A meta-analysis of the diagnostic performance of machine learning-based MRI in the prediction of axillary lymph node
Chen Chen1, Yuhui Qin1, Haotian Chen1
1Department of Radiology, West China Hospital, Sichuan University, 37 Guoxue Road, Chengdu, 610041, Sichuan, People's Republic of China.
Background:
Despite that machine learning (ML)-based MRI has been evaluated for diagnosis of axillary lymph node metastasis (ALNM) in breast cancer patients, diagnostic values they showed have been variable. In this study, we aimed to assess the use of ML to classify ALNM on MRI and to identify potential covariates that might influence the diagnostic performance of ML.
Methods:
A systematic research of PubMed, Embase, Web of Science, and the Cochrane Library was conducted until 27 December 2020 to collect the included articles. Subgroup analysis was also performed.
Findings:
Fourteen studies assessing a total of 2247 breast cancer patients were included in the analysis. The overall AUC for ML in the validation set was 0.80 (95% confidence interval [CI] 0.76-0.83) with a negative predictive value of 0.83. The pooled sensitivity and specificity were 0.79 (95% CI 0.74-0.84) and 0.77 (95% CI 0.73-0.81), respectively. In the subgroup analysis of the validation set, T1-weighted contrast-enhanced (T1CE) imaging with ML yielded a higher sensitivity (0.80 vs. 0.67 vs. 0.76) than the T2-weighted fat-suppressed (T2-FS) imaging and diffusion-weighted imaging (DWI). Support vector machines (SVMs) had a higher specificity than linear regression (LR) and linear discriminant analysis (LDA) (0.79 vs. 0.78 vs. 0.75), whereas LDA showed a higher sensitivity than LR and SVM (0.83 vs. 0.70 vs. 0.77).
Interpretation:
MRI sequences and algorithms were the main factors that affect the diagnostic performance of ML. Although its results were encouraging with the pooled sensitivity of around 0.80, it meant that 1 in 5 women that would go with undetected metastases, which may have a detrimental effect on the overall survival for 20% of patients with positive SLN status. Despite that a high NPV of 0.83 meant that ML could potentially benefit those with negative SLN, it might also translate to 1 in 5 tests being false negative. We would like to suggest that ML may not be yet usable in clinical routine especially when patient survival is used as a primary measurement of its outcome.
