Mechanistic Learning for Predicting Survival Outcomes in Head and Neck Squamous Cell Carcinoma

ABSTRACT We employed a mechanistic learning approach, integrating on‐treatment tumor kinetics (TK) modeling with various machine learning (ML) models to address the challenge of predicting post‐progression survival (PPS)—the duration from the time of documented disease progression to death—and overa...

Full description

Saved in:
Bibliographic Details
Main Authors: Kevin Atsou, Anne Auperin, Jôel Guigay, Sébastien Salas, Sebastien Benzekry
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:CPT: Pharmacometrics & Systems Pharmacology
Subjects:
Online Access:https://doi.org/10.1002/psp4.13294
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850038125753008128
author Kevin Atsou
Anne Auperin
Jôel Guigay
Sébastien Salas
Sebastien Benzekry
author_facet Kevin Atsou
Anne Auperin
Jôel Guigay
Sébastien Salas
Sebastien Benzekry
author_sort Kevin Atsou
collection DOAJ
description ABSTRACT We employed a mechanistic learning approach, integrating on‐treatment tumor kinetics (TK) modeling with various machine learning (ML) models to address the challenge of predicting post‐progression survival (PPS)—the duration from the time of documented disease progression to death—and overall survival (OS) in Head and Neck Squamous Cell Carcinoma (HNSCC). We compared the predictive power of model‐derived TK parameters versus RECIST and assessed the efficacy of nine TK‐OS ML models against conventional survival models. Data from 526 advanced HNSCC patients treated with chemotherapy and cetuximab in the TPExtreme trial were analyzed using a double‐exponential model. TK parameters from the first line and maintenance (TKL1) or after four cycles (TK4) were used to predict PPS and post‐cycle 4 OS (OS4), combined with 12 baseline parameters. While ML algorithms underperformed compared to the Cox model for PPS, a random survival forest was superior for OS prediction using TK4 and surpassed RECIST‐based metrics. This model demonstrated unbiased OS4 prediction, suggesting its potential for improving HNSCC treatment evaluation. Trial Registration: ClinicalTrials.gov identifier: NCT02268695.
format Article
id doaj-art-7ac3f6613a66418c8f207ab41f77bbbe
institution DOAJ
issn 2163-8306
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series CPT: Pharmacometrics & Systems Pharmacology
spelling doaj-art-7ac3f6613a66418c8f207ab41f77bbbe2025-08-20T02:56:39ZengWileyCPT: Pharmacometrics & Systems Pharmacology2163-83062025-03-0114354055010.1002/psp4.13294Mechanistic Learning for Predicting Survival Outcomes in Head and Neck Squamous Cell CarcinomaKevin Atsou0Anne Auperin1Jôel Guigay2Sébastien Salas3Sebastien Benzekry4COMPutational Pharmacology and Clinical Oncology Department, Inria Sophia Antipolis – Méditerranée Cancer Research Center of Marseille, Inserm UMR1068, CNRS UMR7258, Aix Marseille University UM105 Marseille FranceBiostatistical and Epidemiological Division Institut Gustave Roussy Villejuif FranceClinical Oncology, Centre Antoine Lacassagne Nice FranceCOMPutational Pharmacology and Clinical Oncology Department, Inria Sophia Antipolis – Méditerranée Cancer Research Center of Marseille, Inserm UMR1068, CNRS UMR7258, Aix Marseille University UM105 Marseille FranceCOMPutational Pharmacology and Clinical Oncology Department, Inria Sophia Antipolis – Méditerranée Cancer Research Center of Marseille, Inserm UMR1068, CNRS UMR7258, Aix Marseille University UM105 Marseille FranceABSTRACT We employed a mechanistic learning approach, integrating on‐treatment tumor kinetics (TK) modeling with various machine learning (ML) models to address the challenge of predicting post‐progression survival (PPS)—the duration from the time of documented disease progression to death—and overall survival (OS) in Head and Neck Squamous Cell Carcinoma (HNSCC). We compared the predictive power of model‐derived TK parameters versus RECIST and assessed the efficacy of nine TK‐OS ML models against conventional survival models. Data from 526 advanced HNSCC patients treated with chemotherapy and cetuximab in the TPExtreme trial were analyzed using a double‐exponential model. TK parameters from the first line and maintenance (TKL1) or after four cycles (TK4) were used to predict PPS and post‐cycle 4 OS (OS4), combined with 12 baseline parameters. While ML algorithms underperformed compared to the Cox model for PPS, a random survival forest was superior for OS prediction using TK4 and surpassed RECIST‐based metrics. This model demonstrated unbiased OS4 prediction, suggesting its potential for improving HNSCC treatment evaluation. Trial Registration: ClinicalTrials.gov identifier: NCT02268695.https://doi.org/10.1002/psp4.13294deep learninghead and neck squamous cell carcinomamachine learningsurvival analysistumor kinetics
spellingShingle Kevin Atsou
Anne Auperin
Jôel Guigay
Sébastien Salas
Sebastien Benzekry
Mechanistic Learning for Predicting Survival Outcomes in Head and Neck Squamous Cell Carcinoma
CPT: Pharmacometrics & Systems Pharmacology
deep learning
head and neck squamous cell carcinoma
machine learning
survival analysis
tumor kinetics
title Mechanistic Learning for Predicting Survival Outcomes in Head and Neck Squamous Cell Carcinoma
title_full Mechanistic Learning for Predicting Survival Outcomes in Head and Neck Squamous Cell Carcinoma
title_fullStr Mechanistic Learning for Predicting Survival Outcomes in Head and Neck Squamous Cell Carcinoma
title_full_unstemmed Mechanistic Learning for Predicting Survival Outcomes in Head and Neck Squamous Cell Carcinoma
title_short Mechanistic Learning for Predicting Survival Outcomes in Head and Neck Squamous Cell Carcinoma
title_sort mechanistic learning for predicting survival outcomes in head and neck squamous cell carcinoma
topic deep learning
head and neck squamous cell carcinoma
machine learning
survival analysis
tumor kinetics
url https://doi.org/10.1002/psp4.13294
work_keys_str_mv AT kevinatsou mechanisticlearningforpredictingsurvivaloutcomesinheadandnecksquamouscellcarcinoma
AT anneauperin mechanisticlearningforpredictingsurvivaloutcomesinheadandnecksquamouscellcarcinoma
AT joelguigay mechanisticlearningforpredictingsurvivaloutcomesinheadandnecksquamouscellcarcinoma
AT sebastiensalas mechanisticlearningforpredictingsurvivaloutcomesinheadandnecksquamouscellcarcinoma
AT sebastienbenzekry mechanisticlearningforpredictingsurvivaloutcomesinheadandnecksquamouscellcarcinoma