Introduction: Large language models, in particular ChatGPT, have showcased remarkable language processing capabilities. Given the substantial workload of university medical staff, this study aims to assess the quality of multiple-choice questions (MCQs) produced by ChatGPT for use in graduate medical examinations, compared to questions written by university professoriate staffs based on standard medical textbooks. Methods: 50 MCQs were generated by ChatGPT with reference to two standard undergraduate medical textbooks (Harrison’s, and Bailey & Love’s). Another 50 MCQs were drafted by two university professoriate staff using the same medical textbooks. All 100 MCQ were individually numbered, randomized and sent to five independent international assessors for MCQ quality assessment using a standardized assessment score on five assessment domains, namely, appropriateness of the question, clarity and specificity, relevance, discriminative power of alternatives, and suitability for medical graduate examination. Results: The total time required for ChatGPT to create the 50 questions was 20 minutes 25 seconds, while it took two human examiners a total of 211 minutes 33 seconds to draft the 50 questions. When a comparison of the mean score was made between the questions constructed by A.I. with those drafted by humans, only in the relevance domain that the A.I. was inferior to humans (A.I.: 7.56 +/- 0.94 vs human: 7.88 +/- 0.52; p = 0.04). There was no significant difference in question quality between questions drafted by A.I. versus humans, in the total assessment score as well as in other domains. Questions generated by A.I. yielded a wider range of scores, while those created by humans were consistent and within a narrower range. Conclusion: ChatGPT has the potential to generate comparable-quality MCQs for medical graduate examinations within a significantly shorter time.
Introduction: Male breast cancer is uncommon, delay in seeking medical attention often results in late presentation and poor prognosis.Methods: Retrospective review of a prospectively maintained database was performed. Patients who were still having regular follow‐up were contacted for telephone interview.Results: In this study, 56 male breast cancer patients were treated in our center from January 1998 to December 2018, accounting for 0.88% of all breast cancers treated during the same period of time. Median age of onset was 61 years old (Range: 33‐95). In this study, 6 (10.7%) patients presented with distant metastasis at the time of diagnosis and received palliative systemic treatment only. And, 50 patients were surgically treated and all had mastectomy. Axillary dissection was performed in 36 (72%) patients, while sentinel node biopsy was performed in 14 (28%) patients. Median tumor size was 23 mm (2‐100 mm). A Majority were diagnosed with invasive carcinoma (NOS), while 38 (67.8%) patients were node positive.Here 36 (64.3%) patients were alive at the time of the study, 31 (86.1%) patients responded to the telephone interview. More than 90% of our patients expressed various degrees of embarrassment at the time of breast symptom onset. Similarly, more than 90% of these patients experienced embarrassment while waiting in the breast center with predominant female patients. Most patients (N = 26) were not aware that breast cancer can occur in men prior to the diagnosis. Median duration from symptoms to the first medical consultation was 12.4 months (1‐120 months).Conclusion: Male breast cancer is rare and patients usually present late, Lack of knowledge, public education, and embarrassment are the important related factors.
Aims: Phyllodes tumour (PT) is an uncommon fibroepithelial tumour of the breast. It has a spectrum of aggressiveness in biological behaviour with chance of local recurrence and, occasionally, metastasis. Methods: A 15-year retrospective review from a multicentre database in Hong Kong was performed. Results: Clinical and pathological records of 465 patients with 469 PTs between 1998 and 2014 were reviewed. Median age of occurrence was 44 years (range 12–86 years). 281 (59.9%) PTs were benign, 124 (26.4%) were borderline and 64 (13.6%) were malignant. About half of all PTs (239, 51.5%) were between 2 and 5 cm while another 186 (40.1%) were >5 cm in size. Most PT (84.6%) were radiologically benign. Breast-conserving surgery (BCS) was feasible in 384 (82%) patients, whereas 84 (18%) patients had mastectomy. Multivariate analysis found that positive surgical margin (P<0.001) and BCS (P<0.001) were the only significant risk factors for local recurrence, while large tumour size (P=0.008) and malignant PT histotype (P<0.001) were the only significant risk factors for metastasis. Long-term prognosis of benign and borderline PT was excellent. After median follow-up interval of 85 months (range 12–180 months), the disease-specific survival of benign, borderline and malignant PT were 99.6%, 100% and 90.6%, respectively. Conclusions: Local recurrence of PTs occurs irrespective of the tumour grade. Surgical margin is the only amendable factor to reduce the chance of recurrence.
A novel chatbot mobile app for training of undergraduate medical students’ clinical history taking skills was developed in 2021. Students were able to take clinical history from the virtual patient for bedside teaching. A case-control study was conducted to evaluate the effectiveness of learning with chatbot mobile app, versus conventional bedside teachings with real patients. 132 final year medical students were randomized into two groups – Conventional bedside teaching with clinical history taken from a real patient, and Bedside teaching with clinical history taken from the Chatbot. Independent blinded assessment of students' history taking skills was conducted. Students’ performance were assessed by standardized marking scheme. Median age was 23 years old (Range 21–30 years old). There were 62 female and 70 male students. 64 students were randomized into conventional group while 68 students were randomized into the chatbot group. Baseline demographic data were comparable between the two groups. Blinded assessment of students’ performance in clinical history taking were comparable between the conventional group and chatbot group (p > 0.05). With the promising results we have demonstrated in this study, we believe training of history taking skills by chatbot will be a feasible alternative to conventional bedside teaching.