RESUMO
Rural microcredit plays an important role in promoting rural economic development and increasing farmers' income. However, traditional credit risk assessment models may have insufficient adaptability in rural areas. This study is based on the improved Long Short Term Memory (LSTM) algorithm using self organizing method, aiming to design an optimized evaluation model for rural microcredit risk. The improved LSTM algorithm can better capture the long-term dependence between the borrower's historical behavior and risk factors with its advantages in sequential data modeling. The experimental results show that the rural microcredit risk assessment model based on the self organizing LSTM algorithm has higher accuracy and stability compared to traditional models, and can effectively control credit default risk, providing more comprehensive risk management support for financial institutions. In addition, the model also has real-time monitoring and warning functions, which helps financial institutions adjust their decisions in a timely manner and reduce credit losses. The practical application of this study is expected to promote the stable development of rural economy and the advancement of financial technology. However, future work needs to further validate the practical application effectiveness and interpretability of the model, taking into account the special circumstances of different rural areas, in order to achieve sustainable application of the model in the rural microcredit market.
RESUMO
OBJECTIVE: To quantitatively assess hypoattenuation volume ratio and hepatic parenchymal hypoattenuation on contrast enhanced computed tomography (CECT) in patients with pyrrolizidines alkaloids (PAs)-induced hepatic sinusoidal obstruction syndrome (HSOS), and evaluate the correlations of the CT-based quantitative values with clinical factors. METHODS: Thirty-five patients with PAs-induced HSOS who underwent CECT were retrospectively enrolled. The ratio of hypoattenuation volume to total liver volume, and changes in damaged area-to-normal liver density ratio (ΔDR) derived from histogram on portal venous phase were quantitatively measured. Heterogeneous hypoattenuation (CT score) scored by hypoattenuation volume ratio and ΔDR were calculated. The correlation between imaging findings and clinical factors was analyzed using Pearson correlation test. RESULTS: Liver function tests were abnormal in most patients, the mean Hounsfield unit (HU) of damaged area (58.68 ± 17.3) was significantly lower (P < 0.001) than the corresponding normal liver (82.27 ± 23.97). Heterogeneous hypoattenuation were mild in 13 patients (37 %), moderate in 16 patients (46 %), and severe in 6 patients (17 %). ΔDR derived from histogram was positively correlated (weakly to moderately) with total bilirubin (r = 0.341, P = 0.045), direct bilirubin (r = 0.385, P = 0.022), and alkaline phosphatase (r = 0.491, P = 0.003), while such correlation was not observed in hypoattenuation volume ratio. The severity of heterogeneous hypoattenuation scored by hypoattenuation volume ratio and ΔDR was positively correlated (weakly) with prothrombin time (r = 0.357, P = 0.035), international normalized ratio (r = 0.363, P = 0.032), alkaline phosphatase (r = 0.359, P = 0.034), and model for end-stage liver disease (MELD) score (r = 0.347, P = 0.041). CONCLUSION: Heterogeneous hypoattenuation scored by volume ratio and ΔDR on CECT provides a non-invasive approach in evaluating the severity of PAs-induced HSOS.