Risk prediction models for lung cancer: Perspectives and dissemination

Facing an un-met need in lung cancer screening: The never smokers

Lung cancer (LC) is the leading cause of cancer-related deaths worldwide and the second most common cancer in both men and women. In addition to smoking, other risk factors, such as environmental tobacco smoke, air pollution, biomass combustion, radon gas, occupational exposure, lung disease, family history of cancer, geographic variability, and genetic factors, play an essential role in developing LC. Current screening guidelines and eligibility criteria have limited efficacy in identifying LC cases (50 %), as most screening programs primarily target subjects with a smoking history as the leading risk factor. Implementing LC screening programs in people who have never smoked (PNS) can significantly impact cancer-specific survival and early disease detection. However, the available evidence regarding the feasibility and effectiveness of such programs is limited. Therefore, further research on LC screening in PNS is warranted to determine the necessary techniques for accurately identifying individuals who should be included in screening programs.

A collection of multiregistry data on patients at high risk of lung cancer-a Danish retrospective cohort study of nearly 40,000 patients

Background

Lung cancer (LC) is the leading cause of cancer related deaths, and several countries are implementing screening programs. Risk models have been introduced to refine the LC screening criteria, but the use of real-world data for this task demands a robust data infrastructure and quality. In this retrospective cohort study, we aim to address the different relevant risk factors in terms of data sources, descriptive statistics, completeness and quality.

Methods

Data on comorbidity, prescription medication, smoking history, consultations, symptoms, familial predispositions, exposures, laboratory data among others were collected for all patients examined on a risk of LC over a 10-year period in the Region of Southern Denmark. Data were delivered from the regional data warehouse as well as the Danish Lung Cancer Registry. Associations between LC and non-LC groups were examined through Chi-squared test (categorical variables) and Wilcoxon signed-rank test (continuous variables that were non-parametric). These associations were investigated on both the original datasets and the subset of patients with complete data.

Results

The number of examined individuals increased over the study period and more patients were diagnosed with LC in stage I-II, from 18% in 2009 to 31% in 2018. LC patients were more likely to be older, smoker, with a registered prescription of the included medication. They also exhibited differences in laboratory analysis indicating inflammation and hyponatremia. Weight loss, fatigue and pain were more prevalent in the LC group, while hemoptysis and fever were more common among the non-LC patients. Advanced-stage LC patients experienced a higher rate of symptoms compared to those in the low stages. Within the sub-cohort with complete dataset results, most observed trends persisted, although data on comorbidities were susceptibility to change.

Conclusions

This study provides key insights into LC risk assessment using a robust dataset of patients examined for suspected LC. A consistent positive trend in early-stage LC diagnosis was observed throughout the study period. LC patients exhibited distinct smoking behaviors, medication patterns, variations in lab results, and specific symptoms. These discoveries have the potential to enhance discrimination in machine learning-based prediction models, particularly those capable of handling complex distributions. Serving as a detailed account of real-world data collection and processing, the study establishes a foundation for future development of prediction models aimed at facilitating the early referral of LC patients.

Derivation and validation of a prediction model for patients with lung nodules malignancy regardless of mediastinal/hilar lymphadenopathy

BACKGROUND

Clinical prediction models to classify lung nodules often exclude patients with mediastinal/hilar lymphadenopathy, although the presence of mediastinal/hilar lymphadenopathy does not always indicate malignancy. Herein, we developed and validated a multimodal prediction model for lung nodules in which patients with mediastinal/hilar lymphadenopathy were included.

METHODS

A single-center retrospective study was conducted. We developed and validated a logistic regression model including patients with mediastinal/hilar lymphadenopathy. Discrimination of the model was assessed by area under the operating curve. Goodness of fit test was performed via the Hosmer-Lemeshow test, and a nomogram of the logistic regression model was drawn.

RESULTS

There were 311 cases included in the final analysis. A logistic regression model was developed and validated. There were nine independent variables included in the model. The aera under the curve (AUC) of the validation set was 0.91 (95% confidence interval [CI]: 0.85-0.98). In the validation set with mediastinal/hilar lymphadenopathy, the AUC was 0.95 (95% CI: 0.90-0.99). The goodness-of-fit test was 0.22.

CONCLUSIONS

We developed and validated a multimodal risk prediction model for lung nodules with excellent discrimination and calibration, regardless of mediastinal/hilar lymphadenopathy. This broadens the application of lung nodule prediction models. Furthermore, mediastinal/hilar lymphadenopathy added value for predicting lung nodule malignancy in clinical practice.

Radiologists can visually predict mortality risk based on the gestalt of chest radiographs comparable to a deep learning network

Deep learning convolutional neural network (CNN) can predict mortality from chest radiographs, yet, it is unknown whether radiologists can perform the same task. Here, we investigate whether radiologists can visually assess image gestalt (defined as deviation from an unremarkable chest radiograph associated with the likelihood of 6-year mortality) of a chest radiograph to predict 6-year mortality. The assessment was validated in an independent testing dataset and compared to the performance of a CNN developed for mortality prediction. Results are reported for the testing dataset only (n = 100; age 62.5 ± 5.2; male 55%, event rate 50%). The probability of 6-year mortality based on image gestalt had high accuracy (AUC: 0.68 (95% CI 0.58–0.78), similar to that of the CNN (AUC: 0.67 (95% CI 0.57–0.77); p = 0.90). Patients with high/very high image gestalt ratings were significantly more likely to die when compared to those rated as very low (p ≤ 0.04). Assignment to risk categories was not explained by patient characteristics or traditional risk factors and imaging findings (p ≥ 0.2). In conclusion, assessing image gestalt on chest radiographs by radiologists renders high prognostic accuracy for the probability of mortality, similar to that of a specifically trained CNN. Further studies are warranted to confirm this concept and to determine potential clinical benefits.

Development of risk prediction models for lung cancer based on tumor markers and radiological signs

Background

Accurate prediction of malignancy risk for pulmonary lesions with pleural effusion improves early diagnosis of lung cancer. This study aimed to develop and validate a model to predict lung cancer.

Methods

Clinical data of 536 patients with pulmonary diseases were collected. The risk factors were identified by regression analysis. Three prediction models were developed. The predictive performances of the models were measured by the area under the curves (AUCs) and calibrated with 1000 bootstrap samples to minimize the over‐fitting bias. The net benefits of the models were evaluated by decision curve analysis. Finally, a separate cohort of 134 patients was used to validate the models externally.

Results

Seven independent risk factors were identified from 18 clinical variables, which included the pleural fluid carcinoembryonic antigen (CEA), serum cytokeratin‐19 fragment (CYFRA 21‐1), the ratio of CEA in the pleural fluid to serum, extrathoracic cancer history (>5 years), tumor size, vessel convergence, and lobulation. The AUCs of the three models were 0.976, 0.927, and 0.944 in the training set and 0.930, 0.845, and 0.944 in the external set, respectively. The accuracies of the three models were 89.6%, 81.4%, and 88.8%. Model 1 showed the best iteration fit (R² = 0.84, 0.68, and 0.73) and a higher net benefit on decision curve analysis when compared to the other two models.

Conclusion

The advantageous model could assess the risk of lung cancer in patients with pleural effusion and act as a useful tool for early identification of lung cancer.

Advances and challenges in immunotherapy of small cell lung cancer

Small cell lung cancer (SCLC) is a highly lethal disease, characterized by early metastasis and rapid growth, and no effective treatment after relapse. Etoposide-platinum (EP) combination has been the backbone therapy of SCLC over the past 30 years. It is extremely urgent and important to seek new therapies for SCLC. In the past 5 years, immunotherapy, such as immune checkpoint inhibitors programmed cell death protein-1 (PD-1), cytotoxic T lymphocyte associatedprotein-4 (CTLA-4), has made remarkable achievements in the treatment of patients with SCLC, and it has become the first-line option for the treatment of some patients. Some traditional chemotherapeutic drugs or targeted drugs, such as alkylating agent temozolomide and transcription inhibitor lurbinectedin, have been found to have immunomodulatory effects and are expected to become new immunotherapeutic agents. In this study, we aimed to review the efficacy of new treatments for SCLC and discuss the current challenges and application prospect in the treatment of SCLC patients.

Automatic Segmentation of the Gross Target Volume in Non-Small Cell Lung Cancer Using a Modified Version of ResNet

Radiotherapy plays an important role in the treatment of non-small cell lung cancer. Accurate segmentation of the gross target volume is very important for successful radiotherapy delivery. Deep learning techniques can obtain fast and accurate segmentation, which is independent of experts’ experience and saves time compared with manual delineation. In this paper, we introduce a modified version of ResNet and apply it to segment the gross target volume in computed tomography images of patients with non-small cell lung cancer. Normalization was applied to reduce the differences among images and data augmentation techniques were employed to further enrich the data of the training set. Two different residual convolutional blocks were used to efficiently extract the deep features of the computed tomography images, and the features from all levels of the ResNet were merged into a single output. This simple design achieved a fusion of deep semantic features and shallow appearance features to generate dense pixel outputs. The test loss tended to be stable after 50 training epochs, and the segmentation took 21 ms per computed tomography image. The average evaluation metrics were: Dice similarity coefficient, 0.73; Jaccard similarity coefficient, 0.68; true positive rate, 0.71; and false positive rate, 0.0012. Those results were better than those of U-Net, which was used as a benchmark. The modified ResNet directly extracted multi-scale context features from original input images. Thus, the proposed automatic segmentation method can quickly segment the gross target volume in non-small cell lung cancer cases and be applied to improve consistency in contouring.