scholarly journals Predicting Prostate Cancer Upgrading of Biopsy Gleason Grade Group at Radical Prostatectomy Using Machine Learning-Assisted Decision-support Models

2020 ◽  
Author(s):  
Hailang Liu ◽  
Kun Tang ◽  
Ejun Peng ◽  
Liang Wang ◽  
Ding Xia ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
Logistic Regression ◽  
Radical Prostatectomy ◽  
Predictive Value ◽  
Support Vector ◽  
Gleason Grade ◽  
Good Discrimination ◽  
Grade Group ◽  
Testing Dataset

Abstract Objective: To develop a machine learning (ML)-assisted model capable of accurately predicting the probability of biopsy Gleason grade group upgrading before making treatment decisions by integrating multiple clinical characteristics.Materials and Methods: We retrospectively collected data from PCa (prostate cancer) patients who underwent systematic biopsy and radical prostatectomy from January 2015 to December 2019 at Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology. The study cohort was divided into training and testing datasets in a 70:30 ratio for further analysis. Four ML-assisted models were developed from 16 clinical features using logistic regression (LR), logistic regression optimized by Lasso regularization (Lasso-LR), random forest (RF) and support vector machine (SVM). The area under the curve (AUC) was applied to determine the model with the highest discrimination. Calibration plots were used to investigate the extent of over- or underestimation of predicted probabilities relative to the observed probabilities in models. Results: In total, 530 PCa patients were included, with 371 patients in the training dataset and 159 patients in the testing dataset. The Lasso-LR model showed good discrimination with an AUC, accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 0.776, 0.712, 0.679, 0.745, 0.730 and 0.695, respectively, followed by SVM (AUC 0.740, 95%CI: 0.690–0.790), LR (AUC 0.725, 95%CI: 0.674–0.776) and RF (AUC 0.666, 95%CI: 0.618–0.714). Validation of the model showed that the Lasso-LR model had the best discriminative power (AUC 0.735, 95%CI: 0.656–0.813), followed by SVM (AUC 0.723, 95%CI: 0.644–0.802), LR (AUC 0.697, 95%CI: 0.615–0.778) and RF (AUC 0.607, 95%CI: 0.531–0.684) in the testing dataset. Both the Lasso-LR and SVM models were well-calibrated. Conclusions: The Lasso-LR model had good discrimination in the prediction of patients at high risk of harboring incorrect Gleason grade group assignment, and the use of this model may be greatly beneficial to urologists in treatment planning, patient selection, and the decision-making process for PCa patients.

scholarly journals Predicting Prostate Cancer Upgrading of Biopsy Gleason Grade Group at Radical Prostatectomy Using Machine Learning-assisted Decision-support Models 

2020 ◽  
Author(s):  
Hailang Liu ◽  
Kun Tang ◽  
Ejun Peng ◽  
Liang Wang ◽  
Ding Xia ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
Logistic Regression ◽  
Radical Prostatectomy ◽  
Predictive Value ◽  
Support Vector ◽  
Gleason Grade ◽  
Good Discrimination ◽  
Grade Group ◽  
Testing Dataset

Abstract Background: This study aimed to develop a machine learning (ML)-assisted model capable of accurately predicting the probability of biopsy Gleason grade group upgrading before making treatment decisions.Methods: We retrospectively collected data from prostate cancer (PCa) patients who underwent systematic biopsy and radical prostatectomy from January 2015 to December 2019 at Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology. The study cohort was divided into training and testing datasets in a 70:30 ratio for further analysis. Four ML-assisted models were developed from 16 clinical features using logistic regression (LR), logistic regression optimized by least absolute shrinkage and selection operator (Lasso) regularization (Lasso-LR), random forest (RF) and support vector machine (SVM). The area under the curve (AUC) was applied to determine the model with the highest discrimination. Calibration plots were used to investigate the extent of over- or underestimation of predicted probabilities relative to the observed probabilities in models. Results: In total, 530 PCa patients were included, with 371 patients in the training dataset and 159 patients in the testing dataset. The Lasso-LR model showed good discrimination with an AUC, accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 0.776, 0.712, 0.679, 0.745, 0.730 and 0.695, respectively, followed by SVM (AUC 0.740, 95% confidence interval [CI]: 0.690–0.790), LR (AUC 0.725, 95% CI: 0.674–0.776) and RF (AUC 0.666, 95% CI: 0.618–0.714). Validation of the model showed that the Lasso-LR model had the best discriminative power (AUC 0.735, 95% CI: 0.656–0.813), followed by SVM (AUC 0.723, 95% CI: 0.644–0.802), LR (AUC 0.697, 95% CI: 0.615–0.778) and RF (AUC 0.607, 95% CI: 0.531–0.684) in the testing dataset. Both the Lasso-LR and SVM models were well-calibrated. Conclusion: The Lasso-LR model had good discrimination in the prediction of patients at high risk of harboring incorrect Gleason grade group assignment, and the use of this model may be greatly beneficial to urologists in treatment planning, patient selection, and the decision-making process for PCa patients.

scholarly journals Predicting the Grade of Prostate Cancer Based on a Biparametric MRI Radiomics Signature

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Li Zhang ◽  
Xia Zhe ◽  
Min Tang ◽  
Jing Zhang ◽  
Jialiang Ren ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
Logistic Regression ◽  
Learning Algorithm ◽  
Area Under The Curve ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Low Grade ◽  
High Grade ◽  
Random Forest Tree

Purpose. This study aimed to investigate the value of biparametric magnetic resonance imaging (bp-MRI)-based radiomics signatures for the preoperative prediction of prostate cancer (PCa) grade compared with visual assessments by radiologists based on the Prostate Imaging Reporting and Data System Version 2.1 (PI-RADS V2.1) scores of multiparametric MRI (mp-MRI). Methods. This retrospective study included 142 consecutive patients with histologically confirmed PCa who were undergoing mp-MRI before surgery. MRI images were scored and evaluated by two independent radiologists using PI-RADS V2.1. The radiomics workflow was divided into five steps: (a) image selection and segmentation, (b) feature extraction, (c) feature selection, (d) model establishment, and (e) model evaluation. Three machine learning algorithms (random forest tree (RF), logistic regression, and support vector machine (SVM)) were constructed to differentiate high-grade from low-grade PCa. Receiver operating characteristic (ROC) analysis was used to compare the machine learning-based analysis of bp-MRI radiomics models with PI-RADS V2.1. Results. In all, 8 stable radiomics features out of 804 extracted features based on T2-weighted imaging (T2WI) and ADC sequences were selected. Radiomics signatures successfully categorized high-grade and low-grade PCa cases ( P < 0.05 ) in both the training and test datasets. The radiomics model-based RF method (area under the curve, AUC: 0.982; 0.918), logistic regression (AUC: 0.886; 0.886), and SVM (AUC: 0.943; 0.913) in both the training and test cohorts had better diagnostic performance than PI-RADS V2.1 (AUC: 0.767; 0.813) when predicting PCa grade. Conclusions. The results of this clinical study indicate that machine learning-based analysis of bp-MRI radiomic models may be helpful for distinguishing high-grade and low-grade PCa that outperformed the PI-RADS V2.1 scores based on mp-MRI. The machine learning algorithm RF model was slightly better.

Machine learning to predict outcomes in patients with acute pulmonary embolism who prematurely discontinued anticoagulant therapy.

2021 ◽  
Author(s):  
Damian Mora ◽  
José Antonio Nieto ◽  
Jorge Mateo ◽  
Behnood Bikdeli ◽  
Stefano Barco ◽  
...  
Keyword(s):  
Machine Learning ◽  
Pulmonary Embolism ◽  
Logistic Regression ◽  
Anticoagulant Therapy ◽  
Roc Curve ◽  
Predictive Value ◽  
Support Vector ◽  
Calibration Plot ◽  
Composite Outcome ◽  
Increased Risk

Background: Patients with pulmonary embolism (PE) who prematurely discontinue anticoagulant therapy (<90 days) are at an increased risk for death or recurrences. Methods: We used the data from the RIETE registry to compare the prognostic ability of 5 machine-learning (ML) models and logistic regression to identify patients at increased risk for the composite of fatal PE or recurrent venous thromboembolism (VTE) 30 days after discontinuation. ML models included Decision tree, K-Nearest Neighbors algorithm, Support Vector Machine, Ensemble and Neural Network [NN]. A “full” model with 70 variables and a “reduced” model with 23 were analyzed. Model performance was assessed by confusion matrix metrics on the testing data for each model and a calibration plot. Results: Among 34,447 patients with PE, 1,348 (3.9%) discontinued therapy prematurely. Fifty-one (3.8%) developed fatal PE or sudden death and 24 (1.8%) had non-fatal VTE recurrences within 30 days after discontinuation. ML-NN was the best method for identification of patients experiencing the composite endpoint, predicting the composite outcome with an area under receiver operating characteristics (ROC) curve of 0.96 (95% confidence intervals [CI], 0.95-0.98), using either 70 or 23 variables captured before discontinuation. Similar numbers were obtained for sensitivity, specificity, positive predictive value, negative predictive value and accuracy. The discrimination of logistic regression was inferior (area under ROC curve, 0.76 [95% Cl 0.70-0.81]). Calibration plot showed similar deviations from the perfect line for ML-NN and logistic regression. Conclusions: ML-NN method very well predicted the composite outcome after premature discontinuation of anticoagulation and outperformed traditional logistic regression.

A nationwide trend away from radical prostatectomy for Gleason grade group 1 prostate cancer

2021 ◽  
Author(s):  
Joseph B John ◽  
John Pascoe ◽  
Sarah Fowler ◽  
Thomas Walton ◽  
Mark Johnson ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Radical Prostatectomy ◽  
Gleason Grade ◽  
Grade Group ◽  
Group 1

scholarly journals The role of mpMRI in qualification of patients with ISUP 1 prostate cancer on biopsy to radical prostatectomy

BMC Urology ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Łukasz Nyk ◽  
Omar Tayara ◽  
Tomasz Ząbkowski ◽  
Piotr Kryst ◽  
Aneta Andrychowicz ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Radical Prostatectomy ◽  
Digital Rectal Examination ◽  
Gleason Grade ◽  
Shared Decision ◽  
Grade Group ◽  
Final Pathology ◽  
Radical Treatment ◽  
Pathological Report

Abstract Background To investigate the role of mpMRI and high PIRADS score as independent triggers in the qualification of patients with ISUP 1 prostate cancer on biopsy to radical prostatectomy. Methods Between January 2017 and June 2019, 494 laparoscopic radical prostatectomies were performed in our institution, including 203 patients (41.1%) with ISUP 1 cT1c-2c PCa on biopsy. Data regarding biopsy results, digital rectal examination, PSA, mpMRI and postoperative pathological report have been retrospectively analysed. Results In 183 cases (90.1%) mpMRI has been performed at least 6 weeks after biopsy. Final pathology revealed ISUP Gleason Grade Group upgrade in 62.6% of cases. PIRADS 5, PIRADS 4 and PIRADS 3 were associated with Gleason Grade Group upgrade in 70.5%, 62.8%, 48.3% of patients on final pathology, respectively. Within PIRADS 5 group, the number of upgraded cases was statistically significant. Conclusions PIRADS score correlates with an upgrade on final pathology and may justify shared decision of radical treatment in patients unwilling to repeated biopsies. However, the use of PIRADS 5 score as a sole indicator for prostatectomy may result in nonnegligible overtreatment rate.

scholarly journals A Hierarchical Machine Learning Model to Discover Gleason Grade Group-specific Biomarkers in Prostate Cancer

2019 ◽  
Author(s):  
Osama Hamzeh ◽  
Abedalrhman Alkhateeb ◽  
Julia Zheng ◽  
Srinath Kandalam ◽  
Crystal Lueng ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
Cancer Patients ◽  
Gleason Score ◽  
Cancer Progression ◽  
Class Imbalance ◽  
Gleason Grade ◽  
Gene Expressions ◽  
Grade Group ◽  
Potential Biomarkers

1) Background: One of the deadliest cancers that affect men worldwide and North American men is prostate cancer. This disease motivates parts of the cells in the prostate to lose control of their growth and division. 2) Methods: We are proposing a machine learning method used to analyze gene expressions of prostate tumors with different Gleason scores, and to identify potential genetic biomarkers for each group. A publicly-available RNA-Seq dataset of a cohort of 104 prostate cancer patients have been retrieved from the National Center for Biotechnology Information's (NCBI) Gene Expression Omnibus (GEO) repository. We categorize patients by their Gleason scores into different groups to create a hierarchy of disease progression. A hierarchical model with standard classifiers in different Gleason groups (hereinafter called nodes) to identify and predict nodes based on their mRNA or gene expressions. At each node, patient samples are analyzed via class imbalance and hybrid feature selection techniques to build the prediction model. The outcome of each node is a set of genes that can separate the Gleason group from the remaining groups. To validate the proposed method, the set of identified genes are used to classify a second dataset of 499 prostate cancer patients that have been collected from cBioportal.. 3) Results: Two genes have been found to be potential biomarkers of specific Gleason groups; PIAS3 has been identifed for Gleason score 4+3=7, while UBE2 could be a poteintial biomarker for Gleason score 6. Other proposed genes that were not found in the literature might be potential biomarkers. 4) Conclusion: The latest literature supports that the genes predicted by the proposed method are strongly correlated with prostate cancer progression and tumour development processes. Furthermore, pathway analysis shows that both PIAS3 and UBE2 share the same protein interaction pathway, the JAK/STAT signaling process.

Sign in / Sign up

Export Citation Format

Share Document