Resident Physicians Research Articles

Evaluating the use of large language models to provide clinical recommendations in the Emergency Department

The release of GPT-4 and other large language models (LLMs) has the potential to transform healthcare. However, existing research evaluating LLM performance on real-world clinical notes is limited. Here, we conduct a highly-powered study to determine whether LLMs can provide clinical recommendations for three tasks (admission status, radiological investigation(s) request status, and antibiotic prescription status) using clinical notes from the Emergency Department. We randomly selected 10,000 Emergency Department visits to evaluate the accuracy of zero-shot, GPT-3.5-turbo- and GPT-4-turbo-generated clinical recommendations across four different prompting strategies. We found that both GPT-4-turbo and GPT-3.5-turbo performed poorly compared to a resident physician, with accuracy scores 8% and 24%, respectively, lower than physician on average. Both LLMs tended to be overly cautious in its recommendations, with high sensitivity at the cost of specificity. Our findings demonstrate that, while early evaluations of the clinical use of LLMs are promising, LLM performance must be significantly improved before their deployment as decision support systems for clinical recommendations and other complex tasks.

Knowledge, attitudes, and practices of paediatric medical officers and registrars on the developmental origins of health and disease in a tertiary women’s and children’s hospital

BackgroundTo mitigate the growing burden of non-communicable diseases, doctors training to become paediatricians should be equipped with concepts and knowledge regarding Developmental Origins of Health and Disease (DOHaD).MethodsWe assessed the knowledge, attitudes, and practices (KAP) of medical officers, resident physicians, as well as junior and senior residents practising in the paediatric department of a tertiary women’s and children’s hospital. This was done through a cross-sectional online survey, with questions developed after focused group discussions with domain experts, and responses based on a 5-point Likert scale.ResultsA total of 95 physicians met the inclusion criteria, grouped into Medical Officers (MOs) and Registrars (REGs), and we received a 100% response rate. Results showed that few physicians (n = 22, 23.2%) knew the term DOHaD, and majority rated their colleagues to be inadequately informed (n = 84, 88.4%). Among the physicians, one third (n = 32, 33.7%) were not confident in their ability to counsel patients about initiating healthy feeding practices to prevent future metabolic diseases in their children. However, there was a readiness to be better equipped with DOHaD principles and knowledge, and 95.8% (n = 91) strongly acknowledged the physician’s responsibility to optimise early life determinants of cardiometabolic health.ConclusionIn conclusion, the findings suggest a poor translation of DOHaD concepts, indicating that bridging the gap between DOHaD research knowledge and clinical application represents an unmet need. These principles should be inculcated early in the professional training of all healthcare providers.

An interprofessional postgraduate quality improvement curriculum: results and lessons learned over a 5-year implementation

ABSTRACT Problem Quality Improvement (QI) is interprofessional by nature; however, most academic QI programs occur in silos and do not leverage the opportunity to bring interprofessional learners together. Intervention To evaluate QI competencies of physician, nursing, pharmacy, behavioral health, and social work residents after participating in a longitudinal QI curriculum. Lessons learned are shared to guide educators in developing QI curriculum for interprofessional learners. Context Cohorts of graduate students over 5 years participated in a QI curriculum that aligned with each professions’ core quality competencies. Residents engaged in didactics and experiential learning in primary care clinics. Impact All learners (N = 74) demonstrated improvement in QI knowledge measured by the QIKAT-R and applied their skills demonstrated by completion of a QI project presented at the Institute for Healthcare Improvement annual forums. Participation in QI curriculum resulted in knowledge and skill improvement. Lessons learned An experiential QI curriculum is a natural place to bring diverse post-graduate learners together to improve QI knowledge and skills. Successful QI curriculum goals are to (a) align projects with institutional and stakeholder goals, (b) include coaches to promote teamwork and project management, (c) narrow project scope, (d) develop an improvement mindset that failures are learning opportunities, and (e) address needs for data access.

12511 Rhabdomyolysis Related Acute Kidney Injury Presenting as First Manifestation of Autoimmune Hypothyroidism: A Case Report

Abstract Disclosure: A. Tiwari: None. S. Mantravadi: None. N. Doshi: None. A. Dabaja: None. C. Saad: None. Introduction: Autoimmune thyroiditis is the predominant cause of primary hypothyroidism, with an incidence of estimated 0.3-1.5 cases per 1000 people, with female to male predominance of 7-10[1]. Hypothyroid myopathy affects 79 % of the affected population. Its common presentation is fatigue and cramp but in rare instances rhabdomyolysis can occur with trivial triggers like alcohol, exercise2, Case Presentation: A 32-year-old male with no significant medical history, presented with generalized weakness, myalgia, and facial puffiness for last three months. The patient engaged in regular-intensity workouts and reported consuming 12 beers several times a week for past 5 years. Physical examination revealed facial puffiness and proximal muscle weakness. Initial Laboratory findings showed elevated creatinine (1.68 mg/dL, baseline 1.0 mg/dL in April 2020), CK (8113 U/L), AST (260 U/L), ALT (129 U/L). Urinalysis revealed hematuria and mild proteinuria. Serum electrolytes were unremarkable. Abdominal ultrasound showed diffuse hepatic steatosis with normal kidney appearance. This could not explain the reason for the Acute Kidney Injury and further workup showed TSH (>150 mIU/L) and TPO antibodies (197.9 U/mL). Autoimmune panel was unremarkable. Thyroid ultrasound done subsequently revealed a markedly heterogeneous gland. Treatment included parenteral crystalloids, low-dose prednisone which was empirically added for suspected autoimmune myositis and was later discontinued once the autoimmune panel was negative, and Levothyroxine at the recommended dose. At the time of discharge, his creatinine was reduced to 1.33 mg/dL and CK to 2,298 U/L. Discussion: Severe rhabdomyolysis is a rare but significant complication of autoimmune thyroiditis, potentially leading to acute kidney injury (AKI) if not promptly diagnosed and treated. Resident physicians often attribute symptoms like myalgia and generalized weakness in males to clear evident rhabdomyolysis if they find a cause like alcohol consumption and exercise, potentially overlooking the actual etiology. We recommend thyroid workup in such patients to promptly detect and manage underlying etiology predisposing to muscle damage and subsequent kidney injury. Our patient never had any Physician encounter as his prior medical history was unremarkable, however we suggest thorough family history and thyroid profile should be a part of outpatient workup as well for patients who show other risk factors for rhabdomyolysis like daily alcohol consumption, vigorous workout, consume medications like HMG CoA inhibitors, antipsychotics etc. Presentation: 6/3/2024

Exploring medical ethics: moral reasoning among new pediatric resident physicians in a tertiary hospital.

Physicians are frequently faced with ethical dilemmas that require answers based in moral reasoning, which develops and evolves during their lives and their medical education. According to Kohlberg, there are three levels of moral reasoning development: pre-conventional (in which decisions are guided by oneself convenience), conventional (focused on obeying society's rules), and post-conventional (decisions are based in universal ethical principles). The aim of this study was to describe the level of moral reasoning among new pediatric resident physicians in a tertiary hospital. This cross-sectional descriptive study was conducted from 2020 to 2023. The Defining Issues Test was used to assess the level of moral reasoning among 195 new pediatric resident physicians in a tertiary hospital. Most resident physicians considered the fourth stage affirmations to be the most important. The median P-index (PI) was 40, and 49% of participants were on the post-conventional level of moral reasoning. The year with the lowest number of new resident physicians on the post-conventional level was 2021. The moral reasoning level among pediatric resident physicians was higher than the average found in general population. This suggests that the education received during the medical formation may influence the individuals' moral development.

Implementation of a Urologic Surgery Skills Fair for Medical Students

To increase the proportion of applicants to urology residencies, we created a surgical skills fair to introduced urology early in undergraduate medical education. Funded by the Department of Urology, the fair was designed to have student rotations through 12 hands-on practice stations supervised by faculty and an advanced care practitioner or resident physicians. At conclusion, medical students completed a voluntary survey about their experience. Surgical skills fairs were organized at Yale School of Medicine (New Haven, CT) in 2022 and 2023. The fair was designed to encourage interaction between medical students, urology residents, and urology faculty by highlighting common urologic procedures and skills. The fair was well received by medical students at all levels of training. Over 2 years, 155 medical students attended, including 67 (43%) first-year and 60 (39%) second-year medical students. Eighty-two medical students completed the survey. An average of 19 attendings, advanced care practitioners and residents attended each event. Of the survey respondents, 42.7% reported prior interest in a surgical specialty but had not considered urology. Students reported increased interest in urology and greater confidence in urologic skills after the event (p < 0.001). We demonstrate that creating a surgical fair in urology is feasible and enhances early exposure and interest in urology. For students who do not pursue urology, the fair provides knowledge of urological pathologies and valuable skills for all physicians.

Examining the impact of sleep deprivation on medical reasoning’s performance among anaesthesiology residents and doctors: a prospective study

BackgroundWorking long consecutive hours’ is common for anaesthesia and critical care physicians. It is associated with impaired medical reasoning’s performance of anaesthesiology and serious medical errors. However, no study has yet investigated the impact of working long consecutive hours’ on medical reasoning.ObjectiveThe present study evaluated the impact of working long consecutive hours’ on the medical reasoning’s performance of anaesthesiology and intensive care physicians (residents and seniors).MethodsThis multicentric, prospective, cross-over study was conducted in 5 public hospitals of Normandy region. Two groups of anaesthesia and critical care physicians were formed. One was in a rest group, RG (after a 48-hours weekend without hospital work) and the other in Sleep Deprivation Group (SDG) after a 24 h-consecutives-shift. Changes in medical reasoning’s performance were measured by 69-items script concordance tests (SCT) through to the two tests. Group A completed the first part of the assessment (Set A) after a weekend without work and the second part (Set B) after a 24 h-shift; group B did the same in reverse order. The primary outcome was medical reasoning’s performance as measured by SCT in RG and SDG. The secondary outcomes included association between the performance with the demographic data, variation of the KSS (Karolinska sleepiness scale) daytime alertness score, the number of 24 h-shift during the previous 30 days, the vacations during the previous 30 days, the presence of more or less than 4 h consecutives hours slept, the management of a stressful event during the shift, the different resident years, the place where the shift took place (University hospital or general hospitals) and the type of shift (anaesthesia or intensive care).Results84 physicians (26 physicians and 58 residents) were included. RG exhibited significantly higher performance scores than SDG (68 ± 8 vs. 65 ± 9, respectively; p = 0.008). We found a negative correlation between the number of 24 h-shifts performed during the previous month and the variation of medical reasoning’s performance and no significant variation between professionals who slept 4 h or less and those who slept more than 4 h consecutively during the shift (-4 ± 11 vs. -2 ± 11; p = 0.42).ConclusionOur study suggests that medical reasoning’ performance of anaesthesiologists, measured by the SCT, is reduced after 24 h-shift than after rest period. Working long consecutive hours’ and many shifts should be avoided to prevent the occurrence of medical errors.

Knowledge, Attitudes, and Practices of Vaccine Adverse Event Reporting Among Family Medicine Faculty and Resident Physicians

Knowledge, Attitudes, and Practices of Vaccine Adverse Event Reporting Among Family Medicine Faculty and Resident Physicians

The Impact of Diagnosis-Specific Plan Templates on Admission Note Writing Time: A Quality Improvement Initiative.

Background There are limited objective studies regarding the effectiveness of strategies to alleviate the documentation burden on resident physicians. Objective To develop and implement diagnosis-specific templates for the plan of care section of inpatient admission notes, aiming to reduce documentation time. Methods Twelve templates for the plan of care section of admission notes were written by the study authors, reviewed by attending physicians, and shared with the residents through the electronic health record (EHR) on September 23, 2022. EHR audit log data were collected to examine admission note writing times, supplemented by resident feedback on acceptability via an anonymous survey. Feasibility measures included time investment, experience with the EHR, and resident training. Results Between July 1, 2021 and June 30, 2023, 62 pediatric residents contributed 9840 admission notes. The templates were used in 557 admission notes. The mean total time spent on an admission note decreased from 97.9 minutes pre-intervention to 71.0 minutes post-intervention with the use of a template; an adjusted reduction of 23% (95% CI 16%-30%; P<.001). The mean attending time spent editing an admission note was unchanged. The survey results underscored wide acceptability of the templates among the residents. Feasibility data showed that the project required minimal time investment from the health care informatics team and minimal resident training. Conclusions Using templates in the care plan section of admission notes reduces the time residents spend writing admission notes.

Association between physicians’ maldistribution and core clinical competency of resident physicians: a nationwide cross-sectional study

ObjectivesWith physician maldistribution recognised as a global issue, Japan implemented the physician uneven distribution (PUD) index as a strategic measure. Currently, there is a lack of objective assessment of core...

399 What Do Emergency Medicine Residents and Attending Physicians Think of the ACGME Milestones?

399 What Do Emergency Medicine Residents and Attending Physicians Think of the ACGME Milestones?

Impact of patient death on physicians’ mental health

IntroductionPhysicians often encounter stressful situations that can impact their mental well-being. The death of a patient represents one of the most difficult situations in routine medical practice. Literature notably lacks comprehensive studies into physicians’ personal experiences with patients’ deaths. However, it does underscore heightened levels of sorrow, guilt, and stress stemming from the passing of terminally ill patients. As a majority of studies in this realm adopt qualitative methodologies, there is merit in supplementing existing research with a quantitative approach that employs validated psychometric scales. Furthermore, the study of phenomena associated with stress, particularly the perceived professional support by physicians in stressful events, can contribute to the implementation of preventive measures to help physicians cope. ObjectiveOur study aims to measure the traumatic impact on resident and intern physicians at national university hospitals following the death of patients, as well as to assess the perceived level of professional support among these physicians. Materials and methodsWe conducted a nationwide cross-sectional, descriptive, and analytical study. Participants included interns and residents from various specialties (medical, surgical and laboratory) at national university hospitals in Morocco. Assessing the traumatic impact of patients’ death on doctors was conducted using two psychometric scales: the Peri-Traumatic Distress Inventory (PDI) and the Revised Impact of Event Scale (IES-R). Additionally, we used the Perceived Professional Social Support Scale (QSSP-P) to evaluate how supportive the professional environment was towards these doctors. All scales utilized in the study are validated in the French language. ResultsThe study included 96 participants, with 67.7% being female. The average age was 26.8 years, ranging from 23 to 39 years. The majority of participants managed more than nine patients simultaneously (58.3%) while 41.7% were scheduled for more than six 24h shifts per month. During their training, over 64.6% of interns and residents faced more than ten patients’ death incidents, and 68.8% considered their first patient death as the most traumatizing. Half of the physicians evaluated the patients’ care as moderately appropriate, with 46.9% believing that the incident could have been prevented. Notably, 70.8% of interns and residents involved in patient care experienced self-blame and attributed a share of responsibility to themselves for the patient's demise. The majority of participants, 82.3%, exhibited peri-traumatic distress with a PDI score exceeding 15. Among the studied factors, only the perceived responsibility and a management system centered on a single physician (rather than a team) demonstrated a noteworthy correlation with PDI scores. The mean score on the IES-R scale was 25.6, with almost half of the sample (54.2%) reporting moderate to severe PTSD symptoms. The severity of these symptoms was significantly correlated with higher age, high number of patient's deaths experienced and the physician's perceived sense of responsibility. Participants in our study were more satisfied with support from colleagues compared to support functions (paramedical staff, administrative officials) or superiors. Moreover, only colleagues’ support was statistically significantly associated with low scores on the traumatic impact scales. ConclusionPhysicians maintain a unique relationship and therapeutic alliance with their patients. Therefore, the death of a patient can have a significant psychological impact on the physician. This study allowed us to objectively measure this psychological impact and evaluate professional support. The results of these studies encourage further exploration of the issue and the implementation of measures to reduce this psychological impact.

Use of Telemedicine in a Sports Medicine Clinic: An Investigation of Patient Satisfaction

Objective: Compare patient satisfaction between telemedicine and in-office visits and between providers post-operatively in an orthopedics setting with athletic trainers and physicians. Design: Cross-sectional study Methods: Patients from a Sports Medicine Clinic that received an orthopedic surgical intervention from March 2020-September 2021, and engaged in telemedicine, or an in-office visit post-operatively. Provider type included full-time athletic trainers, resident athletic trainers, physician (MD) resident/fellows, and float athletic trainers. Press-Ganey Patient Experience Surveys were collected at the time of follow up visit, with focus on items, “likelihood to recommend” and “how well staff worked together.” Results: There was a total of 255 patients (age=50±17 years). Providers included the attending physician with full-time athletic trainers (n=134, 52.3%), resident athletic trainers (n=77, 30.1%), MD residents/fellows (n=38, 14.8%), or float athletic trainers (n=6, 2.3%). No significant difference was found with patient satisfaction between in-office (n=175, 68.4%), or telemedicine visits (n=80, 31.3%), (p&gt;.44). Patients were more satisfied with care provided by the full-time athletic trainers compared to MD residents/fellows (p.18). Conclusions: This study demonstrates no significant differences with patient satisfaction between in-office or telemedicine visits. Patients seeing full-time athletic trainers had the highest patient satisfaction, demonstrating the capability of athletic trainers to effectively use telemedicine in a physician practice.

Back to Bedside: Kidney Point-of-Care Ultrasonography (POCUS) by Resident Physicians for Identification of Hydronephrosis in Patients with AKI

Back to Bedside: Kidney Point-of-Care Ultrasonography (POCUS) by Resident Physicians for Identification of Hydronephrosis in Patients with AKI

Enhancing Team Dynamics and Leadership Skills for Residents Leading Multidisciplinary In-Patient Cardiac Arrest Teams

Background: Cardiac arrest is a prevalent event with low survival rates, both in out-of-hospital and in-hospital settings. There is a lack of specific training programs addressing team dynamics and leadership skills during resuscitation events, creating a clinical gap. This project aimed to enhance team dynamics and improve leadership skills during IHCA resuscitation events. Methods: We implemented the Mock Code Project for resident physicians from our Internal Medicine Residency Programs in the simulation center (i.e., in a controlled environment) to address this gap. Multidisciplinary team mock code scenarios were created for residents, allowing them to lead resuscitation simulations. The scenarios were based upon common conditions encountered during codes (Cardiac arrest). Trained evaluators provided real-time feedback, and pre-and post-surveys were conducted to assess team perception and gather feedback. Results: Baseline data revealed that 98.6% (143 of 145 residents total) felt uncertain or lacked confidence in leading effective codes in our hospital prior to the intervention. Post-test survey outcome data revealed that 95.1% of participants (136 residents of 143) reported that the sessions challenged their skills at leading codes and improved their skills at managing resuscitation teams. Conclusion: Organized codes with clear roles, responsibilities, bed positioning, and clear leadership significantly improve closed-loop communication, effective team interaction, and patient outcomes. The Mock Code Project fills the gap in training programs by focusing on team dynamics and leadership skills during IHCA resuscitation. Ongoing evaluations and feedback ensure continual improvement in resident confidence and skills. Implementing organized codes benefits residents and healthcare teams, ultimately improving patient care during IHCA. Well-designed mock code scenarios with real-time feedback from senior physicians are an effective way for trainees to develop these skills and this awareness without compromising patient safety.

Hospital Unit Type and Professional Roles as a Predictor of Relational Coordination in an Army Medical Center.

High-quality communication and relationships are associated with quality of care. Workflow differences across hospital units can impede communication and relationships among health care professionals. Relational coordination (RC) is a process of communication supported by shared goals, shared knowledge, and mutual respect and is associated with quality of care and better performance outcomes in civilian hospitals. However, RC has not been explored in military hospitals. The objective of our study was to determine whether RC differs between hospital units and professional roles. Specifically, we examined RC differences by unit type for nurses, resident physicians, and physicians working in an Army Medical Center. We conducted an exploratory analysis of a secondary question from a cross-sectional study using a convenience sample of active-duty and civilian licensed practical nurses (LPNs), registered nurses (RNs), physician residents, and physicians (n = 289). We received institutional review board approval from the study site. Data were collected from January 2020 to March 2020, and participants completed a 47-item survey regarding their experiences of RC in various hospital units. We used t tests and one-way analyses of variance to explore bivariate relationships between RC and other study variables, as well as multiple regression to explore whether RC varied by unit type. We controlled for education and experience by including them in the model because these variables may influence perceptions of nurse-physician RC and their interactions with each other. Seventy percent of participants were civilian (n = 203), 75% RNs (n = 217), and 78% female (n = 216). The mean age of respondents was 40 years (SD = 11.7), and the mean experience level was 11.9 years (SD = 9.5). RC was not associated with unit type. Total RC and between-role RC were associated with professional role. Physicians reported higher RC (β = .45, P = .01), and LPNs reported lower RC (β = -.06, P = .01). Education and experience were associated with RC. Participants with less experience reported higher RC (β = -.01, P = .00), and participants with graduate degrees reported lower RC (β = -.62, P = .00). We recommend hospital leaders consider interventions to build interprofessional relationships, including interdisciplinary meetings, huddles, and structured communication tools. Improving RC among health care professionals is a cost-effective and unique way to enhance communication and collaboration among health care professionals across hospital units.

Determinants and predictors of Occupational Burnout syndrome among Residents Physicians

Background: The burnout syndrome has 3 dimensions; first is emotional exhaustion, second one is depersonalization, and third is low personal accomplishment. Work related burnout is increased nowadays and it becomes a serious problem affecting people who working in human services, particularly healthcare workers. This study aimed to: Determine the frequency of burnout syndrome and related factors among Salahaddin resident physicians. Subject and Method: A cross-sectional study , done from 11th of November 2021 to 15th of March 2022. A convenient sample of 100 resident and permanent doctors, working in Salahdin Public hospitals. Inclusion criteria were current residents doctor who had at least one year in a residency program. Data collected using interview questionnaire form based on the Maslach Burnout Inventory. Results: The 100 resident doctor information analyzed and found that 56(56%) , 44(44%) were male and female respectively. High frequency of the resident aged 26-30 years 68(68%), 75(75%) of them living in Salahdin, junior residents represent 52(52%) and 48(48%) were permanent resident. The high scores of occupational exhaustion was reported among 41(41%). The high scores of depersonalization / loss of empathy was reported among 42(42%). The low scores of personal accomplishment assessment scores was reported among 64(64%). Females 21(47.7%) had more occupational exhaustion than male doctors 20(35.7%). high score of depersonalization / loss of empathy reported among 22(39.3%) of the male and 20(45.5%) of the females. Conclusion: burnout frequency was high among Iraqi residents with high scores of occupational exhaustion, and depersonalization/ loss of empathy, and high percentage of low scores of personal accomplishment assessment.

Educational and personal impacts of the COVID-19 pandemic on emergency medicine resident physicians: a qualitative study

BackgroundThe COVID-19 pandemic had a significant impact on both the clinical practice and the psychological states of frontline physicians in the emergency department. Trainees, at the beginning of their careers and thus still developing their practice styles and identities as physicians, were uniquely affected.ObjectiveIn this qualitative study, we sought to explore how the pandemic environment shaped the experiences of emergency medicine resident physicians.MethodsThis was a qualitative study. We conducted in-depth interviews with emergency medicine faculty, resident physicians, and staff at a single emergency department based at an urban academic institution in the northeastern United States. Interviews were audio recorded and transcribed, and transcripts were then analyzed in an iterative process by our coding team for recurring themes related to the resident experience.ResultsWe reached data saturation with 27 individuals. Of those who were interviewed, 10 were resident physicians [6 senior residents (PGY-3 or PGY-4) and 4 junior residents (PGY-1 or PGY-2)]. Three major recurring themes regarding resident physician experience emerged during our analysis of the interviews: (1) novel educational experiences dampened by negative structural forces from the pandemic, (2) fracturing of social interactions and mitigation through ad-hoc support systems and community of practice, and (3) development of negative emotions and psychological trauma including fear, resentment, and moral injury causing lasting harm.ConclusionsOur results suggest that emergency medicine resident physicians training during the COVID-19 pandemic faced unique experiences concerning their education, social support systems, and emotional states. While the educational and social experiences were described as having both negative and positive impacts, the emotional experiences were largely negative. Residency program leadership may use these insights to improve resident preparation, wellness, and resilience in the face of future adverse events.

Current status, challenges, and future directions of laparoscopic training in young surgeons: a nationwide survey in China

BackgroundWith the rapid advancement of technology, minimally invasive surgery, particularly laparoscopic surgery, has made significant progress in the field of surgery. Despite the advantages of laparoscopic surgery, a systematic training system for laparoscopic procedures is lacking in Chinese postgraduate medical education. Our study aims to explore the prevalence of laparoscopic training among resident and attending physicians in China and to assess the current state of training programs.MethodsA 10-item questionnaire was distributed to 1,750 resident and attending physicians specializing in surgery across China, with 1,324 valid responses (75.7% response rate). The survey focused on demographics, training curriculum content, and feedback on training effectiveness. Data analysis was conducted using Microsoft Excel and IBM SPSS.ResultsAmong the 1,324 respondents, 30.7% reported receiving laparoscopic training, primarily at the attending physician stage. Only 4% of resident physicians and 14% of attending physicians could independently perform complex laparoscopic surgeries. Most respondents (76.6%) could only assist in surgeries. The majority expressed a desire for more frequent and longer training sessions, with suture training being identified as the most beneficial.ConclusionsThis study underscores the critical need for comprehensive laparoscopic training in China. Early, frequent, and structured training programs are essential for developing proficient laparoscopic surgeons. Future initiatives should focus on expanding access to training at all levels of medical education, ensuring continuous skill development and improved surgical care quality.

Emergency department triaging using ChatGPT based on emergency severity index principles: a cross-sectional study

Erroneous and delayed triage in an increasingly crowded emergency department (ED). ChatGPT is an artificial intelligence model developed by OpenAI® and is being trained for use in natural language processing tasks. Our study aims to determine the accuracy of patient triage using ChatGPT according to the emergency severity index (ESI) for triage in EDs. In our cross-sectional study, 18 years and over patients who consecutively presented to our ED within 24 h were included. Age, gender, admission method, chief complaint, state of consciousness, and comorbidities were recorded on the case form, and the vital signs were detected at the triage desk. A five-member expert committee (EC) was formed from the fourth-year resident physicians. The investigators converted real-time patient information into a standardized case format. The urgency status of the patients was evaluated simultaneously by EC and ChatGPT according to ESI criteria. The median value of the EC decision was accepted as the gold standard. There was a statistically significant moderate agreement between EC and ChatGPT assessments regarding urgency status (Cohen’s Kappa = 0.659; P < 0.001). The accuracy between these two assessments was calculated as 76.6%. There was a high degree of agreement between EC and ChatGPT for the prediction of ESI-1 and 2, indicating high acuity (Cohen’s Kappa = 0.828). The diagnostic specificity, NPV, and accuracy of ChatGPT were determined as 95.63, 98.17 and 94.90%, respectively, for ESI high acuity categories. Our study shows that ChatGPT can successfully differentiate patients with high urgency. The findings are promising for integrating artificial intelligence-based applications such as ChatGPT into triage processes in EDs.