While the opportunities of ML and AI in healthcare are promising, the growth of complex data-driven prediction models requires careful quality and applicability assessment before they are applied and disseminated in daily practice. This scoping review aimed to identify actionable guidance for those closely involved in AI-based prediction model (AIPM) development, evaluation and implementation including software engineers, data scientists, and healthcare professionals and to identify potential gaps in this guidance. We performed a scoping review of the relevant literature providing guidance or quality criteria regarding the development, evaluation, and implementation of AIPMs using a comprehensive multi-stage screening strategy. PubMed, Web of Science, and the ACM Digital Library were searched, and AI experts were consulted. Topics were extracted from the identified literature and summarized across the six phases at the core of this review: (1) data preparation, (2) AIPM development, (3) AIPM validation, (4) software development, (5) AIPM impact assessment, and (6) AIPM implementation into daily healthcare practice. From 2683 unique hits, 72 relevant guidance documents were identified. Substantial guidance was found for data preparation, AIPM development and AIPM validation (phases 1–3), while later phases clearly have received less attention (software development, impact assessment and implementation) in the scientific literature. The six phases of the AIPM development, evaluation and implementation cycle provide a framework for responsible introduction of AI-based prediction models in healthcare. Additional domain and technology specific research may be necessary and more practical experience with implementing AIPMs is needed to support further guidance.

Background: Poor adherence to continuous positive airway pressure (CPAP) treatment by adults with obstructive sleep apnea (OSA) is a common issue. Strategies delivered by means of information and communication technologies (ie, electronic health [eHealth]) can address treatment adherence through patient education, real-time monitoring of apnea symptoms and CPAP adherence in daily life, self-management, and early identification and subsequent intervention when device or treatment problems arise. However, the effectiveness of available eHealth technologies in improving CPAP adherence has not yet been systematically studied. Objective: This meta-analytic review was designed to investigate the effectiveness of a broad range of eHealth interventions in improving CPAP treatment adherence. Methods: We conducted a systematic literature search of the databases of Cochrane Library, PsycINFO, PubMed, and Embase to identify relevant randomized controlled trials in adult OSA populations. The risk of bias in included studies was examined using seven items of the Cochrane Collaboration risk-of-bias tool. The meta-analysis was conducted with comprehensive meta-analysis software that computed differences in mean postintervention adherence (MD), which was defined as the average number of nightly hours of CPAP use. Results: The meta-analysis ultimately included 18 studies (N=5429 adults with OSA) comprising 22 comparisons between experimental and control conditions. Postintervention data were assessed at 1 to 6 months after baseline, depending on the length of the experimental intervention. eHealth interventions increased the average nightly use of CPAP in hours as compared with care as usual (MD=0.54, 95% CI 0.29-0.79). Subgroup analyses did not reveal significant differences in effects between studies that used eHealth as an add-on or as a replacement to care as usual (P=.95), between studies that assessed stand-alone eHealth and blended strategies combining eHealth with face-to-face care (P=.23), or between studies of fully automated interventions and guided eHealth interventions (P=.83). Evidence for the long-term follow-up effectiveness of eHealth adherence interventions remains undecided owing to a scarcity of available studies and their mixed results. Conclusions: eHealth interventions for adults with OSA can improve adherence to CPAP in the initial months after the start of treatment, increasing the mean nightly duration of use by about half an hour. Uncertainty still exists regarding the timing, duration, intensity, and specific types of eHealth interventions that could be most effectively implemented by health care providers.

Background: Individuals with eating disorders show deficits in neuropsychological functioning which might preexist and underlie the etiology of the eating disorders and influence relapse. Deficits in cognitive flexibility, i.e. set-shifting and central coherence, might perpetuate the symptoms. Cognitive remediation therapy (CRT) was developed to improve cognitive flexibility, thereby increasing the likelihood of improved outcome. The focus of CRT is on how patients think, rather than on what patients think. The present study investigated the effectiveness of CRT for patients with a severe or enduring eating disorder by means of a randomized controlled trial comparing intensive treatment as usual (TAU) to CRT plus TAU. Methods: Eighty-two patients were randomly assigned to CRT plus TAU (n = 41) or TAU alone (n = 41). Outcome measures were set-shifting, central coherence, eating disorder and general psychopathology, motivation, quality of life and self-esteem. Assessments were performed at baseline (n = 82) and after 6 weeks (T1; n = 75) and 6 months (T2; n = 67). Data were analyzed by means of linear mixed model analyses. Results: Patients who received CRT in addition to TAU improved significantly more with regard to eating disorder-related quality of life at the end of treatment (T1) and eating disorder psychopathology at follow-up (T2), compared to those who received TAU only. Moreover, moderator analyses revealed that patients with poor baseline set-shifting abilities benefited more from CRT than patients with no deficits in set-shifting abilities at baseline; the quality of life of the former group was higher than that of the latter at follow-up. Conclusions: CRT seems to be promising in enhancing the effectiveness of concurrent treatment.

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet