Journal of evaluation in clinical practice
-
Review
The transition from inquiry to evidence to actionable clinical knowledge: A proposed roadmap.
We consider the question "What should we do?" in the context of clinical research/practice. There are several steps along the way to providing a satisfactory answer, many of which have received considerable attention in the literature. We aim to provide a unified summary and explication of these "steps along the way". The result will be an increased appreciation for the meaning and structure of "actionable clinical knowledge". ⋯ Clinical decision-making is not infallible, and the steps we can take to minimize error are context dependent. Medical evidence, produced as it is by human effort, can never be perfect. We will be doing well by assuring that the evidence we use has been produced by a reliable process and is relevant to the question posed.
-
This paper aims to show how the focus on eradicating bias from Machine Learning decision-support systems in medical diagnosis diverts attention from the hermeneutic nature of medical decision-making and the productive role of bias. We want to show how an introduction of Machine Learning systems alters the diagnostic process. Reviewing the negative conception of bias and incorporating the mediating role of Machine Learning systems in the medical diagnosis are essential for an encompassing, critical and informed medical decision-making. ⋯ We show that Machine Learning systems join doctors and patients in co-designing a triad of medical diagnosis. We highlight that it is imperative to examine the hermeneutic role of the Machine Learning systems. Additionally, we suggest including not only the patient, but also colleagues to ensure an encompassing diagnostic process, to respect its inherently hermeneutic nature and to work productively with the existing human and machine biases.
-
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.
-
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 onset of acute illness may be accompanied by a profound sense of disorientation for patients. Addressing this vulnerability is a key part of a physician's purview, yet well-intended efforts to do so may be impeded by myriad competing tasks in clinical practice. Resolving this dilemma goes beyond appealing to altruism, as its limitless demands may lead to physician burnout, disillusionment, and a narrowed focus on the biomedical aspects of care in the interest of self-preservation. The authors propose an ethic of hospitality that may better guide physicians in attending to the comprehensive needs of patients that have entered "the kingdom of the sick." ⋯ While it is unlikely that anything physicians do will make the hospital a place where patients and caregivers will desire to be, hospitality may focus their efforts upon making it less unwelcoming. Specifically, it offers an orientation that supports patients in navigating the disorienting and unfamiliar terrains of acute illness, the hospital setting in which help is sought, and engagement with the health care system writ large.