ABSTRACT
BACKGROUND: Whether GPT-4, the conversational artificial intelligence, can accurately diagnose and triage health conditions and whether it presents racial and ethnic biases in its decisions remain unclear. OBJECTIVE: We aim to assess the accuracy of GPT-4 in the diagnosis and triage of health conditions and whether its performance varies by patient race and ethnicity. METHODS: We compared the performance of GPT-4 and physicians, using 45 typical clinical vignettes, each with a correct diagnosis and triage level, in February and March 2023. For each of the 45 clinical vignettes, GPT-4 and 3 board-certified physicians provided the most likely primary diagnosis and triage level (emergency, nonemergency, or self-care). Independent reviewers evaluated the diagnoses as "correct" or "incorrect." Physician diagnosis was defined as the consensus of the 3 physicians. We evaluated whether the performance of GPT-4 varies by patient race and ethnicity, by adding the information on patient race and ethnicity to the clinical vignettes. RESULTS: The accuracy of diagnosis was comparable between GPT-4 and physicians (the percentage of correct diagnosis was 97.8% (44/45; 95% CI 88.2%-99.9%) for GPT-4 and 91.1% (41/45; 95% CI 78.8%-97.5%) for physicians; P=.38). GPT-4 provided appropriate reasoning for 97.8% (44/45) of the vignettes. The appropriateness of triage was comparable between GPT-4 and physicians (GPT-4: 30/45, 66.7%; 95% CI 51.0%-80.0%; physicians: 30/45, 66.7%; 95% CI 51.0%-80.0%; P=.99). The performance of GPT-4 in diagnosing health conditions did not vary among different races and ethnicities (Black, White, Asian, and Hispanic), with an accuracy of 100% (95% CI 78.2%-100%). P values, compared to the GPT-4 output without incorporating race and ethnicity information, were all .99. The accuracy of triage was not significantly different even if patients' race and ethnicity information was added. The accuracy of triage was 62.2% (95% CI 46.5%-76.2%; P=.50) for Black patients; 66.7% (95% CI 51.0%-80.0%; P=.99) for White patients; 66.7% (95% CI 51.0%-80.0%; P=.99) for Asian patients, and 62.2% (95% CI 46.5%-76.2%; P=.69) for Hispanic patients. P values were calculated by comparing the outputs with and without conditioning on race and ethnicity. CONCLUSIONS: GPT-4's ability to diagnose and triage typical clinical vignettes was comparable to that of board-certified physicians. The performance of GPT-4 did not vary by patient race and ethnicity. These findings should be informative for health systems looking to introduce conversational artificial intelligence to improve the efficiency of patient diagnosis and triage.
ABSTRACT
Aim: Hip fracture is one of the most common fall-related injuries in the elderly population. Although falls may cause multiple types of injuries, no study has investigated the details of fall-related injuries accompanied by hip fractures. This study aimed to characterize the features of such injuries. Methods: This is a cross-sectional study using data from four tertiary emergency departments in Japan. We identified patients diagnosed with hip fracture including femoral neck fracture, trochanter fracture, or subtrochanteric fracture from May 12, 2014 to July 12, 2021. Among patients with hip fracture, we included those with fall-related hip fracture. We excluded patients ages <40 years old and whose fall was high energy onset, defined as fall from more than three steps or 1 m. Results: Among 326 emergency departments patients diagnosed with fall-related hip fracture, 288 patients were eligible for the analysis. Seventeen patients (6%) had injuries in addition to hip fractures. The most frequent injury was upper limb injury (e.g., distal radial fracture; n = 5, 30%), followed by head injury (e.g., subdural hematoma; n = 4, 24%), chest injury (e.g., pneumothorax; n = 2, 12%), and trunk injury (vertebral compression fracture; n = 2, 12%). There were no significantly different clinical characteristics between patients with hip injuries and those without. Conclusion: A total of 6% of patients diagnosed with hip fracture had other fall-related injuries. The most frequent were upper limb injury and head injury. Our findings underscore the importance of whole-body assessment in patients with fall-related hip fracture in the emergency department.
ABSTRACT
The patient was 70-years-old women, 27 years ago, she was diagnosed with total colitis-type ulcerative colitis. Eighteen years after the diagnosis, she self-suspended his hospital visit because her condition was stable. After 4 years, ulcerative colitis rekindled, she resumed taking a 5-ASA. And 2 years later, colonoscopy revealed type 3 tumor in the descending colon. Tumor biopsy indicated an adenocarcinoma(tub1, tub2)derived from ulcerative colitis. Originally total proctocolectomy is necessary, but patient strongly hoped to leave the colon. We performed laparoscopic left hemicolonectomy(D2, SST). The pathological diagnosis was pT3, pN2, pM0, pStage â ¢c. After the operation, chemotherapy(mFOLFOX6)was carried out for 6 months. We regularly checked tumor markers and followed up with a colonoscopy once every 6 months. But 3 years and 9 months after surgery, ulcerative colitis rekindled and adenocarcinoma in the transverse colon found by colonoscopy. We performed total proctocolectomy with ileal J-pouch anal-canal anastomosis. Four months after the second operation, advanced defecation disorder has not been observed.
Subject(s)
Adenocarcinoma , Colitis, Ulcerative , Colonic Pouches , Proctocolectomy, Restorative , Adenocarcinoma/drug therapy , Adenocarcinoma/surgery , Aged , Anastomosis, Surgical , Colitis, Ulcerative/drug therapy , Colitis, Ulcerative/surgery , Female , HumansABSTRACT
A 58-year-old woman visited our hospital for diagnosis and treatment of rectal tumor. The tumor was diagnosed as adenocarcinoma metastasizing to the uterus and vagina. Using CT, metastases were detected in the lung, liver, and right inguinal lymph node. First, we performed sigmoid-loop-colostomy. Thereafter, the patient received chemotherapy(CapeOX plus Bev) for 8 courses and chemoradiotherapy(total 50 Gy plus S-1 therapy). Ten months after the initial examination, we performed abdominoperineal resection of the rectum combined with the resection of the posterior wall of the vagina, hysterectomy, and bilateral adnexectomy. Because of a large defect in the perineal region, we also performed reconstruction using the left gracilis muscle flap. The postoperative course was uneventful, and the patient was discharged 22 days after surgery. Once the wound healed, chemotherapy(CapeIRI plus Bev)was initiated. After 10 courses of chemotherapy, metastasis and local recurrence could no longer be detected. This suggests that preoperative chemotherapy, chemoradiotherapy, and perineum reconstruction could enable the radical resection of advanced rectal cancer.
Subject(s)
Rectal Neoplasms , Antineoplastic Combined Chemotherapy Protocols , Chemoradiotherapy , Female , Humans , Middle Aged , Neoplasm Recurrence, Local , Perineum , Rectal Neoplasms/therapyABSTRACT
A 91-year-old woman visited a local hospital with the chief complaint of bloody stool. The patient was noted that her platelet count is 1,000/µL, so she was referred to our hospital. Also after admission, she had bloody stool continuously. Then lower gastrointestinal endoscopy was done and it indicated that the reason for these symptoms is cecum colon cancer (cT3N0M0). We decided to perform an operation. Before the operation, in order to improve her platelet count to 100,000/µL high dose intravenous immunoglobulin, steroid therapy and platelet transfusion had done. The operation is laparoscopic ileocecal resection and the amount of bleeding is 10 g. The postoperative course was uneventful, and her platelet count became within normal range by platelet transfusion for 4 days. Until latest follow-up she has neither recurrence of the cancer nor thrombocytopenia. This case suggests that appropriate treatments make it impossible laparoscopic surgery for cecum colon cancer with ITP perform safety and resection for cancers may contribute to improve ITP.