Identification of high-risk population of pneumoconiosis using deep learning segmentation of lung 3D images and radiomics texture analysis.

OBJECTION: The aim of this study is to develop an early-warning model for identifying high-risk populations of pneumoconiosis by combining lung 3D images and radiomics lung texture features. METHODS: A retrospective study was conducted, including 600 dust-exposed workers and 300 confirmed pneumoconiosis patients. Chest computed tomography (CT) images were divided into a training set and a test set in a 2:1 ratio. Whole-lung segmentation was performed using deep learning models for feature extraction of radiomics. Two feature selection algorithms and five classification models were used. The optimal model was selected using a 10-fold cross-validation strategy, and the calibration curve and decision curve were evaluated. To verify the applicability of the model, the diagnostic efficiency and accuracy between the model and human interpretation were compared. Additionally, the risk probabilities for different risk groups defined by the model were compared at different time intervals. RESULTS: Four radiomics features were ultimately used to construct the predictive model. The logistic regression model was the most stable in both the training set and testing set, with an area under curve (AUC) of 0.964 (95 % confidence interval [CI], 0.950-0.976) and 0.947 (95 %CI, 0.925-0.964). In the training and testing sets, the Brier scores were 0.092 and 0.14, respectively, with threshold probability ranges of 2 %-99 % and 2 %-85 %. These results indicate that the model exhibits good calibration and clinical benefit. The comparison between the model and human interpretation showed that the model was not inferior in terms of diagnostic efficiency and accuracy. Additionally, the high-risk population identified by the model was diagnosed as pneumoconiosis two years later. CONCLUSION: This study provides a meticulous and quantifiable method for detecting and assessing the risk of pneumoconiosis, building upon accurate diagnosis. Employing risk scoring and probability estimation, not only enhances the efficiency of diagnostic physicians but also provides a valuable reference for controlling the occurrence of pneumoconiosis.

Predicting the risk of nodular thyroid disease in coal miners based on different machine learning models.

Background: Nodular thyroid disease is by far the most common thyroid disease and is closely associated with the development of thyroid cancer. Coal miners with chronic coal dust exposure are at higher risk of developing nodular thyroid disease. There are few studies that use machine learning models to predict the occurrence of nodular thyroid disease in coal miners. The aim of this study was to predict the high risk of nodular thyroid disease in coal miners based on five different Machine learning (ML) models. Methods: This is a retrospective clinical study in which 1,708 coal miners who were examined at the Huaihe Energy Occupational Disease Control Hospital in Anhui Province in April 2021 were selected and their clinical physical examination data, including general information, laboratory tests and imaging findings, were collected. A synthetic minority oversampling technique (SMOTE) was used for sample balancing, and the data set was randomly split into a training and Test dataset in a ratio of 8:2. Lasso regression and correlation heat map were used to screen the predictors of the models, and five ML models, including Extreme Gradient Augmentation (XGBoost), Logistic Classification (LR), Gaussian Parsimonious Bayesian Classification (GNB), Neural Network Classification (MLP), and Complementary Parsimonious Bayesian Classification (CNB) for their predictive efficacy, and the model with the highest AUC was selected as the optimal model for predicting the occurrence of nodular thyroid disease in coal miners. Result: Lasso regression analysis showed Age, H-DLC, HCT, MCH, PLT, and GGT as predictor variables for the ML models; in addition, heat maps showed no significant correlation between the six variables. In the prediction of nodular thyroid disease, the AUC results of the five ML models, XGBoost (0.892), LR (0.577), GNB (0.603), MLP (0.601), and CNB (0.543), with the XGBoost model having the largest AUC, the model can be applied in clinical practice. Conclusion: In this research, all five ML models were found to predict the risk of nodular thyroid disease in coal miners, with the XGBoost model having the best overall predictive performance. The model can assist clinicians in quickly and accurately predicting the occurrence of nodular thyroid disease in coal miners, and in adopting individualized clinical prevention and treatment strategies.

Association of coal mine dust lung disease with Nodular thyroid disease in coal miners: A retrospective observational study in China.

Background: Coal dust is a major risk factor for the occupational health of coal miners, and underground workers with coal mine dust lung disease (Coal miners with coal mine dust lung disease (CMDLD) may have a higher risk of developing Nodular thyroid disease (NTD). The aim of this study was to investigate the relationship between coal mine dust lung disease and the development of Nodular thyroid disease in coal miners. Methods: This was a clinical retrospective observational study that included 955 male coal miners from 31 different coal mining companies in Huainan, Anhui Province, China, who were examined in April 2021 at the Huainan Occupational Disease Prevention and Control Hospital to collect all their clinical physical examination data, including general conditions, laboratory test indices and imaging indices. Based on the presence or absence of Nodular thyroid disease, 429 cases with Nodular thyroid disease were classified as the diseased group and 526 cases without Nodular thyroid disease were classified as the control group. Logistic regression was used to analyse the correlation between the occurrence of Nodular thyroid disease in coal miners, and further single- and multi-factor logistic regression was used to screen the risk exposure factors for Nodular thyroid disease in coal miners. Results: Age, coal mine dust lung disease (CMDLD), red blood cells (RBC), mean red blood cell volume (MCV), albumin (ALB), albumin/globulin (A/G), indirect bilirubin (IBIL), globulin (GLOB), total bilirubin (TBil) and myeloperoxidase (MPO) were associated with the development of Nodular thyroid disease in coal miners (p < 0.05) The results of univariate and multifactorial logistic regression analysis showed that CMDLD (OR:4.5,95%CI:2.79-7.51) had the highest OR and CMDLD was the strongest independent risk exposure factor for the development of Nodular thyroid disease in coal miners. Conclusions: There is a strong correlation between coal mine dust lung disease and Nodular thyroid disease in underground coal miners, and clinicians need to be highly aware of the high risk of NTD in coal miners with CMDLD and adopt individualized clinical prevention strategies.

Construction of a mortality risk prediction model for elderly people at risk of lobectomy for NSCLC.

Background: An increasing number of lung cancer patients are opting for lobectomy for oncological treatment. However, due to the unique organismal condition of elderly patients, their short-term postoperative mortality is significantly higher than that of non-elderly patients. Therefore, there is a need to develop a personalised predictive tool to assess the risk of postoperative mortality in elderly patients. Methods: Information on the diagnosis and survival of 35,411 older patients with confirmed lobectomy NSCLC from 2009 to 2019 was screened from the SEER database. The surgical group was divided into a high-risk mortality population group (≤90 days) and a non-high-risk mortality population group using a 90-day criterion. Survival curves were plotted using the Kaplan-Meier method to compare the differences in overall survival (OS) and lung cancer-specific survival (LCSS) between the two groups. The data set was split into modelling and validation groups in a ratio of 7.5:2.5, and model risk predictors of postoperative death in elderly patients with NSCLC were screened using univariate and multifactorial logistic regression. Columnar plots were constructed for model visualisation, and the area under the subject operating characteristic curve (AUC), DCA decision curve and clinical impact curve were used to assess model predictiveness and clinical utility. Results: Multi-factor logistic regression results showed that sex, age, race, histology and grade were independent predictors of the risk of postoperative death in elderly patients with NSCLC. The above factors were imported into R software to construct a line graph model for predicting the risk of postoperative death in elderly patients with NSCLC. The AUCs of the modelling and validation groups were 0.711 and 0.713 respectively, indicating that the model performed well in terms of predictive performance. The DCA decision curve and clinical impact curve showed that the model had a high net clinical benefit and was of clinical application. Conclusion: The construction and validation of a predictive model for death within 90 days of lobectomy in elderly patients with lung cancer will help the clinic to identify high-risk groups and give timely intervention or adjust treatment decisions.