Comprehensive analysis of the associations between clinical factors and outcomes by machine learning, using post marketing surveillance data of cabazitaxel in patients with castration-resistant prostate cancer.
Cabazitaxel
Castration-resistant prostate cancer
Machine learning technology
Neutropenia
Outcome-associated clinical factors
Journal
BMC cancer
ISSN: 1471-2407
Titre abrégé: BMC Cancer
Pays: England
ID NLM: 100967800
Informations de publication
Date de publication:
29 Apr 2022
29 Apr 2022
Historique:
received:
02
09
2021
accepted:
04
04
2022
entrez:
28
4
2022
pubmed:
29
4
2022
medline:
3
5
2022
Statut:
epublish
Résumé
We aimed to evaluate relationships between clinical outcomes and explanatory variables by network clustering analysis using data from a post marketing surveillance (PMS) study of castration-resistant prostate cancer (CRPC) patients. The PMS was a prospective, multicenter, observational study of patients with metastatic, docetaxel-refractory CRPC treated with cabazitaxel in Japan after its launch in 2014. Graphical Markov (GM) model-based simulations and network clustering in 'R' package were conducted to identify correlations between clinical factors and outcomes. Factors shown to be associated with overall survival (OS) in the machine learning analysis were confirmed according to the clinical outcomes observed in the PMS. Among the 660 patients analyzed, median patient age was 70.0 years, and median OS and time-to-treatment failure (TTF) were 319 and 116 days, respectively. In GM-based simulations, factors associated with OS were liver metastases, performance status (PS), TTF, and neutropenia (threshold 0.05), and liver metastases, PS, and TTF (threshold 0.01). Factors associated with TTF were OS and relative dose intensity (threshold 0.05), and OS (threshold 0.01). In network clustering in 'R' package, factors associated with OS were number of treatment cycles, discontinuation due to disease progression, and TTF (threshold 0.05), and liver and lung metastases, PS, discontinuation due to adverse events, and febrile neutropenia (threshold 0.01). Kaplan-Meier analysis of patient subgroups demonstrated that visceral metastases and poor PS at baseline were associated with worse OS, while neutropenia or febrile neutropenia and higher number of cabazitaxel cycles were associated with better OS. Neutropenia may be a predictive factor for treatment efficacy in terms of survival. Poor PS and distant metastases to the liver and lungs were shown to be associated with worse outcomes, while factors related to treatment duration were shown to positively correlate with better OS.
Sections du résumé
BACKGROUND
BACKGROUND
We aimed to evaluate relationships between clinical outcomes and explanatory variables by network clustering analysis using data from a post marketing surveillance (PMS) study of castration-resistant prostate cancer (CRPC) patients.
METHODS
METHODS
The PMS was a prospective, multicenter, observational study of patients with metastatic, docetaxel-refractory CRPC treated with cabazitaxel in Japan after its launch in 2014. Graphical Markov (GM) model-based simulations and network clustering in 'R' package were conducted to identify correlations between clinical factors and outcomes. Factors shown to be associated with overall survival (OS) in the machine learning analysis were confirmed according to the clinical outcomes observed in the PMS.
RESULTS
RESULTS
Among the 660 patients analyzed, median patient age was 70.0 years, and median OS and time-to-treatment failure (TTF) were 319 and 116 days, respectively. In GM-based simulations, factors associated with OS were liver metastases, performance status (PS), TTF, and neutropenia (threshold 0.05), and liver metastases, PS, and TTF (threshold 0.01). Factors associated with TTF were OS and relative dose intensity (threshold 0.05), and OS (threshold 0.01). In network clustering in 'R' package, factors associated with OS were number of treatment cycles, discontinuation due to disease progression, and TTF (threshold 0.05), and liver and lung metastases, PS, discontinuation due to adverse events, and febrile neutropenia (threshold 0.01). Kaplan-Meier analysis of patient subgroups demonstrated that visceral metastases and poor PS at baseline were associated with worse OS, while neutropenia or febrile neutropenia and higher number of cabazitaxel cycles were associated with better OS.
CONCLUSIONS
CONCLUSIONS
Neutropenia may be a predictive factor for treatment efficacy in terms of survival. Poor PS and distant metastases to the liver and lungs were shown to be associated with worse outcomes, while factors related to treatment duration were shown to positively correlate with better OS.
Identifiants
pubmed: 35484517
doi: 10.1186/s12885-022-09509-0
pii: 10.1186/s12885-022-09509-0
pmc: PMC9052565
doi:
Substances chimiques
Taxoids
0
cabazitaxel
51F690397J
Types de publication
Journal Article
Multicenter Study
Observational Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
470Informations de copyright
© 2022. The Author(s).
Références
Br J Cancer. 2009 Apr 21;100(8):1219-29
pubmed: 19367280
Int J Clin Pract. 2011 Nov;65(11):1180-92
pubmed: 21995694
Crit Rev Oncol Hematol. 2017 Dec;120:163-179
pubmed: 29198330
BMJ. 2009 Feb 23;338:b375
pubmed: 19237405
Drugs. 2018 May;78(7):737-745
pubmed: 29754293
Jpn J Clin Oncol. 2019 Dec 27;49(12):1157-1163
pubmed: 31361807
Ann Oncol. 2013 Sep;24(9):2402-8
pubmed: 23723295
Lancet. 2010 Oct 2;376(9747):1147-54
pubmed: 20888992
Can Urol Assoc J. 2010 Dec;4(6):380-4
pubmed: 21191494
Br J Cancer. 2019 Dec;121(12):1001-1008
pubmed: 31719685
Can Urol Assoc J. 2018 Aug;12(8):E365-E372
pubmed: 29629866
N Engl J Med. 2012 Sep 27;367(13):1187-97
pubmed: 22894553
Int J Urol. 2017 Sep;24(9):648-666
pubmed: 28667698
Anticancer Res. 2019 Oct;39(10):5803-5809
pubmed: 31570485
Asia Pac J Clin Oncol. 2021 Jun;17(3):238-244
pubmed: 32970933
J Clin Oncol. 2014 Mar 1;32(7):671-7
pubmed: 24449231
BMC Cancer. 2020 Jul 13;20(1):649
pubmed: 32660451
Int J Data Min Bioinform. 2013;8(3):366-80
pubmed: 24417028
Eur J Cancer. 2016 Mar;56:93-100
pubmed: 26829012
Cancers (Basel). 2019 Mar 07;11(3):
pubmed: 30866535
J Geriatr Oncol. 2020 Sep;11(7):1067-1073
pubmed: 32198082
J Clin Epidemiol. 2019 Jun;110:12-22
pubmed: 30763612
Cancer Sci. 2020 May;111(5):1452-1460
pubmed: 32133724
Br J Cancer. 2020 Sep;123(6):912-918
pubmed: 32641862
J Clin Oncol. 2017 Oct 1;35(28):3198-3206
pubmed: 28809610
Biomed Res Int. 2017;2017:7538647
pubmed: 28948170
Cancer Lett. 2020 Jul 1;481:55-62
pubmed: 32251707
Technol Cancer Res Treat. 2020 Jan-Dec;19:1533033820909829
pubmed: 32138606
N Engl J Med. 2011 May 26;364(21):1995-2005
pubmed: 21612468
J Clin Oncol. 2016 May 10;34(14):1652-9
pubmed: 26951312
Cancer Sci. 2018 May;109(5):1570-1575
pubmed: 29493842
Oncotarget. 2019 Jun 25;10(41):4161-4168
pubmed: 31289614
Sci Rep. 2017 Aug 7;7(1):7402
pubmed: 28784991
Oncotarget. 2017 Nov 16;8(63):106468-106474
pubmed: 29290963
Curr Cancer Drug Targets. 2015;15(3):243-55
pubmed: 25654638