Abstract 86P
Background
Immunotherapy (IO) alone or in combination with chemotherapy (CT-IO) has become the standard of care for most patients with metastatic Non-Small Cell Lung Cancer (NSCLC). Nevertheless, 20-30% of patients do not benefit from these treatments facing a negative risk-benefit balance and the identification of reliable predictive factors for a better patients’ selection is an important unmet need.
Methods
In this retrospective single-centre analysis, patients with metastatic NSCLC treated with first line (CT)-IO between 2015 and 2021 were eligible. Clinical, pathological and laboratory data were retrieved. Primary aim was to identify the features predicting early progression (radiological progression or death within 3 months from treatment start) by artificial intelligence (AI) models.
Results
201 patients were included: 121 IO (all PD-L1 ≥50%), 80 CT-IO (all PD-L1 <50%). 46% in IO group and 36% in CT-IO group were early progressors. Early progression correlated with poor performance status, elevated neutrophil percentage (>80%) and neutrophil/lymphocyte ratio (≥8), lower-range PD-L1 status (50%-75%, in IO only), use of steroids (in IO only), bone and liver metastases (in CT-IO) by a statistical exploratory data analysis. In IO only population, black-box models (Automated Machine Learning, AutoML) encompassing clinical, laboratory and pathological data reached an AUC of 0.82 in predicting early progression (best model: Voting Ensemble). White box tools (SHapley Additive exPlanations) paired with AutoML generated models increased the interpretability of the results despite slightly lower precision scores. Dimensionality reduction algorithms such as t-SNE (t-distributed stochastic neighbor embedding) and SVM (Support Vector Machine) were applied on our dataset to rebalance sample size with feature list, obtaining a reliable pattern of cases distribution.
Conclusions
Artificial intelligence models can predict trustworthy patterns of early progression in IO-treated patients. Pairing black box and white box methods is feasible and could increase robustness and interpretability of the results.
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
F.R. Ogliari: Financial Interests, Personal, Invited Speaker: Roche, Sanofi. A. Traverso: Financial Interests, Personal, Advisory Board: IQVIA, Illumina, Varian. V. Gregorc: Financial Interests, Personal, Advisory Board: Eli Lilly SPA; Financial Interests, Personal, Invited Speaker: Boehringer Ingelheim, Sanofi, BMS, MSD; Financial Interests, Personal, Expert Testimony: Novartis, Eli Lilly, BMS, MSD. L. Hendriks: Financial Interests, Institutional, Advisory Board: Amgen, Boehringer Ingelheim, Lilly, Novartis, Pfizer, Takeda, Merck, Janssen, MSD, Anheart; Financial Interests, Institutional, Invited Speaker, for educational webinar: AstraZeneca, Lilly; Financial Interests, Institutional, Invited Speaker, educational webinar/interview: Bayer; Financial Interests, Institutional, Invited Speaker, educationals:MSD; Financial Interests, Personal, Invited Speaker, for webinars: Medtalks; Financial Interests, Personal, Invited Speaker, payment for post ASCO round table discussion: VJOncology; Financial Interests, Personal, Invited Speaker, payment for post ASCO/ESMO/WCLC presentations, educational committee member: benecke; Financial Interests, Institutional, Invited Speaker, payment for post ESMO/ASCO discussion: high5oncology; Financial Interests, Institutional, Other, podcast on brain metastases: Takeda; Financial Interests, Institutional, Other, educational webinar: Janssen; Financial Interests, Institutional, Invited Speaker, satellite symposium at conference: GSK, sanofi; Financial Interests, Personal, Invited Speaker, presentation guideline: medimix; Financial Interests, Institutional, Invited Speaker, podcast and educational: Pfizer; Financial Interests, Personal, Other, member of the committee that revised these guidelines: Dutch guidelines NSCLC, brain metastases and leptomeningeal metastases; Financial Interests, Institutional, Research Grant, for IIS: Roche, Boehringer Ingelheim, AstraZeneca, Takeda, Novartis; Financial Interests, Institutional, Research Grant, donation for health care improvement project: Merck; Financial Interests, Institutional, Research Grant, funding for healthcare improvement project: Pfizer; Financial Interests, Institutional, Research Grant, for IIS, under negotiation: gilead; Financial Interests, Institutional, Invited Speaker: AstraZeneca, GSK, Novartis, Merck Serono, Roche, Takeda, Blueprint Medicines, Mirati, AbbVie, MSD, Gilead; Non-Financial Interests, Personal, Other, Chair metastatic NSCLC for lung cancer group: EORTC; Non-Financial Interests, Personal, Other, secretary NVALT studies foundation: NVALT; Non-Financial Interests, Personal, Other, vice chair scientific committee: Dutch Thoracic Group. A. Bulotta: Financial Interests, Personal, Advisory Board: Roche, BMS, AstraZeneca; Financial Interests, Personal, Invited Speaker: BMS, MSD, AstraZeneca, Eli Lilly. R. Ferrara: Financial Interests, Personal, Advisory Board, In April 2022:MSD; Financial Interests, Personal, Advisory Board: BeiGene; Financial Interests, Institutional, Invited Speaker: MSD, Pfizer, AstraZeneca, Roche, Sanofi, Novartis, BMS, IPSEN, Daiichi Sankyo Company. All other authors have declared no conflicts of interest.