Quality, Usability, and Effectiveness of mHealth Apps and the Role of Artificial Intelligence: Current Scenario and Challenges.

The use of artificial intelligence (AI) and big data in medicine has increased in recent years. Indeed, the use of AI in mobile health (mHealth) apps could considerably assist both individuals and health care professionals in the prevention and management of chronic diseases, in a person-centered manner. Nonetheless, there are several challenges that must be overcome to provide high-quality, usable, and effective mHealth apps. Here, we review the rationale and guidelines for the implementation of mHealth apps and the challenges regarding quality, usability, and user engagement and behavior change, with a special focus on the prevention and management of noncommunicable diseases. We suggest that a cocreation-based framework is the best method to address these challenges. Finally, we describe the current and future roles of AI in improving personalized medicine and provide recommendations for developing AI-based mHealth apps. We conclude that the implementation of AI and mHealth apps for routine clinical practice and remote health care will not be feasible until we overcome the main challenges regarding data privacy and security, quality assessment, and the reproducibility and uncertainty of AI results. Moreover, there is a lack of both standardized methods to measure the clinical outcomes of mHealth apps and techniques to encourage user engagement and behavior changes in the long term. We expect that in the near future, these obstacles will be overcome and that the ongoing European project, Watching the risk factors (WARIFA), will provide considerable advances in the implementation of AI-based mHealth apps for disease prevention and health promotion.

How well is the electronic health record supporting the clinical tasks of hospital physicians? A survey of physicians at three Norwegian hospitals.

BACKGROUND: The electronic health record is expected to improve the quality and efficiency of health care. Many novel functionalities have been introduced in order to improve medical decision making and communication between health care personnel. There is however limited evidence on whether these new functionalities are useful. The aim of our study was to investigate how well the electronic health record system supports physicians in performing basic clinical tasks. METHODS: Physicians of three prominent Norwegian hospitals participated in the survey. They were asked, in an online questionnaire, how well the hospital's electronic health record system DIPS supported 49 clinical tasks as well as how satisfied they were with the system in general, including the technical performance. Two hundred and eight of 402 physicians (52%) submitted a completely answered questionnaire. RESULTS: Seventy-two percent of the physicians had their work interrupted or delayed because the electronic health record hangs or crashes at least once a week, while 22% had experienced this problem daily. Fifty-three percent of the physicians indicated that the electronic health record is cumbersome to use and adds to their workload. The majority of physicians were satisfied with managing tests, e.g., requesting laboratory tests, reading test results and managing radiological investigations and electrocardiograms. Physicians were less satisfied with managing referrals. There was high satisfaction with some of the decision support functionalities available for prescribing drugs. This includes drug interaction alerts and drug allergy warnings, which are displayed automatically. However, physicians were less satisfied with other aspects of prescribing drugs, including getting an overview of the ongoing drug therapy. CONCLUSIONS: In the survey physicians asked for improvements of certain electronic health record functionalities like medication, clinical workflow support including planning and better overviews. In addition, there is apparently a need to focus on system stability, number of logins, reliability and better instructions on available electronic health record features. Considerable development is needed in current electronic health record systems to improve usefulness and satisfaction.

Methods to Evaluate the Effects of Internet-Based Digital Health Interventions for Citizens: Systematic Review of Reviews.

BACKGROUND: Digital health can empower citizens to manage their health and address health care system problems including poor access, uncoordinated care and increasing costs. Digital health interventions are typically complex interventions. Therefore, evaluations present methodological challenges. OBJECTIVE: The objective of this study was to provide a systematic overview of the methods used to evaluate the effects of internet-based digital health interventions for citizens. Three research questions were addressed to explore methods regarding approaches (study design), effects and indicators. METHODS: We conducted a systematic review of reviews of the methods used to measure the effects of internet-based digital health interventions for citizens. The protocol was developed a priori according to Preferred Reporting Items for Systematic review and Meta-Analysis Protocols and the Cochrane Collaboration methodology for overviews of reviews. Qualitative, mixed-method, and quantitative reviews published in English or French from January 2010 to October 2016 were included. We searched for published reviews in PubMed, EMBASE, The Cochrane Database of Systematic Reviews, CINHAL and Epistemonikos. We categorized the findings based on a thematic analysis of the reviews structured around study designs, indicators, types of interventions, effects and perspectives. RESULTS: A total of 20 unique reviews were included. The most common digital health interventions for citizens were patient portals and patients' access to electronic health records, covered by 10/20 (50%) and 6/20 (30%) reviews, respectively. Quantitative approaches to study design included observational study (15/20 reviews, 75%), randomized controlled trial (13/20 reviews, 65%), quasi-experimental design (9/20 reviews, 45%), and pre-post studies (6/20 reviews, 30%). Qualitative studies or mixed methods were reported in 13/20 (65%) reviews. Five main categories of effects were identified: (1) health and clinical outcomes, (2) psychological and behavioral outcomes, (3) health care utilization, (4) system adoption and use, and (5) system attributes. Health and clinical outcomes were measured with both general indicators and disease-specific indicators and reported in 11/20 (55%) reviews. Patient-provider communication and patient satisfaction were the most investigated psychological and behavioral outcomes, reported in 13/20 (65%) and 12/20 (60%) reviews, respectively. Evaluation of health care utilization was included in 8/20 (40%) reviews, most of which focused on the economic effects on the health care system. CONCLUSIONS: Although observational studies and surveys have provided evidence of benefits and satisfaction for patients, there is still little reliable evidence from randomized controlled trials of improved health outcomes. Future evaluations of digital health interventions for citizens should focus on specific populations or chronic conditions which are more likely to achieve clinically meaningful benefits and use high-quality approaches such as randomized controlled trials. Implementation research methods should also be considered. We identified a wide range of effects and indicators, most of which focused on patients as main end users. Implications for providers and the health system should also be included in evaluations or monitoring of digital health interventions.