Predicting neoadjuvant treatment response in triple-negative breast cancer using machine learning

Impact of Neoadjuvant Therapy on PD-L1 Expression in Triple-Negative Breast Cancer and Correlation with Clinicopathological Factors

BACKGROUND

This study aims to deliver more insights on the impact of neoadjuvant treatment on Pd-L1 expression and to evaluate its correlation with clinicopathological factors.

METHODS

We reviewed 88 TNBC cases for the period 2021-2023. Data on age, tumor size, stage, and treatment were collected. Histological slides were assessed for subtype, grade, and TILs. A total of 48 received neoadjuvant treatment. HER2 and Ki67 were evaluated via immunohistochemistry. PD-L1 expression was tested on primary and residual tumors. Statistical analysis was performed using IBM SPSS (p < 0.05).

RESULTS

In this study, PD-L1 positive expression was found in 44.3% of primary tumors, with 52.9% of initially positive cases losing expression post-treatment. TILs were significantly higher in PD-L1-positive tumors (mean 41.79% vs. 27.55%, p = 0.001). A notable correlation was found between PD-L1 expression and Ki-67 proliferation index, with PD-L1-positive tumors having a median Ki-67 of 64.49 compared to 52.86 in negative cases (p = 0.015). Neoadjuvant immunotherapy led to a lower mean residual cancer burden (0.95 vs. 2.55, p = 0.002) compared to chemotherapy alone. Higher Ki-67 levels (≥50%) were associated with better treatment outcomes, showing a mean RCB score of 1.60 versus 3.16 for lower levels (p = 0.022). HER2-negative cases had a higher prevalence of favorable pathological response (54.5%) compared to HER2-low tumors (25%, p = 0.048), because of the strong correlation to high proliferative index.

CONCLUSIONS

In conclusion, PD-L1 expression in TNBC shows significant discordance post-treatment, highlighting the need for routine testing and further research on predictive biomarkers.

The Revolution in Breast Cancer Diagnostics: From Visual Inspection of Histopathology Slides to Using Desktop Tissue Analysers for Automated Nanomechanical Profiling of Tumours

We aim to develop new portable desktop tissue analysers (DTAs) to provide fast, low-cost, and precise test results for fast nanomechanical profiling of tumours. This paper will explain the reasoning for choosing indentation-type atomic force microscopy (IT-AFM) to reveal the functional details of cancer. Determining the subtype, cancer stage, and prognosis will be possible, which aids in choosing the best treatment. DTAs are based on fast IT-AFM at the size of a small box that can be made for a low budget compared to other clinical imaging tools. The DTAs can work in remote areas and all parts of the world. There are a number of direct benefits: First, it is no longer needed to wait a week for the pathology report as the test will only take 10 min. Second, it avoids the complicated steps of making histopathology slides and saves costs of labour. Third, computers and robots are more consistent, more reliable, and more economical than human workers which may result in fewer diagnostic errors. Fourth, the IT-AFM analysis is capable of distinguishing between various cancer subtypes. Fifth, the IT-AFM analysis could reveal new insights about why immunotherapy fails. Sixth, IT-AFM may provide new insights into the neoadjuvant treatment response. Seventh, the healthcare system saves money by reducing diagnostic backlogs. Eighth, the results are stored on a central server and can be accessed to develop strategies to prevent cancer. To bring the IT-AFM technology from the bench to the operation theatre, a fast IT-AFM sensor needs to be developed and integrated into the DTAs.