Prediction Model for Nodal Disease Among Patients With Non-Small Cell Lung Cancer

The American Cancer Society National Lung Cancer Roundtable strategic plan: Promoting guideline-concordant lung cancer staging

Accurate staging improves lung cancer survival by increasing the chances of delivering stage-appropriate therapy. However, there is underutilization of, and variability in, the use of guideline-recommended diagnostic tests used to stage lung cancer. Consequently, the American Cancer Society National Lung Cancer Roundtable (ACS NLCRT) convened the Triage for Appropriate Treatment Task Group-a multidisciplinary expert and stakeholder panel-to identify knowledge and/or resource gaps contributing to guideline-discordant staging and make recommendations to overcome these gaps. The task group determined the following: Gap 1: facilitators of and barriers to guideline-concordant staging are incompletely understood; Recommendation 1: identify facilitators of and barriers to guideline-concordant lung cancer staging; Gap 2: the level of evidence supporting staging algorithms is low-to-moderate; Recommendation 2: prioritize comparative-effectiveness studies evaluating lung cancer staging; Gap 3: guideline recommendations vary across professional societies; Recommendation 3: harmonize guideline recommendations across professional societies; Gap 4: existing databases do not contain sufficient information to measure guideline-concordant staging; Recommendation 4: augment existing databases with the information required to measure guideline-concordant staging; Gap 5: health systems do not have a performance feedback mechanism for lung cancer staging; Recommendation 5: develop and implement a performance feedback mechanism for lung cancer staging; Gap 6: patients rarely self-advocate for guideline-concordant staging; Recommendation 6: increase opportunities for patient self-advocacy for guideline-concordant staging; and Gap 7: current health policies do not motivate guideline-concordant lung cancer staging; Recommendation 7: organize a representative working group under the ACS NLCRT that promotes policies that motivate guideline-concordant lung cancer staging. PLAIN LANGUAGE SUMMARY: Staging-determining the degree of cancer spread-is important because it helps clinicians choose the best cancer treatment. Receiving the best cancer treatment leads to the best possible patient outcomes. Practice guidelines are intended to help clinicians stage patients with lung cancer. However, lung cancer staging in the United States often varies from practice guideline recommendations. This report identifies seven opportunities to improve lung cancer staging.

Preoperative computed tomography semantic features in predicting lymph node metastasis of part-solid nodules in non-small cell lung cancer: a multicenter retrospective study

Background

Lymph node metastasis (LNM) is the most common route of metastasis for lung cancer, and it is an independent risk factor for long-term survival and recurrence in patients with non-small cell lung cancer (NSCLC). The purpose of this study was to explore the value of preoperative computed tomography (CT) semantic features in the differential diagnosis of LNM in part-solid nodules (PSNs) of NSCLC.

Methods

A total of 955 patients with NSCLC confirmed by postoperative pathology were retrospectively enrolled from January 2019 to March 2023. The clinical, pathological data and preoperative CT images of these patients were investigated and statistically analyzed in order to identify the risk factors for LNM. Multivariate logistic regression was used to select independent risk factors and establish different prediction models. Ten-fold cross-validation was used for model training and validation. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was calculated, and the Delong test was used to compare the predictive performance between the models.

Results

LNM occurred in 68 of 955 patients. After univariate analysis and adjustment for confounding factors, smoking history, pulmonary disease, solid component proportion, pleural contact type, and mean diameter were identified as the independent risk factors for LNM. The image predictors model established by the four independent factors of CT semantic features, except smoking history, showed a good diagnostic efficacy for LNM. The AUC in the validation group was 0.857, and the sensitivity, specificity, and accuracy of the model were all 77.6%.

Conclusions

Preoperative CT semantic features have good diagnostic value for the LNM of NSCLC. The image predictors model based on pulmonary disease, solid component proportion, pleural contact type, and mean diameter demonstrated excellent diagnostic efficacy and can provide non-invasive evaluation in clinical practice.

Lymph node metastasis in early invasive lung adenocarcinoma: Prediction model establishment and validation based on genomic profiling and clinicopathologic characteristics

BACKGROUND

The presence of lymph node (LN) metastasis directly affects the treatment strategy for lung adenocarcinoma (LUAD). Next-generation sequencing (NGS) has been widely used in patients with advanced LUAD to identify targeted genes, while early detection of pathologic LN metastasis using NGS has not been assessed.

METHODS

Clinicopathologic features and molecular characteristics of 224 patients from Ruijin Hospital were analyzed to detect factors associated with LN metastases. Another 140 patients from Huashan Hospital were set as a test cohort.

RESULTS

Twenty-four out of 224 patients were found to have lymph node metastases (10.7%). Pathologic LN-positive tumors showed higher mutant allele tumor heterogeneity (p < 0.05), higher tumor mutation burden (p < 0.001), as well as more frequent KEAP1 (p = 0.001), STK11 (p = 0.004), KRAS (p = 0.007), CTNNB1 (p = 0.017), TP53, and ARID2 mutations (both p = 0.02); whereas low frequency of EGFR mutation (p = 0.005). A predictive nomogram involving male sex, solid tumor morphology, higher T stage, EGFR wild-type, and TP53, STK11, CDKN2A, KEAP1, ARID2, KRAS, SDHA, SPEN, CTNNB1, DICER1 mutations showed outstanding efficiency in both the training cohort (AUC = 0.819) and the test cohort (AUC = 0.780).

CONCLUSION

This study suggests that the integration of genomic profiling and clinical features identifies early-invasive LUAD patients at higher risk of LN metastasis. Improved identification of LN metastasis is beneficial for the optimization of the patient's therapy decisions.

Prediction Models for Mediastinal Metastasis and Its Detection by Endobronchial Ultrasound-Guided Transbronchial Needle Aspiration in Potentially Operable Non-Small Cell Lung Cancer: A Prospective Study

BACKGROUND

Prediction models for mediastinal metastasis and its detection by endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) have not been developed using a prospective cohort of potentially operable patients with non-small cell lung cancer (NSCLC).

RESEARCH QUESTION

Can mediastinal metastasis and its detection by EBUS-TBNA be predicted with prediction models in NSCLC?

STUDY DESIGN AND METHODS

For the prospective development cohort, 589 potentially operable patients with NSCLC were evaluated (July 2016-June 2019) from five Korean teaching hospitals. Mediastinal staging was performed using EBUS-TBNA (with or without the transesophageal approach). Surgery was performed for patients without clinical N (cN) 2-3 disease by endoscopic staging. The prediction model for lung cancer staging-mediastinal metastasis (PLUS-M) and a model for mediastinal metastasis detection by EBUS-TBNA (PLUS-E) were developed using multivariable logistic regression analyses. Validation was performed using a retrospective cohort (n = 309) from a different period (June 2019-August 2021).

RESULTS

The prevalence of mediastinal metastasis diagnosed by EBUS-TBNA or surgery and the sensitivity of EBUS-TBNA in the development cohort were 35.3% and 87.0%, respectively. In PLUS-M, younger age (< 60 years and 60-70 years compared with ≥ 70 years), nonsquamous histology (adenocarcinoma and others), central tumor location, tumor size (> 3-5 cm), cN1 or cN2-3 stage by CT, and cN1 or cN2-3 stage by PET-CT were significant risk factors for N2-3 disease. Areas under the receiver operating characteristic curve (AUCs) for PLUS-M and PLUS-E were 0.876 (95% CI, 0.845-0.906) and 0.889 (95% CI, 0.859-0.918), respectively. Model fit was good (PLUS-M: Hosmer-Lemeshow P = .658, Brier score = 0.129; PLUS-E: Hosmer-Lemeshow P = .569, Brier score = 0.118). In the validation cohort, PLUS-M (AUC, 0.859 [95% CI, 0.817-0.902], Hosmer-Lemeshow P = .609, Brier score = 0.144) and PLUS-E (AUC, 0.900 [95% CI, 0.865-0.936], Hosmer-Lemeshow P = .361, Brier score = 0.112) showed good discrimination ability and calibration.

INTERPRETATION

PLUS-M and PLUS-E can be used effectively for decision-making for invasive mediastinal staging in NSCLC.

TRIAL REGISTRY

ClinicalTrials.gov; No.: NCT02991924; URL: www.

CLINICALTRIALS

gov.

Endobronchial Ultrasound/Transbronchial Needle Aspiration-Biopsy for Systematic Mediastinal lymph Node Staging of Non-Small Cell Lung Cancer in Patients Eligible for Surgery: A Prospective Multicenter Study

BACKGROUND

The treatment of lung cancer depends on histological and/or cytological evaluation of the mediastinal lymph nodes. Endobronchial ultrasound/transbronchial needle aspiration-biopsy (EBUS/TBNA-TBNB) is the only minimally invasive technique for a diagnostic exploration of the mediastinum. The aim of this study is to analyze the reliability of EBUS in the preoperative staging of non-small cell lung cancer (NSCLC).

METHODS

A prospective study was conducted from December 2019 to December 2022 on 217 NSCLC patients, who underwent preoperative mediastinal staging using EBUS/TBNA-TBNB according to the ACCP and ESTS guidelines. The following variables were analyzed in order to define the performance of the endoscopic technique-comparing the final staging of lung cancer after pulmonary resection with the operative histological findings: clinical characteristics, lymph nodes examined, number of samples, and likelihood ratio for positive and negative outcomes.

RESULTS

No morbidity or mortality was noted. All patients were discharged from hospital on day one. In 201 patients (92.6%), the preoperative staging using EBUS and the definitive staging deriving from the evaluation of the operative specimen after lung resection were the same; the same number of patients were detected in downstaging and upstaging (8 and 8, 7.4%). The sensitivity, specificity, positive and negative predictive value, and diagnostic accuracy were 90%, 90%, 82%, 94%, and 90%, respectively. The likelihood ratio for positive and negative results was 9 and 0.9, respectively, confirming cancer when present and excluding it when absent.

CONCLUSIONS

EBUS is the only low-invasive and easy procedure for mediastinal staging. The possibility to check the method in each of its phases-through direct visualization of the vessels regardless of their location in relation to the lymph nodes-makes it safe both for the endoscopist and for the patient. Certainly, the cytologist/histologist and/or operator must have adequate expertise in order not to negatively affect the outcome of the method, although three procedures appear to reduce the impact of the individual professional involved on performance.

Mathematical models for intraoperative prediction of metastasis to regional lymph nodes in patients with clinical stage I non-small cell lung cancer

It remains challenging to determine the regions of metastasis to lymph nodes during operation for clinical stage I non-small cell lung cancer (NSCLC). This study aimed to establish intraoperative mathematical models with nomograms for predicting the hilar-intrapulmonary node metastasis (HNM) and the mediastinal node metastasis (MNM) in patients with clinical stage I NSCLC. The clinicopathological variables of 585 patients in a derivation cohort who underwent thoracoscopic lobectomy with complete lymph node dissection were retrospectively analyzed for their association with the HNM or the MNM. After analyzing the variables, we developed multivariable logistic models with nomograms to estimate the risk of lymph node metastasis in different regions. The predictive efficacy was then validated in a validation cohort of 418 patients. It was confirmed that carcinoembryonic antigen (>5.75 ng/mL), CYFRA211 (>2.85 ng/mL), the maximum diameter of tumor (>2.75 cm), tumor differentiation (grade III), bronchial mucosa and cartilage invasion, and vascular invasion were predictors of HNM, and carcinoembryonic antigen (>8.25 ng/mL), CYFRA211 (>2.95 ng/mL), the maximum diameter of tumor (>2.75 cm), tumor differentiation (grade III), bronchial mucosa and cartilage invasion, vascular invasion, and visceral pleural invasion were predictors of MNM. The validation of the prediction models based on the above results demonstrated good discriminatory power. Our predictive models are helpful in the decision-making process of specific therapeutic strategies for the regional lymph node metastasis in patients with clinical stage I NSCLC.

Using Natural Language Processing and Machine Learning to Preoperatively Predict Lymph Node Metastasis for Non-Small Cell Lung Cancer With Electronic Medical Records: Development and Validation Study

Background

Lymph node metastasis (LNM) is critical for treatment decision making of patients with resectable non–small cell lung cancer, but it is difficult to precisely diagnose preoperatively. Electronic medical records (EMRs) contain a large volume of valuable information about LNM, but some key information is recorded in free text, which hinders its secondary use.

Objective

This study aims to develop LNM prediction models based on EMRs using natural language processing (NLP) and machine learning algorithms.

Methods

We developed a multiturn question answering NLP model to extract features about the primary tumor and lymph nodes from computed tomography (CT) reports. We then combined these features with other structured clinical characteristics to develop LNM prediction models using machine learning algorithms. We conducted extensive experiments to explore the effectiveness of the predictive models and compared them with size criteria based on CT image findings (the maximum short axis diameter of lymph node >10 mm was regarded as a metastatic node) and clinician’s evaluation. Since the NLP model may extract features with mistakes, we also calculated the concordance correlation between the predicted probabilities of models using NLP-extracted features and gold standard features to explore the influence of NLP-driven automatic extraction.

Results

Experimental results show that the random forest models achieved the best performances with 0.792 area under the receiver operating characteristic curve (AUC) value and 0.456 average precision (AP) value for pN2 LNM prediction and 0.768 AUC value and 0.524 AP value for pN1&N2 LNM prediction. And all machine learning models outperformed the size criteria and clinician’s evaluation. The concordance correlation between the random forest models using NLP-extracted features and gold standard features is 0.950 and improved to 0.984 when the top 5 important NLP-extracted features were replaced with gold standard features.

Conclusions

The LNM models developed can achieve competitive performance using only limited EMR data such as CT reports and tumor markers in comparison with the clinician’s evaluation. The multiturn question answering NLP model can extract features effectively to support the development of LNM prediction models, which may facilitate the clinical application of predictive models.

Pretreatment Invasive Nodal Staging in Lung Cancer: Knowledge, Attitudes, and Beliefs Among Academic and Community Physicians

BACKGROUND

Pretreatment invasive nodal staging is paramount for appropriate treatment decisions in non-small cell lung cancer. Despite guidelines recommending when to perform staging, many studies suggest that invasive nodal staging is underused. Attitudes and barriers to guideline-recommended staging are unclear. The National Lung Cancer Roundtable initiated this study to better understand the factors associated with guideline-adherent nodal staging.

RESEARCH QUESTION

What are the knowledge gaps, attitudes, and beliefs of thoracic surgeons and pulmonologists about invasive nodal staging? What are the barriers to guideline-recommended staging?

STUDY DESIGN AND METHODS

A web-based survey of a random sample of pulmonologists and thoracic surgeons identified as members of American College of Chest Physicians (CHEST) was conducted in 2019. Survey domains included knowledge of invasive nodal staging guidelines, attitudes and beliefs toward implementation, and perceived barriers to guideline adherence.

RESULTS

Among 453 responding physicians, 29% were unaware that invasive nodal staging guidelines exist. Among the 320 physicians who knew guidelines exist, attitudes toward the guidelines were favorable, with 91% agreeing guidelines are generalizable and 90% agreeing that recommendations improved their staging and treatment decisions. Approximately 80% responded that guideline recommendations are based on satisfactory levels of scientific evidence, and 50% stated a lack of evidence linking adherence to guidelines to changes in management or better patient outcomes. Nearly 9 in 10 physicians reported at least one barrier to guideline adherence. The most common barriers included patient anxiety associated with treatment delays (62%), difficulty implementing guidelines into routine practice (52%), and time delays of additional testing (51%).

INTERPRETATION

Among physicians who responded to our survey, more than one-quarter were unaware of invasive nodal staging guidelines. Attitudes toward guideline recommendations were positive, although 20% reported insufficient evidence to support staging algorithms. Most physicians reported barriers to implementing guidelines. Multilevel interventions are likely needed to increase rates of guideline-recommended invasive nodal staging.

Radiomics-guided deep neural networks stratify lung adenocarcinoma prognosis from CT scans

Deep learning (DL) is a breakthrough technology for medical imaging with high sample size requirements and interpretability issues. Using a pretrained DL model through a radiomics-guided approach, we propose a methodology for stratifying the prognosis of lung adenocarcinomas based on pretreatment CT. Our approach allows us to apply DL with smaller sample size requirements and enhanced interpretability. Baseline radiomics and DL models for the prognosis of lung adenocarcinomas were developed and tested using local (n = 617) cohort. The DL models were further tested in an external validation (n = 70) cohort. The local cohort was divided into training and test cohorts. A radiomics risk score (RRS) was developed using Cox-LASSO. Three pretrained DL networks derived from natural images were used to extract the DL features. The features were further guided using radiomics by retaining those DL features whose correlations with the radiomics features were high and Bonferroni-corrected p-values were low. The retained DL features were subject to a Cox-LASSO when constructing DL risk scores (DRS). The risk groups stratified by the RRS and DRS showed a significant difference in training, testing, and validation cohorts. The DL features were interpreted using existing radiomics features, and the texture features explained the DL features well.

Preoperative clinical and tumor genomic features associated with pathologic lymph node metastasis in clinical stage I and II lung adenocarcinoma

While next-generation sequencing (NGS) is used to guide therapy in patients with metastatic lung adenocarcinoma (LUAD), use of NGS to determine pathologic LN metastasis prior to surgery has not been assessed. To bridge this knowledge gap, we performed NGS using MSK-IMPACT in 426 treatment-naive patients with clinical N2-negative LUAD. A multivariable logistic regression model that considered preoperative clinical and genomic variables was constructed. Most patients had cN0 disease (85%) with pN0, pN1, and pN2 rates of 80%, 11%, and 9%, respectively. Genes altered at higher rates in pN-positive than in pN-negative tumors were STK11 (p = 0.024), SMARCA4 (p = 0.006), and SMAD4 (p = 0.011). Fraction of genome altered (p = 0.037), copy number amplifications (p = 0.001), and whole-genome doubling (p = 0.028) were higher in pN-positive tumors. Multivariable analysis revealed solid tumor morphology, tumor SUVmax, clinical stage, SMARCA4 and SMAD4 alterations were independently associated with pathologic LN metastasis. Incorporation of clinical and tumor genomic features can identify patients at risk of pathologic LN metastasis; this may guide therapy decisions before surgical resection.

How We Do It: Mediastinal Staging for Lung Cancer

Mediastinal lymph node staging in the setting of known or suspected lung cancer is supported by multiple professional societies as standard for high-quality care, yet proper mediastinal staging often is lacking. Neglecting pathologic lymph node sampling can understage or overstage the patient and lead to inappropriate treatment. Although some cases of nodal disease are radiographically obvious, others are not as apparent, and both situations require pathologic proof to allow for appropriate treatment selection. This article discusses the nuances of mediastinal staging and emphasizes the usefulness of a multidisciplinary approach and dialog to address lung cancer staging and treatment. We summarize the relevant guidelines and literature and provide a case scenario to illustrate the approach to mediastinal staging from our viewpoints as a thoracic surgeon and pulmonologist.

An Accurate Clinical Implication Assessment for Diabetes Mellitus Prevalence Based on a Study from Nigeria

The increasing rate of diabetes is found across the planet. Therefore, the diagnosis of pre-diabetes and diabetes is important in populations with extreme diabetes risk. In this study, a machine learning technique was implemented over a data mining platform by employing Rule classifiers (PART and Decision table) to measure the accuracy and logistic regression on the classification results for forecasting the prevalence in diabetes mellitus patients suffering simultaneously from other chronic disease symptoms. The real-life data was collected in Nigeria between December 2017 and February 2019 by applying ten non-intrusive and easily available clinical variables. The results disclosed that the Rule classifiers achieved a mean accuracy of 98.75%. The error rate, precision, recall, F-measure, and Matthew’s correlation coefficient MCC were 0.02%, 0.98%, 0.98%, 0.98%, and 0.97%, respectively. The forecast decision, achieved by employing a set of 23 decision rules (DR), indicates that age, gender, glucose level, and body mass are fundamental reasons for diabetes, followed by work stress, diet, family diabetes history, physical exercise, and cardiovascular stroke history. The study validated that the proposed set of DR is practical for quick screening of diabetes mellitus patients at the initial stage without intrusive medical tests and was found to be effective in the initial diagnosis of diabetes.