Unsupervised versus Supervised Identification of Prognostic Factors in Patients with Localized Retroperitoneal Sarcoma: A Data Clustering and Mahalanobis Distance Approach

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The aim of this report is to unveil specific prognostic factors for retroperitoneal sarcoma (RPS) patients by univariate and multivariate statistical techniques. A phase I-II study on localized RPS treated with high-dose ifosfamide and radiotherapy followed by surgery (ISG-STS 0303 protocol) demonstrated that chemo/radiotherapy was safe and increased the 3-year relapse-free survival (RFS) with respect to historical controls. Of 70 patients, twenty-six developed local, 10 distant, and 5 combined relapse. Median disease-free interval (DFI) was 29.47 months. According to a discriminant function analysis, DFI, histology, relapse pattern, and the first treatment approach at relapse had a statistically significant prognostic impact. Based on scientific literature and clinical expertise, clinicopathological data were analyzed using both a supervised and an unsupervised classification method to predict the prognosis, with similar sample sizes (66 and 65, resp., in casewise approach and 70 in mean-substitution one). This is the first attempt to predict patients' prognosis by means of multivariate statistics, and in this light, it looks noticable that (i) some clinical data have a well-defined prognostic value, (ii) the unsupervised model produced comparable results with respect to the supervised one, and (iii) the appropriate combination of both models appears fruitful and easily extensible to different clinical contexts.

Original languageEnglish
Article number2786163
JournalBioMed Research International
Volume2018
DOIs
Publication statusPublished - Apr 23 2018

Fingerprint

Sarcoma
Cluster Analysis
Chemoradiotherapy
Recurrence
Ifosfamide
Histology
Radiotherapy
Surgery
Dosimetry
Substitution reactions
Statistics
Literature
Discriminant Analysis
Sample Size
Survival
Therapeutics

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)

Cite this

@article{17ecc74588df40c3a5a768a3ec167f5e,
title = "Unsupervised versus Supervised Identification of Prognostic Factors in Patients with Localized Retroperitoneal Sarcoma: A Data Clustering and Mahalanobis Distance Approach",
abstract = "The aim of this report is to unveil specific prognostic factors for retroperitoneal sarcoma (RPS) patients by univariate and multivariate statistical techniques. A phase I-II study on localized RPS treated with high-dose ifosfamide and radiotherapy followed by surgery (ISG-STS 0303 protocol) demonstrated that chemo/radiotherapy was safe and increased the 3-year relapse-free survival (RFS) with respect to historical controls. Of 70 patients, twenty-six developed local, 10 distant, and 5 combined relapse. Median disease-free interval (DFI) was 29.47 months. According to a discriminant function analysis, DFI, histology, relapse pattern, and the first treatment approach at relapse had a statistically significant prognostic impact. Based on scientific literature and clinical expertise, clinicopathological data were analyzed using both a supervised and an unsupervised classification method to predict the prognosis, with similar sample sizes (66 and 65, resp., in casewise approach and 70 in mean-substitution one). This is the first attempt to predict patients' prognosis by means of multivariate statistics, and in this light, it looks noticable that (i) some clinical data have a well-defined prognostic value, (ii) the unsupervised model produced comparable results with respect to the supervised one, and (iii) the appropriate combination of both models appears fruitful and easily extensible to different clinical contexts.",
author = "{De Sanctis}, Rita and Alessandro Vigan{\`o} and Alessandro Giuliani and Alessandro Gronchi and {De Paoli}, Antonino and Pierina Navarria and Vittorio Quagliuolo and Armando Santoro and Alfredo Colosimo",
year = "2018",
month = "4",
day = "23",
doi = "10.1155/2018/2786163",
language = "English",
volume = "2018",
journal = "BioMed Research International",
issn = "2314-6133",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Unsupervised versus Supervised Identification of Prognostic Factors in Patients with Localized Retroperitoneal Sarcoma

T2 - A Data Clustering and Mahalanobis Distance Approach

AU - De Sanctis, Rita

AU - Viganò, Alessandro

AU - Giuliani, Alessandro

AU - Gronchi, Alessandro

AU - De Paoli, Antonino

AU - Navarria, Pierina

AU - Quagliuolo, Vittorio

AU - Santoro, Armando

AU - Colosimo, Alfredo

PY - 2018/4/23

Y1 - 2018/4/23

N2 - The aim of this report is to unveil specific prognostic factors for retroperitoneal sarcoma (RPS) patients by univariate and multivariate statistical techniques. A phase I-II study on localized RPS treated with high-dose ifosfamide and radiotherapy followed by surgery (ISG-STS 0303 protocol) demonstrated that chemo/radiotherapy was safe and increased the 3-year relapse-free survival (RFS) with respect to historical controls. Of 70 patients, twenty-six developed local, 10 distant, and 5 combined relapse. Median disease-free interval (DFI) was 29.47 months. According to a discriminant function analysis, DFI, histology, relapse pattern, and the first treatment approach at relapse had a statistically significant prognostic impact. Based on scientific literature and clinical expertise, clinicopathological data were analyzed using both a supervised and an unsupervised classification method to predict the prognosis, with similar sample sizes (66 and 65, resp., in casewise approach and 70 in mean-substitution one). This is the first attempt to predict patients' prognosis by means of multivariate statistics, and in this light, it looks noticable that (i) some clinical data have a well-defined prognostic value, (ii) the unsupervised model produced comparable results with respect to the supervised one, and (iii) the appropriate combination of both models appears fruitful and easily extensible to different clinical contexts.

AB - The aim of this report is to unveil specific prognostic factors for retroperitoneal sarcoma (RPS) patients by univariate and multivariate statistical techniques. A phase I-II study on localized RPS treated with high-dose ifosfamide and radiotherapy followed by surgery (ISG-STS 0303 protocol) demonstrated that chemo/radiotherapy was safe and increased the 3-year relapse-free survival (RFS) with respect to historical controls. Of 70 patients, twenty-six developed local, 10 distant, and 5 combined relapse. Median disease-free interval (DFI) was 29.47 months. According to a discriminant function analysis, DFI, histology, relapse pattern, and the first treatment approach at relapse had a statistically significant prognostic impact. Based on scientific literature and clinical expertise, clinicopathological data were analyzed using both a supervised and an unsupervised classification method to predict the prognosis, with similar sample sizes (66 and 65, resp., in casewise approach and 70 in mean-substitution one). This is the first attempt to predict patients' prognosis by means of multivariate statistics, and in this light, it looks noticable that (i) some clinical data have a well-defined prognostic value, (ii) the unsupervised model produced comparable results with respect to the supervised one, and (iii) the appropriate combination of both models appears fruitful and easily extensible to different clinical contexts.

UR - http://www.scopus.com/inward/record.url?scp=85046719435&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046719435&partnerID=8YFLogxK

U2 - 10.1155/2018/2786163

DO - 10.1155/2018/2786163

M3 - Article

C2 - 29850497

AN - SCOPUS:85046719435

VL - 2018

JO - BioMed Research International

JF - BioMed Research International

SN - 2314-6133

M1 - 2786163

ER -