Development and Validation of an Individualized Nomogram for Predicting Overall Survival in Patients With Typical Lung Carcinoid Tumors

Development and evaluation of a multivariable prediction model for overall survival in advanced stage pulmonary carcinoid using machine learning

BACKGROUND

Evidence is limited on whether patients with advanced pulmonary carcinoid (APC) benefit from comprehensive pulmonary resection (CPR), chemotherapy, or radiotherapy. Existing prognostic models for APC are limited and do not guide treatment selection. This study aims to develop and evaluate a multivariable machine learning model to predict overall survival in APC patients and provide a web-based prognostic tool.

METHODS

Clinical data of APC patients were obtained from SEER database. Propensity score matching reduced retrospective study bias. Kaplan-Meier analysis evaluated survival differences between CPR vs. nonCPR, chemotherapy (Chem) vs. no chemotherapy (nonChem), and radiotherapy (Radio) vs. no radiotherapy (nonRadio). Univariate and multivariate Cox regression identified survival-associated variables. Using these clinical variables, 91 machine learning models were developed to predict APC survival, and the best model led to a web-based prognostic tool.

RESULTS

Among 1077 APC patients, 37.0 % underwent CPR, 30.2 % received chemotherapy, and 19.9 % received radiotherapy. After matching, overall survival was significantly improved in the CPR compared to the nonCPR. However, there were no significant differences in survival between the Chem and nonChem groups or between the Radio and nonRadio groups. Eight out of 13 clinical variables were significant prognostic variables. Models with eight variables reached a mean C-index of 0.770 and a 5-year AUC of 0.835. Using all 13 variables, a C-index of 0.785 and an AUC of 0.850 was achieved. An online tool (https://apcmodel.shinyapps.io/APCsp/) displays survival curves for different treatments.

CONCLUSION

The developed prognostic model enables individualized survival predictions and supports evidence-based treatment decisions for APC patients.

Incidence and prognostic nomogram for resected non-small cell neuroendocrine tumor: A population-based respective study in China and the SEER database

Background

Pulmonary neuroendocrine tumors, including small cell lung cancer (SCLC) and non-small cell neuroendocrine tumor (NSCLC-NET), have obvious heterogeneity. The comparison between SCLC and NSCLC-NET, and prognostic nomogram of resected NSCLC-NET have not been performed.

Methods

We retrieved data from SEER database. The incidence and prognostic factors were compared between SCLC and NSCLC-NET. By Cox regression, we constructed prognostic nomogram of resected NSCLC-NET. The nomogram was evaluated by ROC, calibration plot and decision curve analysis (DCA) and compared with 8th TNM staging system. A Chinese cohort was used for external validation.

Results

The age-adjusted incidence of SCLC declined after 1991 but the incidence of NSCLC-NET continuously rose. Patients with typical carcinoid had the best prognosis in both overall survival and lung cancer specific survival, followed by atypical carcinoid, large cell neuroendocrine tumor and SCLC after operation. Patients receiving sleeve resection in NSCLC-NET had longer survival but segmental resection was more recommended in SCLC. High-smoking index was associated with worse overall survival in both SCLC and NSCLC-NET. Histological subtype, age, surgery type, N, M stage and chemotherapy were independent prognostic factors and used to construct prognostic nomogram of resected NSCLC-NET. The nomogram performed well with good discrimination, calibration and clinical usefulness, which was validated by a Chinese cohort (1, 3, 5-year AUC: SEER cohort 0.873, 0.901, 0.875; Chinese cohort 0.867, 0.892, 0.874). Compared to the 8th staging system, the nomogram had higher C-index (0.87 vs 0.728, P < 0.001), clinical usefulness, increasing AUC value over time and improved 68%.

Conclusion

The prognostic nomogram of resected NSCLC-NET performed better than the 8th TNM staging system. It may have certain value in risk stratification and survival prediction of patients with resected NSCLC-NET and help clinicians to take measures for high-risk patients in advance.

Does Examined Lymph Node Count Influence Survival in Surgically Resected Early‑stage Pulmonary Typical Carcinoid Tumors?

OBJECTIVES

We aimed to evaluate the prognostic impact of the number of examined lymph nodes (ELNs) in resected early‑stage pulmonary typical carcinoid tumors (TC).

METHODS

Patients who underwent sublobar resection and lobectomy for stage T1N0M0 TC between 2004 and 2016 were identified from the Surveillance, Epidemiology, and End Results database and enrolled in the ELNs≥4 or ELNs<4 groups (optimal cutoff using X-tile). Propensity score matching balanced baseline intergroup characteristics. Kaplan-Meier curve and log-rank test were used to calculate and compare overall survival (OS) rates. Cox proportional hazard model analysis was used to identify independent prognostic factors.

RESULTS

Among 2234 participants, 961 (43.02%) and 1273 (56.98%) had ELNs <4 and ≥4, respectively. The 5-year OS was significantly higher in the ELNs≥4, compared with ELNs<4, group, both before and after propensity score matching (95.41% vs. 89.71%, P<0.001 and 95.24% vs. 90.28%, P=0.004), respectively. Surgical subgroup analysis confirmed this survival trend in the lobectomy and sublobar resection groups. Tumor size-based subgroup analysis revealed superior OS with ELNs≥4 than ELNs<4 for tumors measuring 1.1-3.0 cm but not for tumors <1.0 cm. Multivariate Cox analysis showed that ELN≥4 contributed to improved OS.

CONCLUSIONS

The higher the ELNs, the greater the long-term survival rate in patients with early‑stage TC. Therefore, we recommend at least 4 ELNs as the cutoff value for evaluating the prognosis of early‑stage TCs, especially for patients with a tumor size of 1.1 to 3.0 cm.

Construction and validation of nomograms based on the log odds of positive lymph nodes to predict the prognosis of lung neuroendocrine tumors

Background

This research aimed to investigate the predictive performance of log odds of positive lymph nodes (LODDS) for the long-term prognosis of patients with node-positive lung neuroendocrine tumors (LNETs).

Methods

We collected 506 eligible patients with resected N1/N2 classification LNETs from the Surveillance, Epidemiology, and End Results (SEER) database between 2004 and 2015. The study cohort was split into derivation cohort (n=300) and external validation cohort (n=206) based on different geographic regions. Nomograms were constructed based on the derivation cohort and validated using the external validation cohort to predict the 1-, 3-, and 5-year cancer-specific survival (CSS) and overall survival (OS) of patients with LNETs. The accuracy and clinical practicability of nomograms were tested by Harrell’s concordance index (C-index), integrated discrimination improvement (IDI), net reclassification improvement (NRI), calibration plots, and decision curve analyses.

Results

The Cox proportional-hazards model showed the high LODDS group (-0.79≤LODDS) had significantly higher mortality compared to those in the low LODDS group (LODDS<-0.79) for both CSS and OS. In addition, age at diagnosis, sex, histotype, type of surgery, radiotherapy, and chemotherapy were also chosen as predictors in Cox regression analyses using stepwise Akaike information criterion method and included in the nomograms. The values of C-index, NRI, and IDI proved that the established nomograms were better than the conventional eighth edition of the TNM staging system. The calibration plots for predictions of the 1-, 3-, and 5-year CSS/OS were in excellent agreement. Decision curve analyses showed that the nomograms had value in terms of clinical application.

Conclusions

We created visualized nomograms for CSS and OS of LNET patients, facilitating clinicians to bring individually tailored risk assessment and therapy.

Sex-based differences in the outcomes of patients with lung carcinoids

Objective: To assess the impact of sex on the outcomes of patients with well-differentiated lung neuroendocrine neoplasms in a real-world setting. Methods: The Surveillance, Epidemiology and End Results Research Plus database (2000-2018) was accessed, and patients with a diagnosis of typical or atypical carcinoid of the lung were reviewed. Trends in age-standardized rates (per 100,000) of the incidence of lung carcinoid tumors were reviewed among male and female patients as well as the overall population, and annual percent change (APC) was determined for the three groups. Multivariate Cox regression analysis was then used to assess the factors associated with overall and cancer-specific survival. Results: Among all patients, APC (2000-2018) for lung carcinoid diagnosis was 2.9 (95% CI: 2.4-3.5). Among male patients, APC (2000-2018) for lung carcinoid diagnosis was 1.8 (95% CI: 1.2-2.5). By contrast, among female patients, APC (2000-2018) for lung carcinoid diagnosis was 3.4 (95% CI: 2.8-4.1). Based on Kaplan-Meier survival estimates, female sex was associated with better overall survival compared with male sex (p < 0.001). Based on multivariate Cox regression analysis, the following factors were associated with worse cancer-specific survival: older age (hazard ratio [HR]: 1.036; 95% CI: 1.031-1.041), atypical carcinoid histology (HR: 3.10; 95% CI: 2.71-3.56), stage (distant vs localized stage HR: 4.05; 95% CI: 3.48-4.71), sex (male vs female sex HR: 1.76; 95% CI: 1.56-1.99) and no surgical treatment (HR: 3.77; 95% CI: 3.22-4.42). Conclusion: Female patients with lung carcinoid tumors have better overall survival compared with male patients, particularly among patients with typical carcinoid tumors.

Long-term survival analysis of sublobar resection versus lobectomy for older patients with early-stage pulmonary carcinoid tumour: a database-based propensity score-matched study

BACKGROUND

The optimal extent of surgery for older patients with early-stage pulmonary carcinoid tumour (PC) remains controversial.

AIMS

To compare prognostic differences between sublobar resection versus lobectomy in older patients with early-stage PC.

METHODS

The SEER database was searched for stage T1N0M0 PC patients aged ≥ 65 years who underwent lobectomy or sublobar resection from 2000 to 2017. Propensity score matching (PSM) was used to determine intergroup covariate differences. Kaplan-Meier curves and the log-rank test were used for intergroup comparison of overall survival (OS). A Cox proportional hazard model was used to evaluate independent risk factors.

RESULTS

Among 1023 participants, 650 and 373 underwent lobectomy and sublobar resection, respectively. Before PSM, the 5- and 10-year OS in the sublobar resection group were lower than that of the lobectomy group (5-year OS 84.12% vs. 91.16%; 10-year OS 57.43% vs. 64.77%; p = 0.014); after PSM, no significant prognostic difference existed between lobectomy and sublobar resection (5-year OS 88.17% vs. 89.23%; 10-year OS 58.32% vs. 62.75%; p = 0.811). Subgroup analysis included tumour size, age, number of lymph nodes examined and histological type, and showed no statistically significant survival differences between the lobectomy and sublobar resection groups. Multivariable Cox analysis indicated that age ≥ 77 years, male sex, inadequate lymph node assessment (< 7), and atypical carcinoid were associated with reduced OS.

CONCLUSION

Sublobar resection showed a similar long-term survival rate for early-stage PC patients aged ≥ 65 years as with lobectomy, thereby providing a basis for the selection of surgical methods for PC.

Development and Validation of a Prognostic Model to Predict Overall Survival for Lung Adenocarcinoma: A Population-Based Study From the SEER Database and the Chinese Multicenter Lung Cancer Database

Background: Lung adenocarcinoma (LUAD) is the most common subtype of non-small-cell lung cancer (NSCLC). The aim of our study was to determine prognostic risk factors and establish a novel nomogram for lung adenocarcinoma patients. Methods: This retrospective cohort study is based on the Surveillance, Epidemiology, and End Results (SEER) database and the Chinese multicenter lung cancer database. We selected 22,368 eligible LUAD patients diagnosed between 2010 and 2015 from the SEER database and screened them based on the inclusion and exclusion criteria. Subsequently, the patients were randomly divided into the training cohort (n = 15,657) and the testing cohort (n = 6711), with a ratio of 7:3. Meanwhile, 736 eligible LUAD patients from the Chinese multicenter lung cancer database diagnosed between 2011 and 2021 were considered as the validation cohort. Results: We established a nomogram based on each independent prognostic factor analysis for 1-, 3-, and 5-year overall survival (OS) . For the training cohort, the area under the curves (AUCs) for predicting the 1-, 3-, and 5-year OS were 0.806, 0.856, and 0.886. For the testing cohort, AUCs for predicting the 1-, 3-, and 5-year OS were 0.804, 0.849, and 0.873. For the validation cohort, AUCs for predicting the 1-, 3-, and 5-year OS were 0.86, 0.874, and 0.861. The calibration curves were observed to be closer to the ideal 45° dotted line with regard to 1-, 3-, and 5-year OS in the training cohort, the testing cohort, and the validation cohort. The decision curve analysis (DCA) plots indicated that the established nomogram had greater net benefits in comparison with the Tumor-Node-Metastasis (TNM) staging system for predicting 1-, 3-, and 5-year OS of lung adenocarcinoma patients. The Kaplan-Meier curves indicated that patients' survival in the low-risk group was better than that in the high-risk group (P < .001). Conclusion: The nomogram performed very well with excellent predictive ability in both the US population and the Chinese population.

Prognostic nomogram for predicting long-term survival in bronchopulmonary carcinoid tumor patients receiving resection

Background

We analyzed bronchopulmonary carcinoid tumor (BPC) patients receiving resection from the Surveillance, Epidemiology, and End Results (SEER) database to identify the predictive factors of their survival. Then, we developed and validated nomograms to predict overall survival (OS) and cancer-specific survival (CSS) in BPC patients.

Methods

BPC patients registered in the SEER database were included. They were divided into a training set and an internal validation set (7:3). BPC patients from our center were included as an external validation set. Independent prognostic factors identified by a Cox regression model in the training set were used to construct nomograms to predict survival. Discrimination and calibration plots were used to evaluate the predictive accuracy of the nomograms. The nomograms were evaluated in both the internal and the external validation datasets.

Results

Age, pathological type, and N stage were identified as independent prognostic factors of OS and CSS by Cox analyses (all P<0.05). Tumor size ≥2.5 cm (P=0.045) was an independent factor for unfavorable CSS. Based on these variables, nomograms were constructed. All concordance indexes of the training set, internal validation set, and external validation set indicated that the nomograms had the preferable discriminatory ability. The calibration plots for predictions of the 1-, 3-, and 5-year OS and CSS were in excellent agreement.

Conclusions

Age, pathological type, N stage, and tumor size were independent predictive factors of prognosis in BPC patients receiving resection. These nomograms could serve as effective and accurate tools for the prognostic evaluation of patients with BPCs.

Lung carcinoid tumors with Diffuse Idiopathic Pulmonary NeuroEndocrine Cell Hyperplasia (DIPNECH) exhibit pejorative pathological features

INTRODUCTION

Diffuse Idiopathic Pulmonary NeuroEndocrine Cell Hyperplasia (DIPNECH) is a rare disease often associated with carcinoid tumors. We aimed at evaluating the impact of DIPNECH on characteristics and prognosis of patients who underwent radical treatment of pulmonary carcinoid tumors.

MATERIAL AND METHODS

We reviewed all patients operated on for curative-intent resection of carcinoid tumor in our department from 2001 to 2020. Cases exhibiting both pathological and radiological features of DIPNECH, as assessed by respective thoracic expert physicians, were analyzed separately.

RESULTS

172 cases of resected carcinoid tumors were identified, including 25 (14.5 %) harboring pathological criteria of DIPNECH and radiologic features like mosaic attenuation (92.0 %), multiple nodules < 5 mm (76.0 %), and mucoid impactions (32 %). In DIPNECH patients, major pulmonary resections were usually performed (92.0 %) and resected tumors were mostly classified as pT1 (92 %). Mean Ki67 staining was 3.7 ± 5.2 %. The early postoperative period was mostly uneventful (96.0 %) and 5-year survival was 92.9 ± 6.9 %. Compared to non-DIPNECH cases, we found that patients were older (mean 65.6 ± 9.3 versus 54.1 ± 17.9, p = 0.002), more frequently female (84.0 % versus 56.5 %, p = 0.009), and exhibiting diabetes mellitus (45.8 % versus 18.5 %, p < 0.001) or hypertension (45.8 % versus 24.1 %, p = 0.039). The rate of atypical carcinoid tumors was significantly higher in DIPNECH patients (40.0 % versus 19.9 %, p = 0.027), as well as rate of mediastinal lymph-nodes involvement (pN2+) (36.0 % versus 4.1 %, p < 0.001). At multivariate analysis, only DIPNECH pattern and atypical histology were independent factors of pN2 invasion which was the only predictor of poorer prognosis on Log-Rank test.

CONCLUSION

Carcinoid tumors with proven DIPNECH are associated with negative pathological features and may deserve a dedicated perioperative management.

Predictive Indicators of Survival in Patients With Surgically Resected Lung Carcinoid Tumors at a Greek Medical Center

Introduction

Lung carcinoid tumors are neuroendocrine neoplasms, less frequent than other lung tumors. They are subdivided into typical carcinoids (TC) and atypical carcinoids (AC), according to the rate of mitosis and the presence of necrosis. Lung carcinoids are often asymptomatic and only discovered incidentally. They may also present with cough, wheezing, asthma, and chronic obstructive pulmonary disease, chest pain, and hemoptysis depending on the location of the tumor and, less commonly, present with carcinoid syndrome. In our study, we describe the clinical and pathological features of patients with surgically resected lung carcinoids at our institution over a period of 14 years. We also examine if these features, including age, gender, tumor size, type of carcinoid, stage, nodal involvement, and Ki-67 expression are associated with patients' survival.

Materials and methods

We retrospectively reviewed patients that underwent surgery with a final histologic diagnosis of a pulmonary carcinoid tumor from March 2005 to March 2019. The evaluation included history, physical examination, chest radiographs, computerized tomography of the chest, upper abdomen, and brain, and bone scintiscan. All specimens resected during the surgical procedures were sent for pathological examination, including mediastinal and hilar lymph nodes. The patients' age, gender, tumor size, type of carcinoid, nodal involvement, stage, and Ki-67 expression were recorded and correlated to the patients' survival rates.

Results

The study included 108 patients - 52 males and 56 females - with a mean age of 51.5 years (range 11-80 years). Atypical carcinoid was the diagnosis in 28 patients (16 males and 12 females) and 80 patients had the diagnosis of typical carcinoid (36 males and 44 females). Tumor size was ≤3.7 cm in 84 patients (68 with TC and 16 with AC) and >3.7 cm in 22 patients (12 with TC and 10 with AC). Sixteen patients had nodal deposits, 12 in N1 nodes and four in N2 nodes. Eighty patients were classified in stage I, 18 patients in stage II, and 10 patients in stage III. None of the patients had distant metastases. The Ki-67 proliferation index was examined in 84 specimens and Ki-67 was <2.5 in 50 patients and ≥2.5 in 34 patients. Of the 108 patients, eight died, all with disease-related death. According to the Cox regression univariate analysis, four factors were correlated to shorter survival: atypical histology, tumor size >3.7 cm, nodal involvement, and advanced stage

Conclusions

In conclusion, we found that histological type, tumor size, nodal involvement, and stage are associated with survival in patients with surgically resected lung carcinoids without distant metastases. Other parameters, such as age at operation, gender, and Ki-67 index, did not have a role in survival in these patients according to the Cox regression univariate analysis.