Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients.

Autor:	Prelaj A; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy., Galli EG; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Niguarda Cancer Center, Grande Ospedale Metropolitano Niguarda, Milan, Italy.; Oncology Department, University of Milan, Milan, Italy., Miskovic V; Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy., Pesenti M; Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy., Viscardi G; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Medical Oncology Unit, Department of Precision Medicine, University of Campania 'Luigi Vanvitelli', Naples, Italy., Pedica B; Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy., Mazzeo L; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy.; Oncology Department, University of Milan, Milan, Italy., Bottiglieri A; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Oncology Department, University of Milan, Milan, Italy., Provenzano L; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Oncology Department, University of Milan, Milan, Italy., Spagnoletti A; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Oncology Department, University of Milan, Milan, Italy., Marinacci R; Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy., De Toma A; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy., Proto C; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy., Ferrara R; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy., Brambilla M; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy., Occhipinti M; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy., Manglaviti S; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy., Galli G; Medical Oncology Unit, Policlinico San Matteo Fondazione IRCCS, Pavia, Italy., Signorelli D; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Niguarda Cancer Center, Grande Ospedale Metropolitano Niguarda, Milan, Italy., Giani C; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Oncology Department, University of Milan, Milan, Italy., Beninato T; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Oncology Department, University of Milan, Milan, Italy., Pircher CC; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Oncology Department, University of Milan, Milan, Italy., Rametta A; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Oncology Department, University of Milan, Milan, Italy., Kosta S; Department of Electronic System, Aalborg University, Copenhagen, Aalborg, Denmark., Zanitti M; Department of Electronic System, Aalborg University, Copenhagen, Aalborg, Denmark., Di Mauro MR; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy., Rinaldi A; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy., Di Gregorio S; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy., Antonia M; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy., Garassino MC; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Thoracic Oncology Program, Section of Hematology/Oncology, University of Chicago, Chicago, IL, United States., de Braud FGM; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy.; Oncology Department, University of Milan, Milan, Italy., Restelli M; Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy., Lo Russo G; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy., Ganzinelli M; Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, Milan, Italy., Trovò F; Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy., Pedrocchi ALG; Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy.
Jazyk:	angličtina
Zdroj:	Frontiers in oncology [Front Oncol] 2023 Jan 23; Vol. 12, pp. 1078822. Date of Electronic Publication: 2023 Jan 23 (Print Publication: 2022).
DOI:	10.3389/fonc.2022.1078822
Abstrakt:	Introduction: Artificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods. Methods: We prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions. Results: Of 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models' prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR. Conclusions: In this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients. Competing Interests: MCG: declares personal financial interests with the following organizations: AstraZeneca, MSD International GmbH, BMS, Boehringer Ingelheim Italia S.p.A, Celgene, Eli Lilly, Ignyta, Incyte, Inivata, MedImmune, Novartis, Pfizer, Roche, Takeda. FB declares: Consultant Advisory Board for Ignyta, BMS, Daiichi Sankyo, Pfizer, Octimet Oncology, Incyte, Teofarma, Pierre Fabre, Roche, EMD Serono, Sanofi, NMS Nerviano Medical Science, Pharm Research Associated U.K Ltd; as a Speaker BMS, Roche, MSD, Ignyta, Bayer, ACCMED, Dephaforum S.r.l., Nadirex, Merck, Biotechspert Ltd, PriME Oncology, Pfizer, Servier, Celgene, Tesaro, Loxo Oncology Inc., Sanofi, Healthcare Research & Pharmacoepidemiology, as P.I for Novartis, Roche, BMS, Celgene, Incyte, NMS, Merck KGAA, Kymab, Pfizer, Tesaro, MSD. AP declares personal fees from Roche, AstraZeneca and BMS outside the submitted work. CP declares personal fees from BMS and MSD, outside the submitted work. G.LR. declares personal fees from BMS, MSD and Astra Zeneca outside the submitted work. DS declares personal fees from AstraZeneca, Boehringer Ingelheim and BMS, outside the submitted work. DS: Consulting, advisory role: AstraZeneca, Bristol-Myers Squibb, Boehringer Ingelheim, Merck Sharp & Dohme, Sanofi. Honoraria: AstraZeneca, Bristol-Myers Squibb, Boehringer Ingelheim, Eli Lilly, Roche, Merck Sharp & Dohme. Principal Investigator in clinical trial sponsored by Bristol-Myers Squibb, Merck Sharp & Dohme, Eli Lilly. Travel, Accommodations: AstraZeneca, Roche, Bristol-Myers Squibb, Merck Sharp & Dohme, Pfizer. DS consulting, advisory role: AstraZeneca, Bristol-Myers Squibb, Boehringer Ingelheim, Merck Sharp & Dohme, Sanofi. Honoraria: AstraZeneca, Bristol-Myers Squibb, Boehringer Ingelheim, Eli Lilly, Roche, Merck Sharp & Dohme. Principal Investigator in clinical trial sponsored by Bristol-Myers Squibb, Merck Sharp & Dohme, Eli Lilly. Travel, Accommodations: AstraZeneca, Roche, Bristol-Myers Squibb, Merck Sharp & Dohme, Pfizer. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2023 Prelaj, Galli, Miskovic, Pesenti, Viscardi, Pedica, Mazzeo, Bottiglieri, Provenzano, Spagnoletti, Marinacci, De Toma, Proto, Ferrara, Brambilla, Occhipinti, Manglaviti, Galli, Signorelli, Giani, Beninato, Pircher, Rametta, Kosta, Zanitti, Di Mauro, Rinaldi, Di Gregorio, Antonia, Garassino, de Braud, Restelli, Lo Russo, Ganzinelli, Trovò and Pedrocchi.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu