Early predictions of response and survival from a tumor dynamics model in patients with recurrent, metastatic head and neck squamous cell carcinoma treated with immunotherapy
| Autor: | Vincent F. S. Dubois, Stuart Spencer, Vadryn Pierre, Paul Baverel, Helen Moore, Nassim Morsli, Ignacio González-García |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Male
Oncology medicine.medical_specialty Durvalumab Antibodies Monoclonal Humanized Article Machine Learning Antineoplastic Agents Immunological Text mining Drug Development Predictive Value of Tests Internal medicine Humans Medicine Pharmacology (medical) Aged Receiver operating characteristic Squamous Cell Carcinoma of Head and Neck business.industry Research lcsh:RM1-950 Head and neck cancer Antibodies Monoclonal Cancer Articles Middle Aged medicine.disease Survival Analysis Head and neck squamous-cell carcinoma Confidence interval NONMEM lcsh:Therapeutics. Pharmacology Head and Neck Neoplasms Modeling and Simulation Drug Therapy Combination Female Immunotherapy Neoplasm Recurrence Local business |
| Zdroj: | CPT: Pharmacometrics & Systems Pharmacology, Vol 10, Iss 3, Pp 230-240 (2021) CPT: Pharmacometrics & Systems Pharmacology |
| ISSN: | 2163-8306 |
| Popis: | We developed and evaluated a method for making early predictions of best overall response (BOR) and overall survival at 6 months (OS6) in patients with cancer treated with immunotherapy. This method combines machine learning with modeling of longitudinal tumor size data. We applied our method to data from durvalumab‐exposed patients with recurrent/metastatic head and neck cancer. A fivefold cross‐validation was used for model selection. Independent trial data, with various degrees of data truncation, were used for model validation. Mean classification error rates (90% confidence intervals [CIs]) from cross‐validation were 5.99% (90% CI 2.98%–7.50%) for BOR and 19.8% (90% CI 15.8%–39.3%) for OS6. During model validation, the area under the receiver operating characteristic curves was preserved for BOR (0.97, 0.97, and 0.94) and OS6 (0.85, 0.84, and 0.82) at 24, 18, and 12 weeks, respectively. These results suggest our method predicts trial outcomes accurately from early data and could be used to aid drug development. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|