Multimodal Large Language Models for Prognostic Prediction in Cervical Cancer Treated with Definitive Chemoradiotherapy: An Exploratory Study of Systematic Multimodal Data Integration.
- 1Department of Radiation Oncology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100730, China.
Abstract
Background/objectives
About 25-35% of patients with cervical cancer treated with definitive concurrent chemoradiotherapy (CCRT) relapse within five years, and non-imaging clinical factors stratify their risk only modestly. We evaluated whether a general-purpose multimodal large language model (MLLM), used without fine-tuning, could estimate recurrence risk in this setting.Methods
In this retrospective single-center study, 82 patients treated with definitive radiotherapy (79/82 with concurrent platinum-based chemotherapy) who had a complete pretreatment MRI report were analyzed. Gemini 3.1 Pro generated a structured report from pelvic MRI images and, separately, estimated recurrence/metastasis risk from clinical, laboratory, treatment and imaging data. Because treatment cycles and overall treatment time actually completed were included, this was a retrospective treatment-complete risk assessment rather than a strictly pretreatment prediction. Five prompting strategies differing only in their inputs-an ablation of input modalities-were each run three times; AI reports were graded against paired human reports on a 14-item rubric by an independent model (Claude Opus 4.6).Results
Forty patients (48.8%) relapsed. Discrimination rose from an AUC of 0.704 with a clinical baseline to 0.790 with the full multimodal input (95% CI 0.687-0.883; ΔAUC +0.085). This gain was significant on our primary two-sided bootstrap test after Holm correction for ten pairwise comparisons (p = 0.032; a DeLong sensitivity analysis supported some but not all the imaging-benefit comparisons). Adding MRI report text significantly improved the AUC over the clinical baseline, and no statistically significant difference was detected between the human-report and AI-report strategies; this was not an equivalence or non-inferiority test; and the further lymph-node increment was not statistically significant. The AI reports scored 68.8% against an LLM judge on the rubric, with apparent overcalling of parametrial invasion and an inability to assess lymph nodes within the supplied field of view; all strategies underestimated absolute risk (E/O 0.78-0.83).Conclusions
A non-fine-tuned MLLM can integrate multimodal data into a prognostic estimate, but its automatically generated MRI reports are frequently discordant with radiologist reports in specific ways and require expert review and external validation before clinical use.
Related
- Multimodal integration of carotid plaque ultrasound radiomics and dynamic systemic immune-inflammation trajectories for subacute risk stratification after stroke thrombectomy: development and internal validation of an exploratory prognostic model
- Integration of CURB-65 and CT Severity Score for Prognostic Prediction in Community-acquired Pneumonia.
- Fractional tumor burden refines prognostic stratification beyond MGMT status in glioblastoma after chemoradiotherapy
- Prediction Model for Detecting Active Pulmonary Tuberculosis in Patients With Head and Neck Cancer Prior to Concurrent Chemoradiotherapy
- Adverse event risks and prognostic factors associated with endoscopic laryngopharyngeal surgery for superficial head and neck cancer after chemoradiotherapy
BibTeX
@article{gu2026multimodal,
title = {{Multimodal Large Language Models for Prognostic Prediction in Cervical Cancer Treated with Definitive Chemoradiotherapy: An Exploratory Study of Systematic Multimodal Data Integration.}},
author = {Zhaoqi Gu and Chen Wang and Qizhen Zhu and Weiping Wang and Yidong Zhang and Ke Hu},
journal = {Cancers},
year = {2026},
month = sep,
doi = {10.3390/cancers18193136},
url = {https://europepmc.org/article/MED/42882831},
note = {CC BY},
}
RIS
TY - JOUR
TI - Multimodal Large Language Models for Prognostic Prediction in Cervical Cancer Treated with Definitive Chemoradiotherapy: An Exploratory Study of Systematic Multimodal Data Integration.
AU - Zhaoqi Gu
AU - Chen Wang
AU - Qizhen Zhu
AU - Weiping Wang
AU - Yidong Zhang
AU - Ke Hu
PY - 2026
DA - 2026/09/28
JO - Cancers
DO - 10.3390/cancers18193136
UR - https://europepmc.org/article/MED/42882831
AB - Background/objectives About 25-35% of patients with cervical cancer treated with definitive concurrent chemoradiotherapy (CCRT) relapse within five years, and non-imaging clinical factors stratify their risk only modestly. We evaluated whether a general-purpose multimodal large language model (MLLM), used without fine-tuning, could estimate recurrence risk in this setting.Methods In this retrospective single-center study, 82 patients treated with definitive radiotherapy (79/82 with concurrent platinum-based chemotherapy) who had a complete pretreatment MRI report were analyzed. Gemini 3.1 Pro generated a structured report from pelvic MRI images and, separately, estimated recurrence/metastasis risk from clinical, laboratory, treatment and imaging data. Because treatment cycles and overall treatment time actually completed were included, this was a retrospective treatment-complete risk assessment rather than a strictly pretreatment prediction. Five prompting strategies differing only in their inputs-an ablation of input modalities-were each run three times; AI reports were graded against paired human reports on a 14-item rubric by an independent model (Claude Opus 4.6).Results Forty patients (48.8%) relapsed. Discrimination rose from an AUC of 0.704 with a clinical baseline to 0.790 with the full multimodal input (95% CI 0.687-0.883; ΔAUC +0.085). This gain was significant on our primary two-sided bootstrap test after Holm correction for ten pairwise comparisons (p = 0.032; a DeLong sensitivity analysis supported some but not all the imaging-benefit comparisons). Adding MRI report text significantly improved the AUC over the clinical baseline, and no statistically significant difference was detected between the human-report and AI-report strategies; this was not an equivalence or non-inferiority test; and the further lymph-node increment was not statistically significant. The AI reports scored 68.8% against an LLM judge on the rubric, with apparent overcalling of parametrial invasion and an inability to assess lymph nodes within the supplied field of view; all strategies underestimated absolute risk (E/O 0.78-0.83).Conclusions A non-fine-tuned MLLM can integrate multimodal data into a prognostic estimate, but its automatically generated MRI reports are frequently discordant with radiologist reports in specific ways and require expert review and external validation before clinical use.
SN - 2072-6694
ER -