Validation of a Machine Learning Model Based on MR for the Prediction of Prostate Cancer

Recruiting

• Conditions: Prostate Cancer

• Registration Number: NCT06773598
• Lead Sponsor: IRCCS Azienda Ospedaliero-Universitaria di Bologna

Brief Summary

The goal of this observational study is to validate a clinically significant predictive machine learning model based on the processing of images RMmp (Multiparametric Magnetic Resonance Imaging). To be validated the model should be evaluated on:

* Specificity (SP): is the probability of a negative test result, conditioned on the individual truly being negative

* Sensitivity (SN): is the probability of a positive test result, conditioned on the individual truly being positive

Detailed Description

This is a transversal, non-interventional observation study that involves the analysis of data collected both retrospectively and prospectively.

Patients will be enrolled by the radiologist medical staff designated by the Principal Investigator. The Principal Investigator and his delegates will be responsible for the acquisition and pseudo-anonymization of images of patients enrolled (both retrospectively and prospectively) from the RIS-PACS of the IRCCS Bologna University Hospital, Policlinico di Sant'Orsola. When available, for the participants undergoing prostate surgery, the O.U. of Pathological Anatomy will provide digital scans of the prostatic macrosections.

For the validation of the machine learning model of clinically significant CaP, a tool will be made available to radiologists. This tool is developed by the Department of Informatics - Science and Engineering, DISI, University of Bologna and Alma Mater Research Institute on Global Challenges and Climate Change, Alma Climate, University of Bologna, and integrated in an open-source Dicom viewer, Aliza MS Dicom Viewer. The doctors will then have the possibility to carry out independently the segmentation of the ADC sequences (previously pseudo-anonymized) and start the radiomic process to obtain a predictive value of the probability that the segmented lesion is clinically significant. This probability value will be calculated by the software on the basis of the machine learning model developed in PROSTATE_01. The tool also allows data collection (organized and pseudo-anonymous). The validation of the clinically significant predictive model of CaP will be carried out on all patients enrolled both retrospectively and prospectively, excluding those used in the model training phase in PROSTATE_01. After having evaluated the performance of the validated model and the effects of selection bias, once the recruitment is completed both retrospectively and prospectively, a refinement of the previously developed model will be carried out. This will be a "re-training" of the model itself, performed on training and test datasets randomly selected from the entire enrolled population from which it will be obtained randomly, by difference, also the subset for a new validation.

Study Timeline

• Study Start: 2024-05-21
• Status Verified: 2024-11
• Study First Submitted: 2025-01-09
• Study First Submitted QC: 2025-01-09
• Last Update Submitted: 2025-01-09
• Study First Posted: 2025-01-14
• Last Update Posted: 2025-01-14
• Primary Completion: 2028-10
• Study Completion: 2028-11

Recruitment & Eligibility

• Status: RECRUITING
• Sex: All
• Target Recruitment: 1100

Inclusion Criteria

• Participants aged 18 at the time of examination
• Obtaining informed consent
• Presence of one or more lesions classified as PI-RADSv2.1 ≥ 1 at a prostate RMmp at the IRCCS Azienda Ospedaliero-Universitaria in Bologna
• Indication for TRUS biopsy by fusion technique integrated with systematic biopsy at the IRCCS Azienda Ospedaliero-Universitaria in Bologna

Exclusion Criteria

• Previous prostate surgery or hormone therapy
• Technically sub-optimal investigations for the presence of artifacts (hip prosthesis, movement of the endorectal probe, etc.)

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Specificity (SP)	From enrollment to the end of treatment at 5 years	Specificity is the probability of obtaining a negative classification or that the disease is indeed absent.
Sensitivity (SN)	From enrollment to the end of treatment at 5 years	Sensitivity is the probability of a positive classification or that the disease is actually present.
Positive Predictive Value (PPV)	From enrollment to the end of treatment at 5 years	It is the ratio of patients truly diagnosed as positive to all those who had positive test results (including healthy subjects who were incorrectly diagnosed as patient).
Negative Predictive Value (NPV)	From enrollment to the end of treatment at 5 years	It is the ratio of subjects truly diagnosed as negative to all those who had negative test results (including patients who were incorrectly diagnosed as healthy).

Trial Locations

Locations (1)

IRCCS Azienda Ospedaliero-Universitaria di Bologna; 🇮🇹 Bologna, Italy