RESUMEN
BACKGROUND: Diagnosing myocarditis relies on multimodal data, including cardiovascular magnetic resonance (CMR), clinical symptoms, and blood values. The correct interpretation and integration of CMR findings require radiological expertise and knowledge. We aimed to investigate the performance of Generative Pre-trained Transformer 4 (GPT-4), a large language model, for report-based medical decision-making in the context of cardiac MRI for suspected myocarditis. METHODS: This retrospective study includes CMR reports from 396 patients with suspected myocarditis and eight centers, respectively. CMR reports and patient data including blood values, age, and further clinical information were provided to GPT-4 and radiologists with 1 (resident 1), 2 (resident 2), and 4 years (resident 3) of experience in CMR and knowledge of the 2018 Lake Louise Criteria. The final impression of the report regarding the radiological assessment of whether myocarditis is present or not was not provided. The performance of Generative pre-trained transformer 4 (GPT-4) and the human readers were compared to a consensus reading (two board-certified radiologists with 8 and 10 years of experience in CMR). Sensitivity, specificity, and accuracy were calculated. RESULTS: GPT-4 yielded an accuracy of 83%, sensitivity of 90%, and specificity of 78%, which was comparable to the physician with 1 year of experience (R1: 86%, 90%, 84%, p = 0.14) and lower than that of more experienced physicians (R2: 89%, 86%, 91%, p = 0.007 and R3: 91%, 85%, 96%, p < 0.001). GPT-4 and human readers showed a higher diagnostic performance when results from T1- and T2-mapping sequences were part of the reports, for residents 1 and 3 with statistical significance (p = 0.004 and p = 0.02, respectively). CONCLUSION: GPT-4 yielded good accuracy for diagnosing myocarditis based on CMR reports in a large dataset from multiple centers and therefore holds the potential to serve as a diagnostic decision-supporting tool in this capacity, particularly for less experienced physicians. Further studies are required to explore the full potential and elucidate educational aspects of the integration of large language models in medical decision-making.
RESUMEN
BACKGROUND: This multicenter study analyzed the relationship between preoperative symptoms and postsurgical outcomes utilizing the German national DGAV StuDoQ|Pancreas database. METHODS: This retrospective study included 2,643 pancreatic ductal adenocarcinoma patients undergoing pancreatic head resection from 2013-2017 within the German pancreatic surgery registry (DGAV StuDoQ|Pancreas). The association of preoperative symptoms with overall survival was analyzed using Kaplan-Meier and Cox regression analysis. RESULTS: Preoperative symptoms were common, with 2,380 of 2,643 (90%) patients presenting with any one or more of the following symptoms: jaundice (40%), biliary obstruction treated with biliary stent (41%), pain (37%), weight loss (29%), nausea (18%), diabetes (31%), emesis (6%), and recent onset diabetes (5%). Patients were separated into 3 groups: no symptoms (n = 293), symptoms (n = 2,229), and recent onset diabetes (n = 121). The 3 groups differed in body mass index and nodal staging, where patients with recent onset diabetes had the highest values (body mass index: no symptoms: 24.5 kg/m2, symptoms: 25.1 kg/m2; recent-onset diabetes: 26.3 kg/m2, P = .007), (no symptoms: N1: 55%, N2: 10%; symptoms: N1: 53%, N2: 17%; recent-onset diabetes: N1: 56%, N2: 16%, P = .023). Other pathological characteristics, carbohydrate antigen 19-9 levels, and adjuvant chemotherapy receival did not differ between the groups. Interestingly, recent-onset diabetes was associated with better survival compared with the other groups (Median overall survival: 28 months [no symptoms at all], 22 months [symptoms] versus not reached [recent onset diabetes group], and 5-year overall survival rates of 28%, 11%, and 57%, respectively [log rank, P = .013]). Multivariable analysis revealed that recent-onset diabetes and preoperative symptoms were independently associated with overall survival (recent-onset diabetes, relative risk 0.052 P = .027, >5 symptoms relative risk 3.66, P < .001). CONCLUSION: Pancreatic ductal adenocarcinoma symptoms occured in up to 90% of patients with resectable pancreatic ductal adenocarcinoma. In addition, PDAC symptoms were associated with overall survival and might identify unique pancreatic ductal adenocarcinoma subtypes.
