A hybrid machine learning approach for the personalized prognostication of aggressive skin cancers
Abstract Accurate prognostication guides optimal clinical management in skin cancer. Merkel cell carcinoma (MCC) is the most aggressive form of skin cancer that often presents in advanced stages and is associated with poor survival rates. There are no personalized prognostic tools in use in MCC. We...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-024-01329-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544262729072640 |
|---|---|
| author | Tom W. Andrew Mogdad Alrawi Ruth Plummer Nick Reynolds Vern Sondak Isaac Brownell Penny E. Lovat Aidan Rose Sophia Z. Shalhout |
| author_facet | Tom W. Andrew Mogdad Alrawi Ruth Plummer Nick Reynolds Vern Sondak Isaac Brownell Penny E. Lovat Aidan Rose Sophia Z. Shalhout |
| author_sort | Tom W. Andrew |
| collection | DOAJ |
| description | Abstract Accurate prognostication guides optimal clinical management in skin cancer. Merkel cell carcinoma (MCC) is the most aggressive form of skin cancer that often presents in advanced stages and is associated with poor survival rates. There are no personalized prognostic tools in use in MCC. We employed explainability analysis to reveal new insights into mortality risk factors for this highly aggressive cancer. We then combined deep learning feature selection with a modified XGBoost framework, to develop a web-based prognostic tool for MCC termed ‘DeepMerkel’. DeepMerkel can make accurate personalised, time-dependent survival predictions for MCC from readily available clinical information. It demonstrated generalizability through high predictive performance in an international clinical cohort, out-performing current population-based prognostic staging systems. MCC and DeepMerkel provide the exemplar model of personalised machine learning prognostic tools in aggressive skin cancers. |
| format | Article |
| id | doaj-art-13394054dfe747b8952530cda9747534 |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-13394054dfe747b8952530cda97475342025-01-12T12:40:58ZengNature Portfolionpj Digital Medicine2398-63522025-01-01811810.1038/s41746-024-01329-9A hybrid machine learning approach for the personalized prognostication of aggressive skin cancersTom W. Andrew0Mogdad Alrawi1Ruth Plummer2Nick Reynolds3Vern Sondak4Isaac Brownell5Penny E. Lovat6Aidan Rose7Sophia Z. Shalhout8Translation and Clinical Research Institute, Newcastle UniversityDepartment of Plastic and Reconstructive Surgery, Royal Victoria Infirmary, Newcastle Upon Tyne Hospital NHS Foundation Trust (NuTH)Translation and Clinical Research Institute, Newcastle UniversityTranslation and Clinical Research Institute, Newcastle UniversityDepartment of Cutaneous Oncology, Moffitt Cancer Center, and Department of Oncologic Sciences, Morsani College of Medicine, University of South FloridaDermatology Branch, National Institute of Arthritis Musculoskeletal and Skin Diseases (NIAMS), National Institutes of Health (NIH)Translation and Clinical Research Institute, Newcastle UniversityTranslation and Clinical Research Institute, Newcastle UniversityMike Toth Head and Neck Cancer Research Center, Division of Surgical Oncology, Department of Otolaryngology-Head and Neck Surgery, Mass Eye and EarAbstract Accurate prognostication guides optimal clinical management in skin cancer. Merkel cell carcinoma (MCC) is the most aggressive form of skin cancer that often presents in advanced stages and is associated with poor survival rates. There are no personalized prognostic tools in use in MCC. We employed explainability analysis to reveal new insights into mortality risk factors for this highly aggressive cancer. We then combined deep learning feature selection with a modified XGBoost framework, to develop a web-based prognostic tool for MCC termed ‘DeepMerkel’. DeepMerkel can make accurate personalised, time-dependent survival predictions for MCC from readily available clinical information. It demonstrated generalizability through high predictive performance in an international clinical cohort, out-performing current population-based prognostic staging systems. MCC and DeepMerkel provide the exemplar model of personalised machine learning prognostic tools in aggressive skin cancers.https://doi.org/10.1038/s41746-024-01329-9 |
| spellingShingle | Tom W. Andrew Mogdad Alrawi Ruth Plummer Nick Reynolds Vern Sondak Isaac Brownell Penny E. Lovat Aidan Rose Sophia Z. Shalhout A hybrid machine learning approach for the personalized prognostication of aggressive skin cancers npj Digital Medicine |
| title | A hybrid machine learning approach for the personalized prognostication of aggressive skin cancers |
| title_full | A hybrid machine learning approach for the personalized prognostication of aggressive skin cancers |
| title_fullStr | A hybrid machine learning approach for the personalized prognostication of aggressive skin cancers |
| title_full_unstemmed | A hybrid machine learning approach for the personalized prognostication of aggressive skin cancers |
| title_short | A hybrid machine learning approach for the personalized prognostication of aggressive skin cancers |
| title_sort | hybrid machine learning approach for the personalized prognostication of aggressive skin cancers |
| url | https://doi.org/10.1038/s41746-024-01329-9 |
| work_keys_str_mv | AT tomwandrew ahybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT mogdadalrawi ahybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT ruthplummer ahybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT nickreynolds ahybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT vernsondak ahybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT isaacbrownell ahybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT pennyelovat ahybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT aidanrose ahybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT sophiazshalhout ahybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT tomwandrew hybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT mogdadalrawi hybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT ruthplummer hybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT nickreynolds hybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT vernsondak hybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT isaacbrownell hybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT pennyelovat hybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT aidanrose hybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers AT sophiazshalhout hybridmachinelearningapproachforthepersonalizedprognosticationofaggressiveskincancers |