67P - Artificial Intelligence to predict early progressors among aBC patients treated with first-line CDK4/6i: A sub-analysis from PALMARES-2 study

Background

CDK4/6 inhibitors (CDK4/6i) in combination with endocrine therapy (ET) are nowadays the standard of care, 1^st line treatment for Hormone Receptor positive, Human Epidermal growth factor Receptor 2-negative (HR+/HER2-) advanced Breast Cancer (aBC). However, some patients (pts) experience low PFS during ET+CDK4/6i and could be candidate to treatment intensification. Artificial Intelligence (AI) methods, in particular Machine Learning (ML), are effective in integrating data to generate predictive models.

Methods

We used ML to build a predictive model based on Real-world data (RWD) of HR+/HER2- aBC pts enrolled in the multicenter Italian study PALMARES-2. All pts received ET+CDK4/6i as 1^st therapy. PFS status at 18 months was used as the clinical outcome for classification model. The entire dataset was split in training and test cohorts, and undersampling method was used to balance outcomes. Logistic regression (LR), random forest (RF), XGBoost and neural networks with model averaging (avNNet) were used as classifiers. Permutation-based variable importance was used for AI explainability (XAI).

Results

After excluding patients with less than 18 months of follow up and adjusting for outcomes unbalance, a total of 1000 pts from 18 Italian centers were included in the analysis. To fit the model, 52 clinical features were selected based on clinical relevance. All the 4 models consistently demonstrated similar prediction ability, with AUC ranging from 0.72 to 0.74 in training set and from 0.68 to 0.70 in test set. Performance values are reported in the table. XAI revealed endocrine resistance, liver metastases and performance status as the most informative features.

Conclusions

ML demonstrated promising ability in predicting early progressors among HR+/HER2- aBC patients treated with 1^st line ET+CDK4/6i using RWD. Integrating different sources of data, e.g. genomic, radiomics and digital pathology, could further improve model accuracy. Table: 67P

Legal entity responsible for the study

Fondazione IRCCS Istituto Nazionale dei Tumori, Milan.

Funding

Has not received any funding.

Disclosure

M. Giuliano: Financial Interests, Personal, Advisory Role: AstraZeneca, Daiichi Sankyo, Eisai, Exact Sciences, Gilead, Lilly, Menarini Stemline; MSD, Novartis, Pfizer, Roche, Seagen; Financial Interests, Institutional, Funding: AstraZeneca; Financial Interests, Personal, Other, Travel: Lilly, Pfizer, AstraZeneca. A. Toss: Financial Interests, Personal, Advisory Board: Lilly. M. Piras: Financial Interests, Personal, Other, Travel: Pfizer, Novartis. B. Tagliaferri: Financial Interests, Personal, Invited Speaker: Novartis, Daiichi Sankyo, Lilly; Financial Interests, Personal, Other, Travel: Pfizer, Novartis, Daiichi Sankyo, Gentili. D. Generali: Financial Interests, Personal, Funding: Novartis, Pfizer, Lilly, Istituto Gentili, Accord, Roche. A. Zambelli: Financial Interests, Personal, Invited Speaker: Novartis, AstraZeneca, Lilly, Pfizer, Daiichi Sankyo, MSD, Roche, Seagen, Exact Sciences, Gilead, Istituto Gentili. N.M. La Verde: Financial Interests, Personal, Advisory Board: Novartis, Pfizer, Roche, MSD, AstraZeneca, Eisai; Financial Interests, Personal, Speaker’s Bureau: Pfizer, Roche, Gentili, Lilly, Gilead, Daiichi Sankyo, Techdow; Financial Interests, Personal, Other, Travel: Pfizer, Roche; Financial Interests, Personal, Research Grant: GSK, Gilead. M. Lambertini: Financial Interests, Personal, Advisory Board: Roche, Novartis, Lilly, AstraZeneca, Pfizer, Sandoz, Takeda. A. Botticelli: Financial Interests, Personal, Speaker’s Bureau: Roche, MSD, Novartis, Pfizer, Lilly, Amgen, BMS, Gliead, Sofos, Daiichi, AstraZeneca. A. Prelaj: Financial Interests, Personal, Sponsor/Funding: Roche, AstraZeneca, BMS. G. Curigliano: Financial Interests, Personal, Project Lead: European Society for Medical Oncology, European Society of Breast Cancer Specialists (EUSOMA), ESMO Open; Financial Interests, Personal, Other, Honoraria: Ellipses Pharma; Financial Interests, Personal, Advisory Role: Roche/Genentech, Pfizer, Novartis, Lilly, Foundation Medicine, Bristol Myers Squibb, Samsung, AstraZeneca, Daiichi Sankyo-Sankyo, Boerigher, GSK, Seattle Genetics, Guardant Health, Veracyte, Celcuity, Hengrui Therapeutics, Menarini, Merck, Exact Sciences, Bluepr; Financial Interests, Personal, Invited Speaker: Roche/Genentech, Novartis, Pfizer, Lilly, Foundation Medicine, Samsung, Daiichi Sankyo, Seagen, Menarini, Gilead Sciences, AstraZeneca, Exact Sciences; Financial Interests, Institutional, Funding: Merck; Financial Interests, Personal, Ownership Interest, Travel, accomodation: Roche/Genentech, Pfizer, Daiichi Sankyo, AstraZeneca . M.V. Dieci: Financial Interests, Personal, Sponsor/Funding: Eli Lilly, Exact Sciences, Novartis, Pfizer, Seagen, Gilead, MSD, AstraZeneca, Daiichi Sankyo. C. Vernieri: Financial Interests, Personal, Advisory Board: Eli Lilly; Novartis; Pfizer; Daiichi Sankyo; Menarini; Financial Interests, Personal, Invited Speaker: Eli Lilly; Novartis; Istituto Gentili; Accademia di Medicina; Financial Interests, Institutional, Funding: Roche. All other authors have declared no conflicts of interest.