Could Machine Learning Improve the Prediction of Pelvic Nodal Status of Prostate Cancer Patients?: Preliminary Results of a Pilot Study

B. De Bari, M. Vallati, R. Gatta, C. Simeone, G. Girelli, U. Ricardi, I. Meattini, P. Gabriele, R. Bellavita, M. Krengli, I. Cafaro, E. Cagna, F. Bunkheila, S. Borghesi, M. Signor, A. Di Marco, F. Bertoni, M. Stefanacci, N. Pasinetti, M. Buglione & 1 others S. M. Magrini

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

We tested and compared performances of Roach formula, Partin tables and of three Machine Learning (ML) based algorithms based on decision trees in identifying N+ prostate cancer (PC). 1,555 cN0 and 50 cN+ PC were analyzed. Results were also verified on an independent population of 204 operated cN0 patients, with a known pN status (187 pN0, 17 pN1 patients). 

ML performed better, also when tested on the surgical population, with accuracy, specificity, and sensitivity ranging between 48-86%, 35-91%, and 17-79%, respectively. ML potentially allows better prediction of the nodal status of PC, potentially allowing a better tailoring of pelvic irradiation.

LanguageEnglish
Pages232-240
Number of pages9
JournalCancer Investigation
Volume33
Issue number6
DOIs
Publication statusPublished - 2015

Fingerprint

Prostatic Neoplasms
Nomograms
Decision Trees
Population
Sensitivity and Specificity
Machine Learning

Cite this

De Bari, B. ; Vallati, M. ; Gatta, R. ; Simeone, C. ; Girelli, G. ; Ricardi, U. ; Meattini, I. ; Gabriele, P. ; Bellavita, R. ; Krengli, M. ; Cafaro, I. ; Cagna, E. ; Bunkheila, F. ; Borghesi, S. ; Signor, M. ; Di Marco, A. ; Bertoni, F. ; Stefanacci, M. ; Pasinetti, N. ; Buglione, M. ; Magrini, S. M. / Could Machine Learning Improve the Prediction of Pelvic Nodal Status of Prostate Cancer Patients? Preliminary Results of a Pilot Study. In: Cancer Investigation. 2015 ; Vol. 33, No. 6. pp. 232-240.
@article{513cbdd861b14e5f806ed73dad2dd59b,
title = "Could Machine Learning Improve the Prediction of Pelvic Nodal Status of Prostate Cancer Patients?: Preliminary Results of a Pilot Study",
abstract = "We tested and compared performances of Roach formula, Partin tables and of three Machine Learning (ML) based algorithms based on decision trees in identifying N+ prostate cancer (PC). 1,555 cN0 and 50 cN+ PC were analyzed. Results were also verified on an independent population of 204 operated cN0 patients, with a known pN status (187 pN0, 17 pN1 patients). ML performed better, also when tested on the surgical population, with accuracy, specificity, and sensitivity ranging between 48-86{\%}, 35-91{\%}, and 17-79{\%}, respectively. ML potentially allows better prediction of the nodal status of PC, potentially allowing a better tailoring of pelvic irradiation.",
keywords = "Machine Learning, Nodal metastases, Pelvic irradiation, Prostate cancer, Radiotherapy",
author = "{De Bari}, B. and M. Vallati and R. Gatta and C. Simeone and G. Girelli and U. Ricardi and I. Meattini and P. Gabriele and R. Bellavita and M. Krengli and I. Cafaro and E. Cagna and F. Bunkheila and S. Borghesi and M. Signor and {Di Marco}, A. and F. Bertoni and M. Stefanacci and N. Pasinetti and M. Buglione and Magrini, {S. M.}",
year = "2015",
doi = "10.3109/07357907.2015.1024317",
language = "English",
volume = "33",
pages = "232--240",
journal = "Cancer Investigation",
issn = "0735-7907",
publisher = "Informa Healthcare",
number = "6",

}

De Bari, B, Vallati, M, Gatta, R, Simeone, C, Girelli, G, Ricardi, U, Meattini, I, Gabriele, P, Bellavita, R, Krengli, M, Cafaro, I, Cagna, E, Bunkheila, F, Borghesi, S, Signor, M, Di Marco, A, Bertoni, F, Stefanacci, M, Pasinetti, N, Buglione, M & Magrini, SM 2015, 'Could Machine Learning Improve the Prediction of Pelvic Nodal Status of Prostate Cancer Patients? Preliminary Results of a Pilot Study', Cancer Investigation, vol. 33, no. 6, pp. 232-240. https://doi.org/10.3109/07357907.2015.1024317

Could Machine Learning Improve the Prediction of Pelvic Nodal Status of Prostate Cancer Patients? Preliminary Results of a Pilot Study. / De Bari, B.; Vallati, M.; Gatta, R.; Simeone, C.; Girelli, G.; Ricardi, U.; Meattini, I.; Gabriele, P.; Bellavita, R.; Krengli, M.; Cafaro, I.; Cagna, E.; Bunkheila, F.; Borghesi, S.; Signor, M.; Di Marco, A.; Bertoni, F.; Stefanacci, M.; Pasinetti, N.; Buglione, M.; Magrini, S. M.

In: Cancer Investigation, Vol. 33, No. 6, 2015, p. 232-240.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Could Machine Learning Improve the Prediction of Pelvic Nodal Status of Prostate Cancer Patients?

T2 - Cancer Investigation

AU - De Bari, B.

AU - Vallati, M.

AU - Gatta, R.

AU - Simeone, C.

AU - Girelli, G.

AU - Ricardi, U.

AU - Meattini, I.

AU - Gabriele, P.

AU - Bellavita, R.

AU - Krengli, M.

AU - Cafaro, I.

AU - Cagna, E.

AU - Bunkheila, F.

AU - Borghesi, S.

AU - Signor, M.

AU - Di Marco, A.

AU - Bertoni, F.

AU - Stefanacci, M.

AU - Pasinetti, N.

AU - Buglione, M.

AU - Magrini, S. M.

PY - 2015

Y1 - 2015

N2 - We tested and compared performances of Roach formula, Partin tables and of three Machine Learning (ML) based algorithms based on decision trees in identifying N+ prostate cancer (PC). 1,555 cN0 and 50 cN+ PC were analyzed. Results were also verified on an independent population of 204 operated cN0 patients, with a known pN status (187 pN0, 17 pN1 patients). ML performed better, also when tested on the surgical population, with accuracy, specificity, and sensitivity ranging between 48-86%, 35-91%, and 17-79%, respectively. ML potentially allows better prediction of the nodal status of PC, potentially allowing a better tailoring of pelvic irradiation.

AB - We tested and compared performances of Roach formula, Partin tables and of three Machine Learning (ML) based algorithms based on decision trees in identifying N+ prostate cancer (PC). 1,555 cN0 and 50 cN+ PC were analyzed. Results were also verified on an independent population of 204 operated cN0 patients, with a known pN status (187 pN0, 17 pN1 patients). ML performed better, also when tested on the surgical population, with accuracy, specificity, and sensitivity ranging between 48-86%, 35-91%, and 17-79%, respectively. ML potentially allows better prediction of the nodal status of PC, potentially allowing a better tailoring of pelvic irradiation.

KW - Machine Learning

KW - Nodal metastases

KW - Pelvic irradiation

KW - Prostate cancer

KW - Radiotherapy

UR - http://www.scopus.com/inward/record.url?scp=84934287734&partnerID=8YFLogxK

UR - http://www.tandfonline.com/toc/icnv20/current

U2 - 10.3109/07357907.2015.1024317

DO - 10.3109/07357907.2015.1024317

M3 - Article

VL - 33

SP - 232

EP - 240

JO - Cancer Investigation

JF - Cancer Investigation

SN - 0735-7907

IS - 6

ER -