A retrospective validation of CanAssist Breast in European early-stage breast cancer patient cohort

Abstract

CanAssist Breast (CAB), a prognostic test uses immunohistochemistry (IHC) approach coupled with artificial intelligence-based machine learning algorithm for prognosis of early-stage hormone-receptor positive, HER2/neu negative breast cancer patients. It was developed and validated in an Indian cohort. Here we report the first blinded validation of CAB in a multi-country European patient cohort. FFPE tumor samples from 864 patients were obtained from-Spain, Italy, Austria, and Germany. IHC was performed on these samples, followed by recurrence risk score prediction. The outcomes were obtained from medical records. The performance of CAB was analyzed by hazard ratios (HR) and Kaplan Meier curves. CAB stratified European cohort (n = 864) into distinct low- and high-risk groups for recurrence (P < 0.0001) with HR of 3.32 (1.85-5.93) like that of mixed (India, USA, and Europe) (n = 1974), 3.43 (2.34-4.93) and Indian cohort (n = 925), 3.09 (1.83-5.21). CAB provided significant prognostic information (P < 0.0001) in women aged ≤ 50 (HR: 4.42 (1.58-12.3), P < 0.0001) and >50 years (HR: 2.93 (1.44-5.96), P = 0.0002). CAB had an HR of 2.57 (1.26-5.26), P = 0.01) in women with N1 disease. CAB stratified significantly higher proportions (77%) as low-risk over IHC4 (55%) (P < 0.0001). Additionally, 82% of IHC4 intermediate-risk patients were stratified as low-risk by CAB. Accurate risk stratification of European patients by CAB coupled with its similar performance inIndian patients shows that CAB is robust and functions independent of ethnic differences. CAB can potentially prevent overtreatment in a greater number of patients compared to IHC4 demonstrating its usefulness for adjuvant systemic therapy planning in European breast cancer patients.

Keywords: CanAssist Breast; European; Hormone-receptor positive; Prognostication; chemotherapy; early-stage breast cancer; recurrence.

Fig. 1

Kaplan–Meier survival curves for CanAssist Breast risk groups across various clinicopathological characteristics of European cohort. Distant metastais free survival rates of low and high risk groups of the total cohort (a), endocrine therapy treated alone patients of European cohort (b), patient group below and equal to 50 years (c), patient group above 50 years (d) post-menopausal women (e), node-negative sub-cohort (f), one-node positive sub-cohort (g), N1 sub-cohort (h). The box under each graph presents the number of patients at risk at each time point.

Fig. 2

Kaplan-Meier estimates of proportions of patients who had a relapse at a distant site, according to age and clinical parameters: For each group, total patients, CanAssist Breast low and high-risk groups are shown. The horizontal lines represent the 95% confidence interval.

Fig. 3

Kaplan–Meier survival curves showing low, intermediate, and high-risk groups by IHC4 in patients treated with chemoendocrine and endocrine therapy alone: IHC4 risk groups in 751 patients (a), CanAssist Breast risk groups in same 751 patients (b), CanAssist risk groups in IHC4 intermediate and high-risk patients (c), IHC4 risk groups in endocrine therapy only treated - 514 patients (d), CanAssist Breast risk groups in same 514 patients (e).

Fig. 4

Figure S1Kaplan–Meier survival curves for CanAssist Breast risk groups across various cohorts. Distant metastasis free survival rates of low and high-risk groups of the entire mixed cohort comprising patients from India, Europe and USA (a) endocrine therapy alone patients represented in earlier ‘a’ panel (b), Indian cohort (c).

Fig. S1