ABSTRACT
Importance: Diagnostic errors are common and cause significant morbidity. Large language models (LLMs) have shown promise in their performance on both multiple-choice and open-ended medical reasoning examinations, but it remains unknown whether the use of such tools improves diagnostic reasoning. Objective: To assess the impact of the GPT-4 LLM on physicians' diagnostic reasoning compared to conventional resources. Design: Multi-center, randomized clinical vignette study. Setting: The study was conducted using remote video conferencing with physicians across the country and in-person participation across multiple academic medical institutions. Participants: Resident and attending physicians with training in family medicine, internal medicine, or emergency medicine. Interventions: Participants were randomized to access GPT-4 in addition to conventional diagnostic resources or to just conventional resources. They were allocated 60 minutes to review up to six clinical vignettes adapted from established diagnostic reasoning exams. Main Outcomes and Measures: The primary outcome was diagnostic performance based on differential diagnosis accuracy, appropriateness of supporting and opposing factors, and next diagnostic evaluation steps. Secondary outcomes included time spent per case and final diagnosis. Results: 50 physicians (26 attendings, 24 residents) participated, with an average of 5.2 cases completed per participant. The median diagnostic reasoning score per case was 76.3 percent (IQR 65.8 to 86.8) for the GPT-4 group and 73.7 percent (IQR 63.2 to 84.2) for the conventional resources group, with an adjusted difference of 1.6 percentage points (95% CI -4.4 to 7.6; p=0.60). The median time spent on cases for the GPT-4 group was 519 seconds (IQR 371 to 668 seconds), compared to 565 seconds (IQR 456 to 788 seconds) for the conventional resources group, with a time difference of -82 seconds (95% CI -195 to 31; p=0.20). GPT-4 alone scored 15.5 percentage points (95% CI 1.5 to 29, p=0.03) higher than the conventional resources group. Conclusions and Relevance: In a clinical vignette-based study, the availability of GPT-4 to physicians as a diagnostic aid did not significantly improve clinical reasoning compared to conventional resources, although it may improve components of clinical reasoning such as efficiency. GPT-4 alone demonstrated higher performance than both physician groups, suggesting opportunities for further improvement in physician-AI collaboration in clinical practice.
ABSTRACT
In a randomized, pre-post intervention study, we evaluated the influence of a large language model (LLM) generative AI system on accuracy of physician decision-making and bias in healthcare. 50 US-licensed physicians reviewed a video clinical vignette, featuring actors representing different demographics (a White male or a Black female) with chest pain. Participants were asked to answer clinical questions around triage, risk, and treatment based on these vignettes, then asked to reconsider after receiving advice generated by ChatGPT+ (GPT4). The primary outcome was the accuracy of clinical decisions based on pre-established evidence-based guidelines. Results showed that physicians are willing to change their initial clinical impressions given AI assistance, and that this led to a significant improvement in clinical decision-making accuracy in a chest pain evaluation scenario without introducing or exacerbating existing race or gender biases. A survey of physician participants indicates that the majority expect LLM tools to play a significant role in clinical decision making.
ABSTRACT
The StW 573 skeleton of Australopithecus prometheus from Sterkfontein Member 2 is some 93% complete and thus by far the most complete member of that genus yet found. Firmly dated at 3.67 Ma, it is one of the earliest specimens of its genus. A crucial aspect of interpretation of locomotor behaviour from fossil remains is an understanding of the palaeoenvironment in which the individual lived and the manner in which it would have used it. While the value of this ecomorphological approach is largely accepted, it has not been widely used as a stable framework on which to build evolutionary biomechanical interpretations. Here, we collate the available evidence on StW 573's anatomy in order, as far as currently possible, to reconstruct what might have been this individual's realized and potential niche. We explore the concept of a common Australopithecus "bauplan" by comparing the morphology and ecological context of StW 573 to that of paenocontemporaneous australopiths including Australopithecus anamensis and KSD-VP-1/1 Australopithecus afarensis. Each was probably substantially arboreal and woodland-dwelling, relying substantially on arboreal resources. We use a hypothesis-driven approach, tested by: virtual experiments, in the case of extinct species; biomechanical analyses of the locomotor behaviour of living great ape species; and analogical experiments with human subjects. From these, we conclude that the habitual locomotor mode of all australopiths was upright bipedalism, whether on the ground or on branches. Some later australopiths such as Australopithecus sediba undoubtedly became more terrestrial, allowing sacrifice of arboreal stability in favour of manual dexterity. Indeed, modern humans retain arboreal climbing skills but have further sacrificed arboreal effectiveness for enhanced ability to sustain striding terrestrial bipedalism over much greater distances. We compare StW 573's locomotor adaptations to those of living great apes and protohominins, and agree with those earlier observers who suggest that the common panin-hominin last common ancestor was postcranially more like Gorilla than Pan.
