Prognostic power assessment of clinical parameters to predict neoadjuvant response therapy in HER2-positive breast cancer patients: A machine learning approach.
bioinformatics
breast cancer
neoadjuvant therapy
prognostic factor
Journal
Cancer medicine
ISSN: 2045-7634
Titre abrégé: Cancer Med
Pays: United States
ID NLM: 101595310
Informations de publication
Date de publication:
Nov 2023
Nov 2023
Historique:
revised:
27
07
2023
received:
17
10
2022
accepted:
29
08
2023
pubmed:
31
10
2023
medline:
31
10
2023
entrez:
31
10
2023
Statut:
ppublish
Résumé
About 15%-20% of breast cancer (BC) cases is classified as Human Epidermal growth factor Receptor type 2 (HER2) positive. The Neoadjuvant chemotherapy (NAC) was initially introduced for locally advanced and inflammatory BC patients to allow a less extensive surgical resection, whereas now it represents the current standard for early-stage and operable BC. However, only 20%-40% of patients achieve pathologic complete response (pCR). According to the results of practice-changing clinical trials, the addition of trastuzumab to NAC brings improvements to pCR, and recently, the use of pertuzumab plus trastuzumab has registered further statistically significant and clinically meaningful improvements in terms of pCR. The goal of our work is to propose a machine learning model to predict the pCR to NAC in HER2-positive patients based on a subset of clinical features. First, we evaluated the significant association of clinical features with pCR on the retrospectively collected data referred to 67 patients afferent to Istituto Tumori "Giovanni Paolo II." Then, we performed a feature selection procedure to identify a subset of features to be used for training a machine learning-based classification algorithm. As a result, pCR to NAC was associated with ER status, Pgr status, and HER2 score. The machine learning model trained on a subgroup of essential features reached an AUC of 73.27% (72.44%-73.66%) and an accuracy of 71.67% (71.64%-73.13%). According to our results, the clinical features alone are not enough to define a support system useful for clinical pathway. Our results seem worthy of further investigation in large validation studies and this work could be the basis of future study that will also involve radiomics analysis of biomedical images.
Sections du résumé
BACKGROUND
BACKGROUND
About 15%-20% of breast cancer (BC) cases is classified as Human Epidermal growth factor Receptor type 2 (HER2) positive. The Neoadjuvant chemotherapy (NAC) was initially introduced for locally advanced and inflammatory BC patients to allow a less extensive surgical resection, whereas now it represents the current standard for early-stage and operable BC. However, only 20%-40% of patients achieve pathologic complete response (pCR). According to the results of practice-changing clinical trials, the addition of trastuzumab to NAC brings improvements to pCR, and recently, the use of pertuzumab plus trastuzumab has registered further statistically significant and clinically meaningful improvements in terms of pCR. The goal of our work is to propose a machine learning model to predict the pCR to NAC in HER2-positive patients based on a subset of clinical features.
METHOD
METHODS
First, we evaluated the significant association of clinical features with pCR on the retrospectively collected data referred to 67 patients afferent to Istituto Tumori "Giovanni Paolo II." Then, we performed a feature selection procedure to identify a subset of features to be used for training a machine learning-based classification algorithm. As a result, pCR to NAC was associated with ER status, Pgr status, and HER2 score.
RESULTS
RESULTS
The machine learning model trained on a subgroup of essential features reached an AUC of 73.27% (72.44%-73.66%) and an accuracy of 71.67% (71.64%-73.13%). According to our results, the clinical features alone are not enough to define a support system useful for clinical pathway.
CONCLUSION
CONCLUSIONS
Our results seem worthy of further investigation in large validation studies and this work could be the basis of future study that will also involve radiomics analysis of biomedical images.
Identifiants
pubmed: 37905688
doi: 10.1002/cam4.6512
pmc: PMC10709715
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
20663-20669Subventions
Organisme : Ministero della Salute
ID : RC2023
Informations de copyright
© 2023 The Authors. Cancer Medicine published by John Wiley & Sons Ltd.
Références
JAMA Oncol. 2016 Jun 1;2(6):751-60
pubmed: 26914222
Lancet Oncol. 2018 Jan;19(1):115-126
pubmed: 29175149
Eur Radiol. 2016 May;26(5):1474-84
pubmed: 26310583
Breast. 2011 Dec;20(6):485-90
pubmed: 21784637
JCO Clin Cancer Inform. 2022 Feb;6:e2100055
pubmed: 35148170
Sci Rep. 2021 Jul 8;11(1):14123
pubmed: 34238968
Br J Cancer. 2018 Jul;119(1):4-11
pubmed: 29808015
Lancet Oncol. 2017 Apr;18(4):545-554
pubmed: 28238593
Rev Recent Clin Trials. 2017;12(2):81-92
pubmed: 28164759
JAMA Oncol. 2020 Mar 1;6(3):e193692
pubmed: 31647503
Lancet. 2010 Jan 30;375(9712):377-84
pubmed: 20113825
Breast Cancer Res Treat. 2019 Aug;177(1):61-66
pubmed: 31144151
Memo. 2018;11(3):199-203
pubmed: 30220926
J Pers Med. 2022 Jun 10;12(6):
pubmed: 35743737
Neurol Clin Neurophysiol. 2004 Nov 30;2004:37
pubmed: 16012598
Cancer. 1950 Jan;3(1):32-5
pubmed: 15405679
Cancer Treat Rev. 2020 Mar;84:101965
pubmed: 32000054
Clin Cancer Res. 2014 Nov 1;20(21):5359-64
pubmed: 25204553
Cancer Med. 2023 Nov;12(22):20663-20669
pubmed: 37905688
Ann Oncol. 2012 Sep;23 Suppl 10:x231-6
pubmed: 22987968
J Clin Oncol. 2012 Jun 1;30(16):1989-95
pubmed: 22493419
Lancet Oncol. 2016 Jun;17(6):791-800
pubmed: 27179402
Cancer Treat Rev. 2014 Mar;40(2):259-70
pubmed: 24080156
Restor Dent Endod. 2017 May;42(2):152-155
pubmed: 28503482
Ann Surg Oncol. 2021 Jan;28(1):287-294
pubmed: 32514804
Clin Cancer Res. 2019 Jun 15;25(12):3538-3547
pubmed: 30842125
Breast Cancer (Dove Med Press). 2021 Jun 14;13:393-407
pubmed: 34163239