Correction: Artificial Intelligence-Based Prediction of Lung Cancer Risk Using Nonimaging Electronic Medical Records: Deep Learning Approach.

[This corrects the article DOI: 10.2196/26256.].

Artificial Intelligence-Based Prediction of Lung Cancer Risk Using Nonimaging Electronic Medical Records: Deep Learning Approach.

BACKGROUND: Artificial intelligence approaches can integrate complex features and can be used to predict a patient's risk of developing lung cancer, thereby decreasing the need for unnecessary and expensive diagnostic interventions. OBJECTIVE: The aim of this study was to use electronic medical records to prescreen patients who are at risk of developing lung cancer. METHODS: We randomly selected 2 million participants from the Taiwan National Health Insurance Research Database who received care between 1999 and 2013. We built a predictive lung cancer screening model with neural networks that were trained and validated using pre-2012 data, and we tested the model prospectively on post-2012 data. An age- and gender-matched subgroup that was 10 times larger than the original lung cancer group was used to assess the predictive power of the electronic medical record. Discrimination (area under the receiver operating characteristic curve [AUC]) and calibration analyses were performed. RESULTS: The analysis included 11,617 patients with lung cancer and 1,423,154 control patients. The model achieved AUCs of 0.90 for the overall population and 0.87 in patients ≥55 years of age. The AUC in the matched subgroup was 0.82. The positive predictive value was highest (14.3%) among people aged ≥55 years with a pre-existing history of lung disease. CONCLUSIONS: Our model achieved excellent performance in predicting lung cancer within 1 year and has potential to be deployed for digital patient screening. Convolution neural networks facilitate the effective use of EMRs to identify individuals at high risk for developing lung cancer.

Exposure to PM2.5 is associated with malignant pleural effusion in lung cancer patients.

Air pollution has been recognized to be a risk factor for lung cancer. The objective of this study was to investigate the effects of air pollution on heavy metal alterations in the pleural effusion of lung cancer patients. Pleural effusion was collected from patients with lung cancer and congestive heart failure (CHF). One-year average levels of particulate matter with an aerodynamic diameter of < 10 µm (PM10), PM2.5, NO2, and SO2 were linked to the exposure of these subjects. Traffic-related metals, included Al, Fe, Cu, Zn, and Pb, were determined in the pleural effusion. Logistic regression models were used to examine their associations. There were 63 lung cancer patients and 31 CHF patients enrolled in the current study. We found that PM10, PM2.5, and NO2 were negatively correlated with Al in the pleural effusion, whereas PM2.5 was positively correlated with Zn in the pleural effusion. Increases in 1 µg/m3 of PM2.5 and 1 ng/mL of Zn were associated with lung cancer (adjusted OR=2.394, 95% CI= 1.446-3.964 for PM2.5; adjusted OR=1.003, 95% CI=1.000-1.005 for Zn). Increases in PM2.5 and Zn in the pleural effusion increased the risk of malignant pleural effusion in lung cancer patients (adjusted OR=1.517; 95% CI=1.082-2.127 for PM2.5; adjusted OR=1.002, 95% CI=1.000-1.005 for Zn). Furthermore, we observed that adenocarcinomas increased in association with a 1-µg/m3 increase in PM2.5 (crude OR=1.683; 95% CI=1.006-2.817) in lung cancer patients. In conclusion, PM2.5 exposure and the possible resultant Zn in the pleural effusion associated with the development of malignant pleural effusion in lung cancer.

TGF-ß Induced CTGF Expression in Human Lung Epithelial Cells through ERK, ADAM17, RSK1, and C/EBPß Pathways.

BACKGROUND: Lung epithelial cells play critical roles in idiopathic pulmonary fibrosis. METHODS: In the present study, we investigated whether transforming growth factor-ß (TGF-ß)-induced expression of connective tissue growth factor (CTGF) was regulated by the extracellular signal-regulated kinase (ERK)/a disintegrin and metalloproteinase 17 (ADAM17)/ribosomal S6 kinases 1 (RSK1)/CCAAT/enhancer-binding protein ß (C/EBPß) signaling pathway in human lung epithelial cells (A549). RESULTS: Our results revealed that TGF-ß-induced CTGF expression was weakened by ADAM17 small interfering RNA (ADAM17 siRNA), TNF-α processing inhibitor-0 (TAPI-0, an ADAM17 inhibitor), U0126 (an ERK inhibitor), RSK1 siRNA, and C/EBPß siRNA. TGF-ß-induced ERK phosphorylation as well as ADAM17 phosphorylation was attenuated by U0126. The TGF-ß-induced increase in RSK1 phosphorylation was inhibited by TAPI-0 and U0126. TGF-ß-induced C/EBPß phosphorylation was weakened by U0126, ADAM17 siRNA, and RSK1 siRNA. In addition, TGF-ß increased the recruitment of C/EBPß to the CTGF promoter. Furthermore, TGF-ß enhanced fibronectin (FN), an epithelial-mesenchymal transition (EMT) marker, and CTGF mRNA levels and reduced E-cadherin mRNA levels. Moreover, TGF-ß-stimulated FN protein expression was reduced by ADAM17 siRNA and CTGF siRNA. CONCLUSION: The results suggested that TGF-ß induces CTGF expression through the ERK/ADAM17/RSK1/C/EBPß signaling pathway. Moreover, ADAM17 and CTGF participate in TGF-ß-induced FN expression in human lung epithelial cells.

Prognostic value of localization of epidermal growth factor receptor in lung adenocarcinoma.

BACKGROUND: The nuclear translocation of epidermal growth factor receptor (EGFR) has been considered to play a role in carcinogenesis. However, the relevance of differentially located EGFR proteins in lung cancer remains unclear. METHODS: We examined 161 patients with primary lung adenocarcinoma to detect EGFR expression in lung cancer cells using immunohistochemistry and determined the correlations of EGFR expression with clinical characteristics, EGFR mutations, and survival time. Moreover, we graded complete membranous staining with strong intensity as high membranous EGFR (mEGFR) expression, and nuclear EGFR staining with strong intensity as high nuclear (nEGFR) expression. RESULTS: The prevalence of high mEGFR and nEGFR expression in lung adenocarcinoma was 42.86 and 39.13%, respectively. After multivariate analyses, high mEGFR expression was associated with a significantly reduced mortality risk in older patients, those with a history of smoking, and those without brain metastasis (hazard ratio[95% confidential interval], HR[95% CI] = 0.55[0.32~ 0.92]; 0.51[0.26~ 0.98] and 0.56[0.33~ 0.94], in overall survival, respectively). An association between high nEGFR expression and early recurrence was observed in patients with metastasis (HR[95% CI] =1.68[1.05~ 2.68], in progression-free survival). Notably, patients with low mEGFR and low nEGFR expression had the lowest survival rate in cases without brain metastasis (p = 0.018) and with a history of smoking (p = 0.062) and total EGFR (any high mEGFR or nEGFR) expression indicated a more favorable response to platinum-based chemotherapy regardless of EGFR mutations (HR[95% CI] =0.33[0.12-0.92]; adjusted HR[95% CI] = 0.36[0.13~ 1.02] with the use of tyrosine kinase inhibitor). CONCLUSIONS: EGFR proteins at different cellular locations in lung adenocarcinoma might influence the biology of cancer cells and are an independent indicator of more favorable prognosis and treatment response.

Investigation into the pulmonary inflammopathology of exposure to nickel oxide nanoparticles in mice.

We investigated the effects of nickel oxide nanoparticles (NiONPs) on the pulmonary inflammopathology. NiONPs were intratracheally installed into mice, and lung injury and inflammation were evaluated between 1 and 28 days. NiONPs caused significant increases in LDH, total protein, and IL-6 and a decrease in IL-10 in the BALF and increases in 8-OHdG and caspase-3 in lung tissues at 24 h. Airway inflammation was present in a dose-dependent manner from the upper to lower airways at 24 h of exposure as analyzed by SPECT. Lung parenchyma inflammation and small airway inflammation were observed by CT after NiONP exposure. 8-OHdG in lung tissues had increased with formation of fibrosis at 28 days. Focal adhesion was the most important pathways identified at 24 h as determined by protemics, whereas glutathione metabolism was the most important identified at 28 days. Our results demonstrated the pulmonary inflammopathology caused by NiONPs based on image-to-biochemical approaches.

PPARs modulate cardiac metabolism and mitochondrial function in diabetes.

Diabetic cardiomyopathy is a major complication of diabetes mellitus (DM). Currently, effective treatments for diabetic cardiomyopathy are limited. The pathophysiology of diabetic cardiomyopathy is complex, whereas mitochondrial dysfunction plays a vital role in the genesis of diabetic cardiomyopathy. Metabolic regulation targeting mitochondrial dysfunction is expected to be a reasonable strategy for treating diabetic cardiomyopathy. Peroxisome proliferator-activated receptors (PPARs) are master executors in regulating glucose and lipid homeostasis and also modulate mitochondrial function. However, synthetic PPAR agonists used for treating hyperlipidemia and DM have shown controversial effects on cardiovascular regulation. This article reviews our updated understanding of the beneficial and detrimental effects of PPARs on mitochondria in diabetic hearts.

Treatment delay and fatal outcomes of pulmonary tuberculosis in advanced age: a retrospective nationwide cohort study.

BACKGROUND AND OBJECTIVE: Studies focusing on pulmonary tuberculosis in advanced age (≥80 years) are lacking. This study aimed to explore treatment delay, outcomes and their predictors in this group. METHODS: Adult (≥20 years) patients with pulmonary tuberculosis were identified from the National Health Insurance Research Database of Taiwan from 2004 to 2009. Treatment completion and mortality rates were noted at one year after treatment. RESULTS: Among the 81,081 patients with pulmonary tuberculosis identified, 13,923 (17.2%) were aged ≥80 years, and 26,897 (33.2%) were aged 65-79 years. The treatment completion, mortality rates and treatment delay were 54.8%, 34.7% and 61 (12-128) [median, (1st-3rd quartiles)] days in patients aged ≥80 years, 68.3%, 18.5% and 53 (8-122) days in patients aged 65-79 years, and 78.9%, 6.5% and 21 (1-84) days in patients aged <65 years, respectively. The elder patients were more likely to receive second-line anti-tuberculosis agents. The treatment completion rate decreased with older age, female sex, comorbidities, low income, requiring second-line anti-tuberculosis agents, severity of pulmonary tuberculosis and longer treatment delay. Older age, female sex, comorbidities, low income, and not undergoing rapid molecular diagnostic tests were independently associated with longer treatment delays. CONCLUSIONS: Pulmonary tuberculosis in advanced age has a longer treatment delay and a higher mortality rate. Applying rapid molecular diagnostic tools may reduce treatment delay and should be integrated into the diagnostic algorithm for pulmonary tuberculosis, particularly in elderly patients.

Effect of pulmonary tuberculosis on clinical outcomes of long-term dialysis patients: Pre- and post-DOTS implementation in Taiwan.

BACKGROUND AND OBJECTIVE: The link between tuberculosis (TB) and dialysis is known; however, the impact of TB on the clinical outcomes remains to be elucidated. This study aims to determine the clinical consequences of pulmonary TB among patients under long-term dialysis. METHODS: A retrospective propensity-scores matched (1:4) cohort study was conducted by retrieving patient data for pulmonary TB after long-term dialysis commencement from the Taiwan National Health Insurance Research Database between 1999 and 2013. Patients with TB (n = 1993) or without TB (n = 7972) were compared for 3-year morbidity and mortality. The effect of Directly Observed Treatment, Short-Course (DOTS) implementation was also evaluated. Cox proportional hazards models were used to determine adjusted hazard ratios (HRs). RESULTS: TB patients had a significantly higher risk of mortality than non-TB patients even after multivariate adjustment (HR: 1.48; 95% CI: 1.36-1.60; P < 0.001). DOTS implementation reduced the risk of some morbidities such as pneumonia, hospitalization and intensive care unit stay >7 days, but not inotropic agent usage, ventilator therapy >21 days and mortality in TB patients. In pulmonary TB patients with treatment duration ≥180 days, DOTS implementation also lowered the risk of TB relapse (HR: 0.33; 95% CI: 0.19-0.55; P < 0.001), irrespective of treatment duration (180-224 or ≥225 days). CONCLUSION: Pulmonary TB increases the risk of morbidity and mortality in dialysis patients; DOTS implementation reduces some morbidities and TB relapse. Continuing DOTS implementation should be encouraged to improve clinical outcomes in dialysis patients.

Utility of Plasma Osteopontin Levels in Management of Community-Acquired Pneumonia.

Osteopontin (OPN) is an essential cytokine involved in immune cell recruitment and an important regulator of inflammation. The purpose of this study was to examine differences in OPN plasma levels between before and after antibiotic treatment in hospitalized adult patients with community-acquired pneumonia (CAP). OPN levels were measured in 93 patients with CAP and 54 healthy controls using a commercial enzyme-linked immunosorbent assay (ELISA). The CURB-65, Pneumonia Severity Index (PSI), and Acute Physiology and Chronic Health Evaluation II (APACHE II) scores were used to determine the CAP severity in patients upon initial hospitalization. A decline in the number of white blood cells (WBCs) and neutrophils, and decreases in the levels of OPN and C-reactive protein (CRP) were observed after antibiotic treatment. Only the plasma level of OPN, but not CRP, was correlated with the severity of CAP based on the PSI (r = 0.514, p < 0.001), CURB-65 (r = 0.396, p < 0.001), and APACHE II scores (r = 0.473, p < 0.001). The OPN level also showed a significant correlation with the length of hospital stay (r = 0.210, p = 0.044). In conclusion, plasma level of OPN may act as diagnostic adjuvant biomarkers for CAP and further play a role in clinical assessment of the severity of CAP, which could potentially guide the development of treatment strategies.

Plasma Monocyte Chemoattractant Protein-1 Level as a Predictor of the Severity of Community-Acquired Pneumonia.

Monocyte chemoattractant protein (MCP)-1 increases in the serum of immunocompetent patients with community-acquired pneumonia (CAP). However, the correlation between the circulating level of MCP-1 and severity of CAP remains unclear. This study investigated differential changes in the plasma MCP-1 levels of patients with CAP before and after an antibiotic treatment and further analyzes the association between the CAP severity and MCP-1 levels. We measured the plasma MCP-1 levels of 137 patients with CAP and 74 healthy controls by using a commercial enzyme-linked immunosorbent assay. Upon initial hospitalization, Acute Physiology and Chronic Health Evaluation II (APACHE II); confusion, urea level, respiratory rate, blood pressure, and age of >64 years (CURB-65); and pneumonia severity index (PSI) scores were determined for assessing the CAP severity in these patients. The antibiotic treatment reduced the number of white blood cells (WBCs) and neutrophils as well as the level of C-reactive protein (CRP) and MCP-1. The plasma MCP-1 level, but not the CRP level or WBC count, correlated with the CAP severity according to the PSI (r = 0.509, p < 0.001), CURB-65 (r = 0.468, p < 0.001), and APACHE II (r = 0.360, p < 0.001) scores. We concluded that MCP-1 levels act in the development of CAP and are involved in the severity of CAP.

Human papillomavirus infections as a marker to predict overall survival in lung adenocarcinoma.

Human papillomavirus (HPV) has been implicated in multiple cancers, but its significance in lung cancer has remained controversial. As the prevalence of HPV 16/18 infection was higher in lung adenocarcinoma among Taiwanese females, the aim of our study was to evaluate the clinical impact of HPV infections in lung adenocarcinoma. Two hundred and ten patients were enrolled to investigate the associations of HPV status in tumors with clinical characteristics as well as its impact on overall survival. The methods to assess HPV status were by immunohistochemistry for HPV L1 capsid protein and E6 protein and by nested polymerase chain reaction for HPV 16 and HPV 18. HPV infections were identified in 35.2% of patients, and associated with localized and smaller sized tumors (p = 0.022 and p = 0.002, respectively). Patients with HPV infections had a significantly better survival (p = 0.023, by log-rank test) and a significantly reduced mortality risk after adjustments of age, tumor extent, epidermal growth factor receptor (EGFR) mutations status and treatments [adjusted hazard ratio = 0.68, 95% confidence interval (CI) = 0.49-0.96, p = 0.026, by multivariate Cox proportional hazards models]. Specifically, patients with both HPV infections and EGFR mutations had the best survival outcome [1-year survival rate, 68.5% (95% CI = 52.2-4.8%)]. Our findings indicate that HPV infections represent an independent prognostic factor for overall survival in patients with lung adenocarcinoma.

Plasma endothelial cell-specific molecule-1 (ESM-1) in management of community-acquired pneumonia.

BACKGROUND: Endothelial cell-specific molecule (ESM)-1 is a soluble proteoglycan expressed by the vascular endothelium and which also circulates in the bloodstream. Inflammatory cytokines and proangiogenic growth factors increase its expression, and increased serum levels are found in immunocompetent patients with sepsis. The aim of this study was to investigate differential changes in plasma levels of ESM-1 before and after antibiotic treatment in hospitalized adult patients with community-acquired pneumonia (CAP). METHODS: Plasma ESM-1 levels were measured in 82 adult patients with CAP and 82 healthy controls using a commercial enzyme-linked immunosorbent assay (ELISA). Upon initial hospitalization, Acute Physiology and Chronic Health Evaluation II (APACHE II), CURB-65, and Pneumonia Severity Index (PSI) scores were determined to assess CAP severity in these patients. RESULTS: Results showed a decline in the number of white blood cells (WBCs) and neutrophils, and decreases in the concentrations of C-reactive protein (CRP) and ESM-1 after antibiotic treatment. The plasma concentration of ESM-1, but not CRP or the WBC count, was correlated with the severity of CAP based on the PSI (r=0.554, p<0.001), CURB-65 (r=0.510, p<0.001), and APACHE II scores (r=0.447, p<0.001). CONCLUSIONS: Plasma levels of ESM-1 may be able to play a role in the diagnosis and clinical assessment of the severity of CAP, which could potentially guide the development of treatment strategies.

Impact of food intake on the pharmacokinetics of first-line antituberculosis drugs in Taiwanese tuberculosis patients.

BACKGROUND/PURPOSE: Under the directly observed treatment, short course (DOTS) program, antituberculosis (anti-TB) medications were possibly taken at random time, regardless of whether it was prior to or after meals. This study was to evaluate the impact of food intake on pharmacokinetic profiles of first-line TB drugs in Taiwanese TB patients, as well as the relationship between drug levels and pharmacogenetics. METHODS: This open-label, randomized, cross-over study included newly diagnosed Taiwanese TB patients treated between January 2010 and February 2011 at Taipei Medical University-Wan Fang Hospital. Rifater [a fixed-dose combination formulation of isoniazid (INH), rifampicin (RIF), and pyrazinamide (PZA)] and ethambutol (EMB) were given according to national TB guidelines. Blood samples were collected prior to and 1 hour, 2 hours, 4 hours, 6 hours, and 10 hours after dosing under fasting or postprandial conditions. Pharmacokinetic parameters of the maximum serum concentration (Cmax), time to Cmax, and area under the serum concentration-time curve from the beginning to the 10(th) hour (AUC0-10) were calculated. RESULTS: Sixteen TB patients were included and received anti-TB treatment under the DOTS program after discharge. The overall effects showed that food intake reduced the mean Cmax (INH: 40.6%, RIF: 40.2%, EMB 34.4%, PZA: 24.4%) and AUC0-10 (INH: 21.3%, RIF: 26.4%, EMB: 12.2%, PZA: 12.0%). Meanwhile, food increased the time to Cmax (INH: 78.1%, RIF: 151.3%, EMB: 41.4%, PZA: 148.9%). CONCLUSION: Significantly lower serum drug concentrations were observed under postprandial conditions than fasting conditions for INH, RIF, and PZA. The impact of taking random anti-TB drugs under the DOTS program instead of taking drugs regularly prior to meals requires further study.

Particulate matter deposition and its impact on tuberculosis severity: A cross-sectional study in Taipei.

The objective of this study was to examine the association between the lung lobe-deposited dose of inhaled fine particulate matter (PM2.5) and chest X-ray abnormalities in different lung lobes of pulmonary tuberculosis (TB), multidrug-resistant tuberculosis (MDR-TB), and non-tuberculosis mycobacteria infections (NTM). A cross-sectional study was conducted between 2014 and 2022, comprising 1073 patients who were recruited from chest department clinic in a tertial refer hospital in Taipei City, Taiwan. Ambient 1-, 7-, and 30-day PM2.5 exposure and the deposition of PM2.5 in different lung lobes were estimated in each subject. The ß coefficient for PM2.5 and deposited PM2.5 in lungs with the outcome variables (pulmonary TB, MDR-TB, and NTM infection) was derived through regression analysis and adjusted for age, gender, BMI, smoking status, and family income. We observed that a 1 µg/m3 increase in ambient PM2.5 was associated with an increase of MDR-TB infections of 0.004 times (95%CI: 0.001-0.007). A 1 µg/m3 increase in 1-day and 7-day PM2.5 deposition in left upper lobe and left lower lobe was associated with an increase in chest X-ray abnormalities of 9.19 % and 1.18 % (95%CI: 0.87-17.51 and 95%CI: 0.08-2.28), and 4.52 % and 5.20 % (95%CI: 0.66-8.38 and 95%CI: 0.51-9.89) in left lung of TB patients, respectively. A 1 µg/m3 increase in 30-day PM2.5 deposition in alveolar region was associated with an increase in percent abnormality of 2.50 % (95%CI: 0.65-4.35) in left upper lobe and 3.33 % (95%CI: 0.65-6.01) in right middle lobe, while in total lung was 0.63 % (95%CI: 0.01-1.27) in right upper lobe and 0.37 % (95%CI, 0.06-0.81) in right lung of MDR-TB patients. Inhaled PM2.5 deposition in lungs was associated with an exacerbation of the radiographic severity of pulmonary TB, particularly in pulmonary MDR-TB patients in upper and middle lobes. Particulate air pollution may potentially exacerbate the radiographic severity and treatment resistance in individuals with pulmonary TB.

Plasma long pentraxin 3 (PTX3) concentration is a novel marker of disease activity in patients with community-acquired pneumonia.

BACKGROUND: Long pentraxin 3 (PTX3) is an acute-phase protein secreted by various cells, including leukocytes and endothelial cells. Like C-reactive protein (CRP), it belongs to the pentraxin superfamily. The aim of this study was to investigate the differential changes in plasma levels of PTX3 between before and after antibiotic treatment in hospitalized adult patients with community-acquired pneumonia (CAP). METHODS: Plasma PTX3 levels were measured in 61 adult patients with CAP and 60 healthy controls using a commercial enzyme-linked immunosorbent assay (ELISA). Upon initial hospitalization, APACHE II, CURB-65, and pneumonia severity index (PSI) scores were determined to assess CAP severity in patients. RESULTS: The results showed a decline in the number of white blood cells (WBCs) and neutrophils, and decreases in the concentrations of CRP and PTX3 observed after antibiotic treatment. The plasma concentration of PTX3, but not CRP, was correlated with the severity of CAP based on the PSI (r=0.290, p=0.023), CURB-65 (r=0.312, p=0.015), and APACHE II scores (r=0.427, p=0.001). The PTX3 level also exhibited a significant correlation with the length of hospital stay (r=0.500, p<0.0001). CONCLUSIONS: PTX3 may be able to play a role in the diagnosis and clinical assessment of the severity of CAP, which could potentially guide the development of treatment strategies.

Alveolar deposition of inhaled fine particulate matter increased risk of severity of pulmonary tuberculosis in the upper and middle lobes.

Inhaled PM2.5 associated with pulmonary tuberculosis https://bit.ly/3VXAKfq.

Ambient relative humidity-dependent obstructive sleep apnea severity in cold season: A case-control study.

BACKGROUND: The objective of this study was to examine associations of daily averages and daily variations in ambient relative humidity (RH), temperature, and PM2.5 on the obstructive sleep apnea (OSA) severity. METHODS: A case-control study was conducted to retrospectively recruit 8628 subjects in a sleep center between January 2015 and December 2021, including 1307 control (apnea-hypopnea index (AHI) < 5 events/h), 3661 mild-to-moderate OSA (AHI of 5-30 events/h), and 3597 severe OSA subjects (AHI > 30 events/h). A logistic regression was used to examine the odds ratio (OR) of outcome variables (daily mean or difference in RH, temperature, and PM2.5 for 1, 7, and 30 days) with OSA severity (by the groups). Two-factor logistic regression models were conducted to examine the OR of RH with the daily mean or difference in temperature or PM2.5 with OSA severity. An exposure-response relationship analysis was conducted to examine the outcome variables with OSA severity in all, cold and warm seasons. RESULTS: We observed associations of mean PM2.5 and RH with respective increases of 0.04-0.08 and 0.01-0.03 events/h for the AHI in OSA patients. An increase in the daily difference of 1 % RH increased the AHI by 0.02-0.03 events/h in OSA patients. A daily PM2.5 decrease of 1 µg/m3 reduced the AHI by 0.03 events/h, whereas a daily decrease in the RH of 1 % reduced the AHI by 0.03-0.04 events/h. The two-factor model confirmed the most robust associations of ambient RH with AHI in OSA patients. The exposure-response relationship in temperature and RH showed obviously seasonal patterns with OSA severity. CONCLUSION: Short-term ambient variations in RH and PM2.5 were associated with changes in the AHI in OSA patients, especially RH in cold season. Reducing exposure to high ambient RH and PM2.5 levels may have protective effects on the AHI in OSA patients.

Osthole inhibits the invasive ability of human lung adenocarcinoma cells via suppression of NF-κB-mediated matrix metalloproteinase-9 expression.

The induction of matrix metalloproteinase (MMP)-9 is particularly important for the invasiveness of various cancer cells. Osthole, a natural coumarin derivative extracted from traditional Chinese medicines, is known to inhibit the proliferation of a variety of tumor cells, but the effect of osthole on the invasiveness of tumor cells is largely unknown. This study determines whether and by what mechanism osthole inhibits invasion in CL1-5 human lung adenocarcinoma cells. Herein, we found that osthole effectively inhibited the migratory and invasive abilities of CL1-5 cells. A zymographic assay showed that osthole inhibited the proteolytic activity of MMP-9 in CL1-5 cells. Inhibition of migration, invasion, and MMP2 and/or MMP-9 proteolytic activities was also observed in other lung adenocarcinoma cell lines (H1299 and A549). We further found that osthole inhibited MMP-9 expression at the messenger RNA and protein levels. Moreover, a chromatin immunoprecipitation assay showed that osthole inhibited the transcriptional activity of MMP-9 by suppressing the DNA binding activity of nuclear factor (NF)-κB in the MMP-9 promoter. Using reporter assays with point-mutated promoter constructs further confirmed that the inhibitory effect of osthole requires an NF-κB binding site on the MMP-9 promoter. Western blot and immunofluorescence assays demonstrated that osthole inhibited NF-κB activity by inhibiting IκB-α degradation and NF-κB p65 nuclear translocation. In conclusion, we demonstrated that osthole inhibits NF-κB-mediated MMP-9 expression, resulting in suppression of lung cancer cell invasion and migration, and osthole might be a potential agent for preventing the invasion and metastasis of lung cancer.

How platinum-induced nephrotoxicity occurs? Machine learning prediction in non-small cell lung cancer patients.

BACKGROUND AND OBJECTIVE: Platinum-induced nephrotoxicity is a severe and unexpected adverse drug reaction that could lead to treatment failure in non-small cell lung cancer patients. Better prediction and management of this nephrotoxicity can increase patient survival. Our study aimed to build up and compare the best machine learning models with clinical and genomic features to predict platinum-induced nephrotoxicity in non-small cell lung cancer patients. METHODS: Clinical and genomic data of patients undergoing platinum chemotherapy at Wan Fang Hospital were collected after they were recruited. Twelve models were established by artificial neural network, logistic regression, random forest, and support vector machine with integrated, clinical, and genomic modes. Grid search and genetic algorithm were applied to construct the fine-tuned model with the best combination of predictive hyperparameters and features. Accuracy, precision, recall, F1 score, and area under the receiver operating characteristic curve were calculated to compare the performance of the 12 models. RESULTS: In total, 118 patients were recruited for this study, among which 28 (23.73%) were experiencing nephrotoxicity. Machine learning models with clinical and genomic features achieved better prediction performances than clinical or genomic features alone. Artificial neural network with clinical and genomic features demonstrated the best predictive outcomes among all 12 models. The average accuracy, precision, recall, F1 score and area under the receiver operating characteristic curve of the artificial neural network with integrated mode were 0.923, 0.950, 0.713, 0.808 and 0.900, respectively. CONCLUSIONS: Machine learning models with clinical and genomic features can be a preliminary tool for oncologists to predict platinum-induced nephrotoxicity and provide preventive strategies in advance.