Fatima, Maurish

Abstract Background Presacral tumours are rare, heterogeneous lesions. Historical classification systems for presacral tumours have provided a valuable framework, but were based on limited available data. This study aimed to develop a contemporary classification aligned with current tumour entities and clinical practice. Methods A prospectively registered systematic review of surgically managed presacral tumours published from 1975 to 2025 was combined with a retrospective multisite institutional surgical pathology review from 1986 to 2025. Pathological descriptors were extracted, cross-referenced, harmonized to current terminology, and organized through multidisciplinary expert review to obtain a new classification. Results The systematic review identified 5997 records, of which 203 studies met the inclusion criteria and contributed 181 pathological terms after generic and unclassifiable diagnoses were removed. Review of 3606 pathology reports identified 19 additional terms, bringing the total to 200 pathological terms. After harmonization to current terminology and exclusion of non-neoplastic processes, a contemporary classification was developed using biological descriptors: developmental versus acquired origin; tissue lineage (neurogenic, osseous/haematopoietic, soft tissue, or miscellaneous); and tumour behaviour (benign, locally recurrent without metastatic potential, locally recurrent with low metastatic potential, malignant non-sarcoma, or malignant sarcoma). Conclusion The Mayo Clinic classification of presacral tumours updates historical systems by reflecting the broader, more modern spectrum of neoplasms and distinguishing lesions by lineage and biological behaviour. It may improve diagnostic clarity, communication, and selection of appropriate observation, multidisciplinary assessment, and treatment pathways.

Abstract Background The ability of large language models (LLMs) to work collaboratively and screen studies in a systematic review (SR) is under-explored. Hence, we aimed to evaluate the effectiveness of LLMs in automating the process of screening in systematic reviews. Methods This is an observational study which included labeled data (title and abstracts) for five SRs. Originally, two reviewers screened the citations independently for eligibility. A third reviewer cross-checked each citation for quality assurance. GPT-4, Claude-3-Sonnet, and Gemini-Pro-1.0 were used using zero-shot chain-of-thought prompting. Collaborative approaches included (i): conflict resolution using benefit of the doubt, (ii) majority voting using an independent third LLM and (iii) conflict resolution using an informed third LLM. Performance was assessed using accuracy, precision for exclusion, and recall for inclusion. Work saved over samples (WSS) was computed to estimate the reduction in manual human effort. Results A total of 11300 articles were included in this study. The individual models, GPT-4, Claude-3-Sonnet, and Gemini-Pro-1.0 exhibited a high precision for exclusion, achieving 99.7%, 99.7%, and 99.2% and high recall for inclusion achieving 95.5%, 96.6% and 85.7%, respectively. However, the collaborative approach utilizing the two best-performing models (GPT-4 and Claude-3S) achieved an average precision of 99.9% and a recall of 98.5% (across all collaborative approaches). Furthermore, the proposed collaborative approach resulted in an average WSS of 63.5%, compared to the average WSS of 45.2% for individual models. Conversational LLM interactions showed a consistent pattern of results. Limitations This study was limited due to reliance on proprietary models, and evaluation on oncology datasets. Conclusion Evidence shows that collaborative LLMs enable efficient, high-performing screening in systematic reviews, supporting continuous evidence updates. Primary funding source NIH (U24CA265879-01-1) and Carolyn-Ann-Kennedy-Bacon Fund.