Search

Background and Aim Methods Results Conclusions In this study, a deep learning algorithm was used to predict the survival rate of colon cancer (CC) patients, and compared its performance with traditional Cox regression.In this population‐based cohort study, we used the characteristics of patients diagnosed with CC between 2010 and 2015 from the Surveillance, Epidemiology and End Results (SEER) database. The population was randomized into a training set (n = 10 596, 70%) and a test set (n = 4536, 30%). Brier scores, area under the (AUC) receiver operating characteristic curve and calibration curves were used to compare the performance of the three most popular deep learning models, namely, artificial neural networks (ANN), deep neural networks (DNN), and long‐short term memory (LSTM) neural networks with Cox proportional hazard (CPH) model.In the independent test set, the Brier values of ANN, DNN, LSTM and CPH were 0.155, 0.149, 0.148, and 0.170, respectively. The AUC values were 0.906 (95% confidence interval [CI] 0.897–0.916), 0.908 (95% CI 0.899–0.918), 0.910 (95% CI 0.901–0.919), and 0.793 (95% CI 0.769–0.816), respectively. Deep learning showed superior promising results than CPH in predicting CC specific survival.Deep learning showed potential advantages over traditional CPH models in terms of prognostic assessment and treatment recommendations. LSTM exhibited optimal predictive accuracy and has the ability to provide reliable information on individual survival and treatment recommendations for CC patients. [ABSTRACT FROM AUTHOR]

Abstract Polycyclic aromatic hydrocarbons (PAHs) have toxic, teratogenic, mutagenic and carcinogenic effects on living organisms. Plants can function as pollutant bioindicators and bioaccumulators due to their wide surface distribution and specific responses to atmospheric pollutants. However, various plants exhibit significant differences in their capacities to accumulate PAHs. At present, research has mainly focused on the effects of leaf morphology and physiological characteristics, and few studies have evaluated the effects of the leaf surface on PAH accumulation. We aimed to assess the factors impacting the uptake and accumulation of PAHs by leaves. We selected 8 common tree species in Shanghai, China, and used supercritical fluid extraction technology to determine the content of PAHs in their leaves. Specific measurements of leaf area, width/length, wax content, and stomatal density were applied to index the morphological and physiological characteristics; surface roughness, surface free energy, polar components, and dispersion components were compiled into an adsorption performance index. Principal component analysis (PCA) and canonical correlation analysis (CCA) were used to assess the effects of different leaf characteristics on PAH accumulation. We found that the mean concentrations of ΣPAHs ranged from 300 to 2000 ng·g−1 and that the proportions of different benzene rings were significantly different among the different tree species. Leaf morphology and physiological characteristics had more significant effects compared to surface adsorption. CCA showed a significant negative correlation between leaf morphological characteristics and wax content, but had no significant correlation with surface adsorption. Low-molecular-weight PAHs were found to be mainly affected by the morphological characteristics, while medium- and high-molecular-weight PAHs were influenced by wax content and adsorption. Our conclusions provide a theoretical basis for the establishment of a reliable plant atmosphere-monitoring system and a method for screening tree species with strong PAH adsorption capacity. Graphical abstract Unlabelled Image Highlights • Eight plant leaves significantly differ in their ability to uptake and adsorb PAHs. • Morphology and physiological characteristics have greater impact than adsorption. • Retention of particulate PAHs on leaf is a valid way to reduce atmospheric PAHs. • HMW PAHs reserved by leaves are mainly affected by wax content and adsorption. [ABSTRACT FROM AUTHOR]