Collective Wisdom and Multidisciplinary Tumor Boards

Background Due to the complexity of diagnostics, staging and therapy of cancer an interdisciplinary connection between different oncological disciplines is essential. Multidisciplinary tumor boards (MTBs) have been introduced more than a decade ago in order to facilitate interdisciplinary patient discussion and management. However, the efficacy of this approach is rather theoretical and only little evidence is given by the current literature whether patients with thoracic malignancies may benefit from MTBs.

214P Influence of prompt-engineering and custom GPTs on ChatGPT-5.1’s internal consistency (IC) and external validity (EV) when assessing sarcoma cases

213P Efficacy and safety of eribulin in liposarcoma and leiomyosarcoma: A systematic review and meta-analysis

Aim:To evaluate the efficacy of a pediatric multidisciplinary tumor board (MTB) in Uganda.Patients & methods:We documented the discussion of cases presented at a pediatric MTB and subsequently, though retrospective chart review, determined the degree to which decision were implemented.Results:95 patients were discussed. In total, 129 of 226 (57%) distinct management decisions reached during the MTBs were implemented. Of these, 15 resulted in changes in diagnosis and 53 were classified as major changes in management. Decisions on chemotherapy were the most likely to be successfully enacted (51/58), followed by radiotherapy (18/30) and surgery (12/21). Labs/consults were less likely to be implemented.Conclusion:Key improvements, specifically in the documentation and implementation of management decisions, are needed to improve the MTB's efficacy.

585 Background: Pancreatic cancer is the third leading cause of cancer death in the United States; it is a complex disease requiring coordinated patient care. Multidisciplinary tumor boards (MTB) are today's gold standard in pancreatic cancer but are frequently criticized for being time-intensive and inefficient. To address this issue, Cancer Collective and Hive Networks have developed a novel patient-information visualization tool designed to improve the communication and efficiency of multidisciplinary tumor board meetings. This pilot study investigated the patient-information visualization tool's usability, efficiency, and feasibility in pancreatic cancer tumor board meetings. Methods: A prospective multi-center pilot study was conducted at Northwell Health (a comprehensive community cancer program [NCCCP] in the Northeastern United States) and the University of California San Diego (an NCI-designated comprehensive cancer center in [NCCC] in the Southwestern United States. The feasibility of the tool was assessed by measuring the percentage of MTB cases discussed that used the patient-information visualization tool. The usability and efficiency of the tool were assessed via Likert scale questions. Acceptable usability and effectiveness were defined as a 70% score or higher. Additionally, MTB participants were queried for input on design improvements for future iterations and expected future directions of tool use. Results: The patient-information visualization tool was rolled out on 07/22/2022 at the NCCP and NCCC. From 07/22/2022-05/31/2023, 170 (92%) MTB cases were reviewed at the NCCP. From 07/22/2022-05/31/2023, 74 cases (100%) of MTB cases were reviewed using the patient-information visualization tool at the NCCP. The NCCP (n=9) mean scores for usability and efficiency were 4.31 (86%) and 4.17 (83%) respectively. The NCCC (n=6) mean scores for usability and efficiency were 4.04 (81%) and 3.96 (79%) respectively. Qualitative feedback, reported on survey open-ended questions, included suggested enhancements to improve the tool’s usability, such as leveraging data automation to reduce data entry burden, improving the user interface for ease of data visualization, and adding additional data elements (e.g., specific procedure and appointment details) to improve decision-making utility. Conclusions: Implementing the novel digital dashboard to visualize pancreatic cancer patient data was highly feasible, usable, and efficient. Future directions of tool use include refining based on qualitative feedback from end users and planning for data automation and interoperability with the EMR.

e23256 Background: Artificial intelligence (AI) is emerging as a valuable tool to support clinical decisions in oncology. Nevertheless, its practical implementation in clinical settings requires further validation. This study evaluates the concordance between a Genitourinary Multidisciplinary Tumor Board (MTB) and ChatGPT 4.0. Methods: An observational, retrospective design was used to analyze cases discussed in the MTB at a university hospital in Mexico from January 2023 to January 2024. The protocol was developed before implementation, and formal approval was received from the Ethics Committee. Cases with a complete medical record and a comprehensive tumor board record were included. MTB recommendations were compared with those from ChatGPT 4.0 using an open-ended approach. ChatGPT received a structured clinical prompt (demographics, history and physical, laboratory results, imaging, and pathology) requesting a management plan. Concordance between plans was analyzed across three levels of decision-making: Level I (Diagnostic vs. Therapeutic Approach), Level II (Type of Management), specifying tests or treatments, and Level III (Comprehensive Management), focusing on specific tests or treatment selection. Concordance rates and Cohen’s kappa coefficients were calculated and interpreted using medical standards: κ > 0.80 = excellent, κ 0.61–0.80 = acceptable, and κ < 0.60 = questionable. Results: Thirty-seven patients with genitourinary tumors met inclusion criteria with complete medical and MTB records. Median age was 64, 78% (n = 29) were male and 22% female (n = 8). Tumor types included kidney (27%, n = 10), testicular (27%, n = 10), bladder (19%, n = 7), penile (16%, n = 6), prostate (3%, n = 1), and adrenal (3%, n = 1). Concordance between the multidisciplinary tumor board and ChatGPT 4.0 was assessed across three decision levels. Level I showed 86% concordance (κ = 0.65, acceptable). Level II had 70% concordance (κ = 0.61, acceptable), while Level III dropped to 54% (κ = 0.59, questionable). Conclusions: Managing clinical oncology cases is complex, often requiring input from multidisciplinary teams. During MTB discussions, diagnostic results are reviewed, and team feedback may lead to adjustments in treatment plans. This real-time reevaluation remains beyond the scope of large language models like ChatGPT. Exploratory analysis found that most discordance occurred in high-complexity cases requiring dynamic data integration. Further study is essential to identify potential factors influencing differences between MTB and ChatGPT recommendations. This understanding may enhance its role as a supportive tool in oncology. Concordance rates and kappa values across clinical decision-making levels. Level Concordance (%) Kappa Interpretation Level I 86.49 0.65 Acceptable Level II 70.27 0.61 Acceptable Level III 54.05 0.59 Questionable

Squamous cell carcinoma (SCC) of the head and neck is a great burden globally, which is being tackled through treatment options of surgery, radiation therapy, chemotherapy, or a combination of these, to avoid disease-related mortality. Multidisciplinary tumour boards play a pivotal role in customising and deciding management plan based on clinical aspects. The objective of the study is to determine the concordance of opinion between the treatment plan of a primary physician and board members. This is a retrospective cross-sectional study that includes 137 head and neck carcinoma cases. They were discussed in the multidisciplinary tumour board meeting and were reviewed; all demographics were analysed including the tumour staging and the decisions of the primary physician was compared with those of the board. To check the concordance between primary surgeon plans or after board discussion Kappa agreement test was used. Total of 137 patients were included in the study out of which 63 cases were pre-treatment and 74 cases were post-treatment, i.e., surgically treated cases, with the distribution being 46% and 54%, respectively. Most cases, totaling 120, were SCC, accounting for 80% of the total cases. Among the pre-treatment cases, T4a and N0 were the most common categories, with 29 and 40 cases, respectively. Similarly, in post-treatment cases, the majority fell into the T4a and N1 categories, with 29 and 38 cases, respectively. When comparing the primary surgeon's plan with the tumour board meeting decision, the agreement showed a value of 0.273, indicating a slight level of agreement between the two entities. Our data indicates that the multidisciplinary head and neck tumour board may have influenced the treatment plans of the primary surgeon, in approximately one in two patients (43.06%).

The Multidisciplinary Management of Hepatocellular Carcinoma.

BackgroundThe implementation of multidisciplinary tumor board (MDTB) meetings significantly ameliorated the management of oncological diseases. However, few evidences are currently present on their impact on pancreatic cancer (PC) management. The aim of this study was to evaluate the impact of the MDTB on PC diagnosis, resectability and tumor response to oncological treatment compared with indications before discussion.Patients and methodsAll patients with a suspected or proven diagnosis of PC presented at the MDTB from 2017 to 2019 were included in the study. Changes of diagnosis, resectability and tumor response to oncological/radiation treatment between pre- and post-MDTB discussion were analyzed.ResultsA total of 438 cases were included in the study: 249 (56.8%) were presented as new diagnoses, 148 (33.8%) for resectability assessment and 41 (9.4%) for tumor response evaluation to oncological treatment. MDTB discussion led to a change in diagnosis in 54/249 cases (21.7%), with a consequent treatment strategy variation in 36 cases (14.5%). Change in resectability was documented in 44/148 cases (29.7%), with the highest discrepancy for borderline lesions. The treatment strategy was thus modified in 27 patients (18.2%). The MDTB brought a modification in the tumor response assessment in 6/41 cases (14.6%), with a consequent protocol modification in four (9.8%) cases.ConclusionsMDTB discussion significantly impacts on PC management, especially in high-volume centers, with consistent variations in terms of diagnosis, resectability and tumor response assessment compared with indications before discussion.

Patient Dumping: The Physician's Dilemma

INTRODUCTION: The objective of this study was to investigate whether a multidisciplinary approach to breast cancer care with the inclusion of a reproductive health specialist improves referral rates for fertility counseling and/or preservation. METHODS: An IRB-approved retrospective study including women of reproductive age diagnosed with locally advanced breast cancer and treated at a health system before and after the advent of a comprehensive, multidisciplinary tumor board (cMTB) with a reproductive health specialist was conducted. Rates of referral for fertility counseling and utilization of fertility preservation methods were compared between the cMTB and non-cMTB groups using t tests. Secondary analyses comparing baseline group characteristics and rates of referral/fertility preservation by age, insurance type, and race were performed using χ2 tests. RESULTS: Of 306 study participants, 117 were cared for by a non-cMTB and 189 by a cMTB. The groups did not differ in average age, parity, breast cancer subtype, insurance type (public versus private), or treatment site (urban versus suburban); however, the distribution of race was significantly different (P=.003). Overall, a greater percentage of women in the cMTB group received referrals for fertility counseling compared to those in the non-cMTB group (23.3% versus 0.9%, P<.001). Of the patients in the cMTB group who were referred for counseling, 20.5% underwent fertility preservation. Within the cMTB group, women younger than 30 were significantly more likely to be referred for fertility counseling (41.7% versus 20.6%, P=.043) and undergo a fertility preservation procedure (16.7% versus 3.0%, P=.016) than those aged 31–40. No significant differences in rates of referral or fertility preservation by race or insurance type were noted within each group. CONCLUSION: The inclusion of a reproductive health specialist in a multidisciplinary breast cancer tumor board increased rates of referral for fertility counseling for women of reproductive age. A similar, comprehensive approach to the care of reproductive-aged women with gynecologic malignancies should be considered.

BackgroundHead and neck squamous cell carcinoma (HNSCC) is a complex malignancy that requires a multidisciplinary approach in clinical practice, especially in tumor board discussions. In recent years, artificial intelligence has emerged as a tool to assist healthcare professionals in making informed decisions. This study investigates the application of ChatGPT 3.5 and ChatGPT 4.0, natural language processing models, in tumor board decision-making.MethodsWe conducted a pilot study in October 2023 on 20 consecutive head and neck cancer patients discussed in our multidisciplinary tumor board (MDT). Patients with a primary diagnosis of head and neck cancer were included. The MDT and ChatGPT 3.5 and ChatGPT 4.0 recommendations for each patient were compared by two independent reviewers and the number of therapy options, the clinical recommendation, the explanation and the summarization were graded.ResultsIn this study, ChatGPT 3.5 provided mostly general answers for surgery, chemotherapy, and radiation therapy. For clinical recommendation, explanation and summarization ChatGPT 3.5 and 4.0 scored well, but demonstrated to be mostly an assisting tool, suggesting significantly more therapy options than our MDT, while some of the recommended treatment modalities like primary immunotherapy are not part of the current treatment guidelines.ConclusionsThis research demonstrates that advanced AI models at the moment can merely assist in the MDT setting, since the current versions list common therapy options, but sometimes recommend incorrect treatment options and in the case of ChatGPT 3.5 lack information on the source material.

Background and ObjectivesThe COVID‐19 pandemic required rapid adaptation of multidisciplinary tumor board conferences to a virtual setting; however, there are little data describing the benefits and challenges of using such a platform.MethodsAn anonymous quality improvement survey was sent to participants of tumor board meetings at a large academic institution. Participants answered questions pertaining to the relative strengths and weaknesses of in‐person and virtual settings.ResultsA total of 335 responses (23.3% response rate) were recorded, and 253 met inclusion criteria. Respondents represented 25 different tumor board meetings, with colorectal, breast, and liver (18.6%, 17.0%, and 13.0%, respectively) being the most commonly attended. Virtual tumor boards were equivalent to in‐person across 9 of 10 domains queried, while a virtual format was preferred for participation in off‐site tumor boards. The lack of networking opportunities was ranked by physicians to be a significant challenge of the virtual format. Consistent leadership and organization, engaged participation of all attendees, and upgrading technology infrastructure were considered critical for success of virtual meetings.ConclusionsThe implementation of virtual tumor board meetings has been associated with numerous challenges. However, improving several key aspects can improve participant satisfaction and ensure excellent patient care.

Adjuvant! Online does not significantly influence adjuvant chemotherapy decisions of a breast cancer multidisciplinary team (MDT): a prospective study

Pre-B-Cell Leukemia Transcription Factor 1 Regulates Expression of Valosin-Containing Protein, a Gene Involved in Cancer Growth