In CPT: pharmacometrics & systems pharmacology
We developed and evaluated a method for making early predictions of best overall response (BOR) and survival at 6 months (OS6) in cancer patients 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 5-fold 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% (2.98%-7.50%) for BOR and 19.8% (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.
González-García Ignacio, Pierre Vadryn, F S Dubois Vincent, Morsli Nassim, Spencer Stuart, Baverel Paul G, Moore Helen
NONMEM, anti-PD-L1, durvalumab, head and neck squamous cell carcinoma, immuno-oncology (IO), machine learning, nonlinear mixed-effects modeling, response prediction, tumor dynamics model