Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Oct 22:64:1446-1454.
doi: 10.2340/1651-226X.2025.43970.

Development and evaluation of a lymph node invasion risk prediction model in intermediate- and high-risk prostate cancer patients

Håkon Ramberg  1 , Manuela Zucknick  2 , Francesco Barletta  3 , Petter Davik  4 , Åsmund Nybøen  5 , Lars Magne Eri  6 , Sivanthe Sivanesan  7 , Knut Håkon Hole  8 , Tord Hompland  9 , Stian Ole Prestbakk  10 , Giorgio Gandaglia  3 , Tone Frost Bathen  11 , Alberto Briganti  3 , Viktor Berge  6 , Kristin Austild Tasken  12
Affiliations

Development and evaluation of a lymph node invasion risk prediction model in intermediate- and high-risk prostate cancer patients

Håkon Ramberg et al. Acta Oncol. .

Abstract

Background and purpose: Many prostate cancer patients undergoing pelvic lymph node dissection (PLND) have no sign of lymph node invasion (LNI) during final pathological assessment. To improve preoperative staging accuracy, we developed the Oslo model, which estimates the risk of LNI based on clinical, histopathological, and magnetic resonance imaging (MRI) variables.

Patients/materials and methods: We utilized data from 903 prostate cancer patients treated at Oslo University Hospital (OUS) to develop the model using Bayesian logistic regression. The Oslo model was validated with data from 189 patients at IRCCS Ospedale San Raffaele (HRS), 157 from St. Olav's Hospital, and 231 from OUS. We assessed its performance against the Memorial Sloan Kettering Cancer Centre (MSKCC) and Briganti 2019 nomograms using metrics like AUC, R², decision curve analysis, and calibration plots.

Results: The Oslo model outperformed Briganti 2019, demonstrating a higher net benefit and a 10% reduction in interventions at a 7% cutoff. Key variables included clinical T stage on MRI, Prostate Specific Antigen (PSA), prostate volume, International Society of Urological Pathology grade group, and maximum lesion length on MRI. Validation showed strong reliability in the OUS and HRS cohorts but weaker performance in the St. Olav's cohort. The AUCs were 77% for the Oslo model, 74% for Briganti 2019, and 66% for MSKCC. Limitations include small and heterogeneous validation cohorts.

Interpretation: The Oslo model enhances predictive performance in intermediate- and high-risk patients using easily accessible clinical and MRI data, potentially reducing unnecessary PLND interventions and assisting clinicians in treatment decision-making.

PubMed Disclaimer

Conflict of interest statement

The authors report there are no competing interests to declare.

Figures

Figure 1
Figure 1
Calibration plot showing the predictive accuracy of the Oslo model using the complete cases from the OUS cohort. The dashed line represents the linear approximation, and the red line is the flexible calibration curve based on locally estimated scatterplot smoothing. The grey shaded area represents the 95% confidence interval. The diagonal black line represents an ideal calibration curve. Histogram shows the distribution of predicted probabilities of pN0 and pN1 patients. OUS: Oslo University Hospital.
Figure 2
Figure 2
Calibration plots of the external and temporal validation cohorts. The dashed line represents the linear approximation, and the red line is the flexible calibration curve based on locally estimated scatterplot smoothing. The grey shaded area represents the 95% confidence interval. The diagonal black line represents an ideal calibration curve. Histogram shows the distribution of predicted probabilities of pN0 and pN1 patients.
Figure 3
Figure 3
Decision curve analysis with net reduction in PLND interventions when using the Oslo model, Briganti 2019, and recalibrated Briganti 2019 model. This figure shows the development OUS cohort 2015–2022 with complete cases. PLND: pelvic lymph node dissection; OUS: Oslo University Hospital.
See this image and copyright information in PMC

References

    1. Wang H, Xia Z, Xu Y, Sun J, Wu J. The predictive value of machine learning and nomograms for lymph node metastasis of prostate cancer: a systematic review and meta-analysis. Prostate Cancer Prostatic Dis. 2023;26(3):602–13. 10.1038/s41391-023-00704-z - DOI - PubMed
    1. Dong B, Zhan H, Luan T, Wang J. The role and controversy of pelvic lymph node dissection in prostate cancer treatment: a focused review. World J Surg Oncol. 2024;22(1):68. 10.1186/s12957-024-03344-2 - DOI - PMC - PubMed
    1. Hope TA, Eiber M, Armstrong WR, Juarez R, Murthy V, Lawhn-Heath C, et al. Diagnostic accuracy of 68 Ga-PSMA-11 PET for pelvic nodal metastasis detection prior to radical prostatectomy and pelvic lymph node dissection: a multicenter prospective phase 3 imaging trial. JAMA Oncol. 2021;7(11):1635. 10.1001/jamaoncol.2021.3771 - DOI - PMC - PubMed
    1. Gandaglia G, Ploussard G, Valerio M, Mattei A, Fiori C, Fossati N, et al. A novel nomogram to identify candidates for extended pelvic lymph node dissection among patients with clinically localized prostate cancer diagnosed with magnetic resonance imaging-targeted and systematic biopsies. Eur Urol. 2019;75(3):506–14. 10.1016/j.eururo.2018.10.012 - DOI - PubMed
    1. Draulans C, Everaerts W, Isebaert S, Van Bruwaene S, Gevaert T, Oyen R, et al. Development and external validation of a multiparametric magnetic resonance imaging and International Society of Urological Pathology based add-on prediction tool to identify prostate cancer candidates for pelvic lymph node dissection. J Urol. 2020;203(4):713–18. 10.1097/JU.0000000000000652 - DOI - PubMed