Skip to content

Causal multi-modal AI for personalized chemosensitivity prediction

Sep 2026 · 3 citations · 127 references
Computer Science

TL;DR

The model generated treatment-specific recurrence probabilities for each patient, with near-perfect calibration and strong prognostic discrimination across both 5- and 10-year follow-up horizons, and out-performed existing recurrence-score-based tests.

Abstract

Chemotherapy improves survival for some patients with breast cancer, but doctors cannot reliably predict who. Current guidelines rely on recurrence scores as a proxy for treatment benefit, which may contribute to the overprescription of chemotherapy. Here we present a causal multi-modal AI model that predicts personalized chemosensitivity using routinely collected pathology and clinical information. We developed our model on a multi-national dataset of 9,141 patients (twelve cohorts, nine countries) and evaluated it on another 1,994 patients (five cohorts, three countries). The model generated treatment-specific recurrence probabilities for each patient, with near-perfect calibration and strong prognostic discrimination across both 5- and 10-year follow-up horizons. Moreover, its chemotherapy benefit predictions demonstrated robust predictive performance, and out-performed existing recurrence-score-based tests. Compared to the standard of care, using the model to support personally tailored therapeutic decisions could reduce the number of patients receiving chemotherapy by 30% while achieving the same recurrence-free rate. Tumors predicted to be highly chemosensitive displayed concordant molecular and morphological programs of proliferation, cell cycle progression, and replication stress. The model's predictive capabilities transferred zero-shot to non-breast cancers, indicating our causal multi-modal AI approach may provide a universal strategy to predict treatment outcomes across cancer types.

View source

Similar papers

Open access Sep 2026

A multimodal AI biomarker PATH-ORACLE improves prediction of recurrence in stage I lung adenocarcinoma

Extensive validation will be needed to convert PATH-ORACLE from a prognostic biomarker to a predictive biomarker that could be used to prioritize stage IB patients for adjuvant targeted therapy, chemotherapy, or immune checkpoint inhibitor therapy with or without liquid biopsy-based monitoring.

O. Kilim, O. Pipek, Z. Sztupinszki et al. · 0 citations
Open access Aug 2026

Clinical attribute-based risk matrix for prognostication in immunotherapy-treated non-small cell lung cancer

The authors show that CLARITY-ICI Matrix, a clinically deployable, missing-data-tolerant framework, enables population-aware stratification of survival risk in immunotherapy-treated NSCLC using routinely available clinical attributes and complements biomarkers.

Lu Wang, Nan Xu, Hai-Rui Wang et al. · 0 citations
Review Open access Sep 2026

Beyond pCR Prediction: Subtype-Specific Artificial Intelligence for Treatment Tailoring in Breast Cancer Neoadjuvant Therapy

Current evidence is not strong enough for AI to change an individual treatment or surgery decision safely, and models used to estimate response are not interchangeable across subtypes and must be read in their original treatment context.

Jun-Wen Zhou, Bei-Bei Xi, Ke-Huan Yan et al. · 0 citations
Open access Aug 2026

Machine learning prognostic model and drug survival analysis for lung adenocarcinoma in the context of radiotherapy.

BACKGROUND Patients with lung adenocarcinoma (LUAD) receiving radiotherapy represent an important but underexplored clinical subgroup. These patients often undergo concomitant pharmacologic treatments, yet the prognostic impact and underlying determinants of such combined regimens remain poorly understood. OBJECTIVE...

Zaishuang Ju, Yu-Tong Wu, Li-Li Tian et al. · 0 citations
Open access Aug 2026

Machine Learning-Guided Personalized Immunochemotherapy Strategies in Intrahepatic Cholangiocarcinoma.

BACKGROUND & AIMS Immunochemotherapy (IO-chemo) has become standard care for patients with unresectable intrahepatic cholangiocarcinoma (iCCA), but benefit of adding IO varies greatly among individuals. We sought to develop a system to identify patients most likely to benefit from this treatment based on individualized...

Jun-Hao Mei, Kai Zhang, Ying Zhang et al. · 0 citations
Open access Sep 2026

Biomarker discovery and patient stratification in pancreatic cancer using incomplete multi-omics data

Pancreatic ductal adenocarcinoma (PDAC), with a 12% 5-year survival rate, is the most aggressive type of cancer. Early diagnosis for this pathology is rare, and conventional treatments such as surgery, radio- or chemotherapy, have little to no effect on reducing mortality. Machine learning (ML) approaches could be used...

Alejandra Paja-García, Rafael Romero-Becerra, T. Aittokallio et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.