Radiomics and Clinical Characters Based Gaussian Naive Bayes (GNB) Model for Preoperative Differentiation of Pulmonary Pure Invasive Mucinous Adenocarcinoma From Mixed Mucinous Adenocarcinoma.

Objective: To develop and validate predictive models based on clinical parameters, and radiomic features to distinguish pulmonary pure invasive mucinous adenocarcinoma (pIMA) from mixed mucinous adenocarcinoma (mIMA) before surgery. Method: From January 2017 to December 2022, 193 pIMA and 111 mIMA were retrospectively analyzed at our hospital in this retrospective study. From contrast-enhanced computed tomography, 1037 radiomic features were extracted. The patients were randomly divided into a training group and a test group (n = 213 and 91, respectively) in a 7:3 ratio. The least absolute shrinkage and selection operator algorithm was used to select radiomic features. In this study, 9 machine learning radiomics prediction models were applied. The radiomics score was then calculated based on the best-performing machine learning model adopted. The clinical model was developed using the same machine learning model of radiomics. In the end, a combined model based on clinical factors and radiomics features was developed. The area under the receiver operating characteristic curve (AUC) value and decision curve analysis (DCA) were used to evaluate the clinical usefulness of the prediction model. Results: The combined model established by the Gaussian Naive Bayes machine learning method exhibited the best performance. The AUC of the combined model, clinical model, and radiomics model were 0.81, 0.80, and 0.68 in the training group and 0.91, 0.80, and 0.81 in the test group, respectively. The Brier scores of the combined model were 0.171 and 0.112. The DCA curve also showed that the combined model was beneficial to clinical settings. Conclusion: The combined model integration of radiomics features and clinical parameters may have potential value for the preoperative differentiation of pIMA from mIMA.

CT Radiomics Combined With Clinicopathological Features to Predict Invasive Mucinous Adenocarcinoma in Patients With Lung Adenocarcinoma.

Objective: This study aimed to develop and validate predictive models using clinical parameters, radiomic features, and a combination of both for invasive mucinous adenocarcinoma (IMA) of the lung in patients with lung adenocarcinoma. Method: A total of 173 and 391 patients with IMA and non-IMA, respectively, were retrospectively analyzed from January 2017 to September 2022 in our hospital. Propensity Score Matching was used to match the 2 groups of patients. A total of 1037 radiomic features were extracted from contrast-enhanced computed tomography (CT). The patients were randomly divided into training and test groups at a ratio of 7:3. The least absolute shrinkage and selection operator algorithm was used for radiomic feature selection. Three radiomics prediction models were applied: logistic regression (logistic), support vector machine (SVM), and decision tree. The best-performing model was adopted, and the radiomics score (Radscore) was then computed. A clinical model was developed using logistic regression. Finally, a combined model was established based on a clinical model and a radiomics model. The area under the receiver operating characteristic (ROC) curve (AUC) and decision curve analysis were used to evaluate the predictive value of the developed models. Results: Both clinical and radiomics models established using the logistic method showed the best performance. The Delong test revealed that the combined model was superior to the clinical and radiomics models (P = .018 and .020, respectively). The ROC-AUC (also decision curve analysis) of the combined model was 0.840 and 0.850 in the training and testing groups, respectively, which showed good predictive performance for IMA. The Brier scores for the combined model were 0.161 and 0.154 in the training and testing groups, respectively. Conclusion: The combined model incorporating radiomic CT features and clinical predictors may have the potential to predict IMA in patients with lung cancer.

Radiomics nomogram for preoperative differentiation of pulmonary mucinous adenocarcinoma from tuberculoma in solitary pulmonary solid nodules.

OBJECTIVE: To develop and validate predictive models using clinical parameters, radiomic features and a combination of both for preoperative differentiation of pulmonary nodular mucinous adenocarcinoma (PNMA) from pulmonary tuberculoma (PTB). METHOD: A total of 124 and 53 patients with PNMA and PTB, respectively, were retrospectively analyzed from January 2017 to November 2022 in The Fourth Affiliated Hospital of Hebei Medical University (Ligang et al., A machine learning model based on CT and clinical features to distinguish pulmonary nodular mucinous adenocarcinoma from tuberculoma, 2023). A total of 1037 radiomic features were extracted from contrast-enhanced computed tomography (CT). The patients were randomly divided into a training group and a test group at a ratio of 7:3. The least absolute shrinkage and selection operator (LASSO) algorithm was used for radiomic feature selection. Three radiomics prediction models were applied: logistic regression (LR), support vector machine (SVM) and random forest (RF). The best performing model was adopted, and the radiomics score (Radscore) was then computed. The clinical model was developed using logistic regression. Finally, a combined model was established based on clinical factors and radiomics features. We externally validated the three models in a group of 68 patients (46 and 22 patients with PNMA and PTB, respectively) from Xing Tai People's Hospital (30 and 14 patients with PNMA and PTB, respectively) and The First Hospital of Xing Tai (16 and 8 patients with PNMA and PTB, respectively). The area under the receiver operating characteristic (ROC) curve (AUC) value and decision curve analysis were used to evaluate the predictive value of the developed models. RESULTS: The combined model established by the logistic regression method had the best performance. The ROC-AUC (also a decision curve analysis) of the combined model was 0.940, 0.990 and 0.960 in the training group, test group and external validation group, respectively, and the combined model showed good predictive performance for the differentiation of PNMA from PTB. The Brier scores of the combined model were 0.132 and 0.068 in the training group and test group, respectively. CONCLUSION: The combined model incorporating radiomics features and clinical parameters may have potential value for the preoperative differentiation of PNMA from PTB.

Prognostic Value of White Blood Cells Detected for the First Time After Adjuvant Chemotherapy in Primary Operable Non-Small Cell Lung Cancer.

OBJECTIVE: To investigate the prognostic value of white blood cells detected for the first time after adjuvant chemotherapy in primary operable non-small cell lung cancer. METHODS: From January 2010 to May 2016, data from 208 patients who underwent surgery for non-small cell lung cancer were retrospectively analyzed. RESULTS: A white blood cell count detected for the first time after adjuvant chemotherapy greater than 7.00 was an independent predictor of poor disease-free survival (Hazard ratio: 1.736, 95% confidence interval: 1.267-2.378; P = .001) and overall survival (Hazard ratio: 1.802, 95% confidence interval: 1.305-2.471; P = .000). In a further study, after myelosuppression, survival analysis indicated that the patients with white blood cell counts <2.5 had poorer survival than patients with blood cell counts 2.5 to 4.0, P = .031. When the analysis was stratified by the type of histology, patients with a white blood cell count >7.00 and increased white blood cell after chemotherapy compared to pretreatment had a poorer prognosis than patients with white blood cell ≤7.00 and no increase in white blood cell, P = .000 and P = .002, respectively. We further evaluated the prognosis of the 2 groups in different levels of white blood cell. In the group of patients with white blood cell ≤4.0, patients with chemotherapy cycles ≤2, and >2 showed no differences (Hazard ratio: 2.346, 95% confidence interval: 0.288-19.073, P = .425). In the group of patients with white blood cell of 4.0 to 7.0, the prognosis of patients with chemotherapy cycles ≤2 and patients with chemotherapy cycles >2 showed no difference (Hazard ratio: 0.560, 95% confidence interval: 0.248-1.261, P = .161). In the group of patients with white blood cell >7.0, patients with >2 chemotherapy cycles had a better prognosis than patients with chemotherapy cycles ≤2 (Hazard ratio: 0.573, 95% confidence interval: 0.338-0.971, P = .037) Conclusions: The level of white blood cells detected for the first time after adjuvant chemotherapy is an independent risk factor for non-small cell lung cancer, especially for patients with nonadenocarcinoma. In addition, the level of white blood cells after postoperative adjuvant chemotherapy and its change compared with pretreatment might also provide useful information regarding the best choice of cycles of adjuvant chemotherapy.

Kras mutations increase telomerase activity and targeting telomerase is a promising therapeutic strategy for Kras-mutant NSCLC.

As shortened telomeres inhibit tumor formation and prolong life span in a KrasG12D mouse lung cancer model, we investigated the implications of telomerase in Kras-mutant NSCLC. We found that Kras mutations increased TERT (telomerase reverse transcriptase) mRNA expression and telomerase activity and telomere length in both immortalized bronchial epithelial cells (BEAS-2B) and lung adenocarcinoma cells (Calu-3). MEK inhibition led to reduced TERT expression and telomerase activity. Furthermore, telomerase inhibitor BIBR1532 shortened telomere length and inhibited mutant Kras-induced long-term proliferation, colony formation and migration capabilities of BEAS-2B and Calu-3 cells. Importantly, BIBR1532 sensitized oncogenic Kras expressing Calu-3 cells to chemotherapeutic agents. The Calu-3-KrasG12D xenograft mouse model confirmed that BIBR1532 enhanced the antitumor efficacy of paclitaxel in vivo. In addition, higher TERT expression was seen in Kras-mutant NSCLC than that with wild-type Kras. Our data suggest that Kras mutations increase telomerase activity and telomere length by activating the RAS/MEK pathway, which contributes to an aggressive phenotype of NSCLC. Kras mutations-induced lung tumorigenesis and chemoresistance are attenuated by telomerase inhibition. Targeting telomerase/telomere may be a promising therapeutic strategy for patients with Kras-mutant NSCLC.

Positive expression of pro-opiomelanocortin (POMC) is a novel independent poor prognostic marker in surgically resected non-small cell lung cancer.

This study aims to investigate the expression level of pro-opiomelanocortin (POMC) and its prognostic value in non-small cell lung cancer (NSCLC). Immunohistochemical staining was used to detect the expression level of POMC. Correlations between POMC expression and clinical and pathological characteristics were evaluated with the chi-square test, and the prognostic value was determined with the Kaplan-Meier method and COX proportional hazards model, α < 0.05. Of the samples, 48.0% had positive POMC expression. POMC expression was significantly related to poorly differentiated tumors, N-stage, p-stage, postoperative failure pattern, expression of vimentin, and expression of E-cadherin (P < 0.05). Multivariate analysis revealed that POMC-positive expression was an independent risk factor for disease-free survival (hazard ratio (HR) 1.988, 95% confidence interval (CI) 1.094-3.910, P = 0.024) and overall survival (HR 1.892, 95% CI 1.726-3.709, P = 0.036). The addition of POMC protein expression to the prognostic model using pathological stage markedly improved the prognostic potential, and the area under the ROC increased from 0.691 to 0.775. Further study revealed that patients with POMC-negative expression can benefit more from a regimen of paclitaxel and carboplatin chemotherapy than a regimen of vinorelbine and carboplatin compared to patients with POMC-positive expression. We found that POMC-positive expression is a novel, independent poor prognostic marker in patients with NSCLC. Prospective studies are needed to validate the potential prognostic value of POMC in combination with the current staging system and in consideration of adjuvant chemotherapy.

Prognostic value analysis of mutational and clinicopathological factors in non-small cell lung cancer.

INTRODUCTION: Targeting activating oncogenic driver mutations in lung adenocarcinoma has led to prolonged survival in patients harboring these specific genetic alterations. The prognostic value of these mutations has not yet been elucidated. The prevalence of recently uncovered non-coding somatic mutation in promoter region of TERT gene is also to be validated in lung cancer. The purpose of this study is to show the prevalence, association with clinicalpathological features and prognostic value of these factors. METHODS: In a cohort of patients with non-small cell lung cancer (NSCLC) (n = 174, including 107 lung adenocarcinoma and 67 lung squamous cell carcinoma), EGFR, KRAS, HER2 and BRAF were directly sequenced in lung adeoncarcinoma, ALK fusions were screened using FISH (Fluorescence in situ Hybridization).TERT promoter region was sequenced in all of the 174 NSCLC samples. Associations of these somatic mutations and clinicopathological features, as well as prognostic factors were evaluated. RESULTS: EGFR, KRAS, HER2, BRAF mutation and ALK fusion were mutated in 25.2%, 6.5%, 1.9%, 0.9% and 3.7% of lung adenocarcinomas. No TERT promoter mutation was validated by reverse-sided sequencing. Lung adenocarcinoma with EGFR and KRAS mutations showed no significant difference in Disease-free Survival (DFS) and Overall Survival (OS). Cox Multi-variate analysis revealed that only N stage and HER2 mutation were independent predictors of worse overall survival (HR = 1.653, 95% CI 1.219-2.241, P = 0.001; HR = 12.344, 95% CI 2.615-58.275, P = 0.002). CONCLUSIONS: We have further confirmed that TERT promoter mutation may only exist in a very small fraction of NSCLCs. These results indicate that dividing lung adenocarcinoma into molecular subtypes according to oncogenic driver mutations doesn't predict survival difference of the disease.