Purpose: To develop and externally validate nomograms integrating quantitative apparent diffusion coefficient (ADC) sequence, Prostate Imaging Reporting and Data System (PI-RADS) derived from biparametric MRI (bp-MRI), and clinical indicators to detect prostate cancer (PCa) and clinically significant prostate cancer (csPCa) in patients with prostate specific antigen (PSA) between 4-20 ng/mL.
Materials and methods: Nomograms were developed using data from a cohort of suspected prostate cancer patients with elevated PSA of 4–20 ng/mL who underwent prostate MRI and biopsy at our institution between January 1, 2018, and August 31, 2023 (n = 440). The outcomes were the presence of csPCa and PCa. Nomograms were constructed separately for lesions located in the peripheral and transitional zones. Significant variables identified through univariate logistic analysis and LASSO regression analysis were used to construct four separate nomograms. These nomograms were subsequently validated and evaluated using an external independent cohort of patients obtained from the Prostate Imaging: Cancer AI (PI-CAI) database (n = 313).
Results: A total of 131 (29.8%) and 106 (33.9%) patients had csPCa in the training and external validation cohorts, respectively. Age, PI-RADS, ADC, and PSA density (PSAD) were independent predictors in the prediction model for csPCa in the peripheral zone (PZ), showing an area under the curve (AUC) of 0.934 (95% CI, 0.906-0.962). For csPCa in the transitional zone (TZ), PI-RADS, ADC, and PSAD were independent predictors, with an AUC of 0.903 (95% CI, 0.824-0.983). Additionally, PI-RADS and ADC were independent predictors for PCa in PZ, with an AUC of 0.882 (95% CI, 0.840-0.925), while PI-RADS and PSAD were independent predictors in TZ, with an AUC of 0.764 (95% CI, 0.683-0.844). All four nomograms demonstrated good discrimination with high AUCs in the external validation cohort. Calibration curves indicated good agreement, and decision curve analyses (DCAs) confirmed the clinical benefits of the nomograms.
Conclusions: ADC proved to be the strongest predictor of csPCa in both PZ and TZ, and for PCa specifically in PZ. We developed nomograms integrating ADC, bp-MRI-derived PI-RADS, age and PSAD to detect csPCa and PCa in patients with PSA of 4–20 ng/mL.
{{ section.description }}
Ce algorithme est fourni à des fins d'éducation, de formation et d'information. Il ne doit pas être utilisé pour aider à la prise de décision médicale ou pour fournir des services médicaux ou de diagnostic. Lire l'intégralité de notre disclaimer.
With an Evidencio Community account you can:
A personal Evidencio account is free, with no strings attached!
Join us and help create clarity, transparency, and efficiency in the creation, validation, and use of medical prediction algorithms.
{{ (typeof row === 'object') ? row.label : row }} |
{{ column }} | |
---|---|
{{ row.label }} | {{ value }} |
{{ error }}
Veuillez saisir un mot de passe
Un mot de passe doit comporter au moins 8 caractères
Un mot de passe ne peut pas être plus long que 64 caractères.
Choisissez un mot de passe avec au moins une lettre majuscule
Choisissez un mot de passe avec au moins un caractère spécial (@$!%*#?&)
Veuillez accepter les conditions générales et la clause de non-responsabilité
Veuillez fournir votre adresse e-mail et nous vous enverrons un lien pour réinitialiser votre mot de passe.
Adresse email
Veuillez entrer un email valide
Si un compte a été enregistré avec cette adresse e-mail, vous recevrez un lien de récupération dans votre courrier
Veuillez utiliser le lien de réinitialisation du mot de passe contenu dans le mail pour définir votre nouveau mot de passe
Vous n'avez pas encore reçu l'e-mail ? Veuillez vérifier votre dossier spam, ou renvoyer l'email