[Cognitive errors in diagnostic decision making]

[Misdiagnoses in the diagnostics of the abdomen and pelvis]

Misdiagnoses in abdominal radiology are a frequent source of clinical errors, often stemming from cognitive biases and perception errors. Typical sources of error include perceptual and interpretative issues, frequently influenced by cognitive mechanisms, such as anchoring and confirmation biases or the satisfaction of search bias. Technical errors, such as suboptimal windowing in computed tomography, also contribute to diagnostic inaccuracies. Enhancing diagnostic accuracy requires awareness of these biases and a systematic reflection on the diagnostic process. This approach enables early error prevention and improves the diagnostic quality in abdominal imaging.

Effects of interacting with a large language model compared with a human coach on the clinical diagnostic process and outcomes among fourth-year medical students: study protocol for a prospective, randomised experiment using patient vignettes

INTRODUCTION

Versatile large language models (LLMs) have the potential to augment diagnostic decision-making by assisting diagnosticians, thanks to their ability to engage in open-ended, natural conversations and their comprehensive knowledge access. Yet the novelty of LLMs in diagnostic decision-making introduces uncertainties regarding their impact. Clinicians unfamiliar with the use of LLMs in their professional context may rely on general attitudes towards LLMs more broadly, potentially hindering thoughtful use and critical evaluation of their input, leading to either over-reliance and lack of critical thinking or an unwillingness to use LLMs as diagnostic aids. To address these concerns, this study examines the influence on the diagnostic process and outcomes of interacting with an LLM compared with a human coach, and of prior training vs no training for interacting with either of these 'coaches'. Our findings aim to illuminate the potential benefits and risks of employing artificial intelligence (AI) in diagnostic decision-making.

METHODS AND ANALYSIS

We are conducting a prospective, randomised experiment with N=158 fourth-year medical students from Charité Medical School, Berlin, Germany. Participants are asked to diagnose patient vignettes after being assigned to either a human coach or ChatGPT and after either training or no training (both between-subject factors). We are specifically collecting data on the effects of using either of these 'coaches' and of additional training on information search, number of hypotheses entertained, diagnostic accuracy and confidence. Statistical methods will include linear mixed effects models. Exploratory analyses of the interaction patterns and attitudes towards AI will also generate more generalisable knowledge about the role of AI in medicine.

ETHICS AND DISSEMINATION

The Bern Cantonal Ethics Committee considered the study exempt from full ethical review (BASEC No: Req-2023-01396). All methods will be conducted in accordance with relevant guidelines and regulations. Participation is voluntary and informed consent will be obtained. Results will be published in peer-reviewed scientific medical journals. Authorship will be determined according to the International Committee of Medical Journal Editors guidelines.

Fever in the Returning Traveler

BACKGROUND

It is predicted that approximately two billion tourist trips to foreign countries will be taken worldwide each year by 2030. Germany has long been among the most active countries in tourism. The frequency of illness among persons returning from developing and newly industrialized countries is 43-79%. The appropriate diagnosis of fever in returning travelers is a clinically important matter, as it can be a sign of a life-threatening illness.

METHODS

This review is based on publications (2001-2022) retrieved by a selective search in PubMed for studies on the epidemiology, diagnosis, and treatment of febrile illnesses in returning travelers, or on specific tropical diseases.

RESULTS

Diarrhea, fever, and skin changes are the most common manifestations of disease after travel to tropical and sub - tropical areas. The diagnostic evaluation should be performed in a series of steps, beginning with a precise travel history and the identification of specific risk factors. Among travelers returning from sub-Saharan Africa, Plasmodium falciparum malaria is the most common cause of fever on presentation to centers for infectious diseases and tropical medicine, affecting approximately 50 per 1000 travelers. Among persons returning from travel to Southeast Asia, dengue fever is the most common infectious disease, affecting 50-160 per 1000 travelers. Further potentially dangerous diseases include chikungunya and zika fever, typhoid and paratyphoid fever, amoebic liver abscess, visceral leishmaniasis (kala-azar), leptospirosis, and, very rarely, imported cases of viral hemorrhagic fever. COVID-19 and influenza are important differential diagnoses.

CONCLUSION

The differential diagnosis can be narrowed by thorough history-taking with particular attention to the patient's travel route, combined with a good knowledge of the geographic spread and incubation times of the main tropical diseases. Algorithms help clinicians to focus the diagnostic work-up and select the appropriate further laboratory tests and diagnostic procedures.