Towards Precision Oncology: Predicting Mortality and Relapse-Free Survival in Head and Neck Cancer Using Clinical Data
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913692450291712 |
|---|---|
| author | Dhariwal, Naman Giridharan, Abeyankar |
| author_facet | Dhariwal, Naman Giridharan, Abeyankar |
| contents | Head and neck squamous cell carcinoma (HNSCC) presents significant challenges in clinical oncology due to its heterogeneity and high mortality rates. This study aims to leverage clinical data and machine learning (ML) principles to predict key outcomes for HNSCC patients: mortality, and relapse-free survival. Utilizing data sourced from the Cancer Imaging Archive, an extensive pipeline was implemented to ensure robust model training and evaluation. Ensemble and individual classifiers, including XGBoost, Random Forest, and Support Vectors, were employed to develop predictive models. The study identified key clinical features influencing HNSCC mortality outcomes and achieved predictive accuracy and ROC-AUC values exceeding 90\% across tasks. Support Vector Machine strongly excelled in relapse-free survival, with an recall value of 0.99 and precision of 0.97. Key clinical features including loco-regional control, smoking and treatment type, were identified as critical predictors of patient outcomes. This study underscores the medical impact of using ML-driven insights to refine prognostic accuracy and optimize personalized treatment strategies in HNSCC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_11200 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Precision Oncology: Predicting Mortality and Relapse-Free Survival in Head and Neck Cancer Using Clinical Data Dhariwal, Naman Giridharan, Abeyankar Quantitative Methods Head and neck squamous cell carcinoma (HNSCC) presents significant challenges in clinical oncology due to its heterogeneity and high mortality rates. This study aims to leverage clinical data and machine learning (ML) principles to predict key outcomes for HNSCC patients: mortality, and relapse-free survival. Utilizing data sourced from the Cancer Imaging Archive, an extensive pipeline was implemented to ensure robust model training and evaluation. Ensemble and individual classifiers, including XGBoost, Random Forest, and Support Vectors, were employed to develop predictive models. The study identified key clinical features influencing HNSCC mortality outcomes and achieved predictive accuracy and ROC-AUC values exceeding 90\% across tasks. Support Vector Machine strongly excelled in relapse-free survival, with an recall value of 0.99 and precision of 0.97. Key clinical features including loco-regional control, smoking and treatment type, were identified as critical predictors of patient outcomes. This study underscores the medical impact of using ML-driven insights to refine prognostic accuracy and optimize personalized treatment strategies in HNSCC. |
| title | Towards Precision Oncology: Predicting Mortality and Relapse-Free Survival in Head and Neck Cancer Using Clinical Data |
| topic | Quantitative Methods |
| url | https://arxiv.org/abs/2502.11200 |