Thanks to the rapidly evolving integration of LLMs into decision-support tools, a significant transformation is happening across large-scale systems. Like other medical fields, the use of LLMs such as GPT-4 is gaining increasing interest in radiation oncology as well. An attempt to assess GPT-4's performance in radiation oncology was made via a dedicated 100-question examination on the highly specialized topic of radiation oncology physics, revealing GPT-4's superiority over other LLMs. GPT-4's performance on a broader field of clinical radiation oncology is further benchmarked by the ACR Radiation Oncology In-Training (TXIT) exam where GPT-4 achieved a high accuracy of 74.57%. Its performance on re-labelling structure names in accordance with the AAPM TG-263 report has also been benchmarked, achieving above 96% accuracies. Such studies shed light on the potential of LLMs in radiation oncology. As interest in the potential and constraints of LLMs in general healthcare applications continues to rise5, the capabilities and limitations of LLMs in radiation oncology decision support have not yet been fully explored.
Traditional health authority approval for oncology drugs is based on a clinical benefit endpoint, or a valid surrogate. In 1992 the FDA created the Accelerated Approval pathway to allow for earlier approval of therapies in serious conditions with an unmet medical need. This is accomplished typically by granting accelerated approval based on a surrogate endpoint that can be measured earlier than a traditional approval endpoint. Minimal residual disease (MRD) is a sensitive measure of residual cancer cells in hematology oncology after treatment, and is increasingly considered as a secondary or exploratory endpoint due to its prognostic potential for traditional clinical trial endpoints such as progression-free survival (PFS) and overall survival (OS). This work aims to evaluate MRD's surrogacy potential across several hematologic cancer indications while keeping the focus on follicular lymphoma (FL), using data from published studies. We examine individual-level and trial-level correlations extracted from previously published studies to elucidate the potential role of MRD in accelerating the drug approval process in hematology oncology trials.
Designing modern oncology trials requires synthesizing evidence from prior studies to inform hypothesis generation and sample size determination. Trial designs based on incomplete or imprecise summaries can lead to misspecified hypotheses and underpowered studies, resulting in false positive or negative conclusions. To address this challenge, we developed LEAD-ONC (Literature to Evidence for Analytics and Design in Oncology), an AI-assisted framework that transforms published clinical trial reports into quantitative, design-relevant evidence. Given expert-curated trial publications that meet prespecified eligibility criteria, LEAD-ONC uses large language models to extract baseline characteristics and reconstruct individual patient data from Kaplan-Meier curves, followed by Bayesian hierarchical modeling to generate predictive survival distributions for a prespecified target trial population. We demonstrate the framework using five phase III trials in first-line non-small-cell lung cancer evaluating PD-1 or PD-L1 inhibitors with or without CTLA-4 blockade. Clustering based on baseline characteristics identified three clinically interpretable populations defined by histology. For a p
Personalized oncology aims to tailor treatment strategies to the unique molecular and clinical profiles of individual patients, moving beyond the traditional paradigm of treating the disease not the patient. Achieving this vision requires the integration and interpretation of vast, heterogeneous biomedical data within a meaningful scientific framework. Knowledge graphs, structured according to biomedical ontologies, offer a powerful approach to contextualize and interconnect diverse datasets, enabling more precise and informed clinical decision-making. We present ECKO (Explainable Clinical Knowledge for Oncology), a comprehensive knowledge graph that integrates 33 biomedical ontologies and aggregates data from multiple studies to create a unified resource optimized for data-driven clinical applications in oncology. Designed to support personalized drug recommendations, ECKO facilitates the identification of optimal therapeutic options by linking patient-specific molecular data to relevant pharmacological knowledge. It provides transparent, interpretable explanations for drug recommendations, fostering greater trust and understanding among clinicians and researchers. This resource r
In the past year, there has been a growing trend in applying Large Language Models (LLMs) to the field of medicine, particularly with the advent of advanced language models such as ChatGPT developed by OpenAI. However, there is limited research on LLMs specifically addressing oncology-related queries. The primary aim of this research was to develop a specialized language model that demonstrates improved accuracy in providing advice related to oncology. We performed an extensive data collection of online question-answer interactions centered around oncology, sourced from reputable doctor-patient platforms. Following data cleaning and anonymization, a dataset comprising over 180K+ oncology-related conversations was established. The conversations were categorized and meticulously reviewed by field specialists and clinicians to ensure precision. Employing the LLaMA model and other selected open-source datasets, we conducted iterative fine-tuning to enhance the model's proficiency in basic medical conversation and specialized oncology knowledge. We observed a substantial enhancement in the model's understanding of genuine patient inquiries and its reliability in offering oncology-relate
Background: The radiation oncology clinical practice involves many steps relying on the dynamic interplay of abundant text data. Large language models have displayed remarkable capabilities in processing complex text information. But their direct applications in specific fields like radiation oncology remain underexplored. Purpose: This study aims to investigate whether fine-tuning LLMs with domain knowledge can improve the performance on Task (1) treatment regimen generation, Task (2) treatment modality selection (photon, proton, electron, or brachytherapy), and Task (3) ICD-10 code prediction in radiation oncology. Methods: Data for 15,724 patient cases were extracted. Cases where patients had a single diagnostic record, and a clearly identifiable primary treatment plan were selected for preprocessing and manual annotation to have 7,903 cases of the patient diagnosis, treatment plan, treatment modality, and ICD-10 code. Each case was used to construct a pair consisting of patient diagnostics details and an answer (treatment regimen, treatment modality, or ICD-10 code respectively) for the supervised fine-tuning of these three tasks. Open source LLaMA2-7B and Mistral-7B models wer
Mathematical oncology is an interdisciplinary research field where the mathematical sciences meet cancer research. Being situated at the intersection of these two fields makes mathematical oncology highly dynamic, as practicing researchers are incentivised to quickly adapt to both technical and medical research advances. Determining the scope of mathematical oncology is therefore not straightforward; however, it is important for purposes related to funding allocation, education, scientific communication, and community organisation. To address this issue, we here conduct a bibliometric analysis of mathematical oncology. We compare our results to the broader field of mathematical biology, and position our findings within theoretical science of science frameworks. Based on article metadata and citation flows, our results provide evidence that mathematical oncology has undergone a significant evolution since the 1960s marked by increased interactions with other disciplines, geographical expansion, larger research teams, and greater diversity in studied topics. The latter finding contributes to the greater discussion on which models different research communities consider to be valuable
The application of AI in oncology has been limited by its reliance on large, annotated datasets and the need for retraining models for domain-specific diagnostic tasks. Taking heed of these limitations, we investigated in-context learning as a pragmatic alternative to model retraining by allowing models to adapt to new diagnostic tasks using only a few labeled examples at inference, without the need for retraining. Using four vision-language models (VLMs)-Paligemma, CLIP, ALIGN and GPT-4o, we evaluated the performance across three oncology datasets: MHIST, PatchCamelyon and HAM10000. To the best of our knowledge, this is the first study to compare the performance of multiple VLMs on different oncology classification tasks. Without any parameter updates, all models showed significant gains with few-shot prompting, with GPT-4o reaching an F1 score of 0.81 in binary classification and 0.60 in multi-class classification settings. While these results remain below the ceiling of fully fine-tuned systems, they highlight the potential of ICL to approximate task-specific behavior using only a handful of examples, reflecting how clinicians often reason from prior cases. Notably, open-source
Unstructured notes within the electronic health record (EHR) contain rich clinical information vital for cancer treatment decision making and research, yet reliably extracting structured oncology data remains challenging due to extensive variability, specialized terminology, and inconsistent document formats. Manual abstraction, although accurate, is prohibitively costly and unscalable. Existing automated approaches typically address narrow scenarios - either using synthetic datasets, restricting focus to document-level extraction, or isolating specific clinical variables (e.g., staging, biomarkers, histology) - and do not adequately handle patient-level synthesis across the large number of clinical documents containing contradictory information. In this study, we propose an agentic framework that systematically decomposes complex oncology data extraction into modular, adaptive tasks. Specifically, we use large language models (LLMs) as reasoning agents, equipped with context-sensitive retrieval and iterative synthesis capabilities, to exhaustively and comprehensively extract structured clinical variables from real-world oncology notes. Evaluated on a large-scale dataset of over 40
Randomized discontinuation design (RDD) is an enrichment strategy commonly used to address limitations of traditional placebo-controlled trials, particularly the ethical concern of prolonged placebo exposure. RDD consists of two phases: an initial open-label phase in which all eligible patients receive the investigational medicinal product (IMP), followed by a double-blind phase in which responders are randomized to continue with the IMP or switch to placebo. This design tests whether the IMP provides benefit beyond the placebo effect. The estimand framework introduced in ICH E9(R1) strengthens the dialogue among clinical research stakeholders by clarifying trial objectives and aligning them with appropriate statistical analyses. However, its application in oncology trials using RDD remains unclear. This manuscript uses the phase III JAVELIN Gastric 100 trial and the phase II trial of sorafenib (BAY 43-9006) as case studies to propose an estimand framework tailored for oncology trials employing RDD in phase III and phase II settings, respectively. We highlight some similarities and differences between RDDs and traditional randomized controlled trials in the context of ICH E9(R1). T
Cancer evolves continuously over time through a complex interplay of genetic, epigenetic, microenvironmental, and phenotypic changes. This dynamic behavior drives uncontrolled cell growth, metastasis, immune evasion, and therapy resistance, posing challenges for effective monitoring and treatment. However, today's data-driven research in oncology has primarily focused on cross-sectional analysis using data from a single modality, limiting the ability to fully characterize and interpret the disease's dynamic heterogeneity. Advances in multiscale data collection and computational methods now enable the discovery of longitudinal multimodal biomarkers for precision oncology. Longitudinal data reveal patterns of disease progression and treatment response that are not evident from single-timepoint data, enabling timely abnormality detection and dynamic treatment adaptation. Multimodal data integration offers complementary information from diverse sources for more precise risk assessment and targeting of cancer therapy. In this review, we survey methods of longitudinal and multimodal modeling, highlighting their synergy in providing multifaceted insights for personalized care tailored to
Multimodal Large Language Models (LLMs) hold promise for biomedical reasoning, but current benchmarks fail to capture the complexity of real-world clinical workflows. Existing evaluations primarily assess unimodal, decontextualized question-answering, overlooking multi-agent decision-making environments such as Molecular Tumor Boards (MTBs). MTBs bring together diverse experts in oncology, where diagnostic and prognostic tasks require integrating heterogeneous data and evolving insights over time. Current benchmarks lack this longitudinal and multimodal complexity. We introduce MTBBench, an agentic benchmark simulating MTB-style decision-making through clinically challenging, multimodal, and longitudinal oncology questions. Ground truth annotations are validated by clinicians via a co-developed app, ensuring clinical relevance. We benchmark multiple open and closed-source LLMs and show that, even at scale, they lack reliability -- frequently hallucinating, struggling with reasoning from time-resolved data, and failing to reconcile conflicting evidence or different modalities. To address these limitations, MTBBench goes beyond benchmarking by providing an agentic framework with foun
Artificial intelligence (AI) has potential to revolutionize the field of oncology by enhancing the precision of cancer diagnosis, optimizing treatment strategies, and personalizing therapies for a variety of cancers. This review examines the limitations of conventional diagnostic techniques and explores the transformative role of AI in diagnosing and treating cancers such as lung, breast, colorectal, liver, stomach, esophageal, cervical, thyroid, prostate, and skin cancers. The primary objective of this paper is to highlight the significant advancements that AI algorithms have brought to oncology within the medical industry. By enabling early cancer detection, improving diagnostic accuracy, and facilitating targeted treatment delivery, AI contributes to substantial improvements in patient outcomes. The integration of AI in medical imaging, genomic analysis, and pathology enhances diagnostic precision and introduces a novel, less invasive approach to cancer screening. This not only boosts the effectiveness of medical facilities but also reduces operational costs. The study delves into the application of AI in radiomics for detailed cancer characterization, predictive analytics for i
Purpose To evaluate the reasoning capabilities of large language models (LLMs) in performing root cause analysis (RCA) of radiation oncology incidents using narrative reports from the Radiation Oncology Incident Learning System (RO-ILS), and to assess their potential utility in supporting patient safety efforts. Methods and Materials Four LLMs, Gemini 2.5 Pro, GPT-4o, o3, and Grok 3, were prompted with the 'Background and Incident Overview' sections of 19 public RO-ILS cases. Using a standardized prompt based on AAPM RCA guidelines, each model was instructed to identify root causes, lessons learned, and suggested actions. Outputs were assessed using semantic similarity metrics (cosine similarity via Sentence Transformers), semi-subjective evaluations (precision, recall, F1-score, accuracy, hallucination rate, and four performance criteria: relevance, comprehensiveness, justification, and solution quality), and subjective expert ratings (reasoning quality and overall performance) from five board-certified medical physicists. Results LLMs showed promising performance. GPT-4o had the highest cosine similarity (0.831), while Gemini 2.5 Pro had the highest recall (0.799) and accuracy (0
Clinical oncology generates vast, unstructured data that often contain inconsistencies, missing information, and ambiguities, making it difficult to extract reliable insights for data-driven decision-making. General-purpose large language models (LLMs) struggle with these challenges due to their lack of domain-specific reasoning, including specialized clinical terminology, context-dependent interpretations, and multi-modal data integration. We address these issues with an oncology-specialized, efficient, and adaptable NLP framework that combines instruction tuning, retrieval-augmented generation (RAG), and graph-based knowledge integration. Our lightweight models prove effective at oncology-specific tasks, such as named entity recognition (e.g., identifying cancer diagnoses), entity linking (e.g., linking entities to standardized ontologies), TNM staging, document classification (e.g., cancer subtype classification from pathology reports), and treatment response prediction. Our framework emphasizes adaptability and resource efficiency. We include minimal German instructions, collected at the University Hospital Zurich (USZ), to test whether small amounts of non-English language dat
Heterogeneous treatment effect estimation is critical in oncology, particularly in multi-arm trials with overlapping therapeutic components and long-term survivors. These shared mechanisms pose a central challenge to identifying causal effects in precision medicine. We propose a novel covariate-dependent nonparametric Bayesian multi-treatment cure survival model that jointly accounts for common structures among treatments and cure fractions. Through latent link functions, our model leverages sharing among treatments through a flexible modeling approach, enabling individualized survival inference. We adopt a Bayesian route for inference and implement an efficient MCMC algorithm for approximating the posterior. Simulation studies demonstrate the method's robustness and superiority in various specification scenarios. Finally, application to the AALL0434 trial reveals clinically meaningful differences in survival across methotrexate-based regimens and their associations with different covariates, underscoring its practical utility for learning treatment effects in real-world pediatric oncology data.
This research focuses on evaluating and enhancing data readiness for the development of an Artificial Intelligence (AI)-based Clinical Decision Support System (CDSS) in the context of skin cancer treatment. The study, conducted at the Skin Tumor Center of the University Hospital Münster, delves into the essential role of data quality, availability, and extractability in implementing effective AI applications in oncology. By employing a multifaceted methodology, including literature review, data readiness assessment, and expert workshops, the study addresses the challenges of integrating AI into clinical decision-making. The research identifies crucial data points for skin cancer treatment decisions, evaluates their presence and quality in various information systems, and highlights the difficulties in extracting information from unstructured data. The findings underline the significance of high-quality, accessible data for the success of AI-driven CDSS in medical settings, particularly in the complex field of oncology.
The effectiveness of personalized oncology treatments ultimately depends on whether outcomes can be causally attributed to the treatment. Advances in precision oncology have improved molecular profiling of individuals, and tailored therapies have led to more effective treatments for select patient groups. However, treatment responses still vary among individuals. As cancer is a heterogeneous and dynamic disease with varying treatment outcomes across different molecular types and resistance mechanisms, it requires customized approaches to identify cause-and-effect relationships. N-of-1 trials, or single-subject clinical trials, are designed to evaluate individual treatment effects. Several works have described different causal frameworks to identify treatment effects in N-of-1 trials, yet whether these approaches can be extended to single-cancer patient settings remains unclear. To explore this possibility, a longitudinal dataset from a single metastatic cancer patient with adaptively chosen treatments was considered. The dataset consisted of a detailed treatment plan as well as biomarker and lesion measurements recorded over time. After data processing, a treatment period with suff
Cancer remains a leading cause of death worldwide, necessitating personalized treatment approaches to improve outcomes. Theranostics, combining molecular-level imaging with targeted therapy, offers potential for precision oncology but requires optimized, patient-specific care plans. This paper investigates state-of-the-art data-driven decision support applications with a reinforcement learning focus in precision oncology. We review current applications, training environments, state-space representation, performance evaluation criteria, and measurement of risk and reward, highlighting key challenges. We propose a framework integrating data-driven modeling with reinforcement learning-based decision support to optimize radiopharmaceutical therapy dosing, addressing identified challenges and setting directions for future research. The framework leverages Neural Ordinary Differential Equations and Physics-Informed Neural Networks to enhance Physiologically Based Pharmacokinetic models while applying reinforcement learning algorithms to iteratively refine treatment policies based on patient-specific data.
Introduction: Large language models (LLM) have shown great potential in clinical decision support. GPT-5 is a novel LLM system that has been specifically marketed towards oncology use. Methods: Performance was assessed using two complementary benchmarks: (i) the ACR Radiation Oncology In-Training Examination (TXIT, 2021), comprising 300 multiple-choice items, and (ii) a curated set of 60 authentic radiation oncologic vignettes representing diverse disease sites and treatment indications. For the vignette evaluation, GPT-5 was instructed to generate concise therapeutic plans. Four board-certified radiation oncologists rated correctness, comprehensiveness, and hallucinations. Inter-rater reliability was quantified using Fleiss' \k{appa}. Results: On the TXIT benchmark, GPT-5 achieved a mean accuracy of 92.8%, outperforming GPT-4 (78.8%) and GPT-3.5 (62.1%). Domain-specific gains were most pronounced in Dose and Diagnosis. In the vignette evaluation, GPT-5's treatment recommendations were rated highly for correctness (mean 3.24/4, 95% CI: 3.11-3.38) and comprehensiveness (3.59/4, 95% CI: 3.49-3.69). Hallucinations were rare with no case reaching majority consensus for their presence.