The prognostic value of lymph node ratio in comparison to positive lymph node count in penile squamous cell carcinoma

Machine learning-based overall and cancer-specific survival prediction of M0 penile squamous cell carcinoma：A population-based retrospective study

Background

Penile cancer is a rare tumor and few studies have focused on the prognosis of M0 penile squamous cell carcinoma (PSCC). This retrospective study aimed to identify independent prognostic factors and construct predictive models for the overall survival (OS) and cancer-specific survival (CSS) of patients with M0 PSCC.

Methods

Data was extracted from the Surveillance, Epidemiology, and End Results database for patients diagnosed with malignant penile cancer. Eligible patients with M0 PSCC were selected according to predetermined inclusion and exclusion criteria. These patients were then divided into a training set, a validation set, and a test set. Univariate and multivariate COX regression analyses were initially performed to identify independent prognostic factors for OS and CSS in M0 PSCC patients. Subsequently, traditional and machine learning prognostic models, including random survival forest (RSF), COX, gradient boosting, and component-wise gradient boosting modelling, were constructed using the scikit-survival framework. The performance of each model was assessed by calculating time-dependent area under curve (AUC), C-index, and integrated Brier score (IBS), ultimately identifying the model with the highest performance. Finally, the Shapley additive explanation (SHAP) value, feature importance, and cumulative rates analyses were used to further estimate the selected model.

Results

A total of 2, 446 patients were included in our study. Cox regression analyses demonstrated that age, N stage, and tumor size were predictors of OS, while the N stage, tumor size, surgery, and residential area were predictors of CSS. The RSF and COX models had a higher time-independent AUC and C-index, and lower IBS value than other models in OS and CSS prediction. Feature importance analysis revealed the N stage as a common significant feature for predicting M0 PSCC patients' survival. The SHAP and cumulative rate analyses demonstrated that the selected models can effectively evaluate the prognosis of M0 PSCC patients.

Conclusion

In M0 PSCC patients, age, N stage, and tumor size were predictors of OS. In addition, the N stage, tumor size, surgery, and residential area were predictors of CSS. The machine learning-based RSF and COX models effectively predicted the prognosis of M0 PSCC patients.

Inguinal Lymph-Node Ratio (LNR) as a predictor of Pelvic Lymph-Node Metastasis in squamous cell carcinoma of penis

OBJECTIVE

To determine the predictors of pelvic lymph-node metastasis in cases of squamous cell carcinoma (SCC) of penis.

METHODS

Data was retrospectively collected from 267 cases of SCC penis that presented at our institute between 2009 and 2019. Univariate and multivariate logistic regression models were used to identify independent significant factors. Receiver Operating Characteristic (ROC) curve was used to determine the cut-off of Lymph-Node Ratio (LNR) and discriminative ability of new model. Survival analysis was done using Kaplan Meier Curve.

RESULTS

Pelvic Lymph-Node Metastasis (PLNM) was pathologically detected in 56 groins (29.2%). A cut-off of 0.25 was calculated for LNR based on ROC. LNR >0.25 (p = 0.003), ENE (p = 0.037), and LVI (p = 0.043) were found significant on multivariate logistic regression. 71.5% showed PLNM in groins with positive LN (PLN) </ = 2 but LNR >0.25 whereas no PLNM was seen in groins with PLN >2 but LNR </ = 0.25. The AUC was 0.918 and 0.821 for LNR and PLN respectively. The probability of finding PLNM was 0% for patients with no risk factors which increased to 83% for 3 risk factors. The 5-year survival was 60% if no PLNM was found as compared to 12.7% if PLNM were found. The survival according to risk score was 81%, 43%, 16% and, 13% for 0, 1, 2 and, 3 risk score respectively.

CONCLUSION

LNR >0.25, LVI and, ENE are independent predictors of PLNM. The discriminative ability of LNR was better than PLN. PLND could be avoided if no risk factors are present.

French AFU Cancer Committee Guidelines - Update 2022-2024: penile cancer

OBJECTIVE

To update French oncology guidelines concerning penile cancer.

METHODS

Comprehensive Medline search between 2020 and 2022 upon diagnosis, treatment and follow-up of testicular germ cell cancer to update previous guidelines. Level of evidence was evaluated according to AGREE-II.

RESULTS

Epidermoid carcinoma is the most common penile cancer histology. Physical examination is mandatory to define local and inguinal nodal cancer stage. MRI with artificial erection can help to assess deep infiltration in cases of organsparing intention. Node negative patients (defined by palpation and imaging) will present micro nodal metastases in up to 25% of cases. Invasive lymph node assessment is thus advocated except for low risk patients. Sentinel node dynamic biopsy is the first line technique. Modified bilateral inguinal lymphadenectomy is an option with higher morbidity. 18-FDG-PET is recommended in patients with palpable nodes. Chest, abdominal and pelvis computerized tomography is an option. Fine needle aspiration (when positive) is an easy way to assess inguinal palpable node pathological involvement. Its results determine the type of lymphadenectomy to be performed (for diagnostic or curative purposes). Treatment is mostly surgical. Free margins status is essential, but it also has to be organ-sparing when possible. Brachytherapy and topic agents can cure in selected cases. Lymph node assessment should be synchronous to the removal of the tumour when possible. Limited inguinal lymph node involvement (pN1 stage) can be cured with the only lymphadenectomy. In case of larger lymph node stage, one should consider multidisciplinary treatment including chemotherapy and inclusion in a trial.

CONCLUSIONS

Penile cancer needs demanding surgery to be cured, surrounded by chemotherapy in node positive patients. Lymph nodes involvement is a major prognostic factor. Thus, inguinal node assessment cannot be neglected.

Clinical Lymph Node Involvement as a Predictor for Cancer-Specific Survival in Patients with Penile Squamous Cell Cancer

We aimed to identify prognostic predictive factors of patients with penile squamous cell carcinoma (PSCC). This retrospective study reviewed the clinical and pathological data of patients with PSCC at 10 institutions in Japan between January 2008 and December 2019. The primary endpoint was cancer-specific survival (CSS). We also identified useful predictive factors for CSS in patients with PSCC. In total, 64 patients with PSCC were enrolled. At the end of the follow-up period, 15 patients (23.4%) died owing to PSCC and six (9.4%) died owing to other causes. The 2- and 3-year CSS rates were 78.9% and 76.6%, respectively. Using the Kaplan−Meier method, the Eastern Cooperative Oncology Group performance status 0, serum albumin levels ≥4.2 g/dL, hemoglobin levels ≥13.2 g/dL, C-reactive protein levels <0.21 mg/dL, clinical T stage ≤2, clinically negative lymph node (LN) status, and tumor size <30 mm were associated with a significantly better CSS. In the multivariate analysis, the clinically positive LN status was a significant predictive factor for CSS in patients with PSCC. Further prospective large-scale and long-term studies are required to validate our findings.