Journal of evaluation in clinical practice
-
This paper examines the use of artificial intelligence (AI) for the diagnosis of autism spectrum disorder (ASD, hereafter autism). In so doing we examine some problems in existing diagnostic processes and criteria, including issues of bias and interpretation, and on concepts like the 'double empathy problem'. We then consider how novel applications of AI might contribute to these contexts. We're focussed specifically on adult diagnostic procedures as childhood diagnosis is already well covered in the literature.
-
The COVID-19 pandemic has transformed traditional in-person care into a new reality of virtual care for patients with complex chronic disease (CCD), but how has this transformation impacted clinical judgement? I argue that virtual specialist-patient interaction challenges clinical reasoning and clinical judgement (clinical reasoning combined with statistical reasoning). However, clinical reasoning can improve by recognising the abductive, deductive, and inductive methods that the clinician employs. Abductive reasoning leading to an inference to the best explanation or invention of an explanatory hypothesis is the default response to unfamiliar or confusing situations. ⋯ Clinical judgement in virtual encounters especially calls for Gestalt cognition to assess a situational pattern irreducible to its parts and independent of its particulars, so that efficient data interpretation and self-reflection are enabled. Gestalt cognition integrates abduction, deduction, and induction, appropriately divides the time and effort spent on each, and can compensate for reduced available information. Evaluating one's clinical judgement for those components especially vulnerable to compromise can help optimize the delivery of virtual care for patients with CCD.
-
Despite the great promises that artificial intelligence (AI) holds for health care, the uptake of such technologies into medical practice is slow. In this paper, we focus on the epistemological issues arising from the development and implementation of a class of AI for clinical practice, namely clinical decision support systems (CDSS). We will first provide an overview of the epistemic tasks of medical professionals, and then analyse which of these tasks can be supported by CDSS, while also explaining why some of them should remain the territory of human experts. ⋯ In practice, this means that the system indicates what factors contributed to arriving at an advice, allowing the user (clinician) to evaluate whether these factors are medically plausible and applicable to the patient. Finally, we defend that proper implementation of CRSS allows combining human and artificial intelligence into hybrid intelligence, were both perform clearly delineated and complementary empirical tasks. Whereas CRSSs can assist with statistical reasoning and finding patterns in complex data, it is the clinicians' task to interpret, integrate and contextualize.
-
Medical schools and residency programs have become very adept at teaching medical students and residents an enormous amount of information. However, it is much less clear whether they are effective at fostering virtuous qualities like empathy or professionalism in trainees. This would come as no surprise to Plato, who famously argued in the Meno that virtue cannot be taught. ⋯ As such, we address the question of the teachability of virtue in the realm of medicine, analysing Plato's contradictory analyses in the Meno and Protagoras, and drawing upon modern neuroscience to turn an empirical lens on the question. We explore the ways in which Noddings' Ethic of Care may offer a way forward for medical educators keen to foster virtue in trainees. We conclude by demonstrating how, by harnessing the power of caring relationships, the principles of Noddings' Ethic of Care have already been applied to medical education at a university in Israel.
-
Randomized Controlled Trial
Distinctive aspects of consent in pilot and feasibility studies.
Prior to a main randomized clinical trial, investigators often carry out a pilot or feasibility study in order to test certain trial processes or estimate key statistical parameters, so as to optimize the design of the main trial and/or determine whether it can feasibly be run. Pilot studies reflect the design of the intended main trial, whereas feasibility studies may not do so, and may not involve allocation to different treatments. Testing relative clinical effectiveness is not considered an appropriate aim of pilot or feasibility studies. ⋯ Equipoise may also be particularly challenging to grasp in the context of a pilot study. The consent process in pilot and feasibility studies requires a particular focus, and careful communication, if it is to carry the appropriate moral weight. There are corresponding implications for the process of ethical approval.