ChatGPT's Gastrointestinal Tumor Board Tango: A limping dance partner?

OBJECTIVES: This study aimed to assess the consistency and replicability of treatment recommendations provided by ChatGPT 3.5 compared to gastrointestinal tumor cases presented at multidisciplinary tumor boards (MTBs). It also aimed to distinguish between general and case-specific responses and investigated the precision of ChatGPT's recommendations in replicating exact treatment plans, particularly regarding chemotherapy regimens and follow-up protocols. MATERIAL AND METHODS: A retrospective study was carried out on 115 cases of gastrointestinal malignancies, selected from 448 patients reviewed in MTB meetings. A senior resident fed patient data into ChatGPT 3.5 to produce treatment recommendations, which were then evaluated against the tumor board's decisions by senior oncology fellows. RESULTS: Among the examined cases, ChatGPT 3.5 provided general information about the malignancy without considering individual patient characteristics in 19% of cases. However, only in 81% of cases, ChatGPT generated responses that were specific to the individual clinical scenarios. In the subset of case-specific responses, 83% of recommendations exhibited overall treatment strategy concordance between ChatGPT and MTB. However, the exact treatment concordance dropped to 65%, notably lower in recommending specific chemotherapy regimens. Cases recommended for surgery showed the highest concordance rates, while those involving chemotherapy recommendations faced challenges in precision. CONCLUSIONS: ChatGPT 3.5 demonstrates potential in aligning conceptual approaches to treatment strategies with MTB guidelines. However, it falls short in accurately duplicating specific treatment plans, especially concerning chemotherapy regimens and follow-up procedures. Ethical concerns and challenges in achieving exact replication necessitate prudence when considering ChatGPT 3.5 for direct clinical decision-making in MTBs.

Gemcitabine and nab-paclitaxel combined with afatinib in metastatic pancreatic cancer - Results of a phase 1b clinical trial.

PURPOSE: The combination of gemcitabine/nab-paclitaxel is an established standard treatment in the first-line treatment of metastatic ductal adenocarcinoma of the pancreas (mPDAC). Afatinib, an oral second-generation pan ErbB family tyrosine kinase inhibitor, has shown promising pre-clinical signs in the treatment of pancreatic cancer. The aim of this phase 1b trial was to determine the maximum tolerated dose (MTD) of afatinib in combination with gemcitabine/nab-paclitaxel in patients with mPDAC. METHODS: Treatment naïve patients (≥18 years) with histologically proven mPDAC and good performance status (ECOG 0/1) were enrolled to receive gemcitabine/nab-paclitaxel in combination with afatinib. Treatment was continued until disease progression, or unacceptable toxicity. The primary endpoint MTD was determined using a 3 + 3 design. Treatment started at dose level 0 with intravenous gemcitabine/nab-paclitaxel 1000 mg/m2 / 125 mg/m2 (day 1, 8, 15 of a 28-day cycle) + oral afatinib 30 mg daily. At dose level + 1 afatinib was increased to 40 mg. Secondary endpoints included safety parameters and exploratory endpoints evaluated treatment efficacy. RESULTS: Twelve patients were included in this trial, and 11 patients were treated and analysed in the safety and full analysis set (FAS). At dose level 0 the first three patients did not experience a dose-limiting toxicity (DLT). At dose leve (DL) + 1 two patients experienced a DLT. Accordingly, enrolment continued at DL 0 with three more patients, of which one experienced DLT (skin rash ≥ CTCAE grade 3). Seven patients (63.6%) experienced at least one treatment-emergent serious adverse event (TESAE), with four patients (36.4%) experiencing TESAEs grade 3-5 related to the study medication. In the FAS, the objective response rate (ORR) was 36.4%, median progression-free survival (PFS) was 3.5 months and median overall survival in nine evaluable patients was 7.5 months. CONCLUSIONS: In this phase 1b clinical trial, the MTD of gemcitabine/nab-paclitaxel (1000 mg/m2 / 125 mg/m2) and afatinib (30 mg) was established. In a cohort of 11 patients, the combination showed an acceptable safety profile.

Swapping data: A pragmatic approach for enabling academic-industrial partnerships.

Objectives: Academic institutions have access to comprehensive sets of real-world data. However, their potential for secondary use-for example, in medical outcomes research or health care quality management-is often limited due to data privacy concerns. External partners could help achieve this potential, yet documented frameworks for such cooperation are lacking. Therefore, this work presents a pragmatic approach for enabling academic-industrial data partnerships in a health care environment. Methods: We employ a value-swapping strategy to facilitate data sharing. Using tumor documentation and molecular pathology data, we define a data-altering process as well as rules for an organizational pipeline that includes the technical anonymization process. Results: The resulting dataset was fully anonymized while still retaining the critical properties of the original data to allow for external development and the training of analytical algorithms. Conclusion: Value swapping is a pragmatic, yet powerful method to balance data privacy and requirements for algorithm development; therefore, it is well suited to enable academic-industrial data partnerships.

Efficacy of immune checkpoint inhibitors in microsatellite unstable/mismatch repair-deficient advanced pancreatic adenocarcinoma: an AGEO European Cohort.

BACKGROUND: Immune checkpoint inhibitors (ICIs) improve oncological outcomes in patients with microsatellite instability-high (MSI) or mismatch repair-deficient (dMMR) advanced solid tumours. Nevertheless, based on limited published data, the outcome of patients with MSI/dMMR pancreatic ductal adenocarcinoma (PDAC) seems poorer when compared to other malignancies. This multi-institutional analysis sought to assess the efficacy and tolerability of ICIs in a large real-world cohort of patients with MSI/dMMR PDAC. METHODS: We retrospectively collected data from patients with MSI/dMMR advanced PDAC treated with ICIs in 16 centers. Progression-free survival and overall survival were calculated from the start of treatment, and we report objective response and disease control rates according to RECIST V1.1. RESULTS: Thirty-one MSI/dMMR advanced PDAC patients were identified. Twenty-five patients received single-agent anti-PD-1 antibodies, three patients received the combination of nivolumab and ipilimumab and three patients received immunotherapy in combination with chemotherapy. Among 31 evaluable patients, 15 (48.4%) had an objective response (three complete responses and 12 partial responses), and six (19.4%) had stable disease. With a median follow-up of 18 months, the median progression-free survival (PFS) was 26.7 months and the median overall survival (OS) was not reached. Disease control rates (DCRs) among patients with only one line of prior therapy (N = 17) was 76.5%. Grade 3-4 treatment-related adverse events were not observed. CONCLUSION: This retrospective analysis suggests that ICIs are effective and well tolerated in patients with MSI/dMMR advanced PDAC. Hence, our work supports the use of PD-1 inhibition in this group of patients with high unmet medical need.