Algorithm to detect ISUP ≥ 2 prostate cancer using canine detection

• Published in: World journal of urology Vol. 43; no. 1; p. 549
• Main Authors: Hermieu, Margaux, Roux, Alice, Desquilbet, Loïc, Hermieu, Nicolas, Gallet, Capucine, Xylinas, Evanguelos, de La Taille, Alexandre, Grandjean, Dominique, Hermieu, Jean-François
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 11.09.2025; Springer Nature B.V
• Subjects: Age; Aged; Algorithms; Animals; Antigens; Biopsy; Blood pressure; Body mass index; Decision making; Dogs; Family medical history; Feature selection; Humans; Hypertension; Magnetic Resonance Imaging; Male; Medicine; Medicine & Public Health; Middle Aged; Mortality; Nephrology; Oncology; Prospective Studies; Prostate cancer; Prostatic Neoplasms - diagnosis; Prostatic Neoplasms - pathology; Rectum; Urology; Variables; Prostate cancer diagnostic; Olfactory detection; Diagnostic score; Decision algorithm; Dogs
• ISSN: 1433-8726; 0724-4983; 1433-8726
• DOI: 10.1007/s00345-025-05938-1

Purpose Screening and diagnosing ISUP ≥ 2 prostate cancer is challenging. This study aimed to determine whether canine detection could be beneficial addition to the ISUP ≥ 2 prostate cancer diagnostic protocol by creating a decision-making algorithm for men with suspected prostate cancer. Methods We conducted a prospective study at two urology institutions and a French veterinary school, including men with a suspicion of prostate cancer from November to April 2023, which were divided into two groups according to their prostate biopsy results. Eight binary variables known to be associated with a higher risk of prostate cancer were considered: body mass index, family history, age, smoking status, hypertension, digital rectal examination, total PSA level and prostate MRI. A decision-making algorithm was then created using two diagnostic scores. Results 151 patients were included, 78 with ISUP ≥2 prostate cancer, and 73 without. The ProstateDetectScore was based on age, blood pressure, digital rectal examination, and MRI. Weight i is the whole part {rounded (10 x β i )} where β i is the model parameter value associated with the variable i included in this model and var ij is the value of variable i for patient j. The ProstateK9DetectScore is calculated from the same data plus the canine detection result. The following algorithm was constructed: PCa Prostate cancer, NPV negative predictive value, PPV positive predictive value Conclusion The algorithm, involving canine detection, increases ISUP ≥2 prostate cancer detection rate through prostate biopsy, thus reducing the number of unnecessary biopsies.