Development of a Pancreatic Fistula Prediction Model After Pancreaticoduodenectomy Based on a Decision Tree and Random Forest Algorithm.

BACKGROUND: The incidence of postoperative pancreatic fistula (POPF) after pancreaticoduodenectomy (PD) is high. We sought to develop a POPF prediction model based on a decision tree (DT) and random forest (RF) algorithm after PD and to explore its clinical value. METHODS: The case data of 257 patients who underwent PD in a tertiary general hospital from 2013 to 2021 were retrospectively collected in China. The RF model was used to select features by ranking the importance of variables, and both algorithms were used to build the prediction model after automatic adjustment of parameters by setting the respective hyperparameter intervals and resampling as a 10-fold cross-validation method, etc. The prediction model's performance was assessed by the receiver operating characteristic curve (ROC) and the area under curve (AUC). RESULTS: Postoperative pancreatic fistula occurred in 56 cases (56/257, 21.8%). The DT model had an AUC of .743 and an accuracy of .840, while the RF model had an AUC of .977 and an accuracy of .883. The DT plot visualized the process of inferring the risk of pancreatic fistula from the DT model on independent individuals. The top 10 important variables were selected for ranking in the RF variable importance ranking. CONCLUSION: This study successfully developed a DT and RF algorithm for the POPF prediction model, which can be used as a reference for clinical health care professionals to optimize treatment strategies to reduce the incidence of POPF.

Quantitative source apportionment, risk assessment and distribution of heavy metals in agricultural soils from southern Shandong Peninsula of China.

The heavy metals, including cadmium (Cd), chromium (Cr), copper (Cu), mercury (Hg), nickel (Ni), lead (Pb), zinc (Zn), and the metalloid arsenic (As) were detected in surface and core soil samples collected from a tobacco growing region in Shandong Peninsula on the east coast of China to evaluate their pollution levels, ecological and health risks, and to analyze their spatial and vertical distributions. The heavy metal sources were identified quantitatively using the positive matrix factorization (PMF) receptor model. In accordance, most of the soils did not have accumulations and were not contaminated by As, Cr, Cu, Ni, Pb, and Zn. High accumulations of Cd and Hg occurred in the soils, posing an ecological risk to the local agricultural environment, while Cr and Ni levels presented a carcinogenic health risk to humans. Four main sources of heavy metals in the soils were identified. Correspondingly Ni and Cr were mainly originated from natural sources, Hg from coal combustion, Cd from agricultural practices, Cu, Pb, and Zn from agricultural practices and industrial activities, and As from industrial activities.

Risk assessment, spatial distribution, and source apportionment of heavy metals in Chinese surface soils from a typically tobacco cultivated area.

The heavy metals (As, Cd, Cr, Cu, Hg, Ni, Pb, and Zn) in the surface soils of tobacco (Nicotiana tabacum L.) fields in Jiangxi Province were analyzed, and the mean heavy metal concentrations were 3.55, 0.19, 25.89, 14.96, 0.25, 10.89, 27.80, and 44.00 mg/kg, respectively. Spatial distribution analysis showed that the highest concentrations were recorded in the north-western, south-western, and mid-eastern parts of the study area. The index of geo-accumulation and pollution index indicated modest enrichment with Cd and Hg, which were the only two metals posing a potentially high ecological risk to the local agricultural environment. The health risk assessment showed no considerable non-carcinogenic or carcinogenic risks for children and adults from these elements. The principal component analysis (PCA) and cluster analysis (CA) found that the variations in the Cr and Ni concentrations were largely on account of the soil parent rocks, but the As, Cd, Cu, and Hg variations in the soil were largely owing to agricultural practices of years. However, the main factor influencing Pb and Zn was atmospheric deposition.

Screening of novel low-cost adsorbents from agricultural residues to remove ammonia nitrogen from aqueous solution.

Most studies on ammonia adsorption from aqueous solution have been focused on mineral materials. However, a series of batch experiments were performed in this study to screen novel adsorbent materials from 80 agricultural residues, and to investigate the adsorption characteristics of six screened samples. The results showed that the ammonia adsorption efficiencies of 11 agricultural residues were comparable to those of minerals. The equilibrium data fitted well with both the Langmuir and Freundlich models, and the theoretical maximum monolayer adsorption capacities of strawberry leaves and stems, Boston ivy leaves and stems, southern magnolia leaves and poplar leaves were 6.71, 4.62, 6.07, 5.01, 6.22 and 6.25mg/g, respectively at 30 degrees C. The adsorptions reached equilibrium at about 18 h, and the kinetics were well described by the Logistic model. In conclusion, these agricultural residues could be used as adsorbent materials for ammonia removal.