RESUMO
BACKGROUND: Gastric cancer is one of the most common malignant tumors in the digestive system, ranking sixth in incidence and fourth in mortality worldwide. Since 42.5% of metastatic lymph nodes in gastric cancer belong to nodule type and peripheral type, the application of imaging diagnosis is restricted. AIM: To establish models for predicting the risk of lymph node metastasis in gastric cancer patients using machine learning (ML) algorithms and to evaluate their predictive performance in clinical practice. METHODS: Data of a total of 369 patients who underwent radical gastrectomy at the Department of General Surgery of Affiliated Hospital of Xuzhou Medical University (Xuzhou, China) from March 2016 to November 2019 were collected and retrospectively analyzed as the training group. In addition, data of 123 patients who underwent radical gastrectomy at the Department of General Surgery of Jining First People's Hospital (Jining, China) were collected and analyzed as the verification group. Seven ML models, including decision tree, random forest, support vector machine (SVM), gradient boosting machine, naive Bayes, neural network, and logistic regression, were developed to evaluate the occurrence of lymph node metastasis in patients with gastric cancer. The ML models were established following ten cross-validation iterations using the training dataset, and subsequently, each model was assessed using the test dataset. The models' performance was evaluated by comparing the area under the receiver operating characteristic curve of each model. RESULTS: Among the seven ML models, except for SVM, the other ones exhibited higher accuracy and reliability, and the influences of various risk factors on the models are intuitive. CONCLUSION: The ML models developed exhibit strong predictive capabilities for lymph node metastasis in gastric cancer, which can aid in personalized clinical diagnosis and treatment.
RESUMO
Because commercial organic fertilizers may contain cadmium (Cd) and may cause the dual effect of "inhibition" and "activation" on Cd availability in paddy soil with organic fertilizer input, the reduction of rice Cd following organic fertilizer application is still uncertain. Herewith, typical purple mud paddy fields were selected in the eastern Hunan Province. The effect of commercial organic fertilizer input on Cd reduction of double-rice paddy ecosystem was monitored for four consecutive years. The relationships between brown rice Cd content, soil available Cd, and soil factors (pH, soil labile organic carbon fractions, and iron oxide) at different growth stages in double-rice paddy fields were investigated. Results showed that the input of organic fertilizer reduced the Cd content in brown rice by 28%-56%. Meanwhile, the decrease of Cd content in brown rice of late rice (43%-56%) was higher than that of early rice (28%-45%), and the inter-annual fluctuation of the decrease was relatively small. On the one hand, soil available Cd content decreased by 6%-7% during several growth stages of double-rice (from tillering peak stage to full heading stage) with organic fertilizer input. Additionally, the content of soil exchangeable Cd was decreased by 11%, whereas the content of organic bound Cd was increased by 14%. This directly reflects the decrease of soil Cd availability. On the other hand, the soil pH value was steadily increased by 0.1-0.3 units following organic fertilizer input, which promoted the development of soil from acidity to slight acidity. Besides, the content of soil active organic carbon (light fraction organic carbon, coarse particulate organic carbon, and fine particulate organic carbon) was increased significantly (53%, 77%, and 107%, respectively). This indirectly reflects the decrease in soil Cd availability. This study implies that the decrease of soil Cd availability may be the primary driving force for the reduction of rice Cd content with consecutive organic fertilizer input in purple mud paddy fields.
