Abstract 1113P
Background
Biomarkers and clinical features don’t currently enable the identification of standardized risk categories for optimal treatment strategies in metastatic melanoma. This issue underlines the need of a more sophisticated and comprehensive prognostic evaluation. The aim of this retrospective observational study is to develop a machine learning model based on pre-therapy Computed Tomography (CT) images to stratify the single-subject prognosis in melanoma patients.
Methods
Images from 60 metastatic lesions were collected, 32 (53.3%) belonged to “favorable prognosis” class and 28 (46.7%) to “unfavorable prognosis” class, according to patients’ prognosis intended as Progression Free Survival (PFS) > treatment median PFS. This image-set was used for the training and cross-validation of different radiomic-machine learning models through the Trace4Research software (DeepTrace Technologies srl, Italy). A radiomic approach was applied, under the hypothesis that radiomic feature could capture the disease heterogeneity among the two groups. Three models consisting of 4 ensembles of machine learning classifiers (random forests, support vector machines and k-nearest neighbor classifiers) were developed for the binary classification task of interest (favorable vs unfavorable), based on supervised learning, using prognosis as reference standard.
Results
The best model showed ROC-AUC (%) of 82 (majority vote), 81.6** (mean) [77.9-85.4], Accuracy (%) of 77, 75.4** [74.1-76.7], Sensitivity (%) of 84, 80.5** [78-83], Specificity (%) of 68, 69.6** [66.4-72.9], PPV (%) of 75, 75.2** [73.5-76.9], and NPV (%) of 79, 75.7** [73.8-77.7] (*p<0.05, **p<0.005).
The model was external tested on 20 new patients (N=70 lesions) and the classification of each patient’s prognosis was obtained using the one most frequently assigned by the classifier to the metastatic lesions of the same patient. The results show that the classifier can predict subjects with a favorable prognosis with good accuracy (85%). A third of patients (35%) with unfavorable prognosis were predicted.
Conclusions
These preliminary data underscore the potential of radiomics-based machine learning models in predicting prognosis in patients with metastatic melanoma.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
M. Russillo: Financial Interests, Institutional, Financially compensated role: Pierre Fabre Oncologie, Novartis, MSD, BMS. V. Ferraresi: Financial Interests, Institutional, Financially compensated role: BMS, Novartis, Pierre Fabre Oncologie, MSD. All other authors have declared no conflicts of interest.
Resources from the same session
1132P - Regorafenib in Caucasian patients with pretreated advanced KIT-mutant melanoma: A dual center case series
Presenter: Iris Dirven
Session: Poster session 04
1133P - Only early adjuvant radiotherapy, particularly of the tumor bed rather than the lymph node region, improves prognosis in Merkel cell carcinoma: Results from the prospective German MCC registry
Presenter: Juergen Becker
Session: Poster session 04
1134P - Avelumab in metastatic Merkel cell carcinoma (mMCC): Conditional survival and long-term safety in patients treated for ≥1 or ≥2 years in JAVELIN Merkel 200
Presenter: Celeste Lebbe
Session: Poster session 04
1135P - Multi-modal and longitudinal characterization of the tumor and immune microenvironment of Merkel cell carcinoma
Presenter: Maximilian Haist
Session: Poster session 04
1136P - Cosibelimab in advanced cutaneous squamous cell carcinoma (CSCC): Longer-term efficacy and safety results from pivotal study
Presenter: Eva Muñoz-Couselo
Session: Poster session 04
1137P - Efficacy of LNS8801 in melanoma patients with prior immune-related adverse events from immune-checkpoint inhibitors
Presenter: Justine Cohen
Session: Poster session 04
1138P - A prospective study of patients with immune checkpoint inhibitor-induced hepatitis: Management outcome and association with liver injury subtype, immune infiltration, and clinical parameters
Presenter: Rikke Holmstroem
Session: Poster session 04
1139TiP - IDE196 (darovasertib) in combination with crizotinib versus investigator’s choice of treatment as first-line therapy in HLA-A2 negative metastatic uveal melanoma
Presenter: Marcus Butler
Session: Poster session 04
1140TiP - Safe stop IPI-NIVO trial: Early discontinuation of nivolumab upon achieving a complete or partial response in patients with irresectable stage III or metastatic melanoma treated with first-line ipilimumab-nivolumab
Presenter: Joséphine Janssen
Session: Poster session 04
1210P - Neoadjuvant pembrolizumab (pembro) or placebo (pbo) plus chemotherapy and adjuvant pembro or pbo for early stage NSCLC: Subgroup analyses of the phase III KEYNOTE-671 study
Presenter: Marina Garassino
Session: Poster session 04