Jan Clusmann, Fiona R. Kolbinger, Hannah Sophie Muti, Zunamys I. Carrero, Jan-Niklas Eckardt, Narmin Ghaffari Laleh, Chiara Maria Lavinia Loffler, Sophie-Caroline Schwarzkopf, M. Unger, Gregory P. Veldhuizen, Sophia J. Wagner, J. Kather
{"title":"Die kommende Entwicklung großer Sprachmodelle in der Medizin","authors":"Jan Clusmann, Fiona R. Kolbinger, Hannah Sophie Muti, Zunamys I. Carrero, Jan-Niklas Eckardt, Narmin Ghaffari Laleh, Chiara Maria Lavinia Loffler, Sophie-Caroline Schwarzkopf, M. Unger, Gregory P. Veldhuizen, Sophia J. Wagner, J. Kather","doi":"10.1159/000536600","DOIUrl":"https://doi.org/10.1159/000536600","url":null,"abstract":"Große Sprachmodelle (Large Language Models, LLMs) sind Tools der künstlichen Intelligenz (KI), die speziell für die Verarbeitung und Erzeugung von Text trainiert sind. LLMs erregten erhebliche öffentliche Aufmerksamkeit, nachdem ChatGPT von OpenAI im November 2022 öffentlich zugänglich gemacht wurde. LLMs können Fragen beantworten, Texte zusammenfassen, paraphrasieren und übersetzen, und zwar auf einer Ebene, die von menschlichen Fähigkeiten kaum zu unterscheiden ist. Die Möglichkeit, aktiv mit Modellen wie ChatGPT zu interagieren, macht LLMs zu attraktiven Tools in verschiedenen Bereichen, einschließlich der Medizin. Diese Modelle haben zwar das Potenzial, medizinisches Wissen zu demokratisieren und den Zugang zur Gesundheitsversorgung zu erleichtern, sie könnten jedoch aufgrund mangelnder Rechenschaftspflicht und Transparenz ebenso Fehlinformationen verbreiten und wissenschaftliches Fehlverhalten verschlimmern. In diesem Artikel geben wir einen systematischen und umfassenden Überblick über die Potenziale und Grenzen von LLMs in der klinischen Praxis, der medizinischen Forschung und der medizinischen Ausbildung.","PeriodicalId":413988,"journal":{"name":"Kompass Onkologie","volume":"225 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139842476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Cholangioskopie im Fokus: Künstliche Intelligenz verbessert Genauigkeit und Effizienz der Diagnoseverfahren","authors":"K. Homayounfar","doi":"10.1159/000537733","DOIUrl":"https://doi.org/10.1159/000537733","url":null,"abstract":"Background: We aimed to develop a convolutional neural network (CNN) model for detecting neoplastic lesions during real-time digital single-operator cholangioscopy (DSOC) and to clinically validate the model through comparisons with DSOC expert and nonexpert endoscopists. Methods: In this two-stage study, we first developed and validated CNN1. Then, we performed a multicenter diagnostic trial to compare four DSOC experts and nonexperts against an improved model (CNN2). Lesions were classified into neoplastic and non-neoplastic in accordance with Carlos Robles-Medranda (CRM) and Mendoza disaggregated criteria. The final diagnosis of neoplasia was based on histopathology and 12-month follow-up outcomes. Results: In stage I, CNN2 achieved a mean average precision of 0.88, an intersection over the union value of 83.24 %, and a total loss of 0.0975. For clinical validation, a total of 170 videos from newly included patients were analyzed with the CNN2. Half of cases (50 %) had neoplastic lesions. This model achieved significant accuracy values for neoplastic diagnosis, with a 90.5 % sensitivity, 68.2 % specificity, and 74.0 % and 87.8 % positive and negative predictive values, respectively. The CNN2 model outperformed nonexpert #2 (area under the receiver operating characteristic curve [AUC]-CRM 0.657 vs. AUC-CNN2 0.794, P < 0.05; AUC-Mendoza 0.582 vs. AUC-CNN2 0.794, P < 0.05), nonexpert #4 (AUC-CRM 0.683 vs. AUC-CNN2 0.791, P < 0.05), and expert #4 (AUC-CRM 0.755 vs. AUC-CNN2 0.848, P < 0.05; AUC-Mendoza 0.753 vs. AUC-CNN2 0.848, P < 0.05).","PeriodicalId":413988,"journal":{"name":"Kompass Onkologie","volume":"60 52","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139844768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Mobile Health: Potenziale und Herausforderungen in der medizinischen Versorgung","authors":"H. Link","doi":"10.1159/000537716","DOIUrl":"https://doi.org/10.1159/000537716","url":null,"abstract":"Background: Mobile health (mhealth) is gaining interest, with mobile devices and apps being ever more available among medical facilities and patients. However, in the field of radiation oncology, the medical benefits of mhealth apps are still underexplored. As an additional approach to patient care during radiotherapy, we designed a mobile treatment surveillance app based on patient-reported outcomes. Objective: We aimed to examine the feasibility of app-based treatment surveillance in patients undergoing radiotherapy (RT). Alongside technical practicability and acceptance, we assessed patient satisfaction and quality of life during treatment. Methods: This prospective single-center study was performed at Heidelberg University Hospital between August 2018 and January 2020. During RT we measured patients' quality of life, symptoms, and treatment satisfaction. Respective questionnaires (EORTC QLQ-C30 with diagnosis-specific modules, RAND PSQ-18) were presented to patients via a mobile app running on a designated tablet device. The primary endpoint was determined by the fraction of patients who completed at least 80% of the items. Secondary endpoints were disease-related quality of life and patient satisfaction. Results: A total of 49 cancer patients (14 breast, 13 pelvic, 12 lung, 10 prostate) were eligible for analysis. 79.6% (95% confidence interval: 66.4-88.5%; n = 39) of all patients completed at least 80% of the items received by the mobile app. A mean of 227.5 ± 48.25 questions were answered per patient. Breast cancer patients showed the highest rate of answered questions, with 92.9% (n = 13) completing at least 80% of the items.","PeriodicalId":413988,"journal":{"name":"Kompass Onkologie","volume":"34 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139784898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Adenokarzinome des ösophagogastralen Übergangs: Perioperative Therapie mit Ramucirumab und FLOT","authors":"G. Stocker","doi":"10.1159/000535533","DOIUrl":"https://doi.org/10.1159/000535533","url":null,"abstract":"This multicenter, randomized phase II/III study evaluated the addition of the vascular endothelial growth factor receptor-2 inhibitor ramucirumab to FLOT as perioperative treatment for resectable esophagogastric adenocarcinoma. Patients received either FLOT alone (Arm A) or combined with ramucirumab followed by ramucirumab monotherapy (Arm B). The primary endpoint for the phase II portion was the pathological complete or subtotal response (pCR/pSR) rate. Baseline characteristics were comparable between both arms with a high rate of tumors signet-ring cell component (A:47% B:43%). No between-arm difference in pCR/pSR rate was seen (A:29% B:26%), therefore the transition to phase III was not pursued. Nevertheless, the combination was associated with a significantly increased R0-resection rate compared with FLOT alone (A:82% B:96%; P = .009). In addition, the median disease-free survival was numerically improved in Arm B (A:21 months B:32 months, HR 0.75, P = 0.218), while the median overall survival was similar in both treatment arms (A:45 months B:46 months, HR 0.94, P = 0.803). Patients with Siewert type I tumors receiving transthoracic esophagectomy with intrathoracic anastomosis showed an increased risk of serious postoperative complications after ramucirumab treatment, therefore recruitment of those patients was stopped after the first-third of the study. Overall, surgical morbidity and mortality was comparable, whereas more non-surgical grade ≥ 3 adverse events were observed with the combination, especially anorexia (A:1% B:11%), hypertension (A:4% B:13%) and infections (A:19% B:33%). The combination of ramucirumab and FLOT as perioperative treatment shows efficacy signals, particularly in terms of R0 resection rates, for a study population with a high proportion of prognostically poor histological subtypes, and further evaluation in this subgroup seems warranted.","PeriodicalId":413988,"journal":{"name":"Kompass Onkologie","volume":"144 ","pages":"192 - 193"},"PeriodicalIF":0.0,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138983542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Aderhautmelanom: Sensitivität und Spezifität verschiedener prognostischer Systeme zur Lenkung der Überwachung auf Metastasen","authors":"I. Seibel","doi":"10.1159/000535360","DOIUrl":"https://doi.org/10.1159/000535360","url":null,"abstract":"Uveal melanoma (UM) metastasises in ˜50% of patients, most frequently to the liver. Surveillance imaging can provide early detection of hepatic metastases; however, guidance regarding UM patient risk stratification for surveillance is unclear. This study compared sensitivity and specificity of four current prognostic systems, when used for risk stratification for surveillance, on patients treated at the Liverpool Ocular Oncology Centre (LOOC) between 2007–2016 (n = 1047). It found that the Liverpool Uveal Melanoma Prognosticator Online III (LUMPOIII) or Liverpool Parsimonious Model (LPM) offered greater specificity at equal levels of sensitivity than the American Joint Committee on Cancer (AJCC) system or monosomy 3 alone, and suggests guidance to achieve 95% sensitivity and 51% specificity (i.e., how to detect the same number of patients with metastases, while reducing the number of negative scans). For example, 180 scans could be safely avoided over 5 years in 200 patients using the most specific approach. LUMPOIII also offered high sensitivity and improved specificity over the AJCC in the absence of genetic information, making the result relevant to centres that do not perform genetic testing, or where such testing is inappropriate or fails. This study provides valuable information for clinical guidelines for risk stratification for surveillance in UM.","PeriodicalId":413988,"journal":{"name":"Kompass Onkologie","volume":"38 34","pages":"196 - 197"},"PeriodicalIF":0.0,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139011904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Lokal fortgeschrittene Magen- und AEG-Tumoren: Neue Entwicklungen in der perioperativen Therapie","authors":"K. Heinrich, L. Weiss","doi":"10.1159/000535398","DOIUrl":"https://doi.org/10.1159/000535398","url":null,"abstract":"PURPOSE: High pathologic complete response (pCR) rates and comparably good survival data were seen in a phase II trial combining perioperative fluorouracil, leucovorin, oxaliplatin, and docetaxel (FLOT) chemotherapy with trastuzumab for resectable, esophagogastric adenocarcinoma (EGA). The current trial evaluates the addition of trastuzumab and pertuzumab to FLOT as perioperative treatment for human epidermal growth factor receptor 2–positive resectable EGA. METHODS: In this multicenter, randomized phase II/III trial, patients with human epidermal growth factor receptor 2–positive, resectable EGA (≥ clinical tumor 2 or clinical nodal–positive) were assigned to four pre- and postoperative cycles of either FLOT alone (arm A) or combined with trastuzumab and pertuzumab, followed by nine cycles of trastuzumab/pertuzumab (arm B). The primary end point for the phase II part was the rate of pCR. RESULTS: The trial was closed prematurely, without transition into phase III, after results of the JACOB trial were reported. Eighty-one patients were randomly assigned (A: 41/B: 40) during the phase II part. The pCR rate was significantly improved with the trastuzumab/pertuzumab treatment (A: 12%/B: 35%; P = .02). Similarly, the rate of pathologic lymph node negativity was higher with trastuzumab/pertuzumab (A: 39%/B: 68%), whereas the R0 resection rate (A: 90%/B: 93%) and surgical morbidity (A: 43%/B: 44%) were comparable. Moreover, the inhouse mortality was equal in both arms (overall 2.5%). The median disease-free survival was 26 months in arm A and not yet reached in arm B (hazard ratio, 0.58; P = .14). After a median follow-up of 22 months, the median overall survival was not yet reached (hazard ratio, 0.56; P = .24). Disease-free survival and overall survival rates at 24 months were 54% (95% CI, 38 to 71) and 77% (95% CI, 63 to 90) in arm A and 70% (95% CI, 55 to 85) and 84% (95% CI, 72 to 96) in arm B, respectively. More ≥ grade 3 adverse events were reported with trastuzumab/pertuzumab, especially diarrhea (A: 5%/B: 41%) and leukopenia (A: 13%/B: 23%).","PeriodicalId":413988,"journal":{"name":"Kompass Onkologie","volume":"60 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138594966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}