BACKGROUND: Although history taking is fundamental for diagnosing medical conditions, teaching and providing feedback on the skill can be challenging due to resource constraints. Virtual simulated patients and web-based chatbots have thus emerged as educational tools, with recent advancements in artificial intelligence (AI) such as large language models (LLMs) enhancing their realism and potential to provide feedback.
OBJECTIVE: In our study, we aimed to evaluate the effectiveness of a Generative Pretrained Transformer (GPT) 4 model to provide structured feedback on medical students\' performance in history taking with a simulated patient.
METHODS: We conducted a prospective study involving medical students performing history taking with a GPT-powered chatbot. To that end, we designed a chatbot to simulate patients\' responses and provide immediate feedback on the comprehensiveness of the students\' history taking. Students\' interactions with the chatbot were analyzed, and feedback from the chatbot was compared with feedback from a human rater. We measured interrater reliability and performed a descriptive analysis to assess the quality of feedback.
RESULTS: Most of the study\'s participants were in their third year of medical school. A total of 1894 question-answer pairs from 106 conversations were included in our analysis. GPT-4\'s role-play and responses were medically plausible in more than 99% of cases. Interrater reliability between GPT-4 and the human rater showed \"almost perfect\" agreement (Cohen κ=0.832). Less agreement (κ<0.6) detected for 8 out of 45 feedback categories highlighted topics about which the model\'s assessments were overly specific or diverged from human judgement.
CONCLUSIONS: The GPT model was effective in providing structured feedback on history-taking dialogs provided by medical students. Although we unraveled some limitations regarding the specificity of feedback for certain feedback categories, the overall high agreement with human raters suggests that LLMs can be a valuable tool for medical education. Our findings, thus, advocate the careful integration of AI-driven feedback mechanisms in medical training and highlight important aspects when LLMs are used in that context.

UNASSIGNED: Teaching medical students the skills required to acquire, interpret, apply, and communicate clinical information is an integral part of medical education. A crucial aspect of this process involves providing students with feedback regarding the quality of their free-text clinical notes.
UNASSIGNED: The goal of this study was to assess the ability of ChatGPT 3.5, a large language model, to score medical students\' free-text history and physical notes.
UNASSIGNED: This is a single-institution, retrospective study. Standardized patients learned a prespecified clinical case and, acting as the patient, interacted with medical students. Each student wrote a free-text history and physical note of their interaction. The students\' notes were scored independently by the standardized patients and ChatGPT using a prespecified scoring rubric that consisted of 85 case elements. The measure of accuracy was percent correct.
UNASSIGNED: The study population consisted of 168 first-year medical students. There was a total of 14,280 scores. The ChatGPT incorrect scoring rate was 1.0%, and the standardized patient incorrect scoring rate was 7.2%. The ChatGPT error rate was 86%, lower than the standardized patient error rate. The ChatGPT mean incorrect scoring rate of 12 (SD 11) was significantly lower than the standardized patient mean incorrect scoring rate of 85 (SD 74; P=.002).
UNASSIGNED: ChatGPT demonstrated a significantly lower error rate compared to standardized patients. This is the first study to assess the ability of a generative pretrained transformer (GPT) program to score medical students\' standardized patient-based free-text clinical notes. It is expected that, in the near future, large language models will provide real-time feedback to practicing physicians regarding their free-text notes. GPT artificial intelligence programs represent an important advance in medical education and medical practice.

暂无摘要。

OBJECTIVE: This cross-sectional study assessed physicians\' knowledge and attitudes toward occupational diseases, their practice of occupational history taking, and the associated factors and barriers.
METHODS: From January 1 to June 30, 2023, Egyptian physicians from different specialties (n = 278) completed a questionnaire including sociodemographic and occupational data, questions measuring knowledge, attitudes, practice, and barriers.
RESULTS: The significant predictor of low knowledge was the nonuse of a standard history form. The lack of undergraduate education/postgraduate training in occupational diseases was the predictor of unfavorable attitudes and poor practice. Unfavorable attitudes also predicted poor practice. The main barriers were insufficient knowledge and busy schedules.
CONCLUSIONS: Different specialties physicians are essential in recognizing occupational diseases. They need to be knowledgeable about occupational diseases within their specialties. Specialized undergraduate and postgraduate training in this topic can help achieve such needs.

Prostate cancer (PCa) is a major cause of illness and death in men of Sub-Sahara African origin. The study assessed the pattern of PCa, the effect of family history on PSA at diagnosis, and clinical characteristics of PCa in Nigeria. A cross-sectional survey of 200 participants was performed within a 12-month period in Nigeria. Data were collected through patients\' interview and hospital records and analyzed using SPSS version 25. Descriptive and inferential statistics were performed. P values <.05 were significant. Mean age of 68.5 years was observed among the 200 study participants. Only 64 (32.0%) had a positive immediate family history of PCa, and 61 (30.5%) were not aware of their family cancer history. Most patients 140 (70.0%) had lower urinary tract symptom (LUTS)/lower back pain/leg pain, and the average Gleason score was 7.55 (±0.876). Symptoms of LUTS/lower back pain mostly occurred in patients between 58 and 79 years, while LUTS/leg pain was more common in persons between 60 and 84. Average PSA differed among participants; persons with no family cancer history (M = 143.989; 95% confidence interval [CI] = 114.849-173.129), family history of PCa (M = 165.463; 95% CI = 131.435), family history of cervical cancer (M = 133.456; 95% CI = 49.335-217.576), and persons with no knowledge of their family cancer history (M = 121.546; 95% CI = 89.234-153.857). Univariate one-way (F-Tests) showed that family history of cancer had no significant impact on patients\' PSA (R2 = 0.017; adjusted R2 = 0.002; df = 3; F = 1.154; p = .329) at diagnosis. PCa mostly occurred in men within 60 to 70 years of age, and family history of cancer did not predict PSA at diagnosis. Patients presented to health facilities at advanced or metastatic stages. These findings highlight the need for policies and strategies that encourage early PCa screening.

BACKGROUND: Artificial intelligence (AI) holds significant promise for enhancing the efficiency and safety of medical history-taking and triage within primary care. However, there remains a dearth of knowledge concerning the practical implementation of AI systems for these purposes, particularly in the context of healthcare leadership. This study explores the experiences of healthcare leaders regarding the barriers to implementing an AI application for automating medical history-taking and triage in Swedish primary care, as well as the actions they took to overcome these barriers. Furthermore, the study seeks to provide insights that can inform the development of AI implementation strategies for healthcare.
METHODS: We adopted an inductive qualitative approach, conducting semi-structured interviews with 13 healthcare leaders representing seven primary care units across three regions in Sweden. The collected data were subsequently analysed utilizing thematic analysis. Our study adhered to the Consolidated Criteria for Reporting Qualitative Research to ensure transparent and comprehensive reporting.
RESULTS: The study identified implementation barriers encountered by healthcare leaders across three domains: (1) healthcare professionals, (2) organization, and (3) technology. The first domain involved professional scepticism and resistance, the second involved adapting traditional units for digital care, and the third inadequacies in AI application functionality and system integration. To navigate around these barriers, the leaders took steps to (1) address inexperience and fear and reduce professional scepticism, (2) align implementation with digital maturity and guide patients towards digital care, and (3) refine and improve the AI application and adapt to the current state of AI application development.
CONCLUSIONS: The study provides valuable empirical insights into the implementation of AI for automating medical history-taking and triage in primary care as experienced by healthcare leaders. It identifies the barriers to this implementation and how healthcare leaders aligned their actions to overcome them. While progress was evident in overcoming professional-related and organizational-related barriers, unresolved technical complexities highlight the importance of AI implementation strategies that consider how leaders handle AI implementation in situ based on practical wisdom and tacit understanding. This underscores the necessity of a holistic approach for the successful implementation of AI in healthcare.

UNASSIGNED: This study aimed to assess the practicality of using a stepwise pedigree-based approach to differentiate between familial and sporadic Dilated Cardiomyopathy (DCM), while also considering timing of the genetic analysis. The analysis includes an examination of the extent to which complete family investigations were conducted in real-world scenarios as well as the length of the investigation.
UNASSIGNED: The stepwise pedigree approach involved conducting a comprehensive family history spanning 3 to 4 generations, reviewing medical records of relatives, and conducting clinical screening using echocardiography and electrocardiogram on first-degree relatives. Familial DCM was diagnosed when at least 2 family members were found to have DCM, and genetic analysis was considered as an option. This study involved a manual review of all DCM investigations conducted at the Centre of Cardiovascular Genetics at Umeå University Hospital, where the stepwise pedigree approach has been employed since 2007.
UNASSIGNED: The investigation process had a mean duration of 643 days (95% CI 560.5-724.9). Of the investigations preformed, 94 (68%) were complete, 12 (9%) were ongoing, and 33 (24%) were prematurely terminated and thus incomplete. At the conclusion of the investigations, 55 cases (43%) were classified as familial DCM, 50 (39%) as sporadic DCM, and 22 (18%) remained unassessed due to incomplete pedigrees. Among the familial cases, genetic verification was achieved in 40%.
UNASSIGNED: The stepwise pedigree approach is time consuming, and the investigations are often incomplete which may suggest that a more direct approach to genetic analysis, may be warranted.

Linkage studies have indicated a potential genetic predisposition to cholelithiasis. This study aims to determine the frequency of positive family history of gallstone disease in patients presenting with gallstones in a Pakistani population. A descriptive, cross-sectional study was conducted at the surgical department of the University of Lahore Teaching Hospital from June 30, 2023 to August 30, 2023. A total of 102 radiologically confirmed cholelithiasis patients were enrolled. Out of 102 participants, 75.5% (n = 77) were females, with a mean age at presentation of 42.1 ± 12.1 years. The study found that 32.4% (n = 33) of participants had a single family member with gallstones, 3.9% (n = 4) had 2 family members affected, and 1% (n = 1) had 3 family members affected. The attributable risk of genetics from our study was 37.2%. Additionally, there was no significant association between positive family history and earlier onset of disease. A significant percentage of Pakistani population may have gallstone disease due to genetic factors.

BACKGROUND: Simulation based medical training (SBMT) is gaining traction for undergraduate learning and development. We designed, implemented, and independently assessed the impact of an SBMT programme on competency in surgical history taking and clinical examination for senior clinical students.
METHODS: With institutional ethical approval and initial pilot study of student volunteers that ensured format appropriateness, we implemented an SBMT programme weekly for ten weeks during the core surgery module of our Medicine degree programme. Groups of 5 students collaboratively undertook an observed focused history and physical examination while simultaneously directing care on a simulated surgical patient (actor) with acute abdominal pain. This was conducted in a nonclinical, standardised, tutor-supervised environment and followed by a group debriefing led by both the simulated patient and tutor discussing student interaction and competency. All students undertook Southampton Medical Assessment Tool (SMAT) on a surgical inpatient prior to (baseline) and within 2 weeks after SBMT. Students without simulation training functioned as a control group and randomized cluster sampling was utilised for group selection. Second assessments were by independent surgical academics blinded to student group. Feedback was collected via anonymous questionnaire from those who undertook SBMT.
RESULTS: One hundred students took part, fifty of whom undertook SBMT. Global mean SMAT scores were similar between the control and intervention group at baseline (p > 0.05). Scores on the second assessment were significantly higher (p = 0.0006) for those who had undertaken SBMT vs. controls; 94% of students taking SBMT reported benefit via questionnaire with 85% stating increased confidence in history-taking and 78% reporting improved abdominal examination.
CONCLUSIONS: Undergraduate simulation training at scale is feasible and positively impacts undergraduate student core task competency.

暂无摘要。