Non-Invasive Logistic Regression Model for Predicting Regional Lymph Node Metastases in Cutaneous Melanoma
https://doi.org/10.37174/2587-7593-2026-9-3-60-65
Abstract
Relevance: Cutaneous melanoma is characterized by high metastatic potential, and regional lymph node involvement is a key prognostic factor.
Purpose: To develop and evaluate a non-invasive logistic regression model for predicting regional lymph node metastases.
Materials and methods: A retrospective single-center study included 121 patients. Clinical, ultrasound, elastography and scintigraphy parameters were used as predictors; morphological data were excluded.
Results: The model demonstrated a high discriminative ability (ROC AUC ≈ 0.94). At a threshold of p = 0.316, the sensitivity was ≈0.85, the specificity was ≈0.96, the accuracy was ≈0.93, at a lower threshold of p = 0.103, the sensitivity reached about 0.93 with a specificity of about 0.79.
Conclusion: The model may be used for primary risk stratification and guiding invasive staging decisions.
About the Authors
E. V. TikhonovaRussian Federation
Elena V. Tikhonova
+7(901)900-55-15
23 Kashirskoye Highway, Moscow, 115522
Competing Interests:
The authors declare no conflict of interest
A. M. Sergeeva
Russian Federation
Krasnokazarmennaya Street 14, Building 1, Moscow, 111250
Competing Interests:
The authors declare no conflict of interest
S. N. Berdnikov
Russian Federation
23 Kashirskoye Highway, Moscow, 115522
Competing Interests:
The authors declare no conflict of interest
References
1. Tikhonova EV, Berdnikov SN, Samoylenko IV, et al. Multiparametric ultrasound diagnosis in preoperative evaluation of lymph node regionals in high-risk melanoma patients. Effective Pharmacotherapy. 2025;21(15):8-11. (In Russ.). https://doi.org/10.33978/2307-3586-2025-21-15-8-11.
2. Tikhonova EV, Berdnikov SN, Sergeeva AM, et al. Comparison of the diagnostic performance of the full logistic model and sentinel lymph node biopsy in patients with cutaneous melanoma. Effective Pharmacotherapy. 2026;22(8):30-33. (In Russ.).
3. Tikhonova EV, Berdnikov SN, Samoylenko IV, et al. Improvement of ultrasound diagnosis of regional lymph nodes in skin melanoma: melanoma development of the Russian classification (RUCL-M) to reduce hyperdiagnostics and unjustified biopsies. Journal of Oncology: Diagnostic Radiology and Radiotherapy. 2025;8(2):57-64. (In Russ.). https://doi.org/10.37174/2587-7593-2025-8-2-57-64
4. Allahverdieva GF, Danzanova TY, Mudunov AM, et al. Ultrasound evaluation of the status of peripheral lymph nodes (literature review). Ultrasound Classification Node-RADS (US). Journal of Oncology: Diagnostic Radiology and Radiotherapy. 2023;6(4):42-52. (In Russ.). https://doi.org/10.37174/2587-7593-2023-6-4-42-52
5. Tikhonova EV, Berdnikov SN, Samoylenko IV, et al. Compresion of in vivo and ex vivo elastography and elastometric in the diagnosis of metastasis of skin melanoma to peripheral lymph nodes. Journal of Oncology: Diagnostic Radiology and Radiotherapy. 2025;8(2):65-72. (In Russ.). https://doi.org/10.37174/2587-7593-2025-8-2-65-72
Review
For citations:
Tikhonova E.V., Sergeeva A.M., Berdnikov S.N. Non-Invasive Logistic Regression Model for Predicting Regional Lymph Node Metastases in Cutaneous Melanoma. Journal of oncology: diagnostic radiology and radiotherapy. 2026;9(3):60-65. (In Russ.) https://doi.org/10.37174/2587-7593-2026-9-3-60-65
JATS XML























