Phenomapping of Patients with Primary Breast Cancer Using Machine Learning-Based Unsupervised Cluster Analysis.

Sara Ferro,Ileana Baldi,Aline S C Fabricio,Dario Gregori,Daniele Bottigliengo,Massimo Gion

doi:10.3390/jpm11040272

Sara Ferro, Ileana Baldi + Show 4 more

Open Access

https://doi.org/10.3390/jpm11040272

Copy DOI

Abstract

Primary breast cancer (PBC) is a heterogeneous disease at the clinical, histopathological, and molecular levels. The improved classification of PBC might be important to identify subgroups of the disease, relevant to patient management. Machine learning algorithms may allow a better understanding of the relationships within heterogeneous clinical syndromes. This work aims to show the potential of unsupervised learning techniques for improving classification in PBC. A dataset of 712 women with PBC is used as a motivating example. A set of variables containing biological prognostic parameters is considered to define groups of individuals. Four different clustering methods are used: K-means, self-organising maps, hierarchical agglomerative (HAC), and Gaussian mixture models clustering. HAC outperforms the other clustering methods. With an optimal partitioning parameter, the methods identify two clusters with different clinical profiles. Patients in the first cluster are younger and have lower values of the oestrogen receptor (ER) and progesterone receptor (PgR) than patients in the second cluster. Moreover, cathepsin D values are lower in the first cluster. The three most important variables identified by the HAC are: age, ER, and PgR. Unsupervised learning seems a suitable alternative for the analysis of PBC data, opening up new perspectives in the particularly active domain of dissecting clinical heterogeneity.

Highlights

Personalised medicine research aims to improve individual patients’ clinical outcomes through more precise treatment targeting, through the leveraging of genetic, biomarker, phenotypic, or psychosocial characteristics that distinguish a given patient from another with a similar clinical presentation [1].The majority of studies involving patient similarity, mature enough to produce knowledge that directly informs treatment-targeting decisions, belong to the cancer domain [2].Advances in breast cancer care are among the most paradigmatic examples of the benefits of personalised medicine research.Breast cancer is a disease that has been thoroughly profiled on various levels, revealing high heterogeneity [3,4]
D and steroid receptors in a cohort of women with Primary breast cancer (PBC) serves as the motivating example
The following information on biological and pathological prognostic parameters was extracted from the database for each patient: age, menopausal status, oestrogen receptor (ER), progesterone receptor (PgR), pS2 protein, cathepsin D, histological type, number of positive lymph nodes, and tumour size diameters

Summary

Introduction

Personalised medicine research aims to improve individual patients’ clinical outcomes through more precise treatment targeting, through the leveraging of genetic, biomarker, phenotypic, or psychosocial characteristics that distinguish a given patient from another with a similar clinical presentation [1].The majority of studies involving patient similarity, mature enough to produce knowledge that directly informs treatment-targeting decisions, belong to the cancer domain [2].Advances in breast cancer care are among the most paradigmatic examples of the benefits of personalised medicine research.Breast cancer is a disease that has been thoroughly profiled on various levels, revealing high heterogeneity [3,4]. Personalised medicine research aims to improve individual patients’ clinical outcomes through more precise treatment targeting, through the leveraging of genetic, biomarker, phenotypic, or psychosocial characteristics that distinguish a given patient from another with a similar clinical presentation [1]. The majority of studies involving patient similarity, mature enough to produce knowledge that directly informs treatment-targeting decisions, belong to the cancer domain [2]. Breast cancer is a disease that has been thoroughly profiled on various levels, revealing high heterogeneity [3,4]. The separation of breast tumours into different groups has been used to identify disease subgroups [5,6,7], which assist in patient management.

Objectives

Methods

Conclusion