From diagnosis to patient scheduling, AI is increasingly being considered across different clinical applications. Despite increasingly powerful clinical AI, uptake into actual clinical workflows remains limited. One of the major challenges is developing appropriate trust with clinicians. In this paper, we investigate trust in clinical AI in a wider perspective beyond user interactions with the AI. We offer several points in the clinical AI development, usage, and monitoring process that can have a significant impact on trust. We argue that the calibration of trust in AI should go beyond explainable AI and focus on the entire process of clinical AI deployment. We illustrate our argument with case studies from practitioners implementing clinical AI in practice to show how trust can be affected by different stages in the deployment cycle.
Purpose: This study aims to capture the complex clinical reasoning process during tailoring of exercise and dietary interventions to adverse effects and comorbidities of patients with ovarian cancer receiving chemotherapy. Methods: Clinical vignettes were presented to expert physical therapists (n = 4) and dietitians (n = 3). Using the think aloud method, these experts were asked to verbalize their clinical reasoning on how they would tailor the intervention to adverse effects of ovarian cancer and its treatment and comorbidities. Clinical reasoning steps were categorized in questions raised to obtain additional information; anticipated answers; and actions to be taken. Questions and actions were labeled according to the evidence-based practice model. Results: Questions to obtain additional information were frequently related to the patients’ capacities, safety or the etiology of health issues. Various hypothetical answers were proposed which led to different actions. Suggested actions by the experts included extensive monitoring of symptoms and parameters, specific adaptations to the exercise protocol and dietary-related patient education. Conclusions: Our study obtained insight into the complex process of clinical reasoning, in which a variety of patient-related variables are used to tailor interventions. This insight can be useful for description and fidelity assessment of interventions and training of healthcare professionals.
MULTIFILE
Introduction: Given the complexity of teaching clinical reasoning to (future) healthcare professionals, the utilization of serious games has become popular for supporting clinical reasoning education. This scoping review outlines games designed to support teaching clinical reasoning in health professions education, with a specific emphasis on their alignment with the 8-step clinical reasoning cycle and the reflective practice framework, fundamental for effective learning. Methods: A scoping review using systematic searches across seven databases (PubMed, CINAHL, ERIC, PsycINFO, Scopus, Web of Science, and Embase) was conducted. Game characteristics, technical requirements, and incorporation of clinical reasoning cycle steps were analyzed. Additional game information was obtained from the authors. Results: Nineteen unique games emerged, primarily simulation and escape room genres. Most games incorporated the following clinical reasoning steps: patient consideration (step 1), cue collection (step 2), intervention (step 6), and outcome evaluation (step 7). Processing information (step 3) and understanding the patient’s problem (step 4) were less prevalent, while goal setting (step 5) and reflection (step 8) were least integrated. Conclusion: All serious games reviewed show potential for improving clinical reasoning skills, but thoughtful alignment with learning objectives and contextual factors is vital. While this study aids health professions educators in understanding how games may support teaching of clinical reasoning, further research is needed to optimize their effective use in education. Notably, most games lack explicit incorporation of all clinical reasoning cycle steps, especially reflection, limiting its role in reflective practice. Hence, we recommend prioritizing a systematic clinical reasoning model with explicit reflective steps when using serious games for teaching clinical reasoning.
Alcohol use disorder (AUD) is a major problem. In the USA alone there are 15 million people with an AUD and more than 950,000 Dutch people drink excessively. Worldwide, 3-8% of all deaths and 5% of all illnesses and injuries are attributable to AUD. Care faces challenges. For example, more than half of AUD patients relapse within a year of treatment. A solution for this is the use of Cue-Exposure-Therapy (CET). Clients are exposed to triggers through objects, people and environments that arouse craving. Virtual Reality (VRET) is used to experience these triggers in a realistic, safe, and personalized way. In this way, coping skills are trained to counteract alcohol cravings. The effectiveness of VRET has been (clinically) proven. However, the advent of AR technologies raises the question of exploring possibilities of Augmented-Reality-Exposure-Therapy (ARET). ARET enjoys the same benefits as VRET (such as a realistic safe experience). But because AR integrates virtual components into the real environment, with the body visible, it presumably evokes a different type of experience. This may increase the ecological validity of CET in treatment. In addition, ARET is cheaper to develop (fewer virtual elements) and clients/clinics have easier access to AR (via smartphone/tablet). In addition, new AR glasses are being developed, which solve disadvantages such as a smartphone screen that is too small. Despite the demand from practitioners, ARET has never been developed and researched around addiction. In this project, the first ARET prototype is developed around AUD in the treatment of alcohol addiction. The prototype is being developed based on Volumetric-Captured-Digital-Humans and made accessible for AR glasses, tablets and smartphones. The prototype will be based on RECOVRY, a VRET around AUD developed by the consortium. A prototype test among (ex)AUD clients will provide insight into needs and points for improvement from patient and care provider and into the effect of ARET compared to VRET.
Huntington’s disease (HD) and various spinocerebellar ataxias (SCA) are autosomal dominantly inherited neurodegenerative disorders caused by a CAG repeat expansion in the disease-related gene1. The impact of HD and SCA on families and individuals is enormous and far reaching, as patients typically display first symptoms during midlife. HD is characterized by unwanted choreatic movements, behavioral and psychiatric disturbances and dementia. SCAs are mainly characterized by ataxia but also other symptoms including cognitive deficits, similarly affecting quality of life and leading to disability. These problems worsen as the disease progresses and affected individuals are no longer able to work, drive, or care for themselves. It places an enormous burden on their family and caregivers, and patients will require intensive nursing home care when disease progresses, and lifespan is reduced. Although the clinical and pathological phenotypes are distinct for each CAG repeat expansion disorder, it is thought that similar molecular mechanisms underlie the effect of expanded CAG repeats in different genes. The predicted Age of Onset (AO) for both HD, SCA1 and SCA3 (and 5 other CAG-repeat diseases) is based on the polyQ expansion, but the CAG/polyQ determines the AO only for 50% (see figure below). A large variety on AO is observed, especially for the most common range between 40 and 50 repeats11,12. Large differences in onset, especially in the range 40-50 CAGs not only imply that current individual predictions for AO are imprecise (affecting important life decisions that patients need to make and also hampering assessment of potential onset-delaying intervention) but also do offer optimism that (patient-related) factors exist that can delay the onset of disease.To address both items, we need to generate a better model, based on patient-derived cells that generates parameters that not only mirror the CAG-repeat length dependency of these diseases, but that also better predicts inter-patient variations in disease susceptibility and effectiveness of interventions. Hereto, we will use a staggered project design as explained in 5.1, in which we first will determine which cellular and molecular determinants (referred to as landscapes) in isogenic iPSC models are associated with increased CAG repeat lengths using deep-learning algorithms (DLA) (WP1). Hereto, we will use a well characterized control cell line in which we modify the CAG repeat length in the endogenous ataxin-1, Ataxin-3 and Huntingtin gene from wildtype Q repeats to intermediate to adult onset and juvenile polyQ repeats. We will next expand the model with cells from the 3 (SCA1, SCA3, and HD) existing and new cohorts of early-onset, adult-onset and late-onset/intermediate repeat patients for which, besides accurate AO information, also clinical parameters (MRI scans, liquor markers etc) will be (made) available. This will be used for validation and to fine-tune the molecular landscapes (again using DLA) towards the best prediction of individual patient related clinical markers and AO (WP3). The same models and (most relevant) landscapes will also be used for evaluations of novel mutant protein lowering strategies as will emerge from WP4.This overall development process of landscape prediction is an iterative process that involves (a) data processing (WP5) (b) unsupervised data exploration and dimensionality reduction to find patterns in data and create “labels” for similarity and (c) development of data supervised Deep Learning (DL) models for landscape prediction based on the labels from previous step. Each iteration starts with data that is generated and deployed according to FAIR principles, and the developed deep learning system will be instrumental to connect these WPs. Insights in algorithm sensitivity from the predictive models will form the basis for discussion with field experts on the distinction and phenotypic consequences. While full development of accurate diagnostics might go beyond the timespan of the 5 year project, ideally our final landscapes can be used for new genetic counselling: when somebody is positive for the gene, can we use his/her cells, feed it into the generated cell-based model and better predict the AO and severity? While this will answer questions from clinicians and patient communities, it will also generate new ones, which is why we will study the ethical implications of such improved diagnostics in advance (WP6).
It is essential to look for new forms of care, with an emphasis on Prevention, Relocation and Replacement (Health & Care Knowledge and Innovation Agenda 2020-2030). Especially when it comes to Alcohol Use Disorder (AUD). Globally, more than 5% of all illness and injury are attributable to AUD. Treatment is challenging; 47-75% of AUD patients who are clinically detoxified relapse within one year. Recovry aims to prevent an unhealthy lifestyle due to (alcohol) addiction by developing and testing a Virtual Reality (VR) self-prevention tool (relocating and replacing care treatment). Although research shows that VR is used successfully in health care and in the treatment of alcohol addiction, especially through the creation of presence, it has not been tested for effectiveness and implementation (as an adjuvant in a clinical post-detoxification phase of an AUD- therapy). The question of whether virtual-humans should be used in a VR treatment and whether 3600 recorded VR or computer generated (CG) VR should be selected before. The use of a virtual human in VR has expected advantages (more effect) but also disadvantages (more costs). The expected advantages and disadvantages of 360o VR (cheaper, faster, more personal) and CG VR (more flexible and interactive) also cause choice and implementation problems. Recovry is the first project in which a VR tool is (further) developed in which an AUD treatment can (and will) be tested for the effect and effectiveness of adding virtual humans in CG and 360o VR environments as part of preventive care for patients with an AUD. This project thus serves as a prelude to cooperation in the Netherlands around a more effective implementation of VR in the (self) care system and thus the active and independent integration of former AUD patients in society (“more people, less patients”).