The Use of Machine Learning to Reduce Overtreatment of the Axilla in Breast Cancer: Retrospective Cohort Study.
artificial intelligence
artificial neural network
axillary clearance
axillary node
breast
breast cancer
cancer
machine learning
metastases
metastasis
metastatic
oncology
preoperative
preoperative screening
Journal
JMIR perioperative medicine
ISSN: 2561-9128
Titre abrégé: JMIR Perioper Med
Pays: Canada
ID NLM: 101771348
Informations de publication
Date de publication:
15 Nov 2022
15 Nov 2022
Historique:
received:
31
10
2021
accepted:
06
10
2022
revised:
18
09
2022
entrez:
15
11
2022
pubmed:
16
11
2022
medline:
16
11
2022
Statut:
epublish
Résumé
Patients with early breast cancer undergoing primary surgery, who have low axillary nodal burden, can safely forego axillary node clearance (ANC). However, routine use of axillary ultrasound (AUS) leads to 43% of patients in this group having ANC unnecessarily, following a positive AUS. The intersection of machine learning with medicine can provide innovative ways to understand specific risks within large patient data sets, but this has not yet been trialed in the arena of axillary node management in breast cancer. The objective of this study was to assess if machine learning techniques could be used to improve preoperative identification of patients with low and high axillary metastatic burden. A single-center retrospective analysis was performed on patients with breast cancer who had a preoperative AUS, and the specificity and sensitivity of AUS were calculated. Standard statistical methods and machine learning methods, including artificial neural network, naive Bayes, support vector machine, and random forest, were applied to the data to see if they could improve the accuracy of preoperative AUS to better discern high and low axillary burden. The study included 459 patients; 142 (31%) had a positive AUS; among this group, 88 (62%) had 2 or fewer macrometastatic nodes at ANC. Logistic regression outperformed AUS (specificity 0.950 vs 0.809). Of all the methods, the artificial neural network had the highest accuracy (0.919). Interestingly, AUS had the highest sensitivity of all methods (0.777), underlining its utility in this setting. We demonstrated that machine learning improves identification of the important subgroup of patients with no palpable axillary disease, positive ultrasound, and more than 2 metastatically involved nodes. A negative ultrasound in patients with no palpable lymphadenopathy is highly indicative of low axillary burden, and it is unclear whether sentinel node biopsy adds value in this situation. Further studies with larger patient numbers focusing on specific breast cancer subgroups are required to refine these techniques in this setting.
Sections du résumé
BACKGROUND
BACKGROUND
Patients with early breast cancer undergoing primary surgery, who have low axillary nodal burden, can safely forego axillary node clearance (ANC). However, routine use of axillary ultrasound (AUS) leads to 43% of patients in this group having ANC unnecessarily, following a positive AUS. The intersection of machine learning with medicine can provide innovative ways to understand specific risks within large patient data sets, but this has not yet been trialed in the arena of axillary node management in breast cancer.
OBJECTIVE
OBJECTIVE
The objective of this study was to assess if machine learning techniques could be used to improve preoperative identification of patients with low and high axillary metastatic burden.
METHODS
METHODS
A single-center retrospective analysis was performed on patients with breast cancer who had a preoperative AUS, and the specificity and sensitivity of AUS were calculated. Standard statistical methods and machine learning methods, including artificial neural network, naive Bayes, support vector machine, and random forest, were applied to the data to see if they could improve the accuracy of preoperative AUS to better discern high and low axillary burden.
RESULTS
RESULTS
The study included 459 patients; 142 (31%) had a positive AUS; among this group, 88 (62%) had 2 or fewer macrometastatic nodes at ANC. Logistic regression outperformed AUS (specificity 0.950 vs 0.809). Of all the methods, the artificial neural network had the highest accuracy (0.919). Interestingly, AUS had the highest sensitivity of all methods (0.777), underlining its utility in this setting.
CONCLUSIONS
CONCLUSIONS
We demonstrated that machine learning improves identification of the important subgroup of patients with no palpable axillary disease, positive ultrasound, and more than 2 metastatically involved nodes. A negative ultrasound in patients with no palpable lymphadenopathy is highly indicative of low axillary burden, and it is unclear whether sentinel node biopsy adds value in this situation. Further studies with larger patient numbers focusing on specific breast cancer subgroups are required to refine these techniques in this setting.
Identifiants
pubmed: 36378516
pii: v5i1e34600
doi: 10.2196/34600
pmc: PMC9709674
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e34600Informations de copyright
©Felix Jozsa, Rose Baker, Peter Kelly, Muneer Ahmed, Michael Douek. Originally published in JMIR Perioperative Medicine (http://periop.jmir.org), 15.11.2022.
Références
J Clin Oncol. 2016 Apr 1;34(10):1072-8
pubmed: 26811528
JAMA. 2011 Feb 9;305(6):569-75
pubmed: 21304082
Breast Cancer Res Treat. 2017 Nov;166(2):329-336
pubmed: 28755147
Fam Med Community Health. 2021 Dec;9(Suppl 1):
pubmed: 34952854
N Engl J Med. 2002 Oct 17;347(16):1233-41
pubmed: 12393820
J Ultrasound Med. 2004 Jan;23(1):63-71
pubmed: 14756355
Eur J Surg Oncol. 2006 Dec;32(10):1175-9
pubmed: 16979316
Clin Pharmacol Ther. 2021 Jan;109(1):87-100
pubmed: 32449163
J Natl Cancer Inst Monogr. 2015 May;2015(51):90-6
pubmed: 26063896
Lancet Oncol. 2013 Apr;14(4):297-305
pubmed: 23491275
Breast. 2012 Oct;21(5):678-81
pubmed: 22835916
J Clin Epidemiol. 2019 Jun;110:12-22
pubmed: 30763612
Breast Cancer Res Treat. 2019 Aug;177(1):1-4
pubmed: 31152326
N Engl J Med. 2003 Aug 7;349(6):546-53
pubmed: 12904519