the patients. Thus, we addressed the missing values by implementing imputation method where they are replaced with the mean of the available records found in the dataset.
CONCLUSION: We found that J48 produced promising results as compared to other classifiers when tested in both circumstances, with and without missing values. Our findings also suggested that SVM does not necessarily perform well for small and simple datasets. The outcome is hoped to assist health practitioners in making accurate diagnosis of ASD occurrences in patients.
METHODS: We recruited eligible adults from the Klang Asthma Cohort registry in primary care for a 3-month mixed-method study plus a 2-month extended observation. We collected baseline data on socio-demography, health literacy and asthma control level. The outcomes of the intervention were assessed at 1- and 3-month: i) adoption (app download and usage), ii) adherence (app usage), iii) retention (app usage in the observation period), iv) health outcomes (e.g., severe asthma attacks) and v) process outcomes (e.g., ownership and use of action plans). At 1-month, participants were purposively sampled for in-depth interviews, which were audio-recorded, transcribed verbatim, and analysed deductively.
RESULTS: We recruited 48 participants; 35 participants (23 Female; median age = 43 years; median HLS score = 28) completed the 3 months study. Of these, 14 participants (10 Female; median age = 48 years; median HLS score = 28) provided interviews. Thirty-seven (77%) participants adopted the app (downloaded and used it in the first month of the study). The main factor reported as influencing adoption was the ease of using the app. A total of 950 app usage were captured during the 3-month feasibility study. App usage increased gradually, peaking at month 2 (355 total log-ins) accounting for 78% of users. In month 5, 51.4% of the participants used the app at least once. The main factors influencing continued use included adherence features (e.g., prompts and reminders), familiarity with app function and support from family members.
CONCLUSIONS: An asthma self-management app intervention was acceptable for adults with limited health literacy and it was feasible to collect the desired outcomes at different time points during the study. A future trial is warranted to estimate the clinical and cost-effectiveness of the intervention and to explore implementation strategies.
OBJECTIVE: This systematic review and meta-analysis aimed to determine the effectiveness of mobile applications on medication adherence, functional outcomes, cardiovascular risk factors, quality of life and knowledge on stroke in stroke survivors.
METHODS: A review of the literature was conducted using key search terms in PubMed, EMBASE, Cochrane and Web of Science databases until 16 March 2023 to identify eligible randomized controlled trials (RCTs) or controlled clinical trial (CCTs) of mobile application interventions among stroke survivors. Two reviewers independently screened the literature in accordance with the eligibility criteria and collected data from the articles included. Outcomes included medication adherence,functional outcomes,cardiovascular risk factors, quality of life,and knowledge of stroke.
RESULTS: Twenty-three studies involving 2983 participants across nine countries were included in this review. Sixteen trials involved health care professionals in app use, and seven trials reported measures to ensure app-based intervention adherence. Mobile applications targeting stroke survivors primarily encompassed three areas: rehabilitation, education and self-care. The participants in the studies primarily included young and middle-aged stroke survivors. Meta-analysis results demonstrated that mobile application intervention significantly improved trunk control ability (mean differences [MD] 3.00, 95% CI [1.80 to 4.20]; P
METHODS: Convenience sampling was employed for data collection in three government hospitals for 7 months. A standardized effectiveness survey for EHR systems was administered to primary health care providers (specialists, medical officers, and nurses) as they participated in medical education programs. Empirical data were assessed by employing partial least squares-structural equation modeling for hypothesis testing.
RESULTS: The results demonstrated that knowledge quality had the highest score for predicting performance and had a large effect size, whereas system compatibility was the most substantial system quality component. The findings indicated that EHR systems supported the clinical tasks and workflows of care providers, which increased system quality, whereas the increased quality of knowledge improved user performance.
CONCLUSION: Given these findings, knowledge quality and effective use should be incorporated into evaluating EHR system effectiveness in health institutions. Data mining features can be integrated into current systems for efficiently and systematically generating health populations and disease trend analysis, improving clinical knowledge of care providers, and increasing their productivity. The validated survey instrument can be further tested with empirical surveys in other public and private hospitals with different interoperable EHR systems.
METHODS: In this infodemiological study, the Google, Yahoo!, and Bing search engines were searched using specific Arabic terms on periodontal disease. The first 100 consecutive websites from each engine were obtained. The eligible websites were categorized as commercial, health/professional, journalism, and other. The following tools were applied to assess the quality of the information on the included websites: the Health on the Net Foundation Code of Conduct (HONcode), the Journal of the American Medical Association (JAMA) benchmarks, and the DISCERN tool. The readability was assessed using an online readability tool.
RESULTS: Of the 300 websites, 89 were eligible for quality and readability analyses. Only two websites (2.3%) were HONcode certified. Based on the DISCERN tool, 43 (48.3%) websites had low scores. The mean score of the JAMA benchmarks was 1.6 ± 1.0, but only 3 (3.4%) websites achieved "yes" responses for all four JAMA criteria. Based on the DISCERN tool, health/professional websites revealed the highest quality of information compared to other website categories. Most of the health/professional websites revealed moderate-quality information, while 55% of the commercial websites, 66% of journalism websites, and 43% of other websites showed poor quality information. Regarding readability, most of the analyzed websites presented simple and readable written content.
CONCLUSIONS: Aside from readable content, Arabic health information on the analyzed websites on periodontal disease is below the required level of quality.