Latent class analysis of conventional ultrasound features: a novel approach to predicting non-response to neoadjuvant chemotherapy in breast cancer - Summary - MDSpire
Advertisement
Latent class analysis of conventional ultrasound features: a novel approach to predicting non-response to neoadjuvant chemotherapy in breast cancer
To determine if holistic patterns derived from conventional ultrasound features are associated with pathological response to neoadjuvant chemotherapy (NAC) in breast cancer, providing a potential basis for non-invasive treatment monitoring.
Key Findings:
LCA was the superior classification framework for identifying ultrasound patterns.
Two distinct sonographic patterns were identified: Pattern A and Pattern B.
Pattern B was associated with a 2.51-fold higher likelihood of pathological non-response compared to Pattern A (95% CI: 1.05-5.99).
In high-risk groups, Pattern B linked to a non-response risk of 12.84% to 21.34%; in non-high-risk groups, 1.12% to 3.45%.
Interpretation:
Ultrasound-derived patterns may help identify breast cancer patients less likely to benefit from NAC, aiding in individualized treatment planning.
Limitations:
Study was retrospective and conducted at a single institution, which may limit generalizability.
Findings require external validation before clinical application.
Conclusion:
LCA-derived ultrasound patterns could serve as preliminary indicators for non-response to NAC in breast cancer, warranting further validation.
