# CancerGUIDE: Cancer Guideline Understanding via Internal Disagreement Estimation

arXiv: https://arxiv.org/abs/2509.07325 · HTML: https://mlsanity.com/paper/2509.07325/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 78 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 30 of 30)

- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017)
- [Data Programming: Creating Large Training Sets, Quickly](https://mlsanity.com/paper/1605.07723/) (2016)
- [Generating Multi-label Discrete Patient Records using Generative Adversarial Networks](https://mlsanity.com/paper/1703.06490/) (2017)
- [PseudoSeg: Designing Pseudo Labels for Semantic Segmentation](https://mlsanity.com/paper/2010.09713/) (2020)
- [MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks](https://mlsanity.com/paper/2505.23802/) (2025)
- [BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation](https://mlsanity.com/paper/2203.02533/) (2022)
- [Generating Synthetic Mixed-type Longitudinal Electronic Health Records for Artificial Intelligent Applications](https://mlsanity.com/paper/2112.12047/) (2021)
- [A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Models](https://mlsanity.com/paper/2208.01230/) (2022)
- [TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records](https://mlsanity.com/paper/2503.04176/) (2025)
- [PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models](https://mlsanity.com/paper/2401.15042/) (2024)
- [Evaluating the Consistency of LLM Evaluators](https://mlsanity.com/paper/2412.00543/) (2024)
- [Shrinking the Generation-Verification Gap with Weak Verifiers](https://mlsanity.com/paper/2506.18203/) (2025)
- [An Empirical Study of LLM-as-a-Judge: How Design Choices Impact Evaluation Reliability](https://mlsanity.com/paper/2506.13639/) (2025)
- [Multi-Label Clinical Time-Series Generation via Conditional GAN](https://mlsanity.com/paper/2204.04797/) (2022)
- [Rethinking Verification for LLM Code Generation: From Generation to Testing](https://mlsanity.com/paper/2507.06920/) (2025)
- [Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactions](https://mlsanity.com/paper/2503.22353/) (2025)
- [Ground Truth Or Dare: Factors Affecting The Creation Of Medical Datasets For Training AI](https://mlsanity.com/paper/2309.12327/) (2023)
- [MedGUIDE: Benchmarking Clinical Decision-Making in Large Language Models](https://mlsanity.com/paper/2505.11613/) (2025)
- [Time-series Generation by Contrastive Imitation](https://mlsanity.com/paper/2311.01388/) (2023)
- [HREF: Human Response-Guided Evaluation of Instruction Following in Language Models](https://mlsanity.com/paper/2412.15524/) (2024)
- [Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing](https://mlsanity.com/paper/2406.06723/) (2024)
- [Ontology-Driven and Weakly Supervised Rare Disease Identification from Clinical Notes](https://mlsanity.com/paper/2205.05656/) (2022)
- [Rethinking the Role of Proxy Rewards in Language Model Alignment](https://mlsanity.com/paper/2402.03469/) (2024)
- [Generating Synthetic Electronic Health Record Data: a Methodological Scoping Review with Benchmarking on Phenotype Data and Open-Source Software](https://mlsanity.com/paper/2411.04281/) (2024)
- [Alignment Data Map for Efficient Preference Data Selection and Diagnosis](https://mlsanity.com/paper/2505.23114/) (2025)
- [A Large Language Model Pipeline for Breast Cancer Oncology](https://mlsanity.com/paper/2406.06455/) (2024)

## Built on by (most cited first, 1 of 1)

- [Metric Match: A Subset Selection Approach to Evaluating LLM Judge Reliability](https://mlsanity.com/paper/2606.15029/) (2026)

## Abstract (arXiv)

The National Comprehensive Cancer Network (NCCN) provides evidence-based guidelines for cancer treatment. Translating complex patient presentations into guideline-compliant treatment recommendations is time-intensive, requires specialized expertise, and is prone to error. Advances in large language model (LLM) capabilities promise to reduce the time required to generate treatment recommendations and improve accuracy. We present an LLM agent-based approach to automatically generate guideline-concordant treatment trajectories for patients with non-small cell lung cancer (NSCLC). Our contributions are threefold. First, we construct a novel longitudinal dataset of 121 cases of NSCLC patients that includes clinical encounters, diagnostic results, and medical histories, each expertly annotated with the corresponding NCCN guideline trajectories by board-certified oncologists. Second, we demonstrate that existing LLMs possess domain-specific knowledge that enables high-quality proxy benchmark generation for both model development and evaluation, achieving strong correlation (Spearman coefficient r=0.88, RMSE = 0.08) with expert-annotated benchmarks. Third, we develop a hybrid approach combining expensive human annotations with model consistency information to create both the agent framework that predicts the relevant guidelines for a patient, as well as a meta-classifier that verifies prediction accuracy with calibrated confidence scores for treatment recommendations (AUROC=0.800), a critical capability for communicating the accuracy of outputs, custom-tailoring tradeoffs in performance, and supporting regulatory compliance. This work establishes a framework for clinically viable LLM-based guideline adherence systems that balance accuracy, interpretability, and regulatory requirements while reducing annotation costs, providing a scalable pathway toward automated clinical decision support.