Development, validation and comparison of two nomograms predicting prostate cancer at initial 12-core biopsy

Radiomic and Genomic Machine Learning Method Performance for Prostate Cancer Diagnosis: Systematic Literature Review

BACKGROUND

Machine learning algorithms have been drawing attention at the joining of pathology and radiology in prostate cancer research. However, due to their algorithmic learning complexity and the variability of their architecture, there is an ongoing need to analyze their performance.

OBJECTIVE

This study assesses the source of heterogeneity and the performance of machine learning applied to radiomic, genomic, and clinical biomarkers for the diagnosis of prostate cancer. One research focus of this study was on clearly identifying problems and issues related to the implementation of machine learning in clinical studies.

METHODS

Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) protocol, 816 titles were identified from the PubMed, Scopus, and OvidSP databases. Studies that used machine learning to detect prostate cancer and provided performance measures were included in our analysis. The quality of the eligible studies was assessed using the QUADAS-2 (quality assessment of diagnostic accuracy studies-version 2) tool. The hierarchical multivariate model was applied to the pooled data in a meta-analysis. To investigate the heterogeneity among studies, I2 statistics were performed along with visual evaluation of coupled forest plots. Due to the internal heterogeneity among machine learning algorithms, subgroup analysis was carried out to investigate the diagnostic capability of machine learning systems in clinical practice.

RESULTS

In the final analysis, 37 studies were included, of which 29 entered the meta-analysis pooling. The analysis of machine learning methods to detect prostate cancer reveals the limited usage of the methods and the lack of standards that hinder the implementation of machine learning in clinical applications.

CONCLUSIONS

The performance of machine learning for diagnosis of prostate cancer was considered satisfactory for several studies investigating the multiparametric magnetic resonance imaging and urine biomarkers; however, given the limitations indicated in our study, further studies are warranted to extend the potential use of machine learning to clinical settings. Recommendations on the use of machine learning techniques were also provided to help researchers to design robust studies to facilitate evidence generation from the use of radiomic and genomic biomarkers.

A Novel Scoring System for Prediction of Prostate Cancer Based on Shear Wave Elastography and Clinical Parameters

OBJECTIVE

To develop a novel scoring system for the prediction of prostate cancer (PCa).

METHODS

We assessed 127 patients who underwent a prostate biopsy. Prior to biopsy, we performed shear wave elastography (SWE), transrectal ultrasound, digital rectal exam, total prostatic specific antigen, PSA density (PSAD), and free PSA/total PSA ratio (F/T). We developed an 11-point scoring system based on SWE and these clinical parameters.

RESULTS

PCa was diagnosed in 51 (40.2%) of 127 patients and 192 (25.2%) of 762 sextants on initial biopsy. ROC curve analyses showed that the cutoff value (COV) for SWE was 40.8 kpa at the sextant level. The AUC of score system based on the SWE and clinical parameters (0.911) was significantly different from scoring systems based on SWE alone (0.842) or clinical parameters alone (0.868). For this 11-point scoring system, the optimal COV, Youden index, sensitivity, specificity, PPV, NPV, and AUC were 3 points, 0.66, 76.5% 89.5%, 82.98%, 85.00%, and 0.911, respectively. There were 68 negative biopsy results in patients with 0-3 points, and the detection rate of PCa was 100% in patients with scores exceeding 6 points.

CONCLUSION

This 11-point scoring system based on SWE and clinical parameters has the good diagnostic performance for predicting PCa. It may be useful in selecting patients for biopsy, substantially reducing the number of unnecessary biopsies while ensuring that few cancers are missed.