RESUMO
Context: The technological advancement of the Internet of Things (IoT) creates opportunities in various social sectors. Patients in clinics or home care have their comfort and safety enhanced with remote monitoring, sensors and applications that control and transfer patient data. These applications must be trustworthy, since they deal with sensitive data. Purpose: The purpose of this work is to identify gaps in trustworthiness, availability, effectiveness, security and other attributes. Also, to highlight challenges and opportunities for research and give guidance on choosing the right technology or application based on the resources available to support patients and doctors, protocol of communication and maturity level of these technologies. Methodology: This work presents a systematic review of the literature following four steps: Definition of the Research Questions, Conduct Search, Screening of Papers, and Data Extraction and Mapping Process. Results: Based on the articles studied, it was possible to answer important questions about eHealth applications. The results highlight how eHealth applications can enhance patient care by monitoring health data and supporting doctors' decision-making with a reasonable level of trustworthiness. Additionally, the results demonstrate how applications can notify external caregivers in emergencies and assist in diagnosis and treatment of illnesses. However, these applications still face problems related to sensor lifetime, medical data sharing, interoperability and lack of standardization. Finally, we suggest a literature mapping to support the choice of technologies based on resources available, communication protocol and technological maturity. Conclusion: This work carries out a systematic literature review to discuss state-of-the-art eHealth applications and gather new information of current research. In this process it was possible to show how these applications work, map out their main technological characteristics to assist the decision-making process for future works and uncover eHealth applications' strengths, future perspectives and challenges, specifically related to the high level of trustworthiness necessary.
RESUMO
Autism Spectrum Disorder (ASD) diagnosis is still based on behavioral criteria through a lengthy and time-consuming process. Much effort is being made to identify brain imaging biomarkers and develop tools that could facilitate its diagnosis. In particular, using Machine Learning classifiers based on resting-state fMRI (rs-fMRI) data is promising, but there is an ongoing need for further research on their accuracy and reliability. Therefore, we conducted a systematic review and meta-analysis to summarize the available evidence in the literature so far. A bivariate random-effects meta-analytic model was implemented to investigate the sensitivity and specificity across the 55 studies that offered sufficient information for quantitative analysis. Our results indicated overall summary sensitivity and specificity estimates of 73.8% and 74.8%, respectively. SVM stood out as the most used classifier, presenting summary estimates above 76%. Studies with bigger samples tended to obtain worse accuracies, except in the subgroup analysis for ANN classifiers. The use of other brain imaging or phenotypic data to complement rs-fMRI information seems promising, achieving higher sensitivities when compared to rs-fMRI data alone (84.7% versus 72.8%). Finally, our analysis showed AUC values between acceptable and excellent. Still, given the many limitations indicated in our study, further well-designed studies are warranted to extend the potential use of those classification algorithms to clinical settings.