Challenges of developing artificial intelligence‐assisted tools for clinical medicine

Abstract

Machine learning, a subset of artificial intelligence (AI), is a set of computational tools that can be used to enhance provision of clinical care in all areas of medicine. Gastroenterology and hepatology utilize multiple sources of information, including visual findings on endoscopy, radiologic imaging, manometric testing, genomes, proteomes, and metabolomes. However, clinical care is complex and requires a thoughtful approach to best deploy AI tools to improve quality of care and bring value to patients and providers. On the operational level, AI‐assisted clinical management should consider logistic challenges in care delivery, data management, and algorithmic stewardship. There is still much work to be done on a broader societal level in developing ethical, regulatory, and reimbursement frameworks. A multidisciplinary approach and awareness of AI tools will create a vibrant ecosystem for using AI‐assisted tools to guide and enhance clinical practice. From optically enhanced endoscopy to clinical decision support for risk stratification, AI tools will potentially transform our practice by leveraging massive amounts of data to personalize care to the right patient, in the right amount, at the right time.

Status of AI-Enabled Clinical Decision Support Systems Implementations in China

“…Herein we discuss the following aspects—(1) system functions improvement and integration into the clinical process, (2) data quality and availability, and (3) methodological bias, e.g., explainability, transparency, adaptability of algorithms—which were identified as the three most important areas for the surveyed group. These three concerns were also considered as logistic challenges of successful implementations of AI-enabled tools by international scholars 29 30 and based on these considerations, we put forward specific recommendations. While not an exhaustive recommendation set, such key behaviors, informed by previous and this work's China-specific analysis, can help alleviate the concerns and challenges of developing and implementing usable and well-received AI + CDSSs.…”

“…AI + CDSSs which can communicate to the clinician pertinent information such as the clinical evidence behind the recommendation, in a way the clinician can quickly understand it within the timeframe and context of a patient encounter, will likely be preferred over a product with equivalent accuracy. 14 Third, for the purpose of users' trust and preference, AI + CDSSs algorithmic interpretability must be paired with adequate training on system functionality and logic delivered to clinicians, 29 39 so that clinicians can gain insights of the capabilities of AI + CDSSs and how the medical suggestions are reached.…”

“…14 Consequently, before any AI þ CDSS is considered for implementation, a deep understanding of the clinical workflow and care delivery process is the key to these systems to clinical practice. 29 However, more research is still needed on when, where, and how AI þ CDSS should be integrated seamlessly within the clinical and administrative workflow in a way that reduces cognitive burden and does not add new or further encumbrances. 14…”

Clinical Decision Support Systems Research in Nursing: A Visual Survey

“…In the third stage, from 2016 to 2022, particular interest in the latter period has been research on the impact of focused on barriers during implementation [32,33]. Research shows a shift from exploratory research to speci c clinical practice, The possible problems involved in the introduction and use of construction are discussed [32,34,35] [26]. Generally speaking, journals with a high frequency of publication of related literature provide researchers with publication guidelines for documents.…”

Evolution in the Practice of Pediatric Endoscopy and Sedation

“…AI is revolutionizing most industries because of its ability for complex data processing. Though it has been a "hot topic" for decades, AI in medicine is now taking shape largely because of the robust technological infrastructure currently in place (56). Medical education is incorporating AI into its curriculum and manufacturers are adding AI to endoscopy software (57)(58)(59).…”