A multinational study on artificial intelligence adoption: Clinical implementers' perspectives.

BACKGROUND: 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. OBJECTIVE: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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.

Artificial Intelligence Implementation in Healthcare: A Theory-Based Scoping Review of Barriers and Facilitators.

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.

De-Identifying Swedish EHR Text Using Public Resources in the General Domain.

Sensitive data is normally required to develop rule-based or train machine learning-based models for de-identifying electronic health record (EHR) clinical notes; and this presents important problems for patient privacy. In this study, we add non-sensitive public datasets to EHR training data; (i) scientific medical text and (ii) Wikipedia word vectors. The data, all in Swedish, is used to train a deep learning model using recurrent neural networks. Tests on pseudonymized Swedish EHR clinical notes showed improved precision and recall from 55.62% and 80.02% with the base EHR embedding layer, to 85.01% and 87.15% when Wikipedia word vectors are added. These results suggest that non-sensitive text from the general domain can be used to train robust models for de-identifying Swedish clinical text; and this could be useful in cases where the data is both sensitive and in low-resource languages.

Type 1 Diabetes in Twitter: Who All Listen To?

Knowing what the conversation on Twitter regarding type 1 diabetes (T1D) is about can help in understanding the kind of information relevant to the individuals affected by the disease. The profile of Twitter users posting on T1D was collected and classified. The number of re-tweets was also registered. The tweets posted by non-governmental organizations (NGOs), communication media, and individuals affected by T1D had higher number of potential readers. More than a half of the tweets were posted by individuals affected by T1D, and their tweets were the most re-tweeted. The next most active users were NGOs and healthcare professionals. However, while tweets soliciting for research funds posted by the NGOs were the next most re-tweeted messages, tweets posted by healthcare professionals were the least re-tweeted. Twitter could be used more actively by healthcare professionals to disseminate correct information about T1D.