Prostate cancer is the most common male cancer in 112 countries and makes up 7% of global cancer cases, and is the second leading cause of cancer-related deaths in men. Normally, men with suspected prostate cancer undergo a prostate MRI, and then a Radiologist would review this scan to identify any suspicious areas for cancer within the prostate. Prostate MRI interpretation, however, is an expert skill with a steep learning curve, and internationally, there is a growing shortage of Radiologists. The PARADIGM trial aims to assess if AI can perform just as well as Radiologists in interpreting prostate MRI scans to identify prostate cancer. Enrolled participants will undergo a prostate MRI, which is the normal method used for investigating suspected prostate cancer. AI and a Radiologist will both interpret the MRI, without knowledge of each other's interpretation. Once both reports have been made, the Radiologist will be asked to produce a third, combined report. If there is a suspicious area in the prostate identified either by AI or the Radiologist, targeted biopsies will be performed. If there are no suspicious areas on the MRI and if you are at low risk of harbouring cancer, which occurs in about 30% of men, then no biopsy will be taken at all.
Aim: To assess whether artificial intelligence is non-inferior to radiologists in the diagnosis of clinically significant prostate cancer on MRI. Objectives Primary 1\. To compare the proportion of men who have clinically significant prostate cancer detected on MRI using AI ± targeted biopsy with radiologists ± targeted biopsy. Secondary 1. To compare the proportion of men who have clinically insignificant prostate cancer detected on MRI using AI ± targeted biopsy with radiologists ± targeted biopsy. 2. To compare the proportion of men with non-suspicious MRIs for AI vs radiologists. 3. To compare the proportion of men with indeterminately scored MRI as reported by AI vs radiologists. 4. To compare the diagnostic test performance of AI vs radiologist. 5. To compare the additive value of AI when used together with a radiologist interpretation (summative of all identified lesions) compared to a radiologist alone. 6. To compare the additive value of AI when used together with a radiologist interpretation (where the radiologist can interact with the AI system by accepting or rejecting AI-identified lesions) compared to a radiologist alone. 7. To determine the frequency of AI failures. 8. To compare treatment eligibility decisions between AI and Radiologist. 9. To compare the cost-effectiveness of unblinded AI interpreted by the radiologist compared to radiologist alone for prostate cancer detection, and AI alone vs. radiologist alone, and a 3-arm analysis considering all three. Design: Prospective, international, within-patient, multi-centre, level-1 evidence trial in participants referred to hospital with a clinical suspicion of prostate cancer.
Study Type
INTERVENTIONAL
Allocation
NA
Purpose
DIAGNOSTIC
Masking
SINGLE
Enrollment
500
AI algorithm that will interpretate the prostate MRI
Radiologist will interpret the prostate MRI (as per standard of care)
Proportion of men with clinically significant cancer
Proportion of men with clinically significant cancer detected (any pattern 4 disease on any core (i.e. Gleason Grade ≥ 3+4/Gleason grade group ≥2).
Time frame: When biopsy results available, at an expected average of 30 days post-biopsy
Proportion of men with clinically insignificant cancer
Proportion of men with clinically insignificant cancer detected (Gleason grade 3+3/Gleason grade group 1).
Time frame: When biopsy results available, at an expected average of 30 days post-biopsy
Proportion of men with non-suspicious MRIs
Proportion of men with non-suspicious MRIs for AI vs Radiologists
Time frame: When MRI results available, at an expected average of 30 days post-MRI
Proportion of MRIs with indeterminate scores.
Proportion of men with indeterminately scored MRI as reported by AI vs radiologists
Time frame: When MRI results available, at an expected average of 30 days post-MRI
Agreement between AI and Radiologist in score of suspicion
Compare the proportion of MRIs with concordant scores between AI and Radiologist in score of suspicion
Time frame: When MRI results available, at an expected average of 30 days post-MRI
Diagnostic test performance characteristics (AI versus Radiologist)
Test performance characteristics for AI and Radiologists, including sensitivity, specificity, area under the receive operating characteristic curve, positive predictive value and negative predictive value.
Time frame: When biopsy results available, at an expected average of 30 days post-biopsy
Diagnostic test performance characteristics (AI plus Radiologist)
Test performance characteristics of AI in combination with Radiologist (summative of all identified lesions) compared to a radiologist alone, including sensitivity, specificity, area under the receive operating characteristic curve, positive predictive value and negative predictive value.
Time frame: When biopsy results available, at an expected average of 30 days post-biopsy
Diagnostic test performance characteristics (AI-assisted Radiologist)
Test performance characteristics of AI in combination with Radiologist (where the radiologist can interact with the AI system by accepting or rejecting AI-identified lesions) compared to a radiologist alone, including sensitivity, specificity, area under the receive operating characteristic curve, positive predictive value and negative predictive value.
Time frame: When biopsy results available, at an expected average of 30 days post-biopsy
Significant cancer detected by peri-lesional biopsies
Proportion of patients with significant cancer detected taking into account peri-lesional biopsies of AI and Radiologist declared lesions.
Time frame: When biopsy results available, at an expected average of 30 days post-biopsy
Significant cancer detected by systematic biopsies
Proportion of patients with significant cancer detected by systematic biopsies
Time frame: When biopsy results available, at an expected average of 30 days post-biopsy
Frequency of AI failures
Proportion of patients where AI was unable to interpret the MRI scan
Time frame: When MRI results available, at an expected average of 30 days post-MRI
Treatment eligibility decisions
Proportion of patients where treatment eligibility changed between AI and Radiologist
Time frame: When biopsy results available, at an expected average of 30 days post-biopsy
Cost-efffectiveness
Cost-effectiveness of unblinded AI interpreted by the radiologist compared to radiologist alone in detecting significant prostate cancer, and AI alone vs. radiologist alone, and a 3-arm analysis considering all three.
Time frame: At an expected average of 30 days post-intervention
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.