Lung Cancer Screening, Version 3.2018, NCCN Clinical Practice Guidelines in Oncology

Cost-Effectiveness of Low-Dose Computed Tomography Screenings for Lung Cancer in High-Risk Populations: A Markov Model

Background

Domestic and foreign studies on lung cancer have been oriented to the medical efficacy of low-dose computed tomography (LDCT), but there is a lack of studies on the costs, value and cost-effectiveness of the treatment. There is a scarcity of conclusive evidence regarding the cost-effectiveness of LDCT within the specific context of Taiwan. This study is designed to address this gap by conducting a comprehensive analysis of the cost-effectiveness of LDCT and chest X-ray (CXR) as screening methods for lung cancer.

Methods

Markov decision model simulation was used to estimate the cost-effectiveness of biennial screening with LDCT and CXR based on a health provider perspective. Inputs are based on probabilities, health status utility (quality-adjusted life years (QALYs)), costs of lung cancer screening, diagnosis, and treatment from the literatures, and expert opinion. A total of 1,000 simulations and five cycles of Markov bootstrapping simulations were performed to compare the incremental cost-utility ratio (ICUR) of these two screening strategies. Probability and one-way sensitivity analyses were also performed.

Results

The ICUR of early lung cancer screening compared LDCT to CXR is $-24,757.65/QALYs, and 100% of the probability agree to adopt it under a willingness-to-pay (WTP) threshold of the Taiwan gross domestic product (GDP) per capita ($35,513). The one-way sensitivity analysis also showed that ICUR depends heavily on recall rate. Based on the prevalence rate of 39.7 lung cancer cases per 100,000 people in 2020, it could be estimated that LDCT screening for high-risk populations could save $17,154,115.

Conclusion

LDCT can detect more early lung cancers, reduce mortality and is cost-saving than CXR in a long-term simulation of Taiwan's healthcare system. This study provides valuable insights for healthcare decision-makers and suggests analyzing cost-effectiveness for additional variables in future research.

Machine learning based on metabolomics unveils neutrophil extracellular trap-related metabolic signatures in non-small cell lung cancer patients undergoing chemoimmunotherapy

BACKGROUND

Non-small cell lung cancer (NSCLC) is the primary form of lung cancer, and the combination of chemotherapy with immunotherapy offers promising treatment options for patients suffering from this disease. However, the emergence of drug resistance significantly limits the effectiveness of these therapeutic strategies. Consequently, it is imperative to devise methods for accurately detecting and evaluating the efficacy of these treatments.

AIM

To identify the metabolic signatures associated with neutrophil extracellular traps (NETs) and chemoimmunotherapy efficacy in NSCLC patients.

METHODS

In total, 159 NSCLC patients undergoing first-line chemoimmunotherapy were enrolled. We first investigated the characteristics influencing clinical efficacy. Circulating levels of NETs and cytokines were measured by commercial kits. Liquid chromatography tandem mass spectrometry quantified plasma metabolites, and differential metabolites were identified. Least absolute shrinkage and selection operator, support vector machine-recursive feature elimination, and random forest algorithms were employed. By using plasma metabolic profiles and machine learning algorithms, predictive metabolic signatures were established.

RESULTS

First, the levels of circulating interleukin-8, neutrophil-to-lymphocyte ratio, and NETs were closely related to poor efficacy of first-line chemoimmunotherapy. Patients were classed into a low NET group or a high NET group. A total of 54 differential plasma metabolites were identified. These metabolites were primarily involved in arachidonic acid and purine metabolism. Three key metabolites were identified as crucial variables, including 8,9-epoxyeicosatrienoic acid, L-malate, and bis(monoacylglycerol)phosphate (18:1/16:0). Using metabolomic sequencing data and machine learning methods, key metabolic signatures were screened to predict NET level as well as chemoimmunotherapy efficacy.

CONCLUSION

The identified metabolic signatures may effectively distinguish NET levels and predict clinical benefit from chemoimmunotherapy in NSCLC patients.

Efficiency of pulmonary nodule risk scoring systems in Turkish population

Malignancy risk calculation models were developed using the clinical and radiological features. It was aimed to compare pulmonary nodule risk calculation models and evaluate their effectiveness and applicability for the Turkish population. Between 2014 and 2019, 351 patients who were operated on for pulmonary nodules were evaluated with the following data: age, gender, smoking history, family history of lung cancer, extrapulmonary malignancy and granulomatous disease, nodule diameter, attenuation character, side, localization, spiculation, nodule count, presence of pulmonary emphysema, FDG uptake in PET/CT of the nodule, and definitive pathology data. Malignancy risk scores were calculated using the equations of the Brock, Mayo, and Herder models. The results were evaluated statistically. The mean age of the 351 patients (236 men, 115 women) was 57.84 ± 10.87 (range 14-79) years, and 226 malignant and 125 benign nodules were observed. Significant correlations were found between malignancy and age (p < 0.001), nodule diameter (p < 0.001), gender (p < 0.009), speculation (p < 0.001), emphysema (p < 0.05), FDG uptake (p < 0.001). All three models were found effective in the differentiation (p < 0.001). The ideal threshold value was determined for the Brock (19.5%), Mayo (23.1%), and Herder (56%) models. All models were effective for nodules of > 10 mm, but none of them were for 0-10 mm. Brock was effective in ground-glass nodules (p = 0.02) and all models were effective for semi-solid and solid nodules. None of the groups could provide AUC values as high as those achieved in the original studies. This suggests the need to optimize models and malignancy risk thresholds for Turkish population.

(-) - Epicatechin regulates LOC107986454 by targeting the miR-143-3p/EZH2 axis to enhance the radiosensitivity of non-small cell lung cancer

BACKGROUND AND OBJECTIVE

Non-small cell lung cancer (NSCLC) is a pernicious tumor with high incidence and mortality rates. The incidence rate of NSCLC increases with age and poses a serious danger to human health. The aim of this study was to determine the mechanism by which (-)-epicatechin (EC) alleviates NSCLC.

METHODS

Twenty-four pairs of NSCLC tissues and cancer-adjacent tissues were collected, and A549 and H460 radiotherapy-resistant strains were generated by repeatedly irradiating A549 and H460 cells with dose-gradient X-rays. Radiotherapy-resistant H460 cells were successfully injected subcutaneously into the left dorsal side of nude mice at a dose of 1 × 105 to establish an NSCLC animal model. The levels of interrelated genes and proteins were detected by RT‒qPCR and Western blotting, and cell proliferation and apoptosis were evaluated by CCK‒8 assay, Transwell assay, flow cytometry, and TUNEL staining.

RESULTS

LOC107986454 was highly expressed in NSCLC patients, while miR-143-3p was expressed at low levels and was negatively correlated with LOC107986454. Functionally, EC promoted autophagy and apoptosis induced by radiotherapy, restrained cell proliferation and migration, and ultimately enhanced the radiosensitivity of NSCLC cells. A downstream mechanistic study showed that EC facilitated miR-143-3p expression by inhibiting LOC107986454 and then restraining the expression of EZH2, which ultimately facilitated autophagy and apoptosis in cancer cells, inhibited proliferation and migration, and enhanced the radiosensitivity of NSCLC cells.

CONCLUSION

EC can enhance the radiosensitivity of NSCLC cells by regulating the LOC107986454/miR-143-3p/EZH2 axis.

Deep learning model integrating cfDNA methylation and fragment size profiles for lung cancer diagnosis

Detecting aberrant cell-free DNA (cfDNA) methylation is a promising strategy for lung cancer diagnosis. In this study, our aim is to identify methylation markers to distinguish patients with lung cancer from healthy individuals. Additionally, we sought to develop a deep learning model incorporating cfDNA methylation and fragment size profiles. To achieve this, we utilized methylation data collected from The Cancer Genome Atlas and Gene Expression Omnibus databases. Then we generated methylated DNA immunoprecipitation sequencing and genome-wide Enzymatic Methyl-seq (EM-seq) form lung cancer tissue and plasma. Using these data, we selected 366 methylation markers. A targeted EM-seq panel was designed using the selected markers, and 142 lung cancer and 56 healthy samples were produced with the panel. Additionally, cfDNA samples from healthy individuals and lung cancer patients were diluted to evaluate sensitivity. Its lung cancer detection performance reached an accuracy of 81.5% and an area under the receiver operating characteristic curve of 0.87. In the serial dilution experiment, we achieved tumor fraction detection of 1% at 98% specificity and 0.1% at 80% specificity. In conclusion, we successfully developed and validated a combination of methylation panel and a deep learning model that can distinguish between patients with lung cancer and healthy individuals.

Down-regulated expression of TIPE3 inhibits malignant progression of non-small cell lung cancer via Wnt signaling

Non-small cell lung cancer (NSCLC) accounts for approximately 80 % of all lung cancers with a low five-year survival rate. Therefore, the mechanistic pathways and biomarkers of NSCLC must be explored to elucidate its pathogenesis. In this study, we examined TIPE3 expression in NSCLC cells and investigated the molecular mechanisms underlying NSCLC regulation in vivo and in vitro. We collected tissue samples from patients with NSCLC to examine TIPE3 expression and its association with patient metastasis and prognosis. Furthermore, we evaluated the expression level of TIPE3 in NSCLC cells. Cell lines with the highest expression were selected for molecular mechanism experiments, and animal models were established for in vivo verification. The results showed that TIPE3 was significantly increased in patients with NSCLC, and this increased expression was associated with tumor metastasis and patient prognosis. TIPE3 knockdown inhibited proliferation, migration, invasion, EMT, angiogenesis, and tumorsphere formation in NSCLC cells. Moreover, it reduced the metabolic levels of tumor cells. However, overexpression of TIPE3 has the opposite effect. The in vivo results showed that TIPE3 knockdown reduced tumor volume, weight, and metastasis. Furthermore, the results showed that TIPE3 may inhibit malignant progression of NSCLC via the regulation of Wnt/β-catenin expression. These findings suggest that TIPE3 is significantly elevated in patients with NSCLC and that downregulation of TIPE3 can suppress the malignant progression of NSCLC, which could serve as a potential diagnostic and treatment strategy for NSCLC.

Investigating causal associations between pneumonia and lung cancer using a bidirectional mendelian randomization framework

BACKGROUND

Pneumonia and lung cancer are both major respiratory diseases, and observational studies have explored the association between their susceptibility. However, due to the presence of potential confounders and reverse causality, the comprehensive causal relationships between pneumonia and lung cancer require further exploration.

METHODS

Genome-wide association study (GWAS) summary-level data were obtained from the hitherto latest FinnGen database, COVID-19 Host Genetics Initiative resource, and International Lung Cancer Consortium. We implemented a bidirectional Mendelian randomization (MR) framework to evaluate the causal relationships between several specific types of pneumonia and lung cancer. The causal estimates were mainly calculated by inverse-variance weighted (IVW) approach. Additionally, sensitivity analyses were also conducted to validate the robustness of the causalty.

RESULTS

In the MR analyses, overall pneumonia demonstrated a suggestive but modest association with overall lung cancer risk (Odds ratio [OR]: 1.21, 95% confidence interval [CI]: 1.01 - 1.44, P = 0.037). The correlations between specific pneumonia types and overall lung cancer were not as significant, including bacterial pneumonia (OR: 1.07, 95% CI: 0.91 - 1.26, P = 0.386), viral pneumonia (OR: 1.00, 95% CI: 0.95 - 1.06, P = 0.891), asthma-related pneumonia (OR: 1.18, 95% CI: 0.92 - 1.52, P = 0.181), and COVID-19 (OR: 1.01, 95% CI: 0.78 - 1.30, P = 0.952). Reversely, with lung cancer as the exposure, we observed that overall lung cancer had statistically crucial associations with bacterial pneumonia (OR: 1.08, 95% CI: 1.03 - 1.13, P = 0.001) and viral pneumonia (OR: 1.09, 95% CI: 1.01 - 1.19, P = 0.037). Sensitivity analysis also confirmed the robustness of these findings.

CONCLUSION

This study has presented a systematic investigation into the causal relationships between pneumonia and lung cancer subtypes. Further prospective study is warranted to verify these findings.

Increased Utilization of Low-Dose CT for Lung Cancer Screening at an Arkansas Community Oncology Clinic

BACKGROUND

Low-dose CT (LDCT) is underused in Arkansas for lung cancer screening, a rural state with a high incidence of lung cancer. The objective was to determine whether offering free LDCT increased the number of high-risk individuals screened in a rural catchment area.

METHODS

There were 5,402 patients enrolled in screening at Highlands Oncology, a community oncology clinic in Northwest Arkansas, from 2013 to 2020. Screenings were separated into time periods: period 1 (10 months for-fee), period 2 (10 months free with targeted advertisements and primary care outreach), and period 3 (62 months free with only primary care outreach). In all, 5,035 high-risk participants were eligible for analysis based on National Comprehensive Cancer Network Clinical Practice Guidelines in Oncology. Enrollment rates, incidence densities (IDs), Cox proportional hazard models, and Kaplan-Meier curves were performed to investigate differences between enrollment periods and high-risk groups.

RESULTS

Patient volume increased drastically once screenings were offered free of charge (period 1 = 4.6 versus period 2 = 66.0 and period 3 = 69.8 average patients per month). Incidence density per 1,000 person-years increased through each period (IDPeriod 1 = 17.2; IDPeriod 2 = 20.8; IDPeriod 3 = 25.5 cases). Cox models revealed significant differences in lung cancer risk between high-risk groups (P = .012) but not enrollment periods (P = .19). Kaplan-Meier lung cancer-free probabilities differed significantly between high-risk groups (log-rank P = .00068) but not enrollment periods (log-rank P = .18).

CONCLUSIONS

This study suggests that eligible patients are more receptive to free LDCT screening, despite most insurances not having a required copay for eligible patients.

The diagnosis and management of multiple ground-glass nodules in the lung

The prevalence of low-dose CT (LDCT) in lung cancer screening has gradually increased, and more and more lung ground glass nodules (GGNs) have been detected. So far, a consensus has been reached on the treatment of single pulmonary ground glass nodules, and there have been many guidelines that can be widely accepted. However, at present, more than half of the patients have more than one nodule when pulmonary ground glass nodules are found, which means that different treatment methods for nodules may have different effects on the prognosis or quality of life of patients. This article reviews the research progress in the diagnosis and treatment strategies of pulmonary multiple lesions manifested as GGNs.

Development and validation of an early diagnosis model for bone metastasis in non-small cell lung cancer based on serological characteristics of the bone metastasis mechanism

Background

Bone metastasis significantly impact the prognosis of non-small cell lung cancer (NSCLC) patients, reducing their quality of life and shortening their survival. Currently, there are no effective tools for the diagnosis and risk assessment of early bone metastasis in NSCLC patients. This study employed machine learning to analyze serum indicators that are closely associated with bone metastasis, aiming to construct a model for the timely detection and prognostic evaluation of bone metastasis in NSCLC patients.

Methods

The derivation cohort consisted of 664 individuals with stage IV NSCLC, diagnosed between 2015 and 2018. The variables considered in this study included age, sex, and 18 specific serum indicators that have been linked to the occurrence of bone metastasis in NSCLC. Variable selection used multivariate logistic regression analysis and Lasso regression analysis. Six machine learning methods were utilized to develop a bone metastasis diagnostic model, assessed with Area Under the Curve (AUC), Decision Curve Analysis (DCA), sensitivity, specificity, and validation cohorts. External validation used 113 NSCLC patients from the Medical Alliance (2019-2020). Furthermore, a prospective validation study was conducted on a cohort of 316 patients (2019-2020) who were devoid of bone metastasis, and followed-up for at least two years to assess the predictive capabilities of this model. The model's prognostic value was evaluated using Kaplan-Meier survival curves.

Findings

Through variable selection, 11 serum indictors were identified as independent predictive factors for NSCLC bone metastasis. Six machine learning models were developed using age, sex, and these serum indicators. A random forest (RF) model demonstrated strong performance during the training and internal validation cohorts, achieving an AUC of 0.98 (95% CI 0.95-0.99) for internal validation. External validation further confirmed the RF model's effectiveness, yielding an AUC of 0.97 (95% CI 0.94-0.99). The calibration curves demonstrated a high level of concordance between the anticipated risk and the observed risk of the RF model. Prospective validation revealed that the RF model could predict the occurrence of bone metastasis approximately 10.27 ± 3.58 months in advance, according to the results of the SPECT. An online computing platform (https://bonemetastasis.shinyapps.io/shiny_cls_1model/) for this RF model is publicly available and free-to-use by doctors and patients.

Interpretation

This study innovatively employs age, gender, and 11 serological markers closely related to the mechanism of bone metastasis to construct an RF model, providing a reliable tool for the early screening and prognostic assessment of bone metastasis in NSCLC patients. However, as an exploratory study, the findings require further validation through large-scale, multicenter prospective studies.

Funding

This work is supported by the National Natural Science Foundation of China (NO.81974315); Shanghai Municipal Science and Technology Commission Medical Innovation Research Project (NO.20Y11903300); Shanghai Municipal Health Commission Health Industry Clinical Research Youth Program (NO.20204Y034).

Leveraging Serial Low-Dose CT Scans in Radiomics-based Reinforcement Learning to Improve Early Diagnosis of Lung Cancer at Baseline Screening

Purpose To evaluate the feasibility of leveraging serial low-dose CT (LDCT) scans to develop a radiomics-based reinforcement learning (RRL) model for improving early diagnosis of lung cancer at baseline screening. Materials and Methods In this retrospective study, 1951 participants (female patients, 822; median age, 61 years [range, 55-74 years]) (male patients, 1129; median age, 62 years [range, 55-74 years]) were randomly selected from the National Lung Screening Trial between August 2002 and April 2004. An RRL model using serial LDCT scans (S-RRL) was trained and validated using data from 1404 participants (372 with lung cancer) containing 2525 available serial LDCT scans up to 3 years. A baseline RRL (B-RRL) model was trained with only LDCT scans acquired at baseline screening for comparison. The 547 held-out individuals (150 with lung cancer) were used as an independent test set for performance evaluation. The area under the receiver operating characteristic curve (AUC) and the net reclassification index (NRI) were used to assess the performances of the models in the classification of screen-detected nodules. Results Deployment to the held-out baseline scans showed that the S-RRL model achieved a significantly higher test AUC (0.88 [95% CI: 0.85, 0.91]) than both the Brock model (AUC, 0.84 [95% CI: 0.81, 0.88]; P = .02) and the B-RRL model (AUC, 0.86 [95% CI: 0.83, 0.90]; P = .02). Lung cancer risk stratification was significantly improved by the S-RRL model as compared with Lung CT Screening Reporting and Data System (NRI, 0.29; P < .001) and the Brock model (NRI, 0.12; P = .008). Conclusion The S-RRL model demonstrated the potential to improve early diagnosis and risk stratification for lung cancer at baseline screening as compared with the B-RRL model and clinical models. Keywords: Radiomics-based Reinforcement Learning, Lung Cancer Screening, Low-Dose CT, Machine Learning © RSNA, 2024 Supplemental material is available for this article.

Multidimensional biological characteristics of ground glass nodules

The detection rate of ground glass nodules (GGNs) has increased in recent years because of their malignant potential but relatively indolent biological behavior; thus, correct GGN recognition and management has become a research focus. Many scholars have explored the underlying mechanism of the indolent progression of GGNs from several perspectives, such as pathological type, genomic mutational characteristics, and immune microenvironment. GGNs have different major mutated genes at different stages of development; EGFR mutation is the most common mutation in GGNs, and p53 mutation is the most abundant mutation in the invasive stage of GGNs. Pure GGNs have fewer genomic alterations and a simpler genomic profile and exhibit a gradually evolving genomic mutation profile as the pathology progresses. Compared to advanced lung adenocarcinoma, GGN lung adenocarcinoma has a higher immune cell percentage, is under immune surveillance, and has less immune escape. However, as the pathological progression and solid component increase, negative immune regulation and immune escape increase gradually, and a suppressive immune environment is established gradually. Currently, regular computer tomography monitoring and surgery are the main treatment strategies for persistent GGNs. Stereotactic body radiotherapy and radiofrequency ablation are two local therapeutic alternatives, and systemic therapy has been progressively studied for lung cancer with GGNs. In the present review, we discuss the characterization of the multidimensional molecular evolution of GGNs that could facilitate more precise differentiation of such highly heterogeneous lesions, laying a foundation for the development of more effective individualized treatment plans.

A Self-supervised Learning-Based Fine-Grained Classification Model for Distinguishing Malignant From Benign Subcentimeter Solid Pulmonary Nodules

RATIONALE AND OBJECTIVES

Diagnosing subcentimeter solid pulmonary nodules (SSPNs) remains challenging in clinical practice. Deep learning may perform better than conventional methods in differentiating benign and malignant pulmonary nodules. This study aimed to develop and validate a model for differentiating malignant and benign SSPNs using CT images.

MATERIALS AND METHODS

This retrospective study included consecutive patients with SSPNs detected between January 2015 and October 2021 as an internal dataset. Malignancy was confirmed pathologically; benignity was confirmed pathologically or via follow-up evaluations. The SSPNs were segmented manually. A self-supervision pre-training-based fine-grained network was developed for predicting SSPN malignancy. The pre-trained model was established using data from the National Lung Screening Trial, Lung Nodule Analysis 2016, and a database of 5478 pulmonary nodules from the previous study, with subsequent fine-tuning using the internal dataset. The model's efficacy was investigated using an external cohort from another center, and its accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were determined.

RESULTS

Overall, 1276 patients (mean age, 56 ± 10 years; 497 males) with 1389 SSPNs (mean diameter, 7.5 ± 2.0 mm; 625 benign) were enrolled. The internal dataset was specifically enriched for malignancy. The model's performance in the internal testing set (316 SSPNs) was: AUC, 0.964 (95% confidence interval (95%CI): 0.942-0.986); accuracy, 0.934; sensitivity, 0.965; and specificity, 0.908. The model's performance in the external test set (202 SSPNs) was: AUC, 0.945 (95% CI: 0.910-0.979); accuracy, 0.911; sensitivity, 0.977; and specificity, 0.860.

CONCLUSION

This deep learning model was robust and exhibited good performance in predicting the malignancy of SSPNs, which could help optimize patient management.

DNAzyme-based ultrasensitive immunoassay: Recent advances and emerging trends

Immunoassay, as the most commonly used method for protein detection, is simple to operate and highly specific. Sensitivity improvement is always the thrust of immunoassays, especially for the detection of trace quantities. The emergence of artificial enzyme, i.e., DNAzyme, provides a novel approach to improve the detection sensitivity of immunoassay. Simultaneously, its advantages of simple synthesis and high stability enable low cost, broad applicability and long shelf life for immunoassay. In this review, we summarized the recent advances in DNAzyme-based immunoassay. First, we summarized the existing different DNAzymes based on their catalytic activities. Next, the common signal amplification strategies used for DNAzyme-based immunoassays were reviewed to cater to diverse detection requirements. Following, the wide applications in disease diagnosis, environmental monitoring and food safety were discussed. Finally, the current challenges and perspectives on the future development of DNAzyme-based immunoassays were also provided.

Plasma Metabolite Profiling in the Search for Early-Stage Biomarkers for Lung Cancer: Some Important Breakthroughs

Lung cancer is the leading cause of cancer-related mortality worldwide. In order to improve its overall survival, early diagnosis is required. Since current screening methods still face some pitfalls, such as high false positive rates for low-dose computed tomography, researchers are still looking for early biomarkers to complement existing screening techniques in order to provide a safe, faster, and more accurate diagnosis. Biomarkers are biological molecules found in body fluids, such as plasma, that can be used to diagnose a condition or disease. Metabolomics has already been shown to be a powerful tool in the search for cancer biomarkers since cancer cells are characterized by impaired metabolism, resulting in an adapted plasma metabolite profile. The metabolite profile can be determined using nuclear magnetic resonance, or NMR. Although metabolomics and NMR metabolite profiling of blood plasma are still under investigation, there is already evidence for its potential for early-stage lung cancer diagnosis, therapy response, and follow-up monitoring. This review highlights some key breakthroughs in this research field, where the most significant biomarkers will be discussed in relation to their metabolic pathways and in light of the altered cancer metabolism.

Machine Learning in Diagnosis and Prognosis of Lung Cancer by PET-CT

As a disease with high morbidity and high mortality, lung cancer has seriously harmed people's health. Therefore, early diagnosis and treatment are more important. PET/CT is usually used to obtain the early diagnosis, staging, and curative effect evaluation of tumors, especially lung cancer, due to the heterogeneity of tumors and the differences in artificial image interpretation and other reasons, it also fails to entirely reflect the real situation of tumors. Artificial intelligence (AI) has been applied to all aspects of life. Machine learning (ML) is one of the important ways to realize AI. With the help of the ML method used by PET/CT imaging technology, there are many studies in the diagnosis and treatment of lung cancer. This article summarizes the application progress of ML based on PET/CT in lung cancer, in order to better serve the clinical. In this study, we searched PubMed using machine learning, lung cancer, and PET/CT as keywords to find relevant articles in the past 5 years or more. We found that PET/CT-based ML approaches have achieved significant results in the detection, delineation, classification of pathology, molecular subtyping, staging, and response assessment with survival and prognosis of lung cancer, which can provide clinicians a powerful tool to support and assist in critical daily clinical decisions. However, ML has some shortcomings such as slightly poor repeatability and reliability.

The Prognostic Value of Positron Emission Tomography/Computed Tomography in Clinical Stage I Lung Cancer Patients: A Propensity-Match Analysis

Background: The application of positron emission tomography/computed tomography (PET/CT) helps provide accurate clinical staging for lung cancer patients. However, the effects and trends in early-stage lung cancer remain unclear. The aim of this study was to compare differences between clinical stage I lung cancer patients who received PET/CT for staging and those who did not. Methods: Data were obtained from the Taiwan Society of Cancer Registry. There were 6587 clinical stage I lung cancer patients between 2009 and 2014 analyzed in this study. We compared the characteristics of the PET/CT and no PET/CT groups. After propensity score matching, it resulted in both groups having 2649 patients. We measured the overall survival rates of all clinical stage I lung cancer patients and the overall survival rates of patients with PET/CT and without PET/CT. Results: The 1-, 3-, and 5-year survival rates of all clinical stage I lung cancer patients were 97.2%, 88.2%, and 79.0%, respectively. Patients with a larger tumor size tended to receive PET/CT for staging (stage Ib: 38.25% vs. 27.82%, p < 0.0001) and a larger resection (lobectomy: 74.62% vs. 66.61%, p < 0.0001). The 5-year survival rates were 79.8% in the PET/CT group and 78.2% in the no PET/CT group after propensity score matching (p = 0.6528). Conclusions: For clinical stage I lung cancer in Taiwan, patients with larger tumor sizes tend to have PET/CT for staging. Although PET/CT provided more precise clinical staging, these patients still received larger resections and had more pathological migration. However, there was no overall survival rate benefit after PET/CT.

Cymensifin A: a promising pharmaceutical candidate to defeat lung cancer via cellular reactive oxygen species-mediated apoptosis

Background: The upgrade of natural products for cancer treatment is essential since current anticancer drugs still pose severe side effects. Cymensifin A (Cym A) isolated from an orchid Cymbidium ensifolium has shown its potential to induce the death of several cancer cells; however, its underlying molecular mechanisms are hitherto unknown. Methods: Here, we conducted a set of in vitro preliminary tests to assess the cytotoxic effects of Cym A on non-small-cell lung cancer (NSCLC) cells (A549, H23, H292, and H460). A flow cytometry system and Western blot analyses were employed to unveil molecular mechanisms underlying cancer cell apoptosis caused by Cym A. Results: Cym A at 25-50 μM caused the death of all NSCLC cells tested, and its cytotoxicity was comparable to cisplatin, a currently used anticancer drug. The compound induced apoptosis of all NSCLC cells in a dose-dependent manner (5-50 μM), proven by flow cytometry, but H460 cells showed more resistance compared to other cells tested. Cym A-treated H460 cells demonstrated increased reactive oxygen species (ROS) and downregulated antioxidants (catalase, superoxide dismutase, and thioredoxin). The compound also upregulated the tumor suppressor P53 and the pro-apoptotic protein BAX but downregulated pro-survival proteins (BCL-2 and MCL-1) and deactivated survival signals (AKT and ERK) in H460 cells. Cym A was proven to trigger cellular ROS formation, but P53 and BAX were 2-fold more activated by Cym A compared to those treated with hydrogen peroxide. Our findings also supported that Cym A exerted its roles in the downregulation of nuclear factor erythroid 2-related factor 2 (a regulator of cellular antioxidant activity) and the increased levels of cleaved poly (ADP-ribose) polymerase (PARP) and cleaved caspase 3/7 during apoptosis. Conclusion: We propose that Cym A induces lung cancer cell death via ROS-mediated apoptosis, while the modulation of cellular ROS/antioxidant activity, the upregulation of P53 and BAX, the downregulation or deactivation of BCL-2, MCL-1, AKT, and ERK, and the increased cleavage of PARP and caspase 3/7, were the elucidated underlying molecular mechanisms of this phytochemical. The compound can be a promising candidate for future anticancer drug development.

Exosome miR-101-3p derived from bone marrow mesenchymal stem cells promotes radiotherapy sensitivity in non-small cell lung cancer by regulating DNA damage repair and autophagy levels through EZH2

BACKGROUND AND OBJECTIVE

The morbidity rate of non-small cell lung cancer (NSCLC) increases with age, highlighting that NSCLC is a serious threat to human health. The aim of this study was mainly to describe the role of exosomal miR-101-3p derived from bone marrow mesenchymal stem cells (BMSCs) in NSCLC.

METHODS

A549 or NCI-H1703 cells (1×105/mouse) were injected into nude mice to establish an NSCLC animal model. RTqPCR, Western blotting and comet assays were used to assess the changes in gene expression, proteins and DNA damage repair.

RESULTS

miR-101-3p and RAI2 were found to be expressed at low levels in NSCLC, while EZH2 was highly expressed. In terms of function, miR-101-3p downregulated EZH2. In addition, exosomal miR-101-3p derived from BMSCs promoted the expression of RAI2, inhibited DNA damage repair, and inhibited the activation of the PI3K/AKT/mTOR signaling pathway by inhibiting EZH2, thereby promoting autophagy and decreasing cell viability and finally enhancing the sensitivity of NSCLC to radiotherapy and inhibiting the malignant biological behavior of NSCLC.

CONCLUSION

Exosomal miR-101-3p derived from BMSCs can inhibit DNA damage repair, promote autophagy, enhance the radiosensitivity of NSCLC, and inhibit the progression of NSCLC by inhibiting EZH2.

Lung cancer screening use among screening-eligible adults with disabilities

BACKGROUND

Lung cancer screening (LCS) use among adults with disabilities has not been well characterized. We estimated the prevalence of LCS use by disability types and counts and investigated the association between disability counts and LCS utilization among LCS-eligible adults.

METHODS

We used cross-sectional data from the 2019 Behavioral Risk Factor Surveillance System, Lung Cancer Screening Module. Based on the 2013 US Preventive Services Task Force criteria for LCS, the sample included 4407 LCS-eligible adults, aged 55-79 years, with current or former (quit smoking in the past 15 years) tobacco use history of at least 30 pack-years. Disability types included limitations in hearing, vision, cognition, mobility, self-care, and independent living. We also categorized respondents by number of disabilities (no disability, 1 disability, 2 disabilities, 3+ disabilities). We utilized descriptive statistics and multivariable logistic regression analyses to determine the association between disability counts and the receipt of LCS (yes/no) in the past 12 months.

RESULTS

In 2019, 16.4% of LCS-eligible adults were screened for lung cancer. Overall, 49.6% of participants had no disability, and 14.5% had >3 disabilities. Mobility was the most prevalent disability type (35.4%), followed by cognitive impairment (18.2%) and hearing (16.6%). LCS was more prevalent in adults with disability in self-care versus no disability in self-care (24.0% vs. 15.5%, p = 0.01), disability in independent living versus no disability in independent living (22.2% vs. 15.4%, p = 0.02), and cognitive impairment disability versus no cognitive impairment (22.1% vs. 15.3%, p = 0.03). The prevalence rates of LCS among groups of LCS-eligible adults with different disability counts were not significant (p = 0.17).

CONCLUSIONS

Despite the lack of clinical guidelines on LCS among individuals with disabilities, some individuals with disabilities are being screened for lung cancer. Future research should address this knowledge gap to determine clinical benefit versus harm of LCS among those with disabilities.

Recommended approaches for screening and early detection of lung cancer in the Middle East and Africa (MEA) region: a consensus statement

Background

The prevalence of lung cancer in the Middle East and Africa (MEA) region has steadily increased in recent years and is generally associated with a poor prognosis due to the late detection of most of the cases. We explored the factors leading to delayed diagnoses, as well as the challenges and gaps in the early screening, detection, and referral framework for lung cancer in the MEA.

Methods

A steering committee meeting was convened in October 2022, attended by a panel of ten key external experts in the field of oncology from the Kingdom of Saudi Arabia, United Arab Emirates, South Africa, Egypt, Lebanon, Jordan, and Turkey, who critically and extensively analyzed the current unmet needs and challenges in the screening and early diagnosis of lung cancer in the region.

Results

As per the experts' opinion, lack of awareness about disease symptoms, misdiagnosis, limited screening initiatives, and late referral to specialists were the primary reasons for delayed diagnoses emphasizing the need for national-level lung cancer screening programs in the MEA region. Screening guidelines recommend low-dose computerized tomography (LDCT) for lung cancer screening in patients with a high risk of malignancy. However, high cost and lack of awareness among the public as well as healthcare providers prevented the judicious use of LDCT in the MEA region. Well-established screening and referral guidelines were available in only a few of the MEA countries and needed to be implemented in others to identify suspected cases early and provide timely intervention thus improving patient outcomes.

Conclusions

There is a great need for large-scale screening programs, preferably integrated with tobacco-control programs and awareness programs for physicians and patients, which may facilitate higher adherence to lung cancer screening and improve survival outcomes.

Development of hypertension models for lung cancer screening cohorts using clinical and thoracic aorta imaging factors

This study aims to develop and validate nomogram models utilizing clinical and thoracic aorta imaging factors to assess the risk of hypertension for lung cancer screening cohorts. We included 804 patients and collected baseline clinical data, biochemical indicators, coexisting conditions, and thoracic aorta factors. Patients were randomly divided into a training set (70%) and a validation set (30%). In the training set, variance, t-test/Mann-Whitney U-test and standard least absolute shrinkage and selection operator were used to select thoracic aorta imaging features for constructing the AIScore. Multivariate logistic backward stepwise regression was utilized to analyze the influencing factors of hypertension. Five prediction models (named AIMeasure model, BasicClinical model, TotalClinical model, AIBasicClinical model, AITotalClinical model) were constructed for practical clinical use, tailored to different data scenarios. Additionally, the performance of the models was evaluated using receiver operating characteristic (ROC) curves, calibration curves and decision curve analyses (DCA). The areas under the ROC curve for the five models were 0.73, 0.77, 0.83, 0.78, 0.84 in the training set, and 0.77, 0.78, 0.81, 0.78, 0.82 in the validation set, respectively. Furthermore, the calibration curves and DCAs of both sets performed well on accuracy and clinical practicality. The nomogram models for hypertension risk prediction demonstrate good predictive capability and clinical utility. These models can serve as effective tools for assessing hypertension risk, enabling timely non-pharmacological interventions to preempt or delay the future onset of hypertension.

Construction of a predictive model for bone metastasis from first primary lung adenocarcinoma within 3 cm based on machine learning algorithm: a retrospective study

Background

Adenocarcinoma, the most prevalent histological subtype of non-small cell lung cancer, is associated with a significantly higher likelihood of bone metastasis compared to other subtypes. The presence of bone metastasis has a profound adverse impact on patient prognosis. However, to date, there is a lack of accurate bone metastasis prediction models. As a result, this study aims to employ machine learning algorithms for predicting the risk of bone metastasis in patients.

Method

We collected a dataset comprising 19,454 cases of solitary, primary lung adenocarcinoma with pulmonary nodules measuring less than 3 cm. These cases were diagnosed between 2010 and 2015 and were sourced from the Surveillance, Epidemiology, and End Results (SEER) database. Utilizing clinical feature indicators, we developed predictive models using seven machine learning algorithms, namely extreme gradient boosting (XGBoost), logistic regression (LR), light gradient boosting machine (LightGBM), Adaptive Boosting (AdaBoost), Gaussian Naive Bayes (GNB), multilayer perceptron (MLP) and support vector machine (SVM).

Results

The results demonstrated that XGBoost exhibited superior performance among the four algorithms (training set: AUC: 0.913; test set: AUC: 0.853). Furthermore, for convenient application, we created an online scoring system accessible at the following URL: https://www.xsmartanalysis.com/model/predict/?mid=731symbol=7Fr16wX56AR9Mk233917, which is based on the highest performing model.

Conclusion

XGBoost proves to be an effective algorithm for predicting the occurrence of bone metastasis in patients with solitary, primary lung adenocarcinoma featuring pulmonary nodules below 3 cm in size. Moreover, its robust clinical applicability enhances its potential utility.

Tackling Guideline Non-concordance: Primary Care Barriers to Incorporating Life Expectancy into Lung Cancer Screening Decision-Making-A Qualitative Study

BACKGROUND

Primary care providers (PCPs) are often the first point of contact for discussing lung cancer screening (LCS) with patients. While guidelines recommend against screening people with limited life expectancy (LLE) who are less likely to benefit, these patients are regularly referred for LCS.

OBJECTIVE

We sought to understand barriers PCPs face to incorporating life expectancy into LCS decision-making for patients who otherwise meet eligibility criteria, and how a hypothetical point-of-care tool could support patient selection.

DESIGN

Qualitative study based on semi-structured telephone interviews.

PARTICIPANTS

Thirty-one PCPs who refer patients for LCS, from six Veterans Health Administration facilities.

APPROACH

We thematically analyzed interviews to understand how PCPs incorporated life expectancy into LCS decision-making and PCPs' receptivity to a point-of-care tool to support patient selection. Final themes were organized according to the Cabana et al. framework Why Don't Physicians Follow Clinical Practice Guidelines, capturing the influence of clinician knowledge, attitudes, and behavior on LCS appropriateness determinations.

KEY RESULTS

PCP referrals to LCS for patients with LLE were influenced by limited knowledge of the life expectancy threshold at which patients are less likely to benefit from LCS, discomfort estimating life expectancy, fear of missing cancer at the point of early detection, and prioritization of factors such as quality of life, patient values, clinician-patient relationship, and family support. PCPs were receptive to a decision support tool to inform and communicate LCS appropriateness decisions if easy to use and integrated into clinical workflows.

CONCLUSIONS

Our study suggests knowledge gaps and attitudes may drive decisions to offer screening despite LLE, a behavior counter to guideline recommendations. Integrating a LCS decision support tool that incorporates life expectancy within the electronic medical record and existing clinical workflows may be one acceptable solution to improve guideline concordance and increase confidence in selecting high benefit patients for LCS.

A Highly Sensitive and Specific Non-Invasive Test through Genome-Wide 5-Hydroxymethylation Mapping for Early Detection of Lung Cancer

Low-dose computed tomography screening can increase the detection for non-small-cell lung cancer (NSCLC). To improve the diagnostic accuracy of early-stage NSCLC detection, ultrasensitive methods are used to detect cell-free DNA (cfDNA) 5-hydroxymethylcytosine (5hmC) in plasma. Genome-wide 5hmC is profiled in 1990 cfDNA samples collected from patients with non-small cell lung cancer (NSCLC, n = 727), healthy controls (HEA, n = 1,092), as well as patients with small cell lung cancer (SCLC, n = 41), followed by sample randomization, differential analysis, feature selection, and modeling using a machine learning approach. Differentially modified features reflecting tissue origin. A weighted diagnostic model comprised of 105 features is developed to compute a detection score for each individual, which showed an area under the curve (AUC) range of 86.4%-93.1% in the internal and external validation sets for distinguishing lung cancer from HEA controls, significantly outperforming serum biomarkers (p < 0.001). The 5hmC-based model detected high-risk pulmonary nodules (AUC: 82%)and lung cancer of different subtypes with high accuracy as well. A highly sensitive and specific blood-based test is developed for detecting lung cancer. The 5hmC biomarkers in cfDNA offer a promising blood-based test for lung cancer.

Mortality of older construction and craft workers employed at Department of Energy (DOE) nuclear sites: Follow-up through 2021

BACKGROUND

To determine if construction and trades workers formerly employed at US Department of Energy (DOE) nuclear weapons sites are at significant risk for occupational diseases, we studied the mortality experience of participants in the Building Trades National Medical Screening Program (BTMed).

METHODS

The cohort included 26,922 participants enrolled between 1998 and 2021 and 8367 deaths. Standardized mortality ratios were calculated based on US death rates. Cox models compared construction workers (n = 22,747; 7487 deaths) to two nonconstruction subpopulations: administrative, scientific and security workers (n = 1894; 330 deaths), and all other nonconstruction workers (n = 2218; 550 deaths).

RESULTS

Mortality was elevated for all causes, all cancers, cancers of the trachea, bronchus, lung, kidneys, and lymphatic and hematopoietic system, mesothelioma, chronic obstructive pulmonary disease (COPD), asbestosis, transportation injuries, and other injuries, particularly accidental poisonings. There were 167 deaths from coronavirus disease 2019 (COVID-19), which was lower than expected using US death rates. Overall cause-specific mortality was significantly higher among construction workers than for internal comparison groups.

CONCLUSIONS

Construction workers employed at DOE sites have a significantly increased risk for occupational illnesses. Apart from COVID-19 deaths, this update: (1) found that mortality among construction workers is significantly elevated compared to the US population and significantly higher than in the internal comparison populations, and (2) confirmed excess risk for these workers for first employment after 1990. Cancer mortality risks are similar to the cancers identified for DOE compensation from radiation exposures. The high lung cancer risk supports the value of early lung cancer detection. Continued medical surveillance is important.

Knowledge, attitude, and practice of lung cancer screening and associated factors among high-risk population in Lanzhou, China: A cross-sectional study

This study aimed to assess the knowledge, attitude, and practice (KAP) of high-risk populations toward lung cancer screening in Lanzhou, China. Using convenience sampling, this cross-sectional study enrolled outpatients at high-risk for lung cancer at Lanzhou University Second Hospital between November 2022 and March 2023. An anonymous, self-administered online questionnaire was distributed to each participant via the Sojump website (https://www.wjx.cn/), comprising 40 items to collect demographic information and evaluate KAP toward lung cancer screening. The analyses were descriptive. A total of 577 participants (average age of 61.8 ± 7.1 years; 306 males) were included in the study. The participants' scores for KAP were 4.9 ± 2.2, 27.4 ± 3.0, and 7.0 ± 2.1, respectively. Participants with occupational exposure had significantly lower knowledge score (3.3 ± 2.4 vs 5.2 ± 2.1, P < .001), and practice score (5.6 ± 2.4 vs 7.3 ± 1.9, P < .001) than those without occupational exposure. Participants with smoking or passive smoking history had significantly higher attitude scores (27.6 ± 2.9 vs 25.8 ± 3.2, P < .001) and practice scores (7.1 ± 2.0 vs 6.5 ± 2.5, P = .014) than those without smoking history. A total of 360 (62.4%) participants endorsed the doctors' counseling on lung cancer screening, and 355 (61.5%) participants were willing to have screening for lung cancer as doctors advised. The study revealed that 390 (67.6%) participants identified low-dose computed tomography as the appropriate method for lung cancer screening, while 356 (61.7%) participants believed that X-rays were a reliable screening method for lung cancer. However, 365 (63.3%) participants thought that the treatment outcomes for early and late-diagnosed lung cancer were the same. Additionally, 416 (72.10%) participants believed that annual lung cancer CT scanning is unnecessary. On the other hand, 339 (58.8%) participants expressed concerns about exposure to radiation from CT scans, while 349 (60.5%) participants were worried about the cost of lung cancer screening. Only 142 (24.6%) participants reported having undergone annual lung cancer screening. The high-risk population had limited knowledge and insufficient attitude and practice toward lung cancer screening in Lanzhou, China.

Matrix metalloproteinase‑1 and microRNA‑486‑5p in urinary exosomes can be used to detect early lung cancer: A preliminary report

The present study describes a novel molecular-genetic method suitable for lung cancer (LC) screening in the work-place and at community health centers. Using urinary-isolated exosomes from 35 patients with LC and 40 healthy volunteers, the expression ratio of MMP-1/CD63, and the relative expression levels of both microRNA (miRNA)-21 and miRNA-486-5p were measured. MMP-1/CD63 expression ratio was significantly higher in patients with LC than in the healthy controls {1.342 [95% confidence interval (CI): 0.890-1.974] vs. 0.600 (0.490-0.900); P<0.0001}. The relative expression of miRNA-486-5p in male healthy controls was significantly different from that in female healthy controls, whereas there was no significant difference in miRNA-21. Receiver operating characteristic curve (ROC) analysis of MMP-1/CD63 showed 92.5% sensitivity and 54.3% specificity, whereas miRNA-486-5p showed 85% sensitivity and 70.8% specificity for men, and 70.0% sensitivity and 72.7% specificity for women. The logistic regression model used to evaluate the association of LC with the combination of MMP-1/CD63 and miRNA-486-5p revealed that the area under the ROC curve was 0.954 (95% CI: 0.908-1.000), and the model had 89% sensitivity and 88% specificity after adjusting for age, sex and smoking status. These data suggested that the combined analysis of MMP-1/CD63 and miRNA-486-5p in urinary exosomes may be used to detect patients with early-stage LC in the work-place and at community health centers, although confirmational studies are warranted.

LDCT screening results among eligible and ineligible screening candidates in preventive health check-ups population: a real world study in West China

To compare the LDCT screening results between eligible and ineligible screening candidates in preventive health check-ups population. Using a real-world LDCT screening results among people who took yearly health check-up in health management center of West China Hospital between 2006 and 2017. Objects were classified according to the China National Lung Cancer Screening Guideline with Low-dose Computed Tomography (2018 version) eligibility criteria. Descriptive analysis were performed between eligible and ineligible screening candidates. The proportion of ineligible screening candidates was 64.13% (10,259), and among them there were 4005 (39.04%) subjects with positive screenings, 80 cases had a surgical lung biopsy. Pathology results from lung biopsy revealed 154 cancers (true-positive) and 26 benign results (false-positive), the surgical false-positive biopsy rate was 4.17%, and ineligible group (7.69%) was higher than eligible group (2.47%), P < 0.05. Further, in ineligible screening candidates, the proportion of current smokers was higher among males compared to females (53.85% vs. 4.88%, P < 0.05). Of the 69 lung cancer patients detected in ineligible screening candidates, lung adenocarcinoma accounts for a high proportion of lung cancers both in male (75.00%) and female (85.00%). The proportion of ineligible screening candidates and the surgical false-positive biopsy rate in ineligible candidates were both high in health check-ups population.

Lateral Dorsal Basal Lung Resection Based on Functional Preserving Sublobectomy Method: Single-Center Experience

PURPOSE

Functional preserving sublobectomy (FPSL), a novel balancing strategy for segmentectomy and wedge resection, allows rapid and accurate removal of invisible nodules without the use of any preoperative localization markers. This study aimed to share single-center experience of lateral dorsal basal lung resection based on FPSL, so as to provide new surgical options for thoracic surgeons.

METHODS

A retrospective analysis was performed on 13 patients who underwent thoracoscopic basal lung resection after FPSL at XX hospital from January 2021 to August 2022.

RESULTS

The operation was successfully performed in 13 patients by using FPSL, including 12 patients with malignant tumors. The mean operating time was 107.5 ± 25.6 min. The mean postoperative hospital stay was 3.7 ± 2.4 days. None of the patients needed extended excision, such as an entire basal or inferior lobectomy.

CONCLUSION

Our single-center experience showed that the FPSL method only dealt with the target vessels, which greatly reduced the technical difficulty of surgery. In addition, both arteries and veins could be used as target vessels, and in particular cases such as undeveloped interlobar fissure, the operation could still be completed successfully. Lateral dorsal basal lung resection based on FPSL may be a new surgical option for surgeons.

Survival analysis and clinicopathological features of patients with stage IA lung adenocarcinoma

Background

With the development of medical technology and change of life habits, early-stage lung adenocarcinoma (LUAD) has become more common. This study aimed to systematically analyzed clinicopathological factors associated to the overall survival (OS) of patients with Stage IA LUAD.

Methods

A total of 5942 Stage IA LUAD patients were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. Kaplan-Meier methods and log-rank tests were used to compare the differences in OS. A nomogram constructed based on the Cox regression was evaluated by Concordance index (C index), calibration curve, decision curve analysis (DCA) and area under curve (AUC). And 136 patients were recruited from Shandong Province Hospital for external validation.

Results

Cox analysis regression indicated that 12 factors, such as Diagnosis to Treatment Interval (DTI) and Income Level, were independent prognostic factors and were included to establish the nomogram. The C-index of our novel model was 0.702, 0.724 and 0.872 in the training, internal and external validation cohorts, respectively. The 3-year and 5-year survival AUCs and calibration curves showed excellent agreement in each cohort. Some new factors in the SEER database, including DTI and Income Level, were firstly confirmed as independent prognostic factors of Stage IA LUAD patients. The distribution of these factors in the T1a, T1b, and T1c subgroups differed and had different effects on survival.

Conclusion

We summarized 12 factors that affect prognosis and constructed a nomogram to predict OS of Stage IA LUAD patients who underwent operation. For the first time, new SEER database parameters, including DTI and Income Level, were proved to be survival-related.

What Goes into Patient Selection for Lung Cancer Screening? Factors Associated with Clinician Judgments of Suitability for Screening

Rationale: Achieving the net benefit of lung cancer screening (LCS) depends on optimizing patient selection. Objective: To identify factors associated with clinician assessments that a patient was unlikely to benefit from LCS ("LCS-inappropriate") because of comorbidities or limited life expectancy. Methods: Retrospective analysis of patients assessed for LCS at 30 Veterans Health Administration facilities from January 1, 2015 to February 1, 2021. We conducted hierarchical mixed-effects logistic regression analyses to determine factors associated with clinicians' designations of LCS inappropriateness (primary outcome), accounting for 3-year predicted probability (i.e., competing risk) of non-lung cancer death. Measurements and Main Results: Among 38,487 LCS-eligible patients, 1,671 (4.3%) were deemed LCS-inappropriate by clinicians, whereas 4,383 (11.4%) had an estimated 3-year competing risk of non-lung cancer death greater than 20%. Patients with higher competing risks of non-lung cancer death were more likely to be deemed LCS-inappropriate (odds ratio [OR], 2.66; 95% confidence interval [CI], 2.32-3.05). Older patients (ages 75-80; OR, 1.45; 95% CI, 1.18-1.78) and those with interstitial lung disease (OR, 1.98; 95% CI, 1.51-2.59) were more likely to be deemed LCS-inappropriate than would be explained by competing risk of non-lung cancer death, whereas patients currently smoking (OR, 0.65; 95% CI, 0.58-0.73) were less likely to be deemed LCS-inappropriate, suggesting that clinicians over- or underweighted these factors. The probability of being deemed LCS-inappropriate varied from 0.4% to 74%, depending on the clinician making the assessment (median OR, 3.07; 95% CI, 2.89-3.25). Conclusion: Concerningly, the likelihood that a patient is deemed LCS-inappropriate is more strongly associated with the clinician making the assessment than with patient characteristics. Patient selection may be optimized by providing decision support to help clinicians assess net LCS benefit.

Automatic Osteoporosis Screening System Using Radiomics and Deep Learning from Low-Dose Chest CT Images

OBJECTIVE

Develop two fully automatic osteoporosis screening systems using deep learning (DL) and radiomics (Rad) techniques based on low-dose chest CT (LDCT) images and evaluate their diagnostic effectiveness.

METHODS

In total, 434 patients who underwent LDCT and bone mineral density (BMD) examination were retrospectively enrolled and divided into the development set (n = 333) and temporal validation set (n = 101). An automatic thoracic vertebra cancellous bone (TVCB) segmentation model was developed. The Dice similarity coefficient (DSC) was used to evaluate the segmentation performance. Furthermore, the three-class Rad and DL models were developed to distinguish osteoporosis, osteopenia, and normal bone mass. The diagnostic performance of these models was evaluated using the receiver operating characteristic (ROC) curve and decision curve analysis (DCA).

RESULTS

The automatic segmentation model achieved excellent segmentation performance, with a mean DSC of 0.96 ± 0.02 in the temporal validation set. The Rad model was used to identify osteoporosis, osteopenia, and normal BMD in the temporal validation set, with respective area under the receiver operating characteristic curve (AUC) values of 0.943, 0.801, and 0.932. The DL model achieved higher AUC values of 0.983, 0.906, and 0.969 for the same categories in the same validation set. The Delong test affirmed that both models performed similarly in BMD assessment. However, the accuracy of the DL model is 81.2%, which is better than the 73.3% accuracy of the Rad model in the temporal validation set. Additionally, DCA indicated that the DL model provided a greater net benefit compared to the Rad model across the majority of the reasonable threshold probabilities Conclusions: The automated segmentation framework we developed can accurately segment cancellous bone on low-dose chest CT images. These predictive models, which are based on deep learning and radiomics, provided comparable diagnostic performance in automatic BMD assessment. Nevertheless, it is important to highlight that the DL model demonstrates higher accuracy and precision than the Rad model.

Two-stage minimally invasive pulmonary resections with intraoperative localization technique for bilateral multiple primary lung cancers: A case report

Multiple primary lung cancers (MPLCs) are becoming more and more common and these patients can benefit from minimally invasive surgery. Here, we report a case of a patient diagnosed with synchronous MPLCs who underwent bilateral thoracoscopic pulmonary resections in a two-stage strategy, and achieved a good surgical outcome and high quality of life. A 66-year-old female was found to have one major ground-glass nodule (GGN) in the right upper lobe and eight minor GGNs in the left upper and lower lobes. The patient underwent right upper lobe resection and systematic mediastinal lymph node dissection via single-utility port thoracoscopic surgery in September 2018. Pathology was lepidic predominant adenocarcinoma pT1bN0M0, IA2. Regular high-resolution computed tomography examination during 36 months after right upper lobectomy showed gradually increasing diameter and solid component of multiple GGNs in left lung. The patient underwent thoracoscopic multiple pulmonary resections using an intraoperative localization technique in a hybrid operating room in October 2021 and all eight nodules in the left lung were resected. Two segmentectomies and four wedge resections were performed, and the pathological results of the eight nodules included four adenocarcinomas, three adenocarcinomas in situ, and one alveolar epithelial hyperplasia. The two operations were successful with no intra- or postoperative 90-day complications. During more than 20 months of follow-up after the second operation, the patient had well recovered pulmonary function and physical status with a Karnofsky performance status score of 90 and no local recurrence or metastasis. A two-stage surgical strategy for synchronous MPLCs is therefore feasible. The surgical strategy, timing of intervention, and extent of pulmonary resection should be individually designed according to the location and characteristics of each nodule. Intraoperative localization of small GGNs is very important to ensure that all nodules are completely and accurately resected during the operation.

Factors influencing the intention for lung cancer screening in high-risk populations for lung cancer

Objective

Utilizing low-dose computed tomography for lung cancer screening has proven effective in reducing lung cancer mortality among high-risk individuals. This study aimed to investigate the health beliefs, knowledge of lung cancer, and cancer prevention behaviors in adults at high risk for lung cancer, with the goal of identifying predictors influencing their intention to undergo lung cancer screening.

Methods

The study utilized a descriptive cross-sectional design. Online questionnaires, including assessments of lung cancer screening health beliefs, knowledge of lung cancer, cancer prevention behaviors, intention to undergo lung cancer screening, and participant characteristics, were distributed to 186 individuals at high risk of lung cancer through a survey link. The data collection period spanned from April 26 to May 3, 2023. Analytical procedures encompassed descriptive statistics, independent t-test, one-way ANOVA, Pearson's correlations, and hierarchical multiple regression.

Results

The mean score for the intention to undergo lung cancer screening in our study was 3.66 out of 5. The regression model explaining the intention to undergo lung cancer screening accounted for 34.7% of the variance. Significant factors identified included stress level (β = 0.20, P = 0.002), perceived risk (β = 0.13, P = 0.040), self-efficacy (β = 0.35, P < 0.001), and engagement in cancer prevention behavior (β = 0.26, P < 0.001).

Conclusions

Healthcare providers should implement psychological interventions and provide education about cancer screening for high-risk individuals, aiming to enhance their perceived risk and self-efficacy, thus promoting a higher likelihood of undergoing screening.

The prognostic value of the preoperative albumin/globulin and monocyte ratio in resected early-stage non-small cell lung cancer

OBJECTIVE

This study investigated the prognostic value of the preoperative albumin/globulin to monocyte ratio (AGMR) in patients with resected non-small cell lung cancer (NSCLC).

METHODS

The study retrospectively enrolled patients with resected NSCLC from the Department of Thoracic Surgery, China-Japan Union Hospital of Jilin University from January 2016 to December 2017. Baseline demographic and clinicopathological data were collected. The preoperative AGMR was calculated. Propensity score matching (PSM) analysis was applied. The receiver operating characteristic curve was used to determine the optimal AGMR cut-off value. The Kaplan-Meier method was used to calculate the overall survival (OS) and disease-free survival (DFS). The Cox proportional hazards regression model was used to evaluate the prognostic value of the AGMR.

RESULTS

A total of 305 NSCLC patients were included. The optimal AGMR value was 2.80. Before PSM. The high AGMR (>2.80) group had a significantly longer OS (41.34 + 11.32 vs. 32.03 + 17.01 months; P < 0.01) and DFS (39.00 + 14.49 vs. 28.78 + 19.13 months; P < 0.01) compared with the low AGMR (≤2.80) group. Multivariate analyses showed that AGMR (P < 0.01) in addition to sex (P < 0.05), body mass index (P < 0.01), history of respiratory diseases (P < 0.01), lymph node metastasis (P < 0.01), and tumor size (P < 0.01) were associated with OS and DFS. After PSM, AGMR remained as an independent prognostic factor for OS (hazard ratio [HR] 2.572, 95% confidence interval [CI]: 1.470-4.502; P = 0.001) and DFS (HR 2.110, 95% CI: 1.228-3.626; P = 0.007).

CONCLUSION

The preoperative AGMR is a potential prognostic indicator for OS and DFS in resected early-stage NSCLC.

Metabolomics Analysis and Diagnosis of Lung Cancer: Insights from Diverse Sample Types

Lung cancer is a highly fatal disease that poses a significant global health burden. The absence of characteristic clinical symptoms frequently results in the diagnosis of most patients at advanced stages of lung cancer. Although low-dose computed tomography (LDCT) screening has become increasingly prevalent in clinical practice, its high rate of false positives continues to present a significant challenge. In addition to LDCT screening, tumor biomarker detection represents a critical approach for early diagnosis of lung cancer; unfortunately, no tumor marker with optimal sensitivity and specificity is currently available. Metabolomics has recently emerged as a promising field for developing novel tumor biomarkers. In this paper, we introduce metabolic pathways, instrument platforms, and a wide variety of sample types for lung cancer metabolomics. Specifically, we explore the strengths, limitations, and distinguishing features of various sample types employed in lung cancer metabolomics research. Additionally, we present the latest advances in lung cancer metabolomics research that utilize diverse sample types. We summarize and enumerate research studies that have investigated lung cancer metabolomics using different metabolomic sample types. Finally, we provide a perspective on the future of metabolomics research in lung cancer. Our discussion of the potential of metabolomics in developing new tumor biomarkers may inspire further study and innovation in this dynamic field.

"Low-age, low-frequency" lung cancer screening strategies maybe adaptable to the situation in China

BACKGROUND

The object was to compare changes in patients undergoing lung surgery before and after COVID-19 outbreak, and to explore the impact of COVID-19 on lung surgery and its coping strategies.

METHOD

A retrospective review of patients undergoing thoracic surgery at a single institution was conducted. Group A included patients treated between January 23, 2019, and January 23, 2020, while Group B included patients treated between June 1, 2020, and June 1, 2021, at our center. We compared the reasons of seeking medical treatment, the general characteristics of patients, imaging features, pathological features, surgical methods and postoperative recovery.

RESULT

Compared to Group A, the number of patients with pulmonary nodules screened by routine check-up increased in Group B (57.6% vs 46.9%, p < 0.05). Female patient increased (55.2%vs 44.7%). Patient without smoking history or with family history of lung cancer increased (70.7% vs 60.7%) (10.1%vs 7.8%). Early stage lung cancer increased. Lobectomy decreased (53.4% vs 64.1%). Segmental resection increased (33.3% vs 12.7%). Patients without postoperative comorbidities increased (96.1%vs 85.7%). In the case of patients with Ground Glass Opacity(GGO), their age was comparatively lower (52 ± 9.9 vs. 55 ± 10.7), the female patients increased, patient without smoking history, tumor history, family history of tumor increased, small GGO increased. Lobectomy decreased (35.2% vs 49.7%). Segmental resection increased (49.6% vs 21.2%). Patients without postoperative comorbidities increased (96.5% vs 87.4%).

CONCLUSION

Since COVID-19 outbreak, more young, non-smoking, female lung cancers, more Ground Glass Opacity, none high risk patients have been detected through screening, suggesting that our current screening criteria for lung cancer may need to be revised. Higher requirements, including the selection of the timing of nodular surgery, surgical methods were put forward for thoracic surgeons' skills.

Risk prediction of intraoperative pain in percutaneous microwave ablation of lung tumors under CT guidance

OBJECTIVES

To evaluate the effect of intraoperative pain in microwave ablation of lung tumors (MWALT) on local efficacy and establish the pain risk prediction model.

METHODS

It was a retrospectively study. Consecutive patients with MWALT from September 2017 to December 2020 were divided into mild and severe pain groups. Local efficacy was evaluated by comparing technical success, technical effectiveness, and local progression-free survival (LPFS) in two groups. All cases were randomly allocated into training and validation cohorts at a ratio of 7:3. A nomogram model was established using predictors identified by logistics regression in training dataset. The calibration curves, C-statistic, and decision curve analysis (DCA) were used to evaluate the accuracy, ability, and clinical value of the nomogram.

RESULTS

A total of 263 patients (mild pain group: n = 126; severe pain group: n = 137) were included in the study. Technical success rate and technical effectiveness rate were 100% and 99.2% in the mild pain group and 98.5% and 97.8% in the severe pain group. LPFS rates at 12 and 24 months were 97.6% and 87.6% in the mild pain group and 91.9% and 79.3% in the severe pain group (p = 0.034; HR: 1.90). The nomogram was established based on three predictors: depth of nodule, puncture depth, and multi-antenna. The prediction ability and accuracy were verified by C-statistic and calibration curve. DCA curve suggested the proposed prediction model was clinically useful.

CONCLUSIONS

Severe intraoperative pain in MWALT reduced the local efficacy. An established prediction model could accurately predict severe pain and assist physicians in choosing a suitable anesthesia type.

CLINICAL RELEVANCE STATEMENT

This study firstly provides a prediction model for the risk of severe intraoperative pain in MWALT. Physicians can choose a suitable anesthesia type based on pain risk, in order to improve patients' tolerance as well as local efficacy of MWALT.

KEY POINTS

• The severe intraoperative pain in MWALT reduced the local efficacy. • Predictors of severe intraoperative pain in MWALT were the depth of nodule, puncture depth, and multi-antenna. • The prediction model established in this study can accurately predict the risk of severe pain in MWALT and assist physicians in choosing a suitable anesthesia type.

Comparison of two methods for CT-guided pulmonary nodule location before thoracoscopic surgery

Introduction

Preoperative computed tomography (CT)-guided localization can shorten the time of video-assisted thoracoscopic surgery (VATS) and accurately aid in pulmonary nodule removal.

Aim

To discuss the application value and safety of 2 kinds of breast localization needles and anchor localization needles in clinical practice for pulmonary nodules under CT guidance before VATS.

Material and methods

We retrospectively studied 215 patients with 247 pulmonary nodules, who underwent CT-guided pulmonary nodule location before VATS. The 2 kinds of localization needles were randomly used, and we collected and analysed the clinical data.

Results

We used breast and anchor localization needles in 27.9% and 72.1% of cases, respectively. Differences were observed in puncture localization time, detachment rate, and visual analogue scale (VAS). The detachment rate (0%) and positioning time (median: 12 min) were less in the anchor than in the breast localization needle group (8.7% and median: 13 min, respectively). The median VAS was approximately 2 and 5 in the anchor and breast localization needle groups, respectively. Surgical pathology revealed that 155 (62.8%) pulmonary nodules were malignant while 92 (37.2%) were benign. The primary distinction in surgical procedures is the higher proportion of segmental resections in the middle and inner band group (19.3%) compared to the periphery band group (4.2%).

Conclusions

Unlike breast localization needles, anchor localization needles can reduce pain and discomfort after positioning, and they are not easy to decouple. These 2 needles are safe for CT-guided localization, which can shorten the time of VATS and accurately aid in pulmonary nodule removal.

Parameterized Gompertz-Guided Morphological AutoEncoder for Predicting Pulmonary Nodule Growth

The growth rate of pulmonary nodules is a critical clue to the cancerous diagnosis. It is essential to monitor their dynamic progressions during pulmonary nodule management. To facilitate the prosperity of research on nodule growth prediction, we organized and published a temporal dataset called NLSTt with consecutive computed tomography (CT) scans. Based on the self-built dataset, we develop a visual learner to predict the growth for the following CT scan qualitatively and further propose a model to predict the growth rate of pulmonary nodules quantitatively, so that better diagnosis can be achieved with the help of our predicted results. To this end, in this work, we propose a parameterized Gempertz-guided morphological autoencoder (GM-AE) to generate any future-time-span high-quality visual appearances of pulmonary nodules from the baseline CT scan. Specifically, we parameterize a popular mathematical model for tumor growth kinetics, Gompertz, to predict future masses and volumes of pulmonary nodules. Then, we exploit the expected growth rate on the mass and volume to guide decoders generating future shape and texture of pulmonary nodules. We introduce two branches in an autoencoder to encourage shape-aware and textural-aware representation learning and integrate the generated shape into the textural-aware branch to simulate the future morphology of pulmonary nodules. We conduct extensive experiments on the self-built NLSTt dataset to demonstrate the superiority of our GM-AE to its competitive counterparts. Experiment results also reveal the learnable Gompertz function enjoys promising descriptive power in accounting for inter-subject variability of the growth rate for pulmonary nodules. Besides, we evaluate our GM-AE model on an in-house dataset to validate its generalizability and practicality. We make its code publicly available along with the published NLSTt dataset.

The outpost against cancer: universal cancer only markers

Cancer is the leading cause of death worldwide. Early detection of cancer can lower the mortality of all types of cancer; however, effective early-detection biomarkers are lacking for most types of cancers. DNA methylation has always been a major target of interest because DNA methylation usually occurs before other detectable genetic changes. While investigating the common features of cancer using a novel guide positioning sequencing for DNA methylation, a series of universal cancer only markers (UCOMs) have emerged as strong candidates for effective and accurate early detection of cancer. While the clinical value of current cancer biomarkers is diminished by low sensitivity and/or low specificity, the unique characteristics of UCOMs ensure clinically meaningful results. Validation of the clinical potential of UCOMs in lung, cervical, endometrial, and urothelial cancers further supports the application of UCOMs in multiple cancer types and various clinical scenarios. In fact, the applications of UCOMs are currently under active investigation with further evaluation in the early detection of cancer, auxiliary diagnosis, treatment efficacy, and recurrence monitoring. The molecular mechanisms by which UCOMs detect cancers are the next important topics to be investigated. The application of UCOMs in real-world scenarios also requires implementation and refinement.

Results from Lung Cancer Screening Outreach Utilizing a Mobile CT Scanner in an Urban Area

INTRODUCTION

Lung cancer screening using low-dose (LD) CT reduces lung cancer-specific and all-cause mortality in high-risk individuals, although significant barriers to screening remain. We assessed the outreach of a mobile lung cancer screening program to increase screening accessibility and early detection of lung cancer.

METHODS

We placed a mobile CT unit in a high-traffic area in New York City and offered free screening to all eligible patients. Characteristics of the mobile screening cohort were compared with those of our hospital-based screening cohort.

RESULTS

Between December 9, 2019, and January 30, 2020, a total of 216 patients underwent mobile LDCT screening. Compared with the hospital-based screening cohort, mobile screening participants were significantly more likely to be younger, be uninsured, and have lower smoking intensity and were less likely to meet 2013 US Preventive Services Task Force guidelines (but would meet their 2021 guidelines) and self-identify as White race and Hispanic ethnicity. Asian New Yorkers were substantially underrepresented in both hospital and mobile screening cohorts, compared with their level of representation in New York City. Two patients were diagnosed with lung cancer and were treated. Potentially clinically significant non-lung cancer findings were identified in 28.2%, most commonly moderate-severe coronary artery calcification and emphysema.

CONCLUSIONS

Mobile LDCT screening is useful and effective in detecting lung cancer and other significant findings and may engage a distinct high-risk patient demographic. Disproportionately low screening rates among certain high-risk populations highlight the imperative of implementing strategies aimed at understanding health behaviors and access barriers for diverse populations. Effective care-navigation services, facilitating high-quality care for all patients, are critical.

Differences between physician and patient preferences for cancer treatments: a systematic review

BACKGROUND

Shared decision-making is useful to facilitate cancer treatment decisions. However, it is difficult to make treatment decisions when physician and patient preferences are different. This review aimed to summarize and compare the preferences for cancer treatments between physicians and patients.

METHODS

A systematic literature search was conducted on PubMed, Embase, PsycINFO, CINAHL and Scopus. Studies elicited and compared preferences for cancer treatments between physicians and patients were included. Information about the study design and preference measuring attributes or questions were extracted. The available relative rank of every attribute in discrete choice experiment (DCE) studies and answers to preference measuring questions in non-DCE studies were summarized followed by a narrative synthesis to reflect the preference differences.

RESULTS

Of 12,959 studies identified, 8290 were included in the title and abstract screening and 48 were included in the full text screening. Included 37 studies measured the preferences from six treatment-related aspects: health benefit, adverse effects, treatment process, cost, impact on quality of life, and provider qualification. The trade-off between health benefit and adverse effects was the main focus of the included studies. DCE studies showed patients gave a higher rank on health benefit and treatment process, while physicians gave a higher rank on adverse effects. Non-DCE studies suggested that patients were willing to take a higher risk of adverse effects or lower health benefit than physicians when accepting a treatment.

CONCLUSIONS

Physicians and patients had important preference differences for cancer treatment. More sufficient communication is needed in cancer treatment decision-making.

PTPRH promotes the progression of non-small cell lung cancer via glycolysis mediated by the PI3K/AKT/mTOR signaling pathway

BACKGROUND

The protein tyrosine phosphatase H receptor (PTPRH) is known to regulate the occurrence and development of pancreatic and colorectal cancer. However, its association with glycolysis in non-small cell lung cancer (NSCLC) is still unclear. In this study, we aimed to investigate the relationship between PTPRH expression and glucose metabolism and the underlying mechanism of action.

METHODS

The expression of PTPRH in NSCLC cells was evaluated by IHC staining, qRT‒PCR and Western blotting. The effect of PTPRH on cell biological behavior was evaluated by colony assays, EdU experiments, Transwell assays, wound healing assays and flow cytometry. Changes in F-18-fluorodeoxyglucose (18F-FDG) uptake and glucose metabolite levels after altering PTPRH expression were detected via a gamma counter and lactic acid tests. The expression of glycolysis-related proteins in NSCLC cells was detected by Western blotting after altering PTPRH expression.

RESULTS

The results showed that PTPRH was highly expressed in clinical patient tissue samples and closely related to tumor diameter and clinical stage. In addition, PTPRH expression was associated with glycometabolism indexes on 18F-FDG positron emission tomography/computed tomography (PET/CT) imaging, the expression level of Ki67 and the expression levels of glycolysis-related proteins. PTPRH altered cell behavior, inhibited apoptosis, and promoted 18F-FDG uptake, lactate production, and the expression of glycolysis-related proteins. In addition, PTPRH modulated the glycometabolism of NSCLC cells via the phosphatidylinositol-3-kinase (PI3K)/protein kinase B (AKT)/mammalian target of rapamycin (mTOR) signaling pathway, as assessed using LY294002 and 740Y-P (an inhibitor and agonist of PI3K, respectively). The same results were validated in vivo using a xenograft tumor model in nude mice. Protein expression levels of PTPRH, glycolysis-related proteins, p-PI3K/PI3K and p-AKT/AKT were measured by IHC staining using a subcutaneous xenograft model in nude mice.

CONCLUSIONS

In summary, we report that PTPRH promotes glycolysis, proliferation, migration, and invasion via the PI3K/AKT/mTOR signaling pathway in NSCLC and ultimately promotes tumor progression, which can be regulated by LY294002 and 740Y-P. These results suggest that PTPRH is a potential therapeutic target for NSCLC.

Diagnostic value of peripheral blood eosinophils for benign and malignant pulmonary nodule

This retrospective study aims to assess the diagnostic utility of peripheral blood eosinophil counts in distinguishing between benign and malignant pulmonary nodules (PNs) prior to surgical intervention. We involved patients presenting with PNs measuring ≤30 mm as the primary CT imaging finding prior to surgical procedures at the General Hospital of Northern Theater Command in Shenyang, China, during the period spanning 2021 to 2022. Multivariable logistic regression analysis and receiver operator characteristic curve analysis, along with area under the curve (AUC) calculations, were used to determine the diagnostic value of eosinophil. A total of 361 patients with PN were included, consisting of 135 with benign PN and 226 with malignant PN. Multivariable logistic regression analysis showed that eosinophil percentage (OR = 1.909, 95% CI: 1.323-2.844, P < .001), absolute eosinophil value (OR = 0.001, 95% CI: 0.000-0.452, P = .033), tumor diameter (OR = 0.918, 95% CI: 0.877-0.959, P < .001), nodule type (OR = 0.227, 95% CI: 0.125-0.400, P < .001), sex (OR = 2.577, 95% CI: 1.554-4.329, P < .001), and age (OR = 0.967, 95% CI: 0.945-0.989, P = .004) were independently associated with malignant PN. The diagnostic value of regression model (AUC [95% CI]: 0.775 [0.725-0.825]; sensitivity: 74.3%; specificity: 71.1%) was superior to eosinophil percentage (AUC [95% CI]: 0.616 [0.556-0.677]; specificity: 66.8%; specificity: 51.1%) (Delong test: P < .001). Peripheral blood eosinophil percentage might be useful for early malignant PN diagnosis, and combining that with other characteristics might improve the diagnostic performance.

Machine Learning Study of SNPs in Noncoding Regions to Predict Non-small Cell Lung Cancer Susceptibility

Non-small cell lung cancer (NSCLC) is the most common pathological subtype of lung cancer. Both environmental and genetic factors have been reported to impact the lung cancer susceptibility. We conducted a genome-wide association study (GWAS) of 287 NSCLC patients and 467 healthy controls in a Chinese population using the Illumina Genome-Wide Asian Screening Array Chip on 712,095 SNPs (single nucleotide polymorphisms). Using logistic regression modeling, GWAS identified 17 new noncoding region SNP loci associated with the NSCLC risk, and the top three (rs80040741, rs9568547, rs6010259) were under a stringent p-value (<3.02e-6). Notably, rs80040741 and rs6010259 were annotated from the intron regions of MUC3A and MLC1, respectively. Together with another five SNPs previously reported in Chinese NSCLC patients and another four covariates (e.g., smoking status, age, low dose CT screening, sex), a predictive model by machine learning methods can separate the NSCLC from healthy controls with an accuracy of 86%. This is the first time to apply machine learning method in predicting the NSCLC susceptibility using both genetic and clinical characteristics. Our findings will provide a promising method in NSCLC early diagnosis and improve our understanding of applying machine learning methods in precision medicine.

Historical Perspective on Lung Cancer Screening

Lung cancer represents a large burden on society with a staggering incidence and mortality rate that has steadily increased until recently. The impetus to design an effective screening program for the deadliest cancer in the United States and worldwide began in 1950. It has taken more than 50 years of numerous clinical trials and continued persistence to arrive at the development of modern-day screening program. As the program continues to grow, it is important for clinicians to understand its evolution, track outcomes, and continually assess the impact and bias of screening on the medical, social, and economic systems.

MANet: Multi-branch attention auxiliary learning for lung nodule detection and segmentation

BACKGROUND AND OBJECTIVE

Pulmonary nodule detection and segmentation are currently two primary tasks in analyzing chest computed tomography (Chest CT) in order to detect signs of lung cancer, thereby providing early treatment measures to reduce mortality. Even though there are many proposed methods to reduce false positives for obtaining effective detection results, distinguishing between the pulmonary nodule and background region remains challenging because their biological characteristics are similar and varied in size. The purpose of our work is to propose a method for automatic nodule detection and segmentation in Chest CT by enhancing the feature information of pulmonary nodules.

METHODS

We propose a new UNet-based backbone with multi-branch attention auxiliary learning mechanism, which contains three novel modules, namely, Projection module, Fast Cascading Context module, and Boundary Enhancement module, to further enhance the nodule feature representation. Based on that, we build MANet, a lung nodule localization network that simultaneously detects and segments precise nodule positions. Furthermore, our MANet contains a Proposal Refinement step which refines initially generated proposals to effectively reduce false positives and thereby produce the segmentation quality.

RESULTS

Comprehensive experiments on the combination of two benchmarks LUNA16 and LIDC-IDRI show that our proposed model outperforms state-of-the-art methods in the tasks of nodule detection and segmentation tasks in terms of FROC, IoU, and DSC metrics. Our method reports an average FROC score of 88.11% in lung nodule detection. For the lung nodule segmentation, the results reach an average IoU score of 71.29% and a DSC score of 82.74%. The ablation study also shows the effectiveness of the new modules which can be integrated into other UNet-based models.

CONCLUSIONS

The experiments demonstrated our method with multi-branch attention auxiliary learning ability are a promising approach for detecting and segmenting the pulmonary nodule instances compared to the original UNet design.