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
1101P - Efficacy of anti PD-1 therapy in children and adolescent melanoma patients (MELCAYA study)
Presenter: Mario Mandalà
Session: Poster session 04
1102P - Immune checkpoint inhibitor rechallenge after treatment with tumor-infiltrating lymphocytes in unresectable melanoma
Presenter: Allison Betof Warner
Session: Poster session 04
1103P - Real-world efficacy of relatlimab and nivolumab in advanced or resectable melanoma
Presenter: Lilit Karapetyan
Session: Poster session 04
1104P - Early time-point <sup>18</sup>F-FDG-PET/CT at week four (W4) as a prognostic biomarker of survival in metastatic melanoma (mM) patients (pts) on immunotherapy
Presenter: Nezka Hribernik
Session: Poster session 04
1105P - Predicting the outcomes of advanced cutaneous melanoma cases following discontinuation of immune checkpoint inhibition
Presenter: Ka-won Noh
Session: Poster session 04
1106P - NivoLag-when: International real-world study of combination immunotherapy sequences in melanoma
Presenter: Mora Guardamagna
Session: Poster session 04
1107P - Characteristics and quality of life of nine-year survivors from 312 patients with metastatic melanoma treated with pembrolizumab
Presenter: Jessica Hassel
Session: Poster session 04
1108P - Impact of quantitative imaging of all disease on the prognostic value of <sup>18</sup>F-FDG PET/CT in patients treated with immunotherapy for metastatic melanoma
Presenter: Robert Jeraj
Session: Poster session 04
1109P - Association of clinical features with long-term survival in patients with melanoma who responded to distinct checkpoint inhibitors
Presenter: Eva Ellebaek
Session: Poster session 04
1110P - Follow-up brain imaging in patients with melanoma brain metastasis and immune checkpoint inhibitors
Presenter: Imren Ozdamar
Session: Poster session 04