There is a large proliferation of complex data-driven artificial intelligence (AI) applications in many aspects of our daily lives, but their implementation in healthcare is still limited. This scoping review takes a theoretical approach to examine the barriers and facilitators based on empirical data from existing implementations. We searched the major databases of relevant scientific publications for articles related to AI in clinical settings, published between 2015 and 2021. Based on the theoretical constructs of the Consolidated Framework for Implementation Research (CFIR), we used a deductive, followed by an inductive, approach to extract facilitators and barriers. After screening 2784 studies, 19 studies were included in this review. Most of the cited facilitators were related to engagement with and management of the implementation process, while the most cited barriers dealt with the intervention’s generalizability and interoperability with existing systems, as well as the inner settings’ data quality and availability. We noted per-study imbalances related to the reporting of the theoretic domains. Our findings suggest a greater need for implementation science expertise in AI implementation projects, to improve both the implementation process and the quality of scientific reporting.

Computerised clinical decision support (CDS) can potentially better inform decisions, and it can help with the management of information overload. It is perceived to be a key component of a learning health care system. Despite its increasing implementation worldwide, it remains uncertain why the effect of CDS varies and which factors make CDS more effective. To examine which factors make CDS strategies more effective on a number of outcomes, including adherence to recommended practice, patient outcome measures, economic measures, provider or patient satisfaction, and medical decision quality. We identified randomised controlled trials, non-randomised trials, and controlled before-and-after studies that directly compared CDS implementation with a given factor to CDS without that factor by searching CENTRAL, MEDLINE, EMBASE, and CINAHL and checking reference lists of relevant studies. We considered CDS with any objective for any condition in any healthcare setting. We included CDS interventions that were either displayed on screen or provided on paper and that were directed at healthcare professionals or targeted at both professionals and patients. The reviewers screened the potentially relevant studies in duplicate. They extracted data and assessed risk of bias in independent pairs or individually followed by a double check by another reviewer. We summarised results using medians and interquartile ranges and rated our certainty in the evidence using the GRADE system. We identified 66 head-to-head trials that we synthesised across 14 comparisons of CDS intervention factors. Providing CDS automatically versus on demand led to large improvements in adherence. Displaying CDS on-screen versus on paper led to moderate improvements and making CDS more versus less patient-specific improved adherence modestly. When CDS interventions were combined with professional-oriented strategies, combined with patient-oriented strategies, or combined with staff-oriented strategies, then adherence improved slightly. Providing CDS to patients slightly increased adherence versus CDS aimed at the healthcare provider only. Making CDS advice more explicit and requiring users to respond to the advice made little or no difference. The CDS intervention factors made little or no difference to patient outcomes. The results for economic outcomes and satisfaction outcomes were sparse. Multiple factors may affect the success of CDS interventions. CDS may be more effective when the advice is provided automatically and displayed on-screen and when the suggestions are more patient-specific. CDS interventions combined with other strategies probably also improves adherence. Providing CDS directly to patients may also positively affect adherence. The certainty of the evidence was low to moderate for all factors. PROSPERO, CRD42016033738

Background: The internet is being widely used for seeking health information. However, there is no consensus on the association between health information seeking on the internet and the use of health care services. Objective: We examined the association between health information seeking via the internet and physician visits. In addition, we investigated the association between online health information seeking and the decisions to visit and not to visit a physician. Methods: We used the cross-sectional electronic health (eHealth) data of 18,197 participants from the seventh survey of the Tromsø Study (Tromsø 7). The participants were aged ≥40 years and living in Tromsø, Norway. We used logistic regression models to examine the association between online health information seeking and physician visits, the decision to visit a physician, and the decision not to visit a physician, with adjustment for the demographic status, socioeconomic status, and health status of the participants. Results: The use of Web search engines was associated with a physician visit. However, the association was moderated by age, and the OR decreased as age increased. The ORs for the use of Web search engines were 1.99 (95% CI 1.94-2.02) and 1.07 (95% CI 1.03-1.12) at ages 40 and 80 years, respectively. The decision to visit a physician was associated with the use of Web search engines (OR 2.95, 95% CI 2.03-4.46), video search engines (OR 1.43, 95% CI 1.21-1.70), and health apps (OR 1.26, 95% CI 1.13-1.42). The association between social media use and the decision to visit a physician was moderated by gender. Women who used social media had 1.42 (95% CI 1.31-1.55) times higher odds of deciding to visit a physician, whereas the decision to visit a physician was not different between men who used social media and those who did not use social media. Conversely, the decision not to visit a physician was associated with the use of Web search engines (OR 2.78, 95% CI 1.92-4.18), video search engines (OR 1.27, 95% CI 1.07-1.51), social media (OR 1.28, 95% CI 1.10-1.49), and health apps (OR 1.20, 95% CI 1.07-1.35). Conclusions: Health information found on the internet was positively associated with both the decision to visit a physician and the decision not to visit a physician. However, the association of health information seeking with the decision to visit a physician was slightly stronger than the association with the decision not to visit a physician. This could imply that the use of eHealth services is associated with a resultant increase in physician visits. In summary, our findings suggest that the internet serves as a supplement to health care services rather than as a replacement.

Despite substantial progress in AI research for healthcare, translating research achievements to AI systems in clinical settings is challenging and, in many cases, unsatisfactory. As a result, many AI investments have stalled at the prototype level, never reaching clinical settings. To improve the chances of future AI implementation projects succeeding, we analyzed the experiences of clinical AI system implementers to better understand the challenges and success factors in their implementations. Thirty-seven implementers of clinical AI from European and North and South American countries were interviewed. Semi-structured interviews were transcribed and analyzed qualitatively with the framework method, identifying the success factors and the reasons for challenges as well as documenting proposals from implementers to improve AI adoption in clinical settings. We gathered the implementers' requirements for facilitating AI adoption in the clinical setting. The main findings include 1) the lesser importance of AI explainability in favor of proper clinical validation studies, 2) the need to actively involve clinical practitioners, and not only clinical researchers, in the inception of AI research projects, 3) the need for better information structures and processes to manage data access and the ethical approval of AI projects, 4) the need for better support for regulatory compliance and avoidance of duplications in data management approval bodies, 5) the need to increase both clinicians' and citizens' literacy as respects the benefits and limitations of AI, and 6) the need for better funding schemes to support the implementation, embedding, and validation of AI in the clinical workflow, beyond pilots. Participants in the interviews are positive about the future of AI in clinical settings. At the same time, they proposenumerous measures to transfer research advancesinto implementations that will benefit healthcare personnel. Transferring AI research into benefits for healthcare workers and patients requires adjustments in regulations, data access procedures, education, funding schemes, and validation of AI systems.