Survival outcomes of surgery in patients with pulmonary large-cell neuroendocrine carcinoma: a retrospective single-institution analysis and literature review

Implementing machine learning to predict survival outcomes in patients with resected pulmonary large cell neuroendocrine carcinoma

BACKGROUND

The post-surgical prognosis for Pulmonary Large Cell Neuroendocrine Carcinoma (PLCNEC) patients remains largely unexplored. Developing a precise prognostic model is vital to assist clinicians in patient counseling and creating effective treatment strategies.

RESEARCH DESIGN AND METHODS

This retrospective study utilized the Surveillance, Epidemiology, and End Results database from 2000 to 2018 to identify key prognostic features for Overall Survival (OS) in PLCNEC using Boruta analysis. Predictive models employing XGBoost, Random Forest, Decision Trees, Elastic Net, and Support Vector Machine were constructed and evaluated based on Area Under the Receiver Operating Characteristic Curve (AUC), calibration plots, Brier scores, and Decision Curve Analysis (DCA).

RESULTS

Analysis of 604 patients revealed eight significant predictors of OS. The Random Forest model outperformed others, with AUC values of 0.765 and 0.756 for 3 and 5-year survival predictions in the training set, and 0.739 and 0.706 in the validation set, respectively. Its superior validation cohort performance was confirmed by its AUC, calibration, and DCA metrics.

CONCLUSIONS

This study introduces a novel machine learning-based prognostic model with a supportive web-based platform, offering valuable tools for healthcare professionals. These advancements facilitate more personalized clinical decision-making for PLCNEC patients following primary tumor resection.

Clinical Challenges and Management Strategies in Pulmonary Large-Cell Neuroendocrine Carcinoma

Pulmonary large-cell neuroendocrine carcinoma (LCNEC) is a rare but aggressive malignancy of the lung. Its nonspecific presentation and propensity for severe disease at the time of diagnosis create challenges in treatment. We report a case of an asymptomatic 61-year-old female who was incidentally found to have a pulmonary nodule after a fall. Upon further workup, she was found to have an aggressive LCNEC. The patient underwent a robotic-assisted left upper lobectomy, which was complicated by left lower lobe bronchus kinking and post-obstructive atelectasis, warranting further management by thoracic surgery. The patient additionally underwent video-assisted thoracoscopic surgery (VATS), open thoracotomy, pneumopexy, and bronchial stenting. This case highlights the need for strategies for early detection in at-risk populations. A multidisciplinary approach, which may involve both medical and surgical subspecialties, is essential in the management of this complex disease from the time of diagnosis to follow-up postoperatively to achieve the best clinical outcome.

Prognostic factors and nomogram for pulmonary resected high-grade neuroendocrine carcinomas: a 20-year single institutional real-world experience

BACKGROUND

Pulmonary high-grade neuroendocrine carcinomas(pHGNEC) encompassing small cell lung cancer (SCLC) and large cell neuroendocrine carcinoma (LCNEC) are clinically aggressive tumors with poor prognosis. The role of surgery and prognostic factors guiding management remain unclear. We aimed to analyze prognosis following resection and identify predictive variables.

METHODS

This retrospective study analyzed 259 patients undergoing pHGNEC resection from 2001-2023. Overall survival (OS) and disease-free survival (DFS) were evaluated using Kaplan-Meier curves. Prognostic factors were assessed with Cox regression and visualized using nomogram tools.

RESULTS

Minimally invasive surgery was associated with better OS (p = 0.001) and DFS (p = 0.001). Higher T stage predicted worse OS (T2 p = 0.044, T4 p = 0.007) and DFS (T2 p = 0.020, T4 p = 0.004). Advanced TNM stage III (OS p = 0.018; DFS p = 0.015) and IV (OS p < 0.001; DFS p < 0.001) also correlated with poorer prognosis. In the SCLC subgroup, elevated preoperative CEA independently predicted worse OS (p = 0.012) and DFS (p = 0.004). T4 disease (OS p < 0.001; DFS p = 0.002) and advanced TNM staging (stage III OS p = 0.043; DFS p = 0.045; stage IV OS p < 0.001, DFS p < 0.001) were associated with worse outcomes. In LCNEC patients, VATS resection improved OS (p = 0.048) and DFS (p = 0.027) despite conversion. Prior malignancy predicted worse OS (p < 0.001). Advanced TNM disease (stage III OS p = 0.047; stage IV OS p = 0.003, DFS p = 0.005) were also negative prognostic factors. The prognostic nomogram incorporating above variables effectively stratified risk. Calibration plots revealed good correlation between predicted and actual survival.

CONCLUSIONS

We identified minimally invasive surgery, early TNM stage, younger age, and normal preoperative CEA as positive prognostic factors following pHGNEC resection. Our study provides an applicable prognostic nomogram to facilitate personalized pHGNEC management.

A rare report of a metastatic lung large-cell neuroendocrine carcinoma in palatine tonsil

INTRODUCTION

Neuroendocrine carcinoma is a rare form of cancer originating from neuroendocrine cells, with the lungs being the most common site of occurrence. These tumors have the potential to metastasize to the head and neck region.

CASE REPORT

A 57-year-old man, with a smoking history of 74 pack-years, presented with complaints of hoarseness, dry cough, dysphagia, and significant weight loss over a two-month period. During oral examination, a submucosal nodule in the left palatine tonsil was discovered. Histological analysis confirmed a poorly differentiated tumor consisting of large cells with nuclear pleomorphism and abundant cytoplasm. The tumor tested positive for CD56, chromogranin, synaptophysin, and EMA. Further imaging revealed a substantial endobronchial lesion in the upper segment of the left lower lobe. Biopsy results from this lesion were morphologically and immunohistochemically consistent with those from the oral lesion. A diagnosis of metastatic large-cell neuroendocrine carcinoma originating from the lung and involving the oral mucosa was established.

CONCLUSION

This case highlights the metastatic potential of pulmonary neuroendocrine carcinoma and its occurrence in atypical dissemination sites. Additionally, our findings underscore the importance of early detection of oral metastases to ensure accurate diagnosis and expedite appropriate treatment.

Lung Large Cell Neuroendocrine Carcinoma: A Population-Based Retrospective Cohort Study

BACKGROUNDS

Pulmonary large cell neuroendocrine carcinoma (LCNEC) is a rarely high-grade neuroendocrine carcinoma of the lung with features of both small cell and non-small cell lung cancer. In this study, we aim to construct a prognostic nomogram that integrates the clinical features and treatment options to predict disease-specific survival (DSS).

METHODS

A total of 713 patients diagnosed with LCNEC were from the US National Cancer Institute's Surveillance Epidemiology and End Results (SEER) registry between 2010-2016. Cox proportional hazards analysis was conducted to choose the significant predictors of DSS. External validation was performed using 77 patients with LCNEC in the West China Hospital Sichuan University between 2010-2018. The predictive accuracy and discriminative capability were estimated by the concordance index (C-index), calibration curve, and receiver operating characteristic (ROC) curve. The clinical applicability of the nomogram was verified through the decision curve analysis (DCA). Additionally, we conducted a subgroup analysis of data available in the external cohort that may impact prognosis but was not recorded in the SEER database.

RESULTS

Six independent risk factors for DSS were identified and integrated into the nomogram. The nomogram achieved good C- indexes of 0.803 and 0.767 in the training and validation group, respectively. Moreover, the calibration curves for the probability of survival showed good agreement between prediction by nomogram and actual observation in 1-, 3- and 5-year DSS. The ROC curves demonstrated the prediction accuracy of the established nomogram (all Area Under Curve (AUC) > 0.8). DCA exhibited the favorable clinical applicability of the nomogram in the prediction of LCNEC survival. A risk classification system was built which could perfectly classify LCNEC patients into high-, medium- and low-risk groups (p < 0.001). The survival analysis conducted on the West China Hospital cohort indicated that whole brain radiation therapy (WBRT), prophylactic cranial irradiation (PCI), surgical procedures, tumor grade, Ki-67, and PD-L1 expression were not significantly associated with DSS.

CONCLUSION

This study has effectively developed a prognostic nomogram and a corresponding risk stratification system, which demonstrate promising potential for predicting the DSS of patients with LCNEC.

Recurrence-Free Survival in Early and Locally Advanced Large Cell Neuroendocrine Carcinoma of the Lung after Complete Tumor Resection

BACKGROUND

Large Cell Neuroendocrine Carcinoma (LCNEC) is a rare subtype of lung cancer with poor clinical outcomes. Data on recurrence-free survival (RFS) in early and locally advanced pure LCNEC after complete resection (R0) are lacking. This study aims to evaluate clinical outcomes in this subgroup of patients and to identify potential prognostic markers.

METHODS

Retrospective multicenter study including patients with pure LCNEC stage I-III and R0 resection. Clinicopathological characteristics, RFS, and disease-specific survival (DSS) were evaluated. Univariate and multivariate analyses were performed.

RESULTS

39 patients (M:F = 26:13), with a median age of 64 years (44-83), were included. Lobectomy (69.2%), bilobectomy (5.1%), pneumonectomy (18%), and wedge resection (7.7%) were performed mostly associated with lymphadenectomy. Adjuvant therapy included platinum-based chemotherapy and/or radiotherapy in 58.9% of cases. After a median follow-up of 44 (4-169) months, the median RFS was 39 months with 1-, 2- and 5-year RFS rates of 60.0%, 54.6%, and 44.9%, respectively. Median DSS was 72 months with a 1-, 2- and 5-year rate of 86.8, 75.9, and 57.4%, respectively. At multivariate analysis, age (cut-off 65 years old) and pN status were independent prognostic factors for both RFS (HR = 4.19, 95%CI = 1.46-12.07, p = 0.008 and HR = 13.56, 95%CI 2.45-74.89, p = 0.003, respectively) and DSS (HR = 9.30, 95%CI 2.23-38.83, p = 0.002 and HR = 11.88, 95%CI 2.28-61.84, p = 0.003, respectively).

CONCLUSION

After R0 resection of LCNEC, half of the patients recurred mostly within the first two years of follow-up. Age and lymph node metastasis could help to stratify patients for adjuvant therapy.

SOX11 is a sensitive and specific marker for pulmonary high-grade neuroendocrine tumors

BACKGROUND

Synaptophysin (SYN), chromogranin A (CGA), CD56 and insulinoma-associated protein 1 (INSM1) are proposed neuroendocrine (NE) markers used for diagnosis of pulmonary NE tumors. These NE markers have been identified in subsets of non-NE tumors requiring differential diagnosis, thus we sought to explore new NE markers.

METHODS

We evaluated the immunohistochemical expression of SOX11, a transcription factor involved in neurogenesis, in pulmonary NE tumors and large cell carcinomas (LCCs).

RESULTS

We found that SOX11 showed a sensitivity similar to INSM1 and CGA, and less than SYN and CD56 in small cell lung carcinomas (SCLCs) and large cell neuroendocrine carcinomas (LCNECs). While SOX11 is more specific than the other four markers for diagnosis of high-grade neuroendocrine carcinomas (HG-NECs) because 1) None of LCCs (0/63), the most challenging non-NE tumor type for differential diagnosis due to overlapped morphology with LCNECs displayed SOX11 positivity. While expression of at least one of SYN, CGA, CD56 or INSM1 was identified in approximately 60% (18/30) of LCCs. 2) SOX11 was only expressed in 1 of 37 carcinoid tumors in contrast to diffuse expression of SYN, CGA, CD56 and INSM1. In HG-NECs, we noticed that SOX11 was a good complementary marker for SCLC diagnosis as it was positive in 7 of 18 SYN^-/CGA^-/CD56^- SCLCs and 3 of 8 SYN^-/CGA^-/CD56^-/INSM1^- SCLCs, and SOX11 positivity in 4 of 6 SYN^-/CGA^-/CD56^- cases previously diagnosed as LCCs with NE morphology provides additional evidence of NE differentiation for reclassification into LCNECs, which was further confirmed by electromicroscopical identification of neurosecretory granules. We also found SOX11 expression cannot predict the prognosis in patients with HG-NECs.

CONCLUSIONS

Therefore, SOX11 is a useful complementary transcriptional NE marker for diagnosis and differential diagnosis of SCLC and LCNEC.