TwinWeaver: An LLM-Based Foundation Model Framework for Pan-Cancer Digital Twins

2026-01-28

AI Summary

This study addresses the challenge of effectively modeling sparse, multimodal clinical time-series data for predicting patient events and disease trajectories in precision oncology. To this end, the authors propose the Pan-Cancer Digital Twin (GDT) framework, which, for the first time, leverages large language models (LLMs) to model longitudinal patient histories as textual sequences, enabling unified clinical event prediction and trajectory inference. The approach supports zero-shot generalization to clinical trial data and provides interpretable clinical reasoning. Evaluated on a cohort of 93,054 patients, GDT significantly outperforms baseline methods, achieving a mean absolute scaled error (MASE) of 0.87 (versus 0.97) and a concordance index (C-index) of 0.703 (versus 0.662), with consistent superior performance demonstrated in external validation trials.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Precision oncology requires forecasting clinical events and trajectories, yet modeling sparse, multi-modal clinical time series remains a critical challenge. We introduce TwinWeaver, an open-source framework that serializes longitudinal patient histories into text, enabling unified event prediction as well as forecasting with large language models, and use it to build Genie Digital Twin (GDT) on 93,054 patients across 20 cancer types. In benchmarks, GDT significantly reduces forecasting error, achieving a median Mean Absolute Scaled Error (MASE) of 0.87 compared to 0.97 for the strongest time-series baseline (p<0.001). Furthermore, GDT improves risk stratification, achieving an average concordance index (C-index) of 0.703 across survival, progression, and therapy switching tasks, surpassing the best baseline of 0.662. GDT also generalizes to out-of-distribution clinical trials, matching trained baselines at zero-shot and surpassing them with fine-tuning, achieving a median MASE of 0.75-0.88 and outperforming the strongest baseline in event prediction with an average C-index of 0.672 versus 0.648. Finally, TwinWeaver enables an interpretable clinical reasoning extension, providing a scalable and transparent foundation for longitudinal clinical modeling.

Problem

• precision oncology
• clinical time series
• pan-cancer
• digital twins
• event forecasting

Innovation

• Large Language Models
• Digital Twins
• Pan-Cancer Forecasting
• Clinical Time Series
• Interpretable AI