[Active surveillance for prostate cancer]

An Intelligent Decision-Making Support System for the Detection and Staging of Prostate Cancer in Developing Countries

Most developing countries face huge challenges in the medical field; scarce medical resources and inadequate medical personnel will affect the development and stability of the society. Therefore, for most developing countries, the development of intelligent medical systems can greatly alleviate the social contradictions arising from this problem. In this study, a new data decision-making intelligent system for prostate cancer based on perceptron neural network is proposed, which mainly makes decisions by associating some relevant disease indicators and combining them with medical images. Through data collection, analysis and integration of medical data, as well as the disease detection and decision-making process, patients are given an auxiliary diagnosis and treatment, so as to solve the problems and social contradictions faced by most developing countries. Through the study of hospitalization information of more than 8,000 prostate patients in three hospitals, about 2,156,528 data items were collected and compiled for experiment purposes. Experimental data shows that when the patient base increases from 200 to 8,000, the accuracy of the machine-assisted diagnostic system will increase from 61% to 87%, and the doctor's diagnosis rate will be reduced to 81%. From the study, it is concluded that when the patient base reaches a certain number, the diagnostic accuracy of the machine-assisted diagnosis system will exceed the doctor's expertise. Therefore, intelligent systems can help doctors and medical experts treat patients more effectively.

[Pathology findings after radical prostatectomy for prostate cancer in patients eligible for active surveillance: Contribution of multiparametric MRI to treatment decision]

OBJECTIVES

To analyze, in patients with prostate cancer (PC) potentially eligible for active surveillance (AS), whether multiparametric-MRI (mp-MRI) predicts presence of clinically significant cancer on radical prostatectomy (RP) specimen.

METHODS

We identified 77 men with PC eligible for AS (PSA≤15ng/mL, stage≤T2a, Gleason score≤6, up to 3 positive cores, maximal cancer core length≤5mm) who underwent RP between 01/2008 and 08/2015. All patients had prebiopsy mp-MRI followed by systematic±targeted biopsies. For each patient, the likelihood of the presence of cancer on mp-MRI was assigned using Likert scale (1 to 5). The predictive factors for the presence of significant cancer on RP specimen (Gleason score≥7 and/or tumoral maximal diameter>10mm) were evaluated using logistic regression.

RESULTS

Median age was 61 and median PSA was 6.7ng/mL. Overall, 49 (64%) patients had a positive mp-MRI (score≥3). Clinically significant cancer on RP specimen was found in 45 (58%) patients (69% in MRI-positive patients vs 39% in MRI-negative patients). In multivariate analysis, a positive MRI was a predictive factor for the presence of significant cancer on the surgical specimen (OR=3.0; CI95% [1.01-8.88]; P=0.04), as was age (OR=1.17; CI95% [1.05-1.31]; P=0.004) and PSAD (OR=1.10; CI95% [1.01-1.20]; P=0.02).

CONCLUSION

Mp-MRI is a useful exam for selecting patients eligible for AS even if the situation remains unclear after prostate biopsies including targeted biopsies. Upon confirmation by further studies, mp-MRI should be considered as an independent criterion before entering an AS program.

LEVEL OF EVIDENCE

4.