TY  - JOUR
AU  - Marinković, Mladen
AU  - Popović, Marina
AU  - Stojanović-Rundić, Suzana
AU  - Nikolić, Miloš
AU  - Cavić, Milena
AU  - Gavrilović, Dusica
AU  - Teodorović, Dušan
AU  - Mitrović, Nenad
AU  - Mijatovic Teodorović, Ljiljana
PY  - 2022
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3767
AB  - After primary treatment of localized prostate carcinoma (PC), up to a third of patients have disease recurrence. Different predictive models have already been used either for initial stratification of PC patients or to predict disease recurrence. Recently, artificial intelligence has been introduced in the diagnosis and management of PC with a potential to revolutionize this field. The aim of this study was to analyze machine learning (ML) classifiers in order to predict disease progression in the moment of prostate-specific antigen (PSA) elevation during follow-up. The study cohort consisted of 109 PC patients treated with external beam radiotherapy alone or in combination with androgen deprivation therapy. We developed and evaluated the performance of two ML algorithms based on artificial neural networks (ANN) and naive Bayes (NB). Of all patients, 72.5% was randomly selected for a training set while the remaining patients were used for testing of the models. The presence/absence of disease progression was defined as the output variable. The input variables for models were conducted from the univariate analysis preformed among two groups of patients in the training set. They included two pretreatment variables (UICC stage and Gleason's score risk group) and five posttreatment variables (nadir PSA, time to nadir PSA, PSA doubling time, PSA velocity, and PSA in the moment of disease reevaluation). The area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, negative predictive value, and predictive accuracy was calculated to test the models' performance. The results showed that specificity was similar for both models, while NB achieved better sensitivity then ANN (100.0% versus 94.4%). The ANN showed an accuracy of 93.3%, and the matching for NB model was 96.7%. In this study, ML classifiers have shown potential for application in routine clinical practice during follow-up when disease progression was suspected.
PB  - Hindawi Ltd, London
T2  - Biomed Research International
T1  - Comparison of Different Machine Learning Models in Prediction of Postirradiation Recurrence in Prostate Carcinoma Patients
VL  - 2022
DO  - 10.1155/2022/7943609
ER  - 

@article{
author = "Marinković, Mladen and Popović, Marina and Stojanović-Rundić, Suzana and Nikolić, Miloš and Cavić, Milena and Gavrilović, Dusica and Teodorović, Dušan and Mitrović, Nenad and Mijatovic Teodorović, Ljiljana",
year = "2022",
abstract = "After primary treatment of localized prostate carcinoma (PC), up to a third of patients have disease recurrence. Different predictive models have already been used either for initial stratification of PC patients or to predict disease recurrence. Recently, artificial intelligence has been introduced in the diagnosis and management of PC with a potential to revolutionize this field. The aim of this study was to analyze machine learning (ML) classifiers in order to predict disease progression in the moment of prostate-specific antigen (PSA) elevation during follow-up. The study cohort consisted of 109 PC patients treated with external beam radiotherapy alone or in combination with androgen deprivation therapy. We developed and evaluated the performance of two ML algorithms based on artificial neural networks (ANN) and naive Bayes (NB). Of all patients, 72.5% was randomly selected for a training set while the remaining patients were used for testing of the models. The presence/absence of disease progression was defined as the output variable. The input variables for models were conducted from the univariate analysis preformed among two groups of patients in the training set. They included two pretreatment variables (UICC stage and Gleason's score risk group) and five posttreatment variables (nadir PSA, time to nadir PSA, PSA doubling time, PSA velocity, and PSA in the moment of disease reevaluation). The area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, negative predictive value, and predictive accuracy was calculated to test the models' performance. The results showed that specificity was similar for both models, while NB achieved better sensitivity then ANN (100.0% versus 94.4%). The ANN showed an accuracy of 93.3%, and the matching for NB model was 96.7%. In this study, ML classifiers have shown potential for application in routine clinical practice during follow-up when disease progression was suspected.",
publisher = "Hindawi Ltd, London",
journal = "Biomed Research International",
title = "Comparison of Different Machine Learning Models in Prediction of Postirradiation Recurrence in Prostate Carcinoma Patients",
volume = "2022",
doi = "10.1155/2022/7943609"
}

Marinković, M., Popović, M., Stojanović-Rundić, S., Nikolić, M., Cavić, M., Gavrilović, D., Teodorović, D., Mitrović, N.,& Mijatovic Teodorović, L.. (2022). Comparison of Different Machine Learning Models in Prediction of Postirradiation Recurrence in Prostate Carcinoma Patients. in Biomed Research International
Hindawi Ltd, London., 2022.
https://doi.org/10.1155/2022/7943609

Marinković M, Popović M, Stojanović-Rundić S, Nikolić M, Cavić M, Gavrilović D, Teodorović D, Mitrović N, Mijatovic Teodorović L. Comparison of Different Machine Learning Models in Prediction of Postirradiation Recurrence in Prostate Carcinoma Patients. in Biomed Research International. 2022;2022.
doi:10.1155/2022/7943609 .

Marinković, Mladen, Popović, Marina, Stojanović-Rundić, Suzana, Nikolić, Miloš, Cavić, Milena, Gavrilović, Dusica, Teodorović, Dušan, Mitrović, Nenad, Mijatovic Teodorović, Ljiljana, "Comparison of Different Machine Learning Models in Prediction of Postirradiation Recurrence in Prostate Carcinoma Patients" in Biomed Research International, 2022 (2022),
https://doi.org/10.1155/2022/7943609 . .