Machine Learning for Prediction of Immunotherapy Efficacy in Non-Small Cell Lung Cancer from Simple Clinical and Biological Data.
blood counts
lung cancer
machine learning
prediction
response
survival
Journal
Cancers
ISSN: 2072-6694
Titre abrégé: Cancers (Basel)
Pays: Switzerland
ID NLM: 101526829
Informations de publication
Date de publication:
09 Dec 2021
09 Dec 2021
Historique:
received:
08
11
2021
revised:
30
11
2021
accepted:
03
12
2021
entrez:
24
12
2021
pubmed:
25
12
2021
medline:
25
12
2021
Statut:
epublish
Résumé
Immune checkpoint inhibitors (ICIs) are now a therapeutic standard in advanced non-small cell lung cancer (NSCLC), but strong predictive markers for ICIs efficacy are still lacking. We evaluated machine learning models built on simple clinical and biological data to individually predict response to ICIs. Patients with metastatic NSCLC who received ICI in second line or later were included. We collected clinical and hematological data and studied the association of this data with disease control rate (DCR), progression free survival (PFS) and overall survival (OS). Multiple machine learning (ML) algorithms were assessed for their ability to predict response. Overall, 298 patients were enrolled. The overall response rate and DCR were 15.3% and 53%, respectively. Median PFS and OS were 3.3 and 11.4 months, respectively. In multivariable analysis, DCR was significantly associated with performance status (PS) and hemoglobin level (OR 0.58, Combination of simple clinical and biological data could accurately predict disease control rate at the individual level.
Sections du résumé
BACKGROUND
BACKGROUND
Immune checkpoint inhibitors (ICIs) are now a therapeutic standard in advanced non-small cell lung cancer (NSCLC), but strong predictive markers for ICIs efficacy are still lacking. We evaluated machine learning models built on simple clinical and biological data to individually predict response to ICIs.
METHODS
METHODS
Patients with metastatic NSCLC who received ICI in second line or later were included. We collected clinical and hematological data and studied the association of this data with disease control rate (DCR), progression free survival (PFS) and overall survival (OS). Multiple machine learning (ML) algorithms were assessed for their ability to predict response.
RESULTS
RESULTS
Overall, 298 patients were enrolled. The overall response rate and DCR were 15.3% and 53%, respectively. Median PFS and OS were 3.3 and 11.4 months, respectively. In multivariable analysis, DCR was significantly associated with performance status (PS) and hemoglobin level (OR 0.58,
CONCLUSION
CONCLUSIONS
Combination of simple clinical and biological data could accurately predict disease control rate at the individual level.
Identifiants
pubmed: 34944830
pii: cancers13246210
doi: 10.3390/cancers13246210
pmc: PMC8699503
pii:
doi:
Types de publication
Journal Article
Langues
eng
Références
Nature. 2013 Jul 11;499(7457):214-218
pubmed: 23770567
Lancet. 2016 Apr 9;387(10027):1540-1550
pubmed: 26712084
Cancer Res. 2016 Sep 1;76(17):4931-40
pubmed: 27302167
Ann Oncol. 2019 Apr 1;30(4):655-657
pubmed: 30753264
Clin Lung Cancer. 2018 Jul;19(4):e421-e430
pubmed: 29609906
Nature. 2013 Aug 22;500(7463):415-21
pubmed: 23945592
Br J Cancer. 2017 Sep 26;117(7):913-920
pubmed: 28950287
Ther Adv Med Oncol. 2020 Nov 5;12:1758835920970049
pubmed: 33224276
Eur J Cancer. 2009 Jan;45(2):228-47
pubmed: 19097774
Ann Oncol. 2019 Aug 1;30(8):1321-1328
pubmed: 31125062
J Thorac Oncol. 2019 Jun;14(6):1095-1101
pubmed: 30738221
J Thorac Dis. 2019 Jan;11(Suppl 1):S71-S80
pubmed: 30775030
Eur J Cancer. 2021 Aug;153:179-189
pubmed: 34182269
Cancer Discov. 2018 Jul;8(7):822-835
pubmed: 29773717
JAMA Oncol. 2018 Mar 1;4(3):351-357
pubmed: 29327044
Br J Cancer. 2011 Jun 28;105(1):93-103
pubmed: 21629244
JCI Insight. 2020 Jan 30;5(2):
pubmed: 31855576
Eur J Cancer. 2020 Nov;140:76-85
pubmed: 33059196
J Clin Epidemiol. 2019 Jun;110:12-22
pubmed: 30763612
Lung Cancer. 2017 Sep;111:176-181
pubmed: 28838390
N Engl J Med. 2016 Nov 10;375(19):1823-1833
pubmed: 27718847
Ann Oncol. 2020 Nov;31(11):1561-1568
pubmed: 32739409
Eur J Cancer. 2021 Jul;151:211-220
pubmed: 34022698
Lancet Oncol. 2018 Sep;19(9):1180-1191
pubmed: 30120041
Ann Oncol. 2016 Apr;27(4):732-8
pubmed: 26802161
Cancer Treat Rev. 2018 Apr;65:65-77
pubmed: 29567557
BMJ. 2020 Mar 18;368:m441
pubmed: 32188600
Lung Cancer. 2020 Jul;145:95-104
pubmed: 32417680
Ann Oncol. 2018 Oct 1;29(Suppl 4):iv192-iv237
pubmed: 30285222
Lancet. 2001 Feb 17;357(9255):539-45
pubmed: 11229684
JCO Clin Cancer Inform. 2020 Mar;4:259-274
pubmed: 32213092
JCO Oncol Pract. 2021 Aug 5;:OP2001055
pubmed: 34351819
Nat Commun. 2019 Sep 25;10(1):4346
pubmed: 31554815
Cancer Epidemiol Biomarkers Prev. 2017 Jul;26(7):1139-1145
pubmed: 28446544
Radiother Oncol. 2019 Jan;130:2-9
pubmed: 30416044
Cell. 2019 Jul 25;178(3):699-713.e19
pubmed: 31280963
Br J Cancer. 2012 Aug 7;107(4):695-9
pubmed: 22828611
Cancers (Basel). 2020 Nov 30;12(12):
pubmed: 33265926
Clin Pharmacol Ther. 2020 Sep;108(3):471-486
pubmed: 32557598
Ann Oncol. 2019 Jun 1;30(6):998-1004
pubmed: 30895304
J Clin Oncol. 2018 Mar 1;36(7):633-641
pubmed: 29337640
Clin Cancer Res. 2018 Jul 15;24(14):3292-3298
pubmed: 29685883
Sci Rep. 2016 Mar 30;6:23893
pubmed: 27025911
Oncologist. 2019 Aug;24(8):1128-1136
pubmed: 31015312