Risk prediction model for lung cancer incorporating metabolic markers: Development and internal validation in a Chinese population

Predicting the risk of lung cancer using machine learning: A large study based on UK Biobank

In response to the high incidence and poor prognosis of lung cancer, this study tends to develop a generalizable lung-cancer prediction model by using machine learning to define high-risk groups and realize the early identification and prevention of lung cancer. We included 467,888 participants from UK Biobank, using lung cancer incidence as an outcome variable, including 49 previously known high-risk factors and less studied or unstudied predictors. We developed multivariate prediction models using multiple machine learning models, namely logistic regression, naïve Bayes, random forest, and extreme gradient boosting models. The performance of the models was evaluated by calculating the areas under their receiver operating characteristic curves, Brier loss, log loss, precision, recall, and F1 scores. The Shapley additive explanations interpreter was used to visualize the models. Three were ultimately 4299 cases of lung cancer that were diagnosed in our sample. The model containing all the predictors had good predictive power, and the extreme gradient boosting model had the best performance with an area under curve of 0.998. New important predictive factors for lung cancer were also identified, namely hip circumference, waist circumference, number of cigarettes previously smoked daily, neuroticism score, age, and forced expiratory volume in 1 second. The predictive model established by incorporating novel predictive factors can be of value in the early identification of lung cancer. It may be helpful in stratifying individuals and selecting those at higher risk for inclusion in screening programs.

[Research Progress on Tumor Metabolic Biomarkers in Liquid Biopsy of Lung Cancer]

Liquid biopsy is gradually being applied in the clinical diagnosis and treatment of lung cancer. At present, with the development of metabolomics, more and more metabolic biomarkers are considered as potential sensitive markers reflecting the occurrence and development of tumors. This article summarizes the changes in the main metabolic pathways of lung cancer, including glucose metabolism, amino acid metabolism, lipid metabolism, sphingolipid metabolism, glycerophospholipid metabolism, and purine metabolism. Meanwhile, this article reviews the role of metabolic biomarkers in the early diagnosis of lung cancer, predicting disease progression, and evaluating the efficacy of chemotherapy and immunotherapy, aiming to provide effective biomarkers for tumor diagnosis and treatment.
.

Prognostic significance of globulin/low-density lipoprotein ratio in patients with hepatocellular carcinoma after local ablative therapy: a retrospective cohort study

Background

Low-density lipoprotein (LDL) and globulin (GLOB) have been found to be predictors for some malignant tumors, but their predictive value in hepatocellular carcinoma (HCC) has hardly been elucidated. This study assessed the prognostic significance of GLOB to LDL ratio (GLR) in HCC patients before ablation.

Methods

This study analyzed 312 early-stage HCC patients who were hospitalized and underwent ablative treatment in Beijing You'an Hospital, Capital Medical University, from 1 January 2014 to 1 January 2019. The primary endpoint was the recurrence-free survival (RFS), calculated from treatment initiation to cancer recurrence, whereas the overall survival (OS) was measured from treatment initiation to death or last follow-up. Cox regression analysis was used to assess the GLR independently associated with recurrence and survival. OS and RFS were calculated by Kaplan-Meier analysis and compared between groups using the log rank test. The optimal cut-off value and prognostic role of GLR and other markers were evaluated via the receiver operating characteristic (ROC) curves and the Youden index.

Results

Univariate and multivariate analysis found that the tumor number, tumor size, and GLR were independent risk factors of relapse, whereas etiology, tumor number, tumor size, fibrinogen (Fib), and GLR were related to OS. We classified the patients into groups with high and low levels of GLR based on the optimal cut-off value of GLR identified by ROC curve. The cumulative 1-, 3-, and 5-year RFS rates in the low GLR group were 76.4%, 53.8%, and 43.4% respectively, whereas those in the high GLR group were 71%, 31%, and 22%, respectively (P<0.001). In terms of OS, the low GLR group showed a 1-, 3-, and 5-year OS of 99.5%, 92.0%, and 80.2% respectively, and 98%, 73%, and 63% respectively for the high GLR group (P<0.001). Finally, patients were stratified by GLR and tumor size. The outcomes revealed that patients in group A (GLR <16.54 and tumor size ≤30 mm) showed better prognosis than those in group B (GLR ≥16.54 and tumor size ≤30 mm or GLR <16.54 and tumor size >30 mm) and group C (GLR ≥16.54 and tumor size >30 mm) (P<0.001).

Conclusions

Preoperative GLR ratio has predictive value for patients with HCC who have undergone complete ablation.

Lung cancer risk score for ever and never smokers in China

BACKGROUND

Most lung cancer risk prediction models were developed in European and North-American cohorts of smokers aged ≥ 55 years, while less is known about risk profiles in Asia, especially for never smokers or individuals aged < 50 years. Hence, we aimed to develop and validate a lung cancer risk estimate tool for ever and never smokers across a wide age range.

METHODS

Based on the China Kadoorie Biobank cohort, we first systematically selected the predictors and explored the nonlinear association of predictors with lung cancer risk using restricted cubic splines. Then, we separately developed risk prediction models to construct a lung cancer risk score (LCRS) in 159,715 ever smokers and 336,526 never smokers. The LCRS was further validated in an independent cohort over a median follow-up of 13.6 years, consisting of 14,153 never smokers and 5,890 ever smokers.

RESULTS

A total of 13 and 9 routinely available predictors were identified for ever and never smokers, respectively. Of these predictors, cigarettes per day and quit years showed nonlinear associations with lung cancer risk (Pnon-linear < 0.001). The curve of lung cancer incidence increased rapidly above 20 cigarettes per day and then was relatively flat until approximately 30 cigarettes per day. We also observed that lung cancer risk declined sharply within the first 5 years of quitting, and then continued to decrease but at a slower rate in the subsequent years. The 6-year area under the receiver operating curve for the ever and never smokers' models were respectively 0.778 and 0.733 in the derivation cohort, and 0.774 and 0.759 in the validation cohort. In the validation cohort, the 10-year cumulative incidence of lung cancer was 0.39% and 2.57% for ever smokers with low (< 166.2) and intermediate-high LCRS (≥ 166.2), respectively. Never smokers with a high LCRS (≥ 21.2) had a higher 10-year cumulative incidence rate than those with a low LCRS (< 21.2; 1.05% vs. 0.22%). An online risk evaluation tool (LCKEY; http://ccra.njmu.edu.cn/lckey/web) was developed to facilitate the use of LCRS.

CONCLUSIONS

The LCRS can be an effective risk assessment tool designed for ever and never smokers aged 30 to 80 years.

Development and validation of a nomogram model for lung cancer based on radiomics artificial intelligence score and clinical blood test data

Background

Artificial intelligence (AI) discrimination models using single radioactive variables in recognition algorithms of lung nodules cannot predict lung cancer accurately. Hence, we developed a clinical model that combines AI with blood test variables to predict lung cancer.

Methods

Between 2018 and 2021, 584 individuals (358 patients with lung cancer and 226 individuals with lung nodules other than cancer as control) were enrolled prospectively. Machine learning algorithms including lasso regression and random forest (RF) were used to select variables from blood test data, Logistic regression analysis was used to reconfirm the features to build the nomogram model. The predictive performance was assessed by performing the receiver operating characteristic (ROC) curve analysis as well as calibration, clinical decision and impact curves. A cohort of 48 patients was used to independently validate the model. The subgroup application was analyzed by pathological diagnosis.

Findings

A total of 584 patients were enrolled (358 lung cancers, 61.30%,226 patients for the control group) to establish the model. The integrated model identified eight potential factors including carcinoembryonic antigen (CEA), AI score, Pro-Gastrin Releasing Peptide (ProGRP), cytokeratin 19 fragment antigen21-1(CYFRA211), squamous cell carcinoma antigen(SCC), indirect bilirubin(IBIL), activated partial thromboplastin time(APTT) and age. The area under the curve (AUC) of the nomogram was 0.907 (95% CI, 0.881-0.929). The decision and clinical impact curves showed good predictive accuracy of the model. An AUC of 0.844 (95% CI, 0.710 - 0.932) was obtained for the external validation group.

Conclusion

The nomogram model integrating AI and clinical data can accurately predict lung cancer, especially for the squamous cell carcinoma subtype.

Development and Validation of the Random Forest Model via Combining CT-PET Image Features and Demographic Data for Distant Metastases among Lung Cancer Patients

The work aimed at developing and validating a random forest model of CT-PET image features combined with demographic data to diagnose distant metastases among lung cancer patients. This study involved lung cancer patients from The Cancer Genome Atlas lung adenocarcinoma (TCGA-LUAD) dataset, the lung PET-CT dataset, the lung squamous cell carcinoma (LSCC) dataset, and the National Cancer Institute's Clinical Proteomic Tumor Analysis Consortium lung adenocarcinoma (CPTAC-LUAD) dataset and collected the information on 178 CT, 178 PET, and the patients' age, history of smoking, and gender. We conducted image processing and feature extraction. Finally, 4 computed tomography (CT) image features and 2 positron emission tomography (PET) image features were extracted. Four prediction models based on CT image features, PET image features, and demographic data were developed, and the area under the receiver operating characteristic (ROC) curve was used to evaluate the performance of prediction models. A total of 178 eligible samples were randomly divided into a training set (n = 134) and a testing set (n = 44) at a ratio of 3 : 1, with 2021 as a random number. ROC analyses illustrated that the predictive performance for distant metastases of combining CT-PET image features and demographic data for training and testing were 0.923 (95% confidence interval (CI): 0.873-0.973) and 0.873 (95% CI: 0.757-0.990). In addition, the predictive performance of the combined model in the testing set was significantly better than that of the CT-demographic data model (0.716, 95% CI: 0.531-0.902), PET-demographic data model (0.802, 95% CI: 0.633-0.970), and CT-PET model (0.797, 95% CI: 0.666-0.928). The random forest model via combining CT-PET image features and demographic data could have great performance in predicting distant metastases among lung cancer patients.

Construction and Validation of Early Warning Model of Lung Cancer Based on Machine Learning: A Retrospective Study

Background: This study is a retrospective study. The purpose of this study is to construct and validate an early warning model of lung cancer through machine learning. Methods: The CDKN2A gene expression profile and clinical information were downloaded from The Cancer Genome Atlas (TCGA) database and divided into a tumor group and a normal group (n = 57). The top 5 somatic mutation-related genes were extracted from 567 somatic mutation data downloaded from TCGA database using random forest algorithm. Cox proportional hazard model and nomogram were constructed combining CDKN2A, 5 somatic mutation-related genes, gender, and smoking index. Patients were divided into high-risk and low-risk groups according to risk score. The predictability of the model in the prognosis of lung cancer was estimated by Kaplan-Meier survival analysis and receiver operating characteristics curve. Results: We constructed a prognostic model consisting of 5 somatic mutation-related genes (sphingosine 1-phosphate receptor 1 [S1PR1], dedicator of cytokinesis 7 [DOCK7], DEAD-box helicase 4 [DDX4], laminin subunit beta 3 [LAMB3], and importin 5 [IPO5]), cyclin-dependent kinase inhibitor 2A (CDKN2A), gender, and smoking indicators. The high-risk group had a lower overall survival rate compared to the low-risk group (hazard ratio = 2.14, P = 0 .0323). The area under the curve predicted for 3-year, 5-year, and 10-year survival rates are 0.609, 0.673, and 0.698, respectively. The accuracy, sensitivity, and specificity of the model for predicting the 10-year survival rate of lung cancer are 76.19%, 56.71%, and 86.23%. Conclusion: The lung cancer early warning model and nomogram may provide an essential reference for patients with lung cancer management in the clinic.

The roles of risk model based on the 3-XRCC genes in lung adenocarcinoma progression

Background

The abnormal expression of deoxyribonucleic acid (DNA) repair genes might be the cause of tumor development and resistance of malignant cells to chemotherapeutic drugs. A risk model based on the X-ray repair of cross-complementary (XRCC) genes was constructed to improve the diagnosis and treatment of lung adenocarcinoma (LUAD) patients.

Methods

The expression levels, diagnostic values, and prognostic values of XRCC genes were identified, and the roles and regulatory mechanisms of the risk model based on the XRCC4/5/6 in LUAD progression was explored via The Cancer Genome Atlas (TCGA) and Oncomine databases.

Results

XRCC1/2/3/4/5/6, XRCC7 (PRKDC), and XRCC9 (FANCG) were overexpressed, and had diagnostic value for LUAD. The XRCC genes were involved in DNA repair, and participated in the regulation of non-homologous end-joining, homologous recombination, etc. The overall survival (OS), tumor (T) stage, and survival status of patients were significantly different between the Cluster1 and Cluster2 groups. XRCC4/5/6 were independent risk factors affecting the prognosis of LUAD patients. The risk score was related to the prognosis, sex, clinical stage, T, lymph node (N), and metastasis (M) stage, as well as the survival status of LUAD patients. The clinical stage and risk score were independent risk factors for poor prognosis in LUAD patients. The risk model was involved in RNA degradation, cell cycle, basal transcription factors, DNA replication etc. The risk scores were significantly correlated with the expression levels of TGFBR1, CD160, TNFSF4, TNFRSF14, IL6R, CXCL16, TNFRSF25, TAPBP, CCL16, and CCL14.

Conclusions

The risk model based on the XRCC4/5/6 genes could predict the progression of LUAD patients.

Construction and Validation of a Lung Cancer Risk Prediction Model for Non-Smokers in China

Background

About 15% of lung cancers in men and 53% in women are not attributable to smoking worldwide. The aim was to develop and validate a simple and non-invasive model which could assess and stratify lung cancer risk in non-smokers in China.

Methods

A large-sample size, population-based study was conducted under the framework of the Cancer Screening Program in Urban China (CanSPUC). Data on the lung cancer screening in Henan province, China, from October 2013 to October 2019 were used and randomly divided into the training and validation sets. Related risk factors were identified through multivariable Cox regression analysis, followed by establishment of risk prediction nomogram. Discrimination [area under the curve (AUC)] and calibration were further performed to assess the validation of risk prediction nomogram in the training set, and then validated by the validation set.

Results

A total of 214,764 eligible subjects were included, with a mean age of 55.19 years. Subjects were randomly divided into the training (107,382) and validation (107,382) sets. Elder age, being male, a low education level, family history of lung cancer, history of tuberculosis, and without a history of hyperlipidemia were the independent risk factors for lung cancer. Using these six variables, we plotted 1-year, 3-year, and 5-year lung cancer risk prediction nomogram. The AUC was 0.753, 0.752, and 0.755 for the 1-, 3- and 5-year lung cancer risk in the training set, respectively. In the validation set, the model showed a moderate predictive discrimination, with the AUC was 0.668, 0.678, and 0.685 for the 1-, 3- and 5-year lung cancer risk.

Conclusions

We developed and validated a simple and non-invasive lung cancer risk model in non-smokers. This model can be applied to identify and triage patients at high risk for developing lung cancers in non-smokers.

Computer-aided diagnosis system versus conventional reading system in low-dose (< 2 mSv) computed tomography: comparative study for patients at risk of lung cancer

BACKGROUND

Computer-aided diagnosis in low-dose (≤ 3 mSv) computed tomography (CT) is a potential screening tool for lung nodules, with quality interpretation and less inter-observer variability among readers. Therefore, we aimed to determine the screening potential of CT using a radiation dose that does not exceed 2 mSv.

OBJECTIVE

We aimed to compare the diagnostic parameters of low-dose (< 2 mSv) CT interpretation results using a computer-aided diagnosis system for lung cancer screening with those of a conventional reading system used by radiologists.

DESIGN AND SETTING

We conducted a comparative study of chest CT images for lung cancer screening at three private institutions.

METHODS

A database of low-dose (< 2 mSv) chest CT images of patients at risk of lung cancer was viewed with the conventional reading system (301 patients and 226 nodules) or computer-aided diagnosis system without any subsequent radiologist review (944 patients and 1,048 nodules).

RESULTS

The numbers of detected and solid nodules per patient (both P < 0.0001) were higher using the computer-aided diagnosis system than those using the conventional reading system. The nodule size was reported as the maximum size in any plane in the computer-aided diagnosis system. Higher numbers of patients (102 [11%] versus 20 [7%], P = 0.0345) and nodules (154 [15%] versus 17 [8%], P = 0.0035) were diagnosed with cancer using the computer-aided diagnosis system.

CONCLUSIONS

The computer-aided diagnosis system facilitates the diagnosis of cancerous nodules, especially solid nodules, in low-dose (< 2 mSv) CT among patients at risk for lung cancer.

Lung cancer pathogenesis and poor response to therapy were dependent on driver oncogenic mutations

AIMS

Lung cancer was the most fatal malignancy, dominated the cancer related mortality list for years, and we tried to distinguish the lung adenocarcinoma patients at higher risk from those bearing lower therapy resistance and recurrence risk.

MATERIALS

Patients information from clinical Sequencing Cohorts and from the Regional Medical Center of the Middle-West China were included. The whole-exome sequencing was analyzed for risk evaluation.

KEY FINDINGS

We found that Smoking stimulated the oncogenic genes mutations, and the most frequently mutated genes of EGFR, KRAS, and TP53 (E/K/P) were identified. Different N stage affected the survival prognosis of patients bearing E/K/P mutations, but the T stage and AJCC stage did not. Radiation failed to prolong survival of phase II/III patients who didn't receive surgery. In those received surgery, radiation also failed to prolong survival of phase II/III patients. Radiation did not improve the prognosis in patients bearing E/K/P mutation burdens, whose differences were identified in gender or smoking-history classified groups.

SIGNIFICANCE

Smoking status and history contributed to oncogenic mutation burdens associated therapy resistance, and the aggressive treatment, especially to radiation, may lead to worse therapy response to current and past smoking behavior.

Risk prediction model for lung cancer incorporating metabolic markers: Development and internal validation in a Chinese population

BACKGROUND

Low-dose computed tomography screening has been proved to reduce lung cancer mortality, however, the issues of high false-positive rate and overdiagnosis remain unsolved. Risk prediction models for lung cancer that could accurately identify high-risk populations may help to increase efficiency. We thus sought to develop a risk prediction model for lung cancer incorporating epidemiological and metabolic markers in a Chinese population.

METHODS

During 2006 and 2015, a total of 122 497 people were observed prospectively for lung cancer incidence with the total person-years of 976 663. Stepwise multivariable-adjusted logistic regressions with P_entry  = .15 and P_stay  = .20 were conducted to select the candidate variables including demographics and metabolic markers such as high-sensitivity C-reactive protein (hsCRP) and low-density lipoprotein cholesterol (LDL-C) into the prediction model. We used the C-statistic to evaluate discrimination, and Hosmer-Lemeshow tests for calibration. Tenfold cross-validation was conducted for internal validation to assess the model's stability.

RESULTS

A total of 984 lung cancer cases were identified during the follow-up. The epidemiological model including age, gender, smoking status, alcohol intake status, coal dust exposure status, and body mass index generated a C-statistic of 0.731. The full model additionally included hsCRP and LDL-C showed significantly better discrimination (C-statistic = 0.735, P = .033). In stratified analysis, the full model showed better predictive power in terms of C-statistic in younger participants (<50 years, 0.709), females (0.726), and former or current smokers (0.742). The model calibrated well across the deciles of predicted risk in both the overall population (P_HL  = .689) and all subgroups.

CONCLUSIONS

We developed and internally validated an easy-to-use risk prediction model for lung cancer among the Chinese population that could provide guidance for screening and surveillance.