A Machine Learning-Driven Approach to Predict the Outcome of Prostate Biopsy: Identifying Cancer, Clinically Significant Disease, and Unfavorable Pathological Features on Prostate Biopsy

2021 ◽  
pp. 591-600
Author(s):  
John L. Pfail ◽  
Dara J. Lundon ◽  
Parita Ratnani ◽  
Vinayak Wagaskar ◽  
Peter Wiklund ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prostate Biopsy ◽  
Pathological Features ◽  
Clinically Significant ◽  
Significant Disease

scholarly journals Applying Machine Learning to Predict the Exportome of Bovine and Canine Babesia Species That Cause Babesiosis

Pathogens ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 660
Author(s):  
Stephen J. Goodswen ◽  
Paul J. Kennedy ◽  
John T. Ellis
Keyword(s):  
Machine Learning ◽  
Severe Disease ◽  
Economic Loss ◽  
Babesia Bovis ◽  
Training Data ◽  
Babesia Bigemina ◽  
Bovine Babesiosis ◽  
Canine Babesiosis ◽  
Clinically Significant ◽  
Significant Disease

Babesia infection of red blood cells can cause a severe disease called babesiosis in susceptible hosts. Bovine babesiosis causes global economic loss to the beef and dairy cattle industries, and canine babesiosis is considered a clinically significant disease. Potential therapeutic targets against bovine and canine babesiosis include members of the exportome, i.e., those proteins exported from the parasite into the host red blood cell. We developed three machine learning-derived methods (two novel and one adapted) to predict for every known Babesia bovis, Babesia bigemina, and Babesia canis protein the probability of being an exportome member. Two well-studied apicomplexan-related species, Plasmodium falciparum and Toxoplasma gondii, with extensive experimental evidence on their exportome or excreted/secreted proteins were used as important benchmarks for the three methods. Based on 10-fold cross validation and multiple train–validation–test splits of training data, we expect that over 90% of the predicted probabilities accurately provide a secretory or non-secretory indicator. Only laboratory testing can verify that predicted high exportome membership probabilities are creditable exportome indicators. However, the presented methods at least provide those proteins most worthy of laboratory validation and will ultimately save time and money.

MRI-based nomogram for the prediction of prostate cancer diagnosis: A multi-centre validated patient–physician decision tool

2022 ◽  
pp. 205141582110659
Author(s):  
Edwin M Chau ◽  
Beth Russell ◽  
Aida Santaolalla ◽  
Mieke Van Hemelrijck ◽  
Stuart McCracken ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Logistic Regression Analysis ◽  
Prostate Biopsy ◽  
Gleason Grade ◽  
Grade Group ◽  
Group 2 ◽  
Clinically Significant ◽  
Significant Disease

Objective: To update and externally validate a magnetic resonance imaging (MRI)-based nomogram for predicting prostate biopsy outcomes with a multi-centre cohort. Materials and methods: Prospective data from five UK-based centres were analysed. All men were biopsy naïve. Those with missing data, no MRI, or prostate-specific antigen (PSA) > 30 ng/mL were excluded. Logistic regression analysis was used to confirm predictors of prostate cancer outcomes including MRI-PIRADS (Prostate Imaging Reporting and Data System) score, PSA density, and age. Clinically significant disease was defined as International Society of Urological Pathology (ISUP) Grade Group ⩾ 2 (Gleason grade ⩾ 7). Biopsy strategy included transrectal and transperineal approaches. Nomograms were produced using logistic regression analysis results. Results: A total of 506 men were included in the analysis with median age 66 (interquartile range (IQR) = 60–69). Median PSA was 6.6 ng/mL (IQR = 4.72–9.26). PIRADS ⩾ 3 was reported in 387 (76.4%). Grade Group ⩾ 2 detection was 227 (44.9%) and 318 (62.8%) for any cancer. Performance of the MRI-based nomogram was an area under curve (AUC) of 0.84 (95% confidence interval (CI) = 0.81–0.88) for Grade Group ⩾ 2% and 0.85 (95% CI = 0.82–0.88) for any prostate cancer. Conclusion: We present external validation of a novel MRI-based nomogram in a multi-centre UK-based cohort, showing good discrimination in identifying men at high risk of having clinically significant disease. These findings support this risk calculator use in the prostate biopsy decision-making process. Level of evidence: 2c

Integrative Machine Learning Prediction of Prostate Biopsy Results From Negative Multiparametric MRI

2021 ◽  
Author(s):  
Haoxin Zheng ◽  
Qi Miao ◽  
Yongkai Liu ◽  
Steven S. Raman ◽  
Fabien Scalzo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prostate Biopsy ◽  
Multiparametric Mri

One-year experience of government-funded magnetic resonance imaging prior to prostate biopsy: A case for omitting biopsy in men with a negative magnetic resonance imaging

2021 ◽  
pp. 205141582110043
Author(s):  
Hanna J El-Khoury ◽  
Niranjan J Sathianathen ◽  
Yuxin Jiao ◽  
Reza Farzan ◽  
Dennis Gyomber ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Prostate Cancer ◽  
Magnetic Resonance ◽  
Prostate Biopsy ◽  
Multivariable Analysis ◽  
Transrectal Ultrasound ◽  
Resonance Imaging ◽  
Retrospective Case ◽  
Level Of Evidence ◽  
Clinically Significant

Objectives: This study aimed to characterise the accuracy of multiparametric magnetic resonance imaging (mpMRI) as an adjunct to prostate biopsy, and to assess the effect of the new Australian Medicare rebate on practice at a metropolitan public hospital. Patients and methods: We identified patients who underwent transrectal ultrasound (TRUS)-guided prostate biopsy at a single institution over a two-year period. Patients were placed into two groups, depending upon whether their consent was obtained before or after the introduction of the Australian Medicare rebate for mpMRI. We extracted data on mpMRI results and TRUS-guided biopsy histopathology. Descriptive statistics were used to demonstrate baseline patient characteristics as well as MRI and histopathology results. Results: A total of 252 patients were included for analysis, of whom 128 underwent biopsy following the introduction of the Medicare rebate for mpMRI. There was a significant association between Prostate Imaging Reporting and Data System v2 (PI-RADS) classification and the diagnosis of clinically significant prostate cancer ( p<0.01). Only one man with PI-RADS ⩽2 was found to have clinically significant prostate cancer. Four men with a PI-RADS 3 lesion were found to have clinically significant cancer. A PI-RADS 4 or 5 lesion was significantly associated with the diagnosis of clinically significant cancer on multivariable analysis. Conclusion: mpMRI is an important adjunct to biopsy in the diagnosis of clinically significant prostate cancer. Our findings support the safety of omitting/delaying prostate biopsy in men with negative mpMRI. Level of evidence: Level 3 retrospective case-control study.

Development of a machine learning algorithm to accurately detect clinically significant prostate cancer on MRI

2019 ◽  
Vol 18 (11) ◽  
pp. e3493
Author(s):  
J.W.M. Dillon ◽  
T.I. Whish-Wilson ◽  
S.J. Riddell ◽  
L-M. Wong ◽  
P. Brotchie ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Clinically Significant

Validation and adaptation of the Spanish version of the systemic lupus activity questionnaire (S-SLAQ) in an Argentinean population

Lupus ◽  
2021 ◽  
pp. 096120332110610
Author(s):  
Cecilia Catoggio ◽  
Alejandro Martínez Muñoz ◽  
Rafael Chaparro del Moral ◽  
Diana S Klajn ◽  
Silvia B Papasidero ◽  
...  
Keyword(s):  
Disease Activity ◽  
Correlation Coefficient ◽  
Intraclass Correlation Coefficient ◽  
Internal Consistency ◽  
Intraclass Correlation ◽  
Systemic Lupus ◽  
Cronbach's Alpha ◽  
Clinically Significant ◽  
Significant Disease ◽  
Activity Questionnaire

Objectives To validate the systemic lupus activity questionnaire (SLAQ) in Spanish language. Methods The SLAQ questionnaire was translated and adapted in Spanish. Consecutive SLE patients from 8 centers in Argentina were included. A rheumatologist completed a Systemic Lupus Activity Measure (SLAM), Systemic Lupus Erythematosus Disease Activity Index (SLEDAI)-2K, and a physician’s assessment. Reliability was assessed by internal consistency (Cronbach’s alpha), stability by test–retest reliability (intraclass correlation coefficient), and construct validity by evaluating the correlation with clinically relevant scores. Sensitivity and specificity for clinically significant disease activity (SLEDAI ≥6) of different S-SLAQ cut-off points were evaluated. Results We included 97 patients ((93% female, mean age: 40 years (SD14.7)). Internal consistency was excellent (Cronbach’s alpha = 0.84, p < 0.001), and the intraclass correlation coefficient was 0.95 ( p < 0.001). Mean score of S-SLAQ was 8.2 (SD 7.31). Correlation of S-SLAQ was moderate with Patient NRS (r= 0.63 p< 0.001), weak with SLAM-no lab ( r = 0.42, p <0.001) and SLAM ( r = 0.38, p < 0.0001), and very weak with SLEDAI-2K ( r = 0.15, p =0.1394). Using the S-SLAQ cutoff of five points, the sensitivity was 72.2% and specificity was 37.9%, for clinically significant disease activity. Conclusions The S-SLAQ showed good validity and reliability. A good correlation, similar to the original instrument, was observed with patient´s global disease activity. No correlation was found between S-SLAQ and gold standard disease activity measures like SLEDAI-2K and SLAM. The S-SLAQ cutoff point of 5 showed a good sensitivity to identify the active SLE population and therefore could be an appropriate screening instrument for disease activity in clinical and epidemiological studies.

Sign in / Sign up

Export Citation Format

Share Document