Development and application of machine learning models for prediction of soil available cadmium based on soil properties and climate features.

Identifying the key influencing factors in soil available cadmium (Cd) is crucial for preventing the Cd accumulation in the food chain. However, current experimental methods and traditional prediction models for assessing available Cd are time-consuming and ineffective. In this study, machine learning (ML) models were developed to investigate the intricate interactions among soil properties, climate features, and available Cd, aiming to identify the key influencing factors. The optimal model was obtained through a combination of stratified sampling, Bayesian optimization, and 10-fold cross-validation. It was further explained through the utilization of permutation feature importance, 2D partial dependence plot, and 3D interaction plot. The findings revealed that pH, surface pressure, sensible heat net flux and organic matter content significantly influenced the Cd accumulation in the soil. By utilizing historical soil surveys and climate change data from China, this study predicted the spatial distribution trend of available Cd in the Chinese region, highlighting the primary areas with heightened Cd activity. These areas were primarily located in the eastern, southern, central, and northeastern China. This study introduces a novel methodology for comprehending the process of available Cd accumulation in soil. Furthermore, it provides recommendations and directions for the remediation and control of soil Cd pollution.

Prognostic Predictive Characteristics in Patients With Fibrosing Interstitial Lung Disease: A Retrospective Cohort Study.

Background: Limited data are available regarding the entire spectrum of interstitial lung disease with a progressive fibrosing feature. We investigated the prevalence and prognostic predictive characteristics in patients with PF-ILD. Methods: This retrospective cohort study included patients with fibrosing ILD who were investigated between 1 January 2015 and 30 April 2021. We recorded clinical features and outcomes to identify the possible risk factors for fibrosing progression as well as mortality. Results: Of the 579 patients with fibrosing ILD, 227 (39.21%) met the criteria for progression. Clubbing of fingers [odds ratio (OR) 1.52, 95% confidence interval (CI) 1.03 to 2.24, p = 0.035] and a high-resolution computed tomography (HRCT)-documented usual interstitial pneumonia (UIP)-like fibrotic pattern (OR 1.95, 95% CI 1.33 to 2.86, p = 0.001) were risk factors for fibrosis progression. The mortality was worse in patients with PF with hypoxemia [hazard ratio (HR) 2.08, 95% CI 1.31 to 3.32, p = 0.002], in those with baseline diffusion capacity of the lung for carbon monoxide (DLCO) % predicted <50% (HR 2.25, 95% CI 1.45 to 3.50, p < 0.001), or in those with UIP-like fibrotic pattern (HR 1.68, 95% CI 1.04 to 2.71, p < 0.001). Conclusion: Clubbing of fingers and an HRCT-documented UIP-like fibrotic pattern were more likely to be associated with progressive fibrosing with varied prevalence based on the specific diagnosis. Among patients with progressive fibrosing, those with hypoxemia, lower baseline DLCO% predicted, or UIP-like fibrotic pattern showed poor mortality.