Understanding Physician's Perspectives on AI in Health Care: Protocol for a Sequential Multiple Assignment Randomized Vignette Study.

BACKGROUND: As the availability and performance of artificial intelligence (AI)-based clinical decision support (CDS) systems improve, physicians and other care providers poised to be on the front lines will be increasingly tasked with using these tools in patient care and incorporating their outputs into clinical decision-making processes. Vignette studies provide a means to explore emerging hypotheses regarding how context-specific factors, such as clinical risk, the amount of information provided about the AI, and the AI result, may impact physician acceptance and use of AI-based CDS tools. To best anticipate how such factors influence the decision-making of frontline physicians in clinical scenarios involving AI decision-support tools, hypothesis-driven research is needed that enables scenario testing before the implementation and deployment of these tools. OBJECTIVE: This study's objectives are to (1) design an original, web-based vignette-based survey that features hypothetical scenarios based on emerging or real-world applications of AI-based CDS systems that will vary systematically by features related to clinical risk, the amount of information provided about the AI, and the AI result; and (2) test and determine causal effects of specific factors on the judgments and perceptions salient to physicians' clinical decision-making. METHODS: US-based physicians with specialties in family or internal medicine will be recruited through email and mail (target n=420). Through a web-based survey, participants will be randomized to a 3-part "sequential multiple assignment randomization trial (SMART) vignette" detailing a hypothetical clinical scenario involving an AI decision support tool. The SMART vignette design is similar to the SMART design but adapted to a survey design. Each respondent will be randomly assigned to 1 of the possible vignette variations of the factors we are testing at each stage, which include the level of clinical risk, the amount of information provided about the AI, and the certainty of the AI output. Respondents will be given questions regarding their hypothetical decision-making in response to the hypothetical scenarios. RESULTS: The study is currently in progress and data collection is anticipated to be completed in 2024. CONCLUSIONS: The web-based vignette study will provide information on how contextual factors such as clinical risk, the amount of information provided about an AI tool, and the AI result influence physicians' reactions to hypothetical scenarios that are based on emerging applications of AI in frontline health care settings. Our newly proposed "SMART vignette" design offers several benefits not afforded by the extensively used traditional vignette design, due to the 2 aforementioned features. These advantages are (1) increased validity of analyses targeted at understanding the impact of a factor on the decision outcome, given previous outcomes and other contextual factors; and (2) balanced sample sizes across groups. This study will generate a better understanding of physician decision-making within this context. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/54787.

Manufacturing seamless three-dimensional woven preforms with complex shapes based on a new weaving technology.

A new weaving technology using a modified z-binder interlacement system was designed to demonstrate its potential for the effective, continuous, efficient, and rapid manufacturing of various three-dimensional (3D) woven structures. First, three representative 3D woven preforms were fabricated. Then, epoxy resin was transferred to a preform. The manufactured 3D woven textile-reinforced composites were investigated using micro-CT analysis, tensile tests, and bending tests to study the effect of the z-binder interlacing on the structure. Furthermore, a design rule was established that could seamlessly create complex 3D woven structures with non-uniform heights in the z-direction, such as boxes, bowls, and pyramids, demonstrating that the seamless 3D woven preform of the complex shape can be fabricated with structural integrity.

Protocol for a randomized clinical trial for Avoidant Restrictive Food Intake Disorder (ARFID) in low-weight youth.

Background Avoidant Restrictive Food Intake Disorder (ARFID) is an eating disorder recently added to the Diagnostic and Statistical Manual, 5th Edition (DSM-5) that involves nutritional, developmental, and/or psychosocial impairment, and often presents with a lack of interest in eating, sensory-related eating concerns, and/or fear of adverse consequences related to eating. There is limited evidence on treatments for ARFID, and in particular, treatments for children in the outpatient setting. Pilot data suggest that Family-Based Treatment (FBT) modified for ARFID is efficacious, and that improvements in parental self-efficacy may be the mechanism behind its success. This manuscript describes a study protocol seeking to confirm these preliminary findings through an adequately powered, randomized clinical trial (RCT). METHODS: This trial will randomize 100 children ages 6-12 years old who meet DSM-5 criteria for ARFID and their families to receive either 14 telehealth sessions of FBT-ARFID (n = 50) or a manualized Psychoeducational Motivation Therapy (PMT) treatment (n = 50), an individual therapy addressing the child's understanding of the problems ARFID is causing and promoting non-behavioral motivation and exploration of changing their eating patterns. Masked assessments will be conducted at baseline, one and two months within treatment, end-of-treatment, and six-month follow-up. Primary outcomes include change in body weight, parental self-efficacy, and parent feeding behaviors between baseline and end-of-treatment. CONCLUSIONS: The results of this RCT will advance our understanding of effective treatments for low-weight ARFID in youth.

Study protocol for training providers in private practice in family-based treatment for adolescents with anorexia nervosa: A randomized controlled feasibility trial.

BACKGROUND: Private practice clinicians make up approximately 50% of US mental health outpatient providers and treat a high number of eating disorder patients. While family-based treatment (FBT) is a first-line treatment for adolescent anorexia nervosa (AN), private practice clinicians experience difficulties receiving training in evidence-based treatments such as FBT. This report outlines the study protocol for a randomized control trial (RCT) training private practice clinicians in FBT for adolescent AN (NCT04428580). METHODS: In this study, we intend to recruit 140 private practice mental health practitioners and randomize them to complete either a standard webinar-based online training or an enhanced online training that incorporates additional modules related to the putative mechanisms of treatment effect in FBT (i.e., use of externalization and agnosticism). Following the training, participants will begin expert case consultation for an adolescent with AN using FBT from their private practice. CONCLUSION: Based on preliminary studies suggesting the importance of enhanced skills related to agnosticism and externalization, we hypothesize that feasibility data will support a larger randomized clinical trial (RCT) and that the enhanced training arm will significantly improve FBT knowledge and skills compared to the standard webinar training arm. We also expect that patient weight gain early in treatment will be associated with clinician fidelity to the inventions used in FBT regardless of training type.