Machine learning explainability for survival outcome in head and neck squamous cell carcinoma

被引:1
作者
Alabi, Rasheed Omobolaji [1 ,2 ]
Makitie, Antti A. [1 ,3 ,4 ,5 ,6 ]
Elmusrati, Mohammed [2 ]
Almangush, Alhadi [1 ,7 ,8 ,9 ]
Ehrsson, Ylva Tiblom [10 ]
Laurell, Goran [10 ]
机构
[1] Univ Helsinki, Fac Med, Res Program Syst Oncol, Helsinki, Finland
[2] Univ Vaasa, Sch Technol & Innovat, Dept Ind Digitalizat, Vaasa, Finland
[3] Univ Helsinki, Dept Otorhinolaryngol Head & Neck Surg, Helsinki, Finland
[4] Helsinki Univ Hosp, Helsinki, Finland
[5] Karolinska Inst, Dept Clin Sci Intervent & Technol, Div Ear Nose & Throat Dis, Stockholm, Sweden
[6] Karolinska Univ Hosp, Stockholm, Sweden
[7] Univ Turku, Inst Biomed, Pathol, Turku, Finland
[8] Univ Helsinki, Dept Pathol, Helsinki, Finland
[9] Misurata Univ, Fac Dent, Misurata, Libya
[10] Uppsala Univ, Dept Surg Sci, Sect Otorhinolaryngol & Head & Neck Surg, Uppsala, Sweden
关键词
Machine learning (ML); Head and Neck Squamous Cell Carcinoma (HNSCC); Overall survival; Explainability; HUMAN-PAPILLOMAVIRUS; PROGNOSTIC-FACTOR; NONOROPHARYNGEAL HEAD; OROPHARYNGEAL CANCER; HPV; LEVEL; P16; HEMOGLOBIN; EXPRESSION; AGE;
D O I
10.1016/j.ijmedinf.2025.105873
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Background: Diagnosis and treatment of head and neck squamous cell carcinoma (HNSCC) induces psychological variables and treatment-related toxicity in patients. The evaluation of outcomes is warranted for effective treatment planning and improved disease management. Objectives: This study aimed to build a prognostic system by combining clinicopathological parameters, treatment-related factors, and sociodemographic factors as integrative inputs to build a machine learning (ML) model to estimate the overall survival (OS) of patients with HNSCC. Furthermore, we explored the complementary prognostic potentials of these input parameters. We provide explainability and interpretability using Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) techniques. Methods: A total of 419 patients with HNSCC were recruited from three University Hospitals in Sweden. We compared the performance of TabNet, a state-of-the-art deep learning algorithm for tabular data, with extreme gradient boosting (XGBoost) and voting ensemble to predict OS in patients with HNSCC. Results: Both TabNet and XGBoost showed comparable performance accuracies, with TabNet and XGBoost showing a performance accuracy of 88.1% each and voting ensemble showing an accuracy of 88.7%. The aggregate feature importance showed that p16 (a tumor suppressor protein that plays a crucial role in cell cycle regulation), cancer stage, hemoglobin, age at diagnosis, T class, N class, smoking pack-years, body mass index (BMI), treatment modality, erythrocyte count, and human papillomavirus (HPV) status were the most important parameters for the predictive ability of the model for OS. Furthermore, we found survival trends in this cohort by individually considering parameters such as p16, cancer stage, hemoglobin, age at diagnosis, HPV status, Tumor Nodal Metastasis staging, and socioeconomic factors (marital status, housing, and level of education). In addition, both the LIME and SHAP techniques showed the contribution of each feature to the prediction made by the model. Conclusions: The clinical implementation of an ML model can lead to individualized risk-based therapeutic decision-making. Therefore, validating these models with multiinstitutional datasets and testing them in the context of clinical trials is warranted for safe clinical implementation.
引用
收藏
页数:13
相关论文
共 65 条
[1]   The predictive factors of primary head and neck cancer stage at presentation and survival in a developing nation's tertiary hospital [J].
Adoga, Adeyi A. ;
Kokong, Daniel D. ;
Ma'an, Nuhu D. ;
Mugu, Joyce G. ;
Mgbachi, Chukwunonso J. ;
Dauda, Ayuba M. .
SAGE OPEN MEDICINE, 2018, 6
[2]   Machine Learning Methods in Classification of Prolonged Radiation Therapy in Oropharyngeal Cancer: National Cancer Database [J].
Ahn, Seungjun ;
Oh, Eun Jeong ;
Saleem, Matthew I. ;
Tham, Tristan .
OTOLARYNGOLOGY-HEAD AND NECK SURGERY, 2024, 171 (06) :1764-1772
[3]   Evaluation of Prognosis in Nasopharyngeal Cancer Using Machine Learning [J].
Akcay, Melek ;
Etiz, Durmus ;
Celik, Ozer ;
Ozen, Alaattin .
TECHNOLOGY IN CANCER RESEARCH & TREATMENT, 2020, 19
[4]   Artificial Intelligence-Driven Radiomics in Head and Neck Cancer: Current Status and Future Prospects [J].
Alabi, Rasheed Omobolaji ;
Elmusrati, Mohammed ;
Leivo, Ilmo ;
Almangush, Alhadi ;
Makitie, Antti A. .
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, 2024, 188
[5]   Interpretable machine learning model for prediction of overall survival in laryngeal cancer [J].
Alabi, Rasheed Omobolaji ;
Almangush, Alhadi ;
Elmusrati, Mohammed ;
Leivo, Ilmo ;
Makitie, Antti A. .
ACTA OTO-LARYNGOLOGICA, 2025, 145 (03) :256-262
[6]   Machine learning explainability in nasopharyngeal cancer survival using LIME and SHAP [J].
Alabi, Rasheed Omobolaji ;
Elmusrati, Mohammed ;
Leivo, Ilmo ;
Almangush, Alhadi ;
Maekitie, Antti A. .
SCIENTIFIC REPORTS, 2023, 13 (01)
[7]   Application of artificial intelligence for overall survival risk stratification in oropharyngeal carcinoma: A validation of ProgTOOL [J].
Alabi, Rasheed Omobolaji ;
Sjoblom, Anni ;
Carpen, Timo ;
Elmusrati, Mohammed ;
Leivo, Ilmo ;
Almangush, Alhadi ;
Makitie, Antti A. .
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, 2023, 175
[8]   An interpretable machine learning prognostic system for risk stratification in oropharyngeal cancer [J].
Alabi, Rasheed Omobolaji ;
Almangush, Alhadi ;
Elmusrati, Mohammed ;
Leivo, Ilmo ;
Makitie, Antti A. .
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, 2022, 168
[9]   Deep Machine Learning for Oral Cancer: From Precise Diagnosis to Precision Medicine [J].
Alabi, Rasheed Omobolaji ;
Almangush, Alhadi ;
Elmusrati, Mohammed ;
Maekitie, Antti A. .
FRONTIERS IN ORAL HEALTH, 2022, 2
[10]   Machine learning in oral squamous cell carcinoma: Current status, clinical concerns and prospects for future-A systematic review [J].
Alabi, Rasheed Omobolaji ;
Youssef, Omar ;
Pirinen, Matti ;
Elmusrati, Mohammed ;
Makitie, Antti A. ;
Leivo, Ilmo ;
Almangush, Alhadi .
ARTIFICIAL INTELLIGENCE IN MEDICINE, 2021, 115