Development and external validation of a multimodal integrated feature neural network (MIFNN) for the diagnosis of malignancy in small pulmonary nodules (≤10 mm).

Objectives. Current lung cancer screening protocols primarily evaluate pulmonary nodules, yet often neglect the malignancy risk associated with small nodules (≤10 mm). This study endeavors to optimize the management of pulmonary nodules in this population by devising and externally validating a Multimodal Integrated Feature Neural Network (MIFNN). We hypothesize that the fusion of deep learning algorithms with morphological nodule features will significantly enhance diagnostic accuracy.Materials and Methods. Data were retrospectively collected from the Lung Nodule Analysis 2016 (LUNA16) dataset and four local centers in Beijing, China. The study includes patients with small pulmonary nodules (≤10 mm). We developed a neural network, termed MIFNN, that synergistically combines computed tomography (CT) images and morphological characteristics of pulmonary nodules. The network is designed to acquire clinically relevant deep learning features, thereby elevating the diagnostic accuracy of existing models. Importantly, the network's simple architecture and use of standard screening variables enable seamless integration into standard lung cancer screening protocols.Results. In summary, the study analyzed a total of 382 small pulmonary nodules (85 malignant) from the LUNA16 dataset and 101 small pulmonary nodules (33 malignant) obtained from four specialized centers in Beijing, China, for model training and external validation. Both internal and external validation metrics indicate that the MIFNN significantly surpasses extant state-of-the-art models, achieving an internal area under the curve (AUC) of 0.890 (95% CI: 0.848-0.932) and an external AUC of 0.843 (95% CI: 0.784-0.891).Conclusion. The MIFNN model significantly enhances the diagnostic accuracy of small pulmonary nodules, outperforming existing benchmarks by Zhanget alwith a 6.34% improvement for nodules less than 10 mm. Leveraging advanced integration techniques for imaging and clinical data, MIFNN increases the efficiency of lung cancer screenings and optimizes nodule management, potentially reducing false positives and unnecessary biopsies.Clinical relevance statement. The MIFNN enhances lung cancer screening efficiency and patient management for small pulmonary nodules, while seamlessly integrating into existing workflows due to its reliance on standard screening variables.

Machine Learning Model of ResNet50-Ensemble Voting for Malignant-Benign Small Pulmonary Nodule Classification on Computed Tomography Images.

BACKGROUND: The early detection of benign and malignant lung tumors enabled patients to diagnose lesions and implement appropriate health measures earlier, dramatically improving lung cancer patients' quality of living. Machine learning methods performed admirably when recognizing small benign and malignant lung nodules. However, exploration and investigation are required to fully leverage the potential of machine learning in distinguishing between benign and malignant small lung nodules. OBJECTIVE: The aim of this study was to develop and evaluate the ResNet50-Ensemble Voting model for detecting the benign and malignant nature of small pulmonary nodules (<20 mm) based on CT images. METHODS: In this study, 834 CT imaging data from 396 patients with small pulmonary nodules were gathered and randomly assigned to the training and validation sets in an 8:2 ratio. ResNet50 and VGG16 algorithms were utilized to extract CT image features, followed by XGBoost, SVM, and Ensemble Voting techniques for classification, for a total of ten different classes of machine learning combinatorial classifiers. Indicators such as accuracy, sensitivity, and specificity were used to assess the models. The collected features are also shown to investigate the contrasts between them. RESULTS: The algorithm we presented, ResNet50-Ensemble Voting, performed best in the test set, with an accuracy of 0.943 (0.938, 0.948) and sensitivity and specificity of 0.964 and 0.911, respectively. VGG16-Ensemble Voting had an accuracy of 0.887 (0.880, 0.894), with a sensitivity and specificity of 0.952 and 0.784, respectively. CONCLUSION: Machine learning models that were implemented and integrated ResNet50-Ensemble Voting performed exceptionally well in identifying benign and malignant small pulmonary nodules (<20 mm) from various sites, which might help doctors in accurately diagnosing the nature of early-stage lung nodules in clinical practice.

Intraindividual difference in estimated GFR by creatinine and cystatin C, cognitive trajectories and motoric cognitive risk syndrome.

BACKGROUND: Intraindividual differences between estimated glomerular filtration rate (eGFR) based on cystatin C (eGFRcys) and creatinine (eGFRcr) can convey important clinical information regarding the health status. However, the clinical implications of these differences (eGFRdiff) for risk of cognitive decline and motoric cognitive risk syndrome (MCR) remains unclear. We aimed to investigate the longitudinal associations of eGFRdiff with cognitive trajectories and incident MCR. METHODS: Based on the China Health and Retirement Longitudinal Study, we identified two study sub-cohorts: one for cognitive trajectory follow-up (6423 participants; years:2011-2018) and another for incident MCR follow-up (2477 participants; years:2011-2015). The eGFRdiff was defined as eGFRcys minus eGFRcr. Adjusted ordinal and binary logistics regression models were separately used to assess the associations of eGFRdiff with cognitive trajectories and incident MCR. We also performed discordance analyses for eGFRdiff vs eGFRcys, eGFRcr or eGFR based on both creatinine and cystatin C (eGFRcys-cr). RESULTS: In the first sub-cohort, four distinct 7-year cognitive trajectories were identified. Each 1-SD higher eGFRdiff (value for eGFRcys minus eGFRcr) was associated with a lower risk of poorer cognitive trajectories (OR: 0.909, 95% CI: 0.877-0.942). In the second sub-cohort, 121 participants developed incident MCR after a 4-year follow-up. Each 1-SD higher eGFRdiff (value for eGFRcys minus eGFRcr) was linked with a 25.3% (95%CI: 16.6%-33.2%) decreased risk for MCR. The above associations persisted in individuals with normal kidney function. Additionally, the risk for cognitive decline and incident MCR was more strongly associated with eGFRcys than eGFRcr and eGFRcys-cr. For the discordance analyses, 'discordantly high eGFRdiff/low eGFR' group, but not 'discordantly low eGFRdiff/high eGFR', exhibited a significantly lower risk of poorer cognitive trajectories and MCR compared to the concordant group. CONCLUSIONS: A large negative difference between eGFRcys and eGFRcr (eGFRcys lower than eGFRcr) was associated with higher risk of cognitive decline and incident MCR. The eGFRdiff could capture additional valuable risk information beyond eGFRcys, eGFRcr, and eGFRcys-cr.

Deep-Learning Model of ResNet Combined with CBAM for Malignant-Benign Pulmonary Nodules Classification on Computed Tomography Images.

Background and Objectives: Lung cancer remains a leading cause of cancer mortality worldwide. Accurately classifying benign pulmonary nodules and malignant ones is crucial for early diagnosis and improved patient outcomes. The purpose of this study is to explore the deep-learning model of ResNet combined with a convolutional block attention module (CBAM) for the differentiation between benign and malignant lung cancer, based on computed tomography (CT) images, morphological features, and clinical information. Methods and materials: In this study, 8241 CT slices containing pulmonary nodules were retrospectively included. A random sample comprising 20% (n = 1647) of the images was used as the test set, and the remaining data were used as the training set. ResNet combined CBAM (ResNet-CBAM) was used to establish classifiers on the basis of images, morphological features, and clinical information. Nonsubsampled dual-tree complex contourlet transform (NSDTCT) combined with SVM classifier (NSDTCT-SVM) was used as a comparative model. Results: The AUC and the accuracy of the CBAM-ResNet model were 0.940 and 0.867, respectively, in test set when there were only images as inputs. By combining the morphological features and clinical information, CBAM-ResNet shows better performance (AUC: 0.957, accuracy: 0.898). In comparison, a radiomic analysis using NSDTCT-SVM achieved AUC and accuracy values of 0.807 and 0.779, respectively. Conclusions: Our findings demonstrate that deep-learning models, combined with additional information, can enhance the classification performance of pulmonary nodules. This model can assist clinicians in accurately diagnosing pulmonary nodules in clinical practice.

Identification and validation of IgG N-glycosylation biomarkers of esophageal carcinoma.

Introduction: Altered Immunoglobulin G (IgG) N-glycosylation is associated with aging, inflammation, and diseases status, while its effect on esophageal squamous cell carcinoma (ESCC) remains unknown. As far as we know, this is the first study to explore and validate the association of IgG N-glycosylation and the carcinogenesis progression of ESCC, providing innovative biomarkers for the predictive identification and targeted prevention of ESCC. Methods: In total, 496 individuals of ESCC (n=114), precancerosis (n=187) and controls (n=195) from the discovery population (n=348) and validation population (n=148) were recruited in the study. IgG N-glycosylation profile was analyzed and an ESCC-related glycan score was composed by a stepwise ordinal logistic model in the discovery population. The receiver operating characteristic (ROC) curve with the bootstrapping procedure was used to assess the performance of the glycan score. Results: In the discovery population, the adjusted OR of GP20 (digalactosylated monosialylated biantennary with core and antennary fucose), IGP33 (the ratio of all fucosylated monosyalilated and disialylated structures), IGP44 (the proportion of high mannose glycan structures in total neutral IgG glycans), IGP58 (the percentage of all fucosylated structures in total neutral IgG glycans), IGP75 (the incidence of bisecting GlcNAc in all fucosylated digalactosylated structures in total neutral IgG glycans), and the glycan score are 4.03 (95% CI: 3.03-5.36, P<0.001), 0.69 (95% CI: 0.55-0.87, P<0.001), 0.56 (95% CI: 0.45-0.69, P<0.001), 0.52 (95% CI: 0.41-0.65, P<0.001), 7.17 (95% CI: 4.77-10.79, P<0.001), and 2.86 (95% CI: 2.33-3.53, P<0.001), respectively. Individuals in the highest tertile of the glycan score own an increased risk (OR: 11.41), compared with those in the lowest. The average multi-class AUC are 0.822 (95% CI: 0.786-0.849). Findings are verified in the validation population, with an average AUC of 0.807 (95% CI: 0.758-0.864). Discussion: Our study demonstrated that IgG N-glycans and the proposed glycan score appear to be promising predictive markers for ESCC, contributing to the early prevention of esophageal cancer. From the perspective of biological mechanism, IgG fucosylation and mannosylation might involve in the carcinogenesis progression of ESCC, and provide potential therapeutic targets for personalized interventions of cancer progression.

Long-term exposure to PM2.5 and PM10 and chronic kidney disease: the Beijing Health Management Cohort, from 2013 to 2018.

Long-term exposure to ambient particulate pollutants (PM2.5 and PM10) may increase the risk of chronic kidney disease (CKD), but the results of previous research were limited and inconsistent. The purpose of this study was to assess the relationships of PM2.5 and PM10 with CKD. This study was a cohort study based on the physical examination data of 2082 Beijing residents from 2013 to 2018 in the Beijing Health Management Cohort (BHMC). A land-use regression model was used to estimate the individual exposure concentration of air pollution based on the address provided by each participant. CKD events were identified based on self-report or medical evaluation (estimated glomerular filtration rate, eGFR less than 60 ml/min/1.73 m2). Finally, the associations of PM2.5 and PM10 with CKD were calculated using univariate and multivariate logistic regression models. During the research period, we collected potentially confounding information. After adjusting for confounders, each 10 µg/m3 increase in PM2.5 and PM10 exposure was associated with an 84% (OR: 1.84; 95% CI: 1.45, 2.33) and 37% (OR: 1.37; 95% CI: 1.15, 1.63) increased risk of CKD. Adjusting for the four common gaseous air pollutants (CO, NO2, SO2, O3), the effect of PM2.5 and PM10 on CKD was significantly enhanced, but the effect of PM10 was no longer significant in the multi-pollutant model. The results of the stratified analysis showed that PM2.5 and PM10 were more significant in males, middle-aged and elderly people over 45 years old, smokers, drinkers, BMI ≥ 24 kg/m2, and abnormal metabolic components. In conclusion, long-term exposure to ambient PM2.5 and PM10 was associated with an increased risk of CKD.

Risk factors for esophageal squamous cell carcinoma and its histological precursor lesions in China: a multicenter cross-sectional study.

BACKGROUND: Despite research efforts, the causative factors that contribute to esophageal squamous cell carcinoma (ESCC) in high-risk areas have not yet been understood. In this study, we, therefore, aimed to describe the risk factors associated with ESCC and its precursor lesions. METHODS: We performed an endoscopic examination of 44,857 individuals aged 40-69 years from five high incidence regions of China in 2017-2018. Participants were classified as 4 groups of normal control, esophagitis, low-grade intraepithelial neoplasia (LGIN) and high-grade intraepithelial neoplasia/esophageal squamous cell carcinoma (HGIN/ESCC) using an unconditional logistic regression determine risk factors. RESULTS: We identified 4890 esophagitis, 1874 LGIN and 437 HGIN/ESCC cases. Crude odds ratios (ORs) and adjusted odds ratios were calculated using unconditional logistic regression. Drinking well and surface water, salty diet, and positive family history of cancer were the common risk factors for esophagitis, LGIN and HGIN/ESCC. History of chronic hepatitis/cirrhosis was the greatest risk factor of esophagitis (adjusted OR 2.96, 95%CI 2.52-3.47) and HGIN/ESCC (adjusted OR 1.91, 95%CI 1.03-3.22). Pesticide exposure (adjusted OR 1.20, 95%CI 1.05-1.37) was essential risk factor of LGIN. CONCLUSIONS: Among individuals aged 40-69 years in high incidence regions of upper gastrointestinal cancer, the results provided important epidemiological evidence for the prevention of different precancerous lesions of ESCC.

Application of an Anomaly Detection Model to Screen for Ocular Diseases Using Color Retinal Fundus Images: Design and Evaluation Study.

BACKGROUND: The supervised deep learning approach provides state-of-the-art performance in a variety of fundus image classification tasks, but it is not applicable for screening tasks with numerous or unknown disease types. The unsupervised anomaly detection (AD) approach, which needs only normal samples to develop a model, may be a workable and cost-saving method of screening for ocular diseases. OBJECTIVE: This study aimed to develop and evaluate an AD model for detecting ocular diseases on the basis of color fundus images. METHODS: A generative adversarial network-based AD method for detecting possible ocular diseases was developed and evaluated using 90,499 retinal fundus images derived from 4 large-scale real-world data sets. Four other independent external test sets were used for external testing and further analysis of the model's performance in detecting 6 common ocular diseases (diabetic retinopathy [DR], glaucoma, cataract, age-related macular degeneration, hypertensive retinopathy [HR], and myopia), DR of different severity levels, and 36 categories of abnormal fundus images. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the model's performance were calculated and presented. RESULTS: Our model achieved an AUC of 0.896 with 82.69% sensitivity and 82.63% specificity in detecting abnormal fundus images in the internal test set, and it achieved an AUC of 0.900 with 83.25% sensitivity and 85.19% specificity in 1 external proprietary data set. In the detection of 6 common ocular diseases, the AUCs for DR, glaucoma, cataract, AMD, HR, and myopia were 0.891, 0.916, 0.912, 0.867, 0.895, and 0.961, respectively. Moreover, the AD model had an AUC of 0.868 for detecting any DR, 0.908 for detecting referable DR, and 0.926 for detecting vision-threatening DR. CONCLUSIONS: The AD approach achieved high sensitivity and specificity in detecting ocular diseases on the basis of fundus images, which implies that this model might be an efficient and economical tool for optimizing current clinical pathways for ophthalmologists. Future studies are required to evaluate the practical applicability of the AD approach in ocular disease screening.

Association of IgG Glycosylation and Esophageal Precancerosis Beyond Inflammation.

This study aimed to investigate the association of IgG glycosylation and esophageal precancerosis for squamous cell carcinoma and determine its role in inflammation. Primary glycans selected by the least absolute shrinkage and selection operator (LASSO) algorithm were validated using univariate and multivariate logistics models plus restricted cubic spline functions. In total, 24 direct glycans and 27 derived traits were detected, among which four glycans and three derived traits were primarily selected. Then, GP5 (adjusted OR: 0.805), GP17 (adjusted OR: 1.305), G12n (adjusted OR: 1.271), Gal_1 (adjusted OR: 0.776) and Fuc (adjusted OR: 0.737) were validated and significantly associated with esophageal precancerosis. In addition, there was a consistent positive association in GP17 and G12n and a negative association in GP5, Gal_1, and Fuc by restricted cubic spline function. Compared with esophageal inflammation, GP17, G12n, and Fuc were still independently associated with precancerosis. In brief, the IgG glycosylation profile was independently associated with esophageal precancerosis beyond inflammation, which could be an early biomarker for esophageal cancer.Prevention Relevance: IgG glycosylation profile is associated with esophageal precancerosis and specific IgG glycans involves in the early stage of esophageal cancer, which is independent of inflammation.

Histologic subtype classification of non-small cell lung cancer using PET/CT images.

PURPOSES: To evaluate the capability of PET/CT images for differentiating the histologic subtypes of non-small cell lung cancer (NSCLC) and to identify the optimal model from radiomics-based machine learning/deep learning algorithms. METHODS: In this study, 867 patients with adenocarcinoma (ADC) and 552 patients with squamous cell carcinoma (SCC) were retrospectively analysed. A stratified random sample of 283 patients (20%) was used as the testing set (173 ADC and 110 SCC); the remaining data were used as the training set. A total of 688 features were extracted from each outlined tumour region. Ten feature selection techniques, ten machine learning (ML) models and the VGG16 deep learning (DL) algorithm were evaluated to construct an optimal classification model for the differential diagnosis of ADC and SCC. Tenfold cross-validation and grid search technique were employed to evaluate and optimize the model hyperparameters on the training dataset. The area under the receiver operating characteristic curve (AUROC), accuracy, precision, sensitivity and specificity was used to evaluate the performance of the models on the test dataset. RESULTS: Fifty top-ranked subset features were selected by each feature selection technique for classification. The linear discriminant analysis (LDA) (AUROC, 0.863; accuracy, 0.794) and support vector machine (SVM) (AUROC, 0.863; accuracy, 0.792) classifiers, both of which coupled with the ℓ2,1NR feature selection method, achieved optimal performance. The random forest (RF) classifier (AUROC, 0.824; accuracy, 0.775) and ℓ2,1NR feature selection method (AUROC, 0.815; accuracy, 0.764) showed excellent average performance among the classifiers and feature selection methods employed in our study, respectively. Furthermore, the VGG16 DL algorithm (AUROC, 0.903; accuracy, 0.841) outperformed all conventional machine learning methods in combination with radiomics. CONCLUSION: Employing radiomic machine learning/deep learning algorithms could help radiologists to differentiate the histologic subtypes of NSCLC via PET/CT images.

Disability Transitions and Health Expectancies among Elderly People Aged 65 Years and Over in China: A Nationwide Longitudinal Study.

Disability has become a critical issue among elderly populations, yet limited large-scale research related to this issue has been conducted in China, an aging society. This study explored sex and urban-rural differences in disability transitions and life expectancies among older adults in China. Data were collected from the Chinese Longitudinal Health Longevity Survey (CLHLS), which enrolled people aged 65 and older and was conducted in randomly selected counties and cities across 22 provinces in China. Disability was diagnosed based on basic activities of daily living (BADLs) and instrumental activities of daily living (IADLs). Several individual characteristics were assessed, including sociodemographic factors (age, sex and region, etc.) and health behaviors (currently smoking, currently drinking, etc.). Multistate models were applied to analyze the transition rates among 4 states: no disability, mild disability, severe disability and death. The transition rates from disabled states to the no-disability state were found to decrease markedly with age. The rates of recovery from mild disability in rural areas were higher than those in urban areas. Rural elderly individuals lived shorter lives than their urban counterparts, but they tended to live with better functional status, spending a larger fraction of their remaining life with less severe disability. Based on these findings, devoting more attention and resources to rural areas may help less severely disabled people recuperate and prevent severe disability. The study provides insights into health plan strategies to help guide the allocation of limited resources.

The prevalence of carotid plaque with different stability and its association with metabolic syndrome in China: The Asymptomatic Polyvascular Abnormalities Community study.

Few studies have investigated the prevalence of carotid plaque with different stability in Chinese. As is well known, carotid atherosclerosis is tightly associated with metabolic syndrome (MetS); however, the data about the association between the presence of carotid plaque with different stability and MetS was limited. The aim of our study was to investigate the prevalence of carotid plaque with different stability and its potential association with MetS in general Chinese population.The Asymptomatic Polyvascular Abnormalities Community study is a community-based study to investigate the epidemiology of asymptomatic polyvascular abnormalities in Chinese adults. A total of 5393 participants were finally eligible and included in this study. The carotid plaque and its stability were assessed using ultrasonography. The MetS was defined using the criteria from US National Cholesterol Education Program-Adult Treatment Panel III. Data were analyzed with multivariate logistic regression models.Of the 5393 subjects, 1397 (25.9%) participants had stable carotid plaque, 1518 (28.1%) had unstable carotid plaque in participants, and 1456 (27.0%) had a MetS. MetS was, respectively, significantly associated with the prevalence of carotid plaque (odds ratio [OR]: 1.25; 95% confidence interval [CI]: 1.07, 1.47), stable carotid plaque (OR: 1.23; 95% CI: 1.02,1.48), and unstable carotid plaque (OR: 1.27; 95% CI: 1.03,1.56) after adjusting for age, gender, level of education, income, smoking, drinking, physical activity, body mass index, low-density lipoprotein, and high-sensitivity C-reactive protein. With the number of MetS components, the prevalence of carotid plaque, stable carotid plaque, and unstable carotid plaque significantly increased (P for trend <0.0001), respectively.In summary, the prevalence of carotid plaque was 54.1%, stable carotid plaque was 25.9%, and unstable carotid plaque was 28.1%. Our study revealed that the prevalence of carotid plaque, stable carotid plaque, and unstable carotid plaque was, respectively, significantly associated with MetS in the general population.

Five-Year Long-Term Prognosis of Epileptic Children After Hemispheric Surgery: A Systematic Review and Meta-analysis.

To estimate children's long-term seizure outcomes after hemispheric surgery and the associated predictors.A systematic review of 4 databases and a meta-analysis were performed from January 1, 1995 to August 31, 2015. The databases included PubMed, Embase, Science Direct, and Web of Science; patients were classified into the Engel Class I group and the Engel Class II to IV group, according to their seizure outcomes. Nine potential predictors were then stratified across the groups and estimated using the Wilcoxon rank-sum test for continuous variables and the Chi-squared test for categorical variables.The search yielded 15 retrospective studies, with a total sample size of 380. Five years after surgery, 268 (0.71, 95% confidence interval [CI]: 0.64-0.78) children were seizure free; the seizure onset age in the Engel Class I group was significantly higher than that of the Engel Class II to IV group (standardized mean difference [SMD] = 0.26, 95% CI: 0.03-0.49, P = 0.028); specifically, when predicting the positive long-term outcomes, the odds ratio for late onset age (≥3.6 months, median value of the Engel Class II-IV group) versus early onset age was 2.65 (95% CI: 1.454-4.836, z = 3.18, P = 0.001). The abnormal magnetic resonance imaging (MRI) findings were more predictive for positive seizure outcomes than the normal findings (odds ratio [OR] = 4.60, 95% CI: 1.27-16.62, P = 0.02).Following hemispheric surgery, the long-term prognosis of children with epilepsy was good. Late seizure onset (age ≥ 3.6 months) and abnormal MRI findings were positive predictors for long-term seizure control in children.

Knowledge, attitude, and practices (KAP) and risk factors analysis related to cystic echinococcosis among residents in Tibetan communities, Xiahe County, Gansu Province, China.

Cystic echinococcosis (CE) is a global parasitic zoonosis caused by Echinococcus granulosus. The disease is highly endemic in western China, especially in Tibetan areas, because of poor economic development and hygiene conditions, limited community knowledge of CE, a large scale of dogs, and home slaughtering of livestock. Although many researchers have analyzed risk factors of CE transmission in Tibetan Plateau, there are rare reports of knowledge, attitude, and practice (KAP) of residents about CE in Tibetan communities. In our current study, community based cross-sectional study was conducted in three townships in Xiahe County, Gannan Tibetan Autonomous Prefectures of Gansu Province from May to September 2013. A total of 972 participants originating from Tibetan communities of 31 villages in the 3 townships were registered and data were collected using structured questionnaires. From the total of 972 study participants (457 males and 515 females), 65.9% heard of the disease CE. Most of them (96.1%) would like to accept CE inspection. About half of the peoples feed their dogs often and major of them do not play with the dogs. Risk factors included resident, knowing dog could be infected, knowing eating could be route of infection, oldest dog's age, usually feed your dog by self, feed dogs with internal organs. In general our findings showed that most of residents had positive attitude toward treatments of the disease, but their practice about disease prevention and control was low. Therefore, our study called for continued and strengthened education of changing the life style, especially the behaviors related to dogs.

Prevalence and risk factors for cervical neoplasia: a cervical cancer screening program in Beijing.

BACKGROUND: Cervical cancer is the second most common cancer and cause of cancer-related death for women worldwide. The aims of this study were to investigate the prevalence of cervical neoplasia and examine factors associated with high-grade cervical squamous intraepithelial lesions (HSIL) among women taking part in a cervical cancer screening program in Beijing. METHODS: Women aged 25-65 years were screened using the ThinPrep cytologic test and gynecologic examination. Univariate and multivariate logistic regressions were conducted to investigate factors associated with HSIL. RESULTS: Among 728,704 women screened, the prevalence of cervical intraepithelial neoplasia (CIN) I, II, III was 50.2, 34.0, and 36.4 per 100,000, respectively. Prevalence of cervical cancer was 12.2 per 100,000. Risk factors for HSIL included being in age group of 46-55 years (adjusted odds ratio [aOR] = 1.15, 95% CI: 1.07-1.44, compared with the 25-35 age group), bleeding after intercourse (aOR = 2.08, 95% CI: 1.40-3.10), and presence of trichomonas vaginalis infection (aOR = 2.62, 95% CI: 1.35-5.07), cervical inflammation (aOR = 4.22, 95% CI: 3.39-5.26), and genital warts (aOR = 3.89, 95% CI: 2.54-7.70). High education level (college and above compared with junior middle school or lower) was found to be protective (aOR = 0.79, 95% CI: 0.37-0.90). CONCLUSIONS: The prevalence of cervical neoplasia is relatively high in Beijing. Women aged 46-55 years, those with a lower education level, those reporting bleeding after intercourse, and those affected by Trichomonas vaginalis infection, cervical inflammation and genital warts are at higher risk for HSIL. Particular efforts should be made to ensure these women are included in cervical cancer screening programs.

Contourlet textual features: improving the diagnosis of solitary pulmonary nodules in two dimensional CT images.

OBJECTIVE: To determine the value of contourlet textural features obtained from solitary pulmonary nodules in two dimensional CT images used in diagnoses of lung cancer. MATERIALS AND METHODS: A total of 6,299 CT images were acquired from 336 patients, with 1,454 benign pulmonary nodule images from 84 patients (50 male, 34 female) and 4,845 malignant from 252 patients (150 male, 102 female). Further to this, nineteen patient information categories, which included seven demographic parameters and twelve morphological features, were also collected. A contourlet was used to extract fourteen types of textural features. These were then used to establish three support vector machine models. One comprised a database constructed of nineteen collected patient information categories, another included contourlet textural features and the third one contained both sets of information. Ten-fold cross-validation was used to evaluate the diagnosis results for the three databases, with sensitivity, specificity, accuracy, the area under the curve (AUC), precision, Youden index, and F-measure were used as the assessment criteria. In addition, the synthetic minority over-sampling technique (SMOTE) was used to preprocess the unbalanced data. RESULTS: Using a database containing textural features and patient information, sensitivity, specificity, accuracy, AUC, precision, Youden index, and F-measure were: 0.95, 0.71, 0.89, 0.89, 0.92, 0.66, and 0.93 respectively. These results were higher than results derived using the database without textural features (0.82, 0.47, 0.74, 0.67, 0.84, 0.29, and 0.83 respectively) as well as the database comprising only textural features (0.81, 0.64, 0.67, 0.72, 0.88, 0.44, and 0.85 respectively). Using the SMOTE as a pre-processing procedure, new balanced database generated, including observations of 5,816 benign ROIs and 5,815 malignant ROIs, and accuracy was 0.93. CONCLUSION: Our results indicate that the combined contourlet textural features of solitary pulmonary nodules in CT images with patient profile information could potentially improve the diagnosis of lung cancer.

Risk factors for cerebrovascular disease mortality among the elderly in Beijing: a competing risk analysis.

OBJECTIVE: To examine the associations of combined lifestyle factors and physical conditions with cerebrovascular diseases (CBVD) mortality, after accounting for competing risk events, including death from cardiovascular diseases, cancers and other diseases. METHODS: Data on 2010 subjects aged over 55 years were finally analyzed using competing risk models. All the subjects were interviewed by the Beijing Longitudinal Study of Aging (BLSA), in China, between 1 January 1992 and 30 August 2009. RESULTS: Elderly females were at a lower risk of death from CBVD than elderly males (HR = 0.639, 95% CI = 0.457-0.895). Increasing age (HR = 1.543, 95% CI = 1.013-2.349), poor self-rated health (HR = 1.652, 95% CI = 1.198-2.277), hypertension (HR = 2.201, 95% CI = 1.524-3.178) and overweight (HR = 1.473, 95% CI = 1.013-2.142) or obesity (HR = 1.711, 95% CI = 1.1754-2.490) was associated with higher CBVD mortality risk. Normal cognition function (HR = 0.650, 95% CI = 0.434-0.973) and living in urban (HR = 0.456, 95% CI = 0.286-0.727) was associated with lower CBVD mortality risk. Gray's test also confirmed the cumulative incidence (CIF) of CBVD was lower in the 'married' group than those without spouse, and the mortality was lowest in the 'nutrition sufficient' group among the 'frequent consumption of meat group' and the 'medial type group' (P value<0.001). CONCLUSIONS: CBVD mortality was associated with gender, age, blood pressure, residence, BMI, cognitive function, nutrition and the result of self-rated health assessment in the elderly in Beijing, China.

Prediction models for solitary pulmonary nodules based on curvelet textural features and clinical parameters.

Lung cancer, one of the leading causes of cancer-related deaths, usually appears as solitary pulmonary nodules (SPNs) which are hard to diagnose using the naked eye. In this paper, curvelet-based textural features and clinical parameters are used with three prediction models [a multilevel model, a least absolute shrinkage and selection operator (LASSO) regression method, and a support vector machine (SVM)] to improve the diagnosis of benign and malignant SPNs. Dimensionality reduction of the original curvelet-based textural features was achieved using principal component analysis. In addition, non-conditional logistical regression was used to find clinical predictors among demographic parameters and morphological features. The results showed that, combined with 11 clinical predictors, the accuracy rates using 12 principal components were higher than those using the original curvelet-based textural features. To evaluate the models, 10-fold cross validation and back substitution were applied. The results obtained, respectively, were 0.8549 and 0.9221 for the LASSO method, 0.9443 and 0.9831 for SVM, and 0.8722 and 0.9722 for the multilevel model. All in all, it was found that using curvelet-based textural features after dimensionality reduction and using clinical predictors, the highest accuracy rate was achieved with SVM. The method may be used as an auxiliary tool to differentiate between benign and malignant SPNs in CT images.

Clinical risk factor analysis for breast cancer: 568,000 subjects undergoing breast cancer screening in Beijing, 2009.

OBJECTIVES: Although there are many reports about the risk of breast cancer, few have reported clinical factors including history of breast-related or other diseases that affect the prevalence of breast cancer. This study explores these risk factors for breast cancer cases reported in Beijing in 2009. MATERIALS AND METHODS: Data were derived from a Beijing breast cancer screening performed in 2009, of 568,000 women, from 16 districts of Beijing, all aged between 40 and 60 years. In this study, multilevel statistical modeling was used to identify clinical factors that affect the prevalence of breast cancer and to provide more reliable evidence for clinical diagnostics by using screening data. RESULTS AND CONCLUSION: Those women who had organ transplants, compared with those with none, were associated with breast cancer with an odds ratio (OR) = 65.352 [95% confidence interval (CI): 8.488-503.165] and those with solid breast mass compared with none had OR = 1.384 (95% CI: 1.022- 1.873). Malignant tendency was strongly associated with increased risk of breast cancer, OR = 207.999(95% CI: 151.950-284.721). The risk of breast cancer increased with age, OR1 = 2.759 (95% CI: 1.837-4.144, 56-60 vs. 40-45), OR2 = 2.047 (95% CI: 1.394-3.077, 51-55 vs. 40-45), OR3 = 1.668 (95% CI: 1.145-2.431). Normal results of B ultrasonic examination show a lower risk among participants, OR= 0.136 (95% CI: 0.085-0.218). Those women with ductal papilloma compared with none were associated with breast cancer, OR=6.524 (95% CI: 1.871-22.746). Therefore, this study suggests that clinical doctors should pay attention to these high-risk factors.