Machine Learning Using Real-World and Translational Data to Improve Treatment Selection for NSCLC Patients Treated with Immunotherapy
(1) Background: In advanced non-small cell lung cancer (aNSCLC), programmed death ligand 1 (PD-L1) remains the only biomarker for candidate patients to immunotherapy (IO). This study aimed at using artificial intelligence (AI) and machine learning (ML) tools to improve response and efficacy predicti...
Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-01-01
|
Series: | Cancers |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-6694/14/2/435 |
_version_ | 1797495271447330816 |
---|---|
author | Arsela Prelaj Mattia Boeri Alessandro Robuschi Roberto Ferrara Claudia Proto Giuseppe Lo Russo Giulia Galli Alessandro De Toma Marta Brambilla Mario Occhipinti Sara Manglaviti Teresa Beninato Achille Bottiglieri Giacomo Massa Emma Zattarin Rosaria Gallucci Edoardo Gregorio Galli Monica Ganzinelli Gabriella Sozzi Filippo G. M. de Braud Marina Chiara Garassino Marcello Restelli Alessandra Laura Giulia Pedrocchi Francesco Trovo' |
author_facet | Arsela Prelaj Mattia Boeri Alessandro Robuschi Roberto Ferrara Claudia Proto Giuseppe Lo Russo Giulia Galli Alessandro De Toma Marta Brambilla Mario Occhipinti Sara Manglaviti Teresa Beninato Achille Bottiglieri Giacomo Massa Emma Zattarin Rosaria Gallucci Edoardo Gregorio Galli Monica Ganzinelli Gabriella Sozzi Filippo G. M. de Braud Marina Chiara Garassino Marcello Restelli Alessandra Laura Giulia Pedrocchi Francesco Trovo' |
author_sort | Arsela Prelaj |
collection | DOAJ |
description | (1) Background: In advanced non-small cell lung cancer (aNSCLC), programmed death ligand 1 (PD-L1) remains the only biomarker for candidate patients to immunotherapy (IO). This study aimed at using artificial intelligence (AI) and machine learning (ML) tools to improve response and efficacy predictions in aNSCLC patients treated with IO. (2) Methods: Real world data and the blood microRNA signature classifier (MSC) were used. Patients were divided into responders (R) and non-responders (NR) to determine if the overall survival of the patients was likely to be shorter or longer than 24 months from baseline IO. (3) Results: One-hundred sixty-four out of 200 patients (i.e., only those ones with PD-L1 data available) were considered in the model, 73 (44.5%) were R and 91 (55.5%) NR. Overall, the best model was the linear regression (RL) and included 5 features. The model predicting R/NR of patients achieved accuracy ACC = 0.756, F1 score F1 = 0.722, and area under the ROC curve AUC = 0.82. LR was also the best-performing model in predicting patients with long survival (24 months OS), achieving ACC = 0.839, F1 = 0.908, and AUC = 0.87. (4) Conclusions: The results suggest that the integration of multifactorial data provided by ML techniques is a useful tool to select NSCLC patients as candidates for IO. |
first_indexed | 2024-03-10T01:46:26Z |
format | Article |
id | doaj.art-ad41281b62b04e7a9b1e3186536ae12f |
institution | Directory Open Access Journal |
issn | 2072-6694 |
language | English |
last_indexed | 2024-03-10T01:46:26Z |
publishDate | 2022-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Cancers |
spelling | doaj.art-ad41281b62b04e7a9b1e3186536ae12f2023-11-23T13:14:59ZengMDPI AGCancers2072-66942022-01-0114243510.3390/cancers14020435Machine Learning Using Real-World and Translational Data to Improve Treatment Selection for NSCLC Patients Treated with ImmunotherapyArsela Prelaj0Mattia Boeri1Alessandro Robuschi2Roberto Ferrara3Claudia Proto4Giuseppe Lo Russo5Giulia Galli6Alessandro De Toma7Marta Brambilla8Mario Occhipinti9Sara Manglaviti10Teresa Beninato11Achille Bottiglieri12Giacomo Massa13Emma Zattarin14Rosaria Gallucci15Edoardo Gregorio Galli16Monica Ganzinelli17Gabriella Sozzi18Filippo G. M. de Braud19Marina Chiara Garassino20Marcello Restelli21Alessandra Laura Giulia Pedrocchi22Francesco Trovo'23Medical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyTumor Genomics Unit, Department of Research, Fondazione IRCCS Istituto Nazionale dei Tumori, 20133 Milan, ItalyDepartment of Electronics, Information and Bioengineering, Politecnico di Milano, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyTumor Genomics Unit, Department of Research, Fondazione IRCCS Istituto Nazionale dei Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyMedical Oncology Department, Fondazione IRCCS Istituto Nazionale Tumori, 20133 Milan, ItalyDepartment of Electronics, Information and Bioengineering, Politecnico di Milano, 20133 Milan, ItalyDepartment of Electronics, Information and Bioengineering, Politecnico di Milano, 20133 Milan, ItalyDepartment of Electronics, Information and Bioengineering, Politecnico di Milano, 20133 Milan, Italy(1) Background: In advanced non-small cell lung cancer (aNSCLC), programmed death ligand 1 (PD-L1) remains the only biomarker for candidate patients to immunotherapy (IO). This study aimed at using artificial intelligence (AI) and machine learning (ML) tools to improve response and efficacy predictions in aNSCLC patients treated with IO. (2) Methods: Real world data and the blood microRNA signature classifier (MSC) were used. Patients were divided into responders (R) and non-responders (NR) to determine if the overall survival of the patients was likely to be shorter or longer than 24 months from baseline IO. (3) Results: One-hundred sixty-four out of 200 patients (i.e., only those ones with PD-L1 data available) were considered in the model, 73 (44.5%) were R and 91 (55.5%) NR. Overall, the best model was the linear regression (RL) and included 5 features. The model predicting R/NR of patients achieved accuracy ACC = 0.756, F1 score F1 = 0.722, and area under the ROC curve AUC = 0.82. LR was also the best-performing model in predicting patients with long survival (24 months OS), achieving ACC = 0.839, F1 = 0.908, and AUC = 0.87. (4) Conclusions: The results suggest that the integration of multifactorial data provided by ML techniques is a useful tool to select NSCLC patients as candidates for IO.https://www.mdpi.com/2072-6694/14/2/435non-small cell lung cancerimmunotherapybiomarkerartificial intelligencemachine learning |
spellingShingle | Arsela Prelaj Mattia Boeri Alessandro Robuschi Roberto Ferrara Claudia Proto Giuseppe Lo Russo Giulia Galli Alessandro De Toma Marta Brambilla Mario Occhipinti Sara Manglaviti Teresa Beninato Achille Bottiglieri Giacomo Massa Emma Zattarin Rosaria Gallucci Edoardo Gregorio Galli Monica Ganzinelli Gabriella Sozzi Filippo G. M. de Braud Marina Chiara Garassino Marcello Restelli Alessandra Laura Giulia Pedrocchi Francesco Trovo' Machine Learning Using Real-World and Translational Data to Improve Treatment Selection for NSCLC Patients Treated with Immunotherapy Cancers non-small cell lung cancer immunotherapy biomarker artificial intelligence machine learning |
title | Machine Learning Using Real-World and Translational Data to Improve Treatment Selection for NSCLC Patients Treated with Immunotherapy |
title_full | Machine Learning Using Real-World and Translational Data to Improve Treatment Selection for NSCLC Patients Treated with Immunotherapy |
title_fullStr | Machine Learning Using Real-World and Translational Data to Improve Treatment Selection for NSCLC Patients Treated with Immunotherapy |
title_full_unstemmed | Machine Learning Using Real-World and Translational Data to Improve Treatment Selection for NSCLC Patients Treated with Immunotherapy |
title_short | Machine Learning Using Real-World and Translational Data to Improve Treatment Selection for NSCLC Patients Treated with Immunotherapy |
title_sort | machine learning using real world and translational data to improve treatment selection for nsclc patients treated with immunotherapy |
topic | non-small cell lung cancer immunotherapy biomarker artificial intelligence machine learning |
url | https://www.mdpi.com/2072-6694/14/2/435 |
work_keys_str_mv | AT arselaprelaj machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT mattiaboeri machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT alessandrorobuschi machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT robertoferrara machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT claudiaproto machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT giuseppelorusso machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT giuliagalli machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT alessandrodetoma machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT martabrambilla machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT marioocchipinti machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT saramanglaviti machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT teresabeninato machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT achillebottiglieri machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT giacomomassa machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT emmazattarin machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT rosariagallucci machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT edoardogregoriogalli machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT monicaganzinelli machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT gabriellasozzi machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT filippogmdebraud machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT marinachiaragarassino machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT marcellorestelli machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT alessandralauragiuliapedrocchi machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy AT francescotrovo machinelearningusingrealworldandtranslationaldatatoimprovetreatmentselectionfornsclcpatientstreatedwithimmunotherapy |