Data Mining in Healthcare: Applying Strategic Intelligence Techniques to Depict 25 Years of Research Development

In order to identify the strategic topics and the thematic evolution structure of data mining applied to healthcare, in this paper, a bibliometric performance and network analysis (BPNA) was conducted. For this purpose, 6138 articles were sourced from the Web of Science covering the period from 1995 to July 2020 and the SciMAT software was used. Our results present a strategic diagram composed of 19 themes, of which the 8 motor themes ('NEURAL-NETWORKS', 'CANCER', 'ELETRONIC-HEALTH-RECORDS', 'DIABETES-MELLITUS', 'ALZHEIMER'S-DISEASE', 'BREAST-CANCER', 'DEPRESSION', and 'RANDOM-FOREST') are depicted in a thematic network. An in-depth analysis was carried out in order to find hidden patterns and to provide a general perspective of the field. The thematic network structure is arranged thusly that its subjects are organized into two different areas, (i) practices and techniques related to data mining in healthcare, and (ii) health concepts and disease supported by data mining, embodying, respectively, the hotspots related to the data mining and medical scopes, hence demonstrating the field's evolution over time. Such results make it possible to form the basis for future research and facilitate decision-making by researchers and practitioners, institutions, and governments interested in data mining in healthcare.

Prognostic significance of hedgehog signaling network-related gene expression in breast cancer patients

Breast cancer continues to be a serious public health problem. The role of the hedgehog pathway in normal development of the mammary gland as well as in carcinogenesis and progression of breast cancer is the subject of intense investigation, revealing functional interactions with cell surface heparan sulfate. Nevertheless, its influence on breast cancer prognosis, and its relation to specific sulfation motifs in heparan sulfate have only been poorly studied in large patient cohorts. Using the public database KMplotter that includes gene expression and survival data of 3951 patients, we found that the higher expression of SHH, HHAT, PTCH1, GLI1, GLI2, and GLI3 positively influences breast cancer prognosis. Stratifying patients according to the expression of hormone receptors, histological grade, lymph node metastasis, and systemic therapy, we observed that GLI1, GLI2, and GLI3 expression, as well as co-expression of SHH and ELP1 were associated with worse relapse-free survival in patients with HER2-positive tumors. Moreover, GLI1 expression in progesterone receptor-negative tumors and GLI3 expression in grade 3 tumors correlated with poor prognosis. SHH, in a panel of cell lines representing different breast cancer subtypes, and HHAT, PTCH1, GLI1, GLI2, and GLI3 were mostly expressed in cell lines classified as HER2-positive and basal-like. Expression of SHH, HHAT, GLI2, and GLI3 was differentially affected by overexpression of the heparan sulfate sulfotransferases HS2ST1 and HS3ST2 in vitro. Although high HS2ST1 expression was associated with poor prognosis in KMplotter analysis, high levels of HS3ST2 were associated with a good prognosis, except for ER-positive breast cancer. We suggest the GLI transcription factors as possible markers for the diagnosis, treatment, and prognosis of breast cancer especially in HER2-positive tumors, but also in progesterone receptor-negative and grade-3 tumors. The pathway interaction and prognostic impact of specific heparan sulfate sulfotransferases provide novel perspectives regarding a therapeutical targeting of the hedgehog pathway in breast cancer.