A novel machine learning-derived decision tree including uPA/PAI-1 for breast cancer care

Abstract

Background uPA and PAI-1 are breast cancer biomarkers that evaluate the benefit of chemotherapy (CT) for HER2-negative, estrogen receptor-positive, low or intermediate grade patients. Our objectives were to observe clinical routine use of uPA/PAI-1 and to build a new therapeutic decision tree integrating uPA/PAI-1. Methods We observed the concordance between CT indications proposed by a canonical decision tree representative of French practices (not including uPA/PAI-1) and actual CT prescriptions decided by a medical board which included uPA/PAI-1. We used a method of machine learning for the analysis of concordant and non-concordant CT prescriptions to generate a novel scheme for CT indications. Results We observed a concordance rate of 71% between indications proposed by the canonical decision tree and actual prescriptions. Discrepancies were due to CT contraindications, high tumor grade and uPA/PAI-1 level. Altogether, uPA/PAI-1 were a decisive factor for the final decision in 17% of cases by avoiding CT prescription in two-thirds of cases and inducing CT in other cases. Remarkably, we noted that in routine practice, elevated uPA/PAI-1 levels seem not to be considered as a sufficient indication for CT for N≤3, Ki 67≤30% tumors, but are considered in association with at least one additional marker such as Ki 67>14%, vascular invasion and ER-H score <150. Conclusions This study highlights that in the routine clinical practice uPA/PAI-1 are never used as the sole indication for CT. Combined with other routinely used biomarkers, uPA/PAI-1 present an added value to orientate the therapeutic choice.

Biomarkers in Breast Cancer: An Old Story with a New End

“…uPA/PAI-1 is used together with other biomarkers in routine clinical practice, guiding the therapeutic choice, but, so far, uPA/PAI-1 is not considered sufficient to replace established parameters in clinical practice [128]. Uhl et al [125] showed that heteromerization of uPA and PAI-1 attracts neutrophils to cancerous lesions, thereby supporting tumor growth and metastasis.…”

MLLBC: A Machine Learning Toolbox for Modeling the Loss Rate of the Lining Bearing Capacity

“…1) Decision tree algorithm is to construct a suitable decision tree by learning the source data [40]. The decision tree generation is mainly divided into the flowing two steps, which are usually achieved by learning the labeled samples: (a) Node splitting: in general, when the attribute represented by a node cannot be judged, the node is divided into two.…”

“…Different from kernel-based method, tree and forest method are a summary of expert experience, which are widely used in practical application [44]. For example, Reix et al [40] built a new canonical decision tree model to analysis concordant and non-concordant CT prescriptions and find the decisive factor for breast cancer care. To provide a low-cost sensing strategy for air quality monitoring, Zimmerman et al [60] used random forests to design a comprehensive machine learning calibration model, and this model performed well on real-time air monitoring.…”