clinTALL: machine learning-driven multimodal subtype classification and treatment outcome prediction in…

AI / informaticsGenome medicine· Jul 2026

clinTALL: machine learning-driven multimodal subtype classification and treatment outcome prediction in pediatric T-ALL.

Lukas Stoiber, Željko Antić, Stefano Rebellato … Anke Katharina Bergmann

AI in MedicineAI / informaticsQ1IF 10.6

Machine learning model accurately predicts induction failure in pediatric T-lineage acute lymphoblastic leukemia.

clinTALL: machine learning-driven multimodal subtype classification and treatment outcome prediction in pediatric T-ALL.

Lukas Stoiber … Anke Katharina Bergmann

Genome medicine · Jul 2026

Background

Childhood T-lineage acute lymphoblastic leukemia (T-ALL) is an aggressive hematologic malignancy with poor prognosis.

Methods

Here, we present clinTALL, a deep learning based multi-task pipeline for pediatric T-ALL subtype classification and treatment outcome estimation.

n = 1309 pediatric T-ALL samples

C-index = 96.0%

Results

C-index = 96.0%

The model accurately predicted when initial leukemia treatment would not work

n = 1309 pediatric T-ALL samples

More results

We observed that the transcriptomic-only model achieved superior single-modality results, with 92.2% accuracy for subtype prediction and a 65.9% concordance index (C-index) for event-free survival (event-free survival) in a cross-validation setup.

More results

Integrating all data modalities maintained high subtype classification accuracy (91.7%) and improved the overall concordance index for event-free survival estimation to 67.5%.

We validated molecular subtype predictions on an internal dataset of 120 pediatric T-ALL samples and obtained an accuracy of 81.8%.

“

Conclusion · 1 of 2

Together, our machine learning-based framework allows for automated, accurate subtype classification and treatment outcome inference using multimodal input data, advancing precision risk stratification for pediatric T-ALL.

Conclusion · 2 of 2

The full source code of clinTALL is available on GitHub ( https://github.com/UKWgenommedizin/clinTALL ).

clinTALL: machine learning-driven multimodal subtype classification and treatment outcome prediction in pediatric T-ALL.

clinTALL: machine learning-driven multimodal subtype classification and treatment outcome prediction in pediatric T-ALL.

Related papers