AURORA: Analysing and understanding responses to oncological regimens with artificial intelligence
- 1Technical University of Applied Sciences Augsburg
Abstract
BackgroundImmunochemotherapy (ICT) is considered standard in regards to care for small-cell lung cancer (SCLC) in extensive stages, yet reliable biomarkers for treatment response remain elusive. While previous univariate analyses suggest specific peripheral lymphocyte subsets correlate with survival, the systemic immune response involves complex, multivariate interactions that require advanced analytical approaches.
MethodsThis paper analysed high-dimensional flow cytometry data from 32 patients with stage IV SCLC treated with carboplatin, etoposide, and atezolizumab. Peripheral blood was analysed at baseline (V0) and longitudinally during treatment. To identify potential early predictive biomarkers and mitigate sample attrition in later cycles, we focused on baseline and measurements after two cycles of ICT (V1). We employed a rigorous machine learning framework utilising nested cross-validation, bootstrapping, and permutation-based statistical testing to evaluate eleven different regression and survival models.
ResultsUnder model-appropriate metrics, regressors did not generalise (R2 < 0); conversely, censoring- aware Random Survival Forests (RSF) successfully extracted robust prognostic signatures. Baseline immune profiles (V0) achieved a concordance index (C-index) of 0.66 (p = 0.015), while dynamic changes from V0 to V1 ({Delta}V) achieved a C-index of 0.65 (p = 0.022). Crucially, absolute values measured after two cycles of ICT (V1) yielded no significant signal (p = 0.445). Feature importance analysis confirmed the prognostic value of Th17 normalisation and identified Naive Regulatory T cells and Memory B cells as candidate components.
ConclusionMachine learning validation confirms a predictive signal in the peripheral immune profile of SCLC patients. Early dynamic shifts in the balance between regulatory and effector immune arms are associated with prognosis, contrasting with the lack of signal in absolute counts after two cycles of ICT. These findings establish a proof of concept for multivariate liquid biopsy immune profiling, warranting confirmation in larger cohorts and highlighting the necessity of integrating systemic and tumour-intrinsic data.
Related
- From digital reminders to artificial intelligence–enabled understanding: can personalized treatment predictions improve therapeutic adherence?
- Understanding and Mitigating Bias From Artificial Intelligence in Otolaryngology: A State‐of‐the‐Art Review
- Prevalence and predictors of artificial intelligence chatbots use for caregiving: Evidence from the Understanding America Study
- Self-reported understanding and attitudes of healthcare workers and caregivers toward artificial intelligence in pediatric healthcare in a children’s hospital in China: a cross-sectional study
- Quality, transparency, and readability of artificial intelligence chatbot responses to fibrous dysplasia-related searches: a cross-sectional comparative study
BibTeX
@misc{lebmeier2026aurora,
title = {{AURORA: Analysing and understanding responses to oncological regimens with artificial intelligence}},
author = {A. Lebmeier and T. Lindner and C. Karl and T. Schöler and A. Rank},
howpublished = {medRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.30.26361778},
url = {https://www.medrxiv.org/content/10.64898/2026.08.30.26361778v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - AURORA: Analysing and understanding responses to oncological regimens with artificial intelligence
AU - A. Lebmeier
AU - T. Lindner
AU - C. Karl
AU - T. Schöler
AU - A. Rank
PY - 2026
DA - 2026/08/30
PB - medRxiv
DO - 10.64898/2026.08.30.26361778
UR - https://www.medrxiv.org/content/10.64898/2026.08.30.26361778v1
AB - BackgroundImmunochemotherapy (ICT) is considered standard in regards to care for small-cell lung cancer (SCLC) in extensive stages, yet reliable biomarkers for treatment response remain elusive. While previous univariate analyses suggest specific peripheral lymphocyte subsets correlate with survival, the systemic immune response involves complex, multivariate interactions that require advanced analytical approaches. MethodsThis paper analysed high-dimensional flow cytometry data from 32 patients with stage IV SCLC treated with carboplatin, etoposide, and atezolizumab. Peripheral blood was analysed at baseline (V0) and longitudinally during treatment. To identify potential early predictive biomarkers and mitigate sample attrition in later cycles, we focused on baseline and measurements after two cycles of ICT (V1). We employed a rigorous machine learning framework utilising nested cross-validation, bootstrapping, and permutation-based statistical testing to evaluate eleven different regression and survival models. ResultsUnder model-appropriate metrics, regressors did not generalise (R2 < 0); conversely, censoring- aware Random Survival Forests (RSF) successfully extracted robust prognostic signatures. Baseline immune profiles (V0) achieved a concordance index (C-index) of 0.66 (p = 0.015), while dynamic changes from V0 to V1 ({Delta}V) achieved a C-index of 0.65 (p = 0.022). Crucially, absolute values measured after two cycles of ICT (V1) yielded no significant signal (p = 0.445). Feature importance analysis confirmed the prognostic value of Th17 normalisation and identified Naive Regulatory T cells and Memory B cells as candidate components. ConclusionMachine learning validation confirms a predictive signal in the peripheral immune profile of SCLC patients. Early dynamic shifts in the balance between regulatory and effector immune arms are associated with prognosis, contrasting with the lack of signal in absolute counts after two cycles of ICT. These findings establish a proof of concept for multivariate liquid biopsy immune profiling, warranting confirmation in larger cohorts and highlighting the necessity of integrating systemic and tumour-intrinsic data.
ER -