Comparison of Different Machine Learning Models in Prediction of Postirradiation Recurrence in Prostate Carcinoma Patients
2022
Аутори
Marinković, MladenPopović, Marina
Stojanović-Rundić, Suzana
Nikolić, Miloš
Cavić, Milena
Gavrilović, Dusica
Teodorović, Dušan
Mitrović, Nenad
Mijatovic Teodorović, Ljiljana
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
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.
Извор:
Biomed Research International, 2022, 2022Издавач:
- Hindawi Ltd, London
Финансирање / пројекти:
- TRACEPIGEN - Tracking Systemic Therapy Resistance of Lung and Colorectal Cancer Through Targeted Ngs Analysis of Genetic and Epigenetic Variants in Liquid Biopsies (RS-ScienceFundRS-Promis-6060876)
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200043 (Институт за онкологију и радиологију Србије, Београд) (RS-MESTD-inst-2020-200043)
- Идентификација молекуларних маркера за предикцију прогресије тумора, одговора на терапију и исхода болести (RS-MESTD-Integrated and Interdisciplinary Research (IIR or III)-41031)
DOI: 10.1155/2022/7943609
ISSN: 2314-6133
PubMed: 35178455
WoS: 000774914900011
Scopus: 2-s2.0-85124858705
Колекције
Институција/група
Mašinski fakultetTY - 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 . .