RESUMEN
AIM: To develop a classifier for traditional Chinese medicine (TCM) syndrome differentiation of diabetic retinopathy (DR), using optimized machine learning algorithms, which can provide the basis for TCM objective and intelligent syndrome differentiation. METHODS: Collated data on real-world DR cases were collected. A variety of machine learning methods were used to construct TCM syndrome classification model, and the best performance was selected as the basic model. Genetic Algorithm (GA) was used for feature selection to obtain the optimal feature combination. Harris Hawk Optimization (HHO) was used for parameter optimization, and a classification model based on feature selection and parameter optimization was constructed. The performance of the model was compared with other optimization algorithms. The models were evaluated with accuracy, precision, recall, and F1 score as indicators. RESULTS: Data on 970 cases that met screening requirements were collected. Support Vector Machine (SVM) was the best basic classification model. The accuracy rate of the model was 82.05%, the precision rate was 82.34%, the recall rate was 81.81%, and the F1 value was 81.76%. After GA screening, the optimal feature combination contained 37 feature values, which was consistent with TCM clinical practice. The model based on optimal combination and SVM (GA_SVM) had an accuracy improvement of 1.92% compared to the basic classifier. SVM model based on HHO and GA optimization (HHO_GA_SVM) had the best performance and convergence speed compared with other optimization algorithms. Compared with the basic classification model, the accuracy was improved by 3.51%. CONCLUSION: HHO and GA optimization can improve the model performance of SVM in TCM syndrome differentiation of DR. It provides a new method and research idea for TCM intelligent assisted syndrome differentiation.
RESUMEN
Ili Valley is an important ecological barrier in western China and an important economic zone of the Belt and Road Initiative. Exploring the driving factors of ecosystem service value (ESV) based on land use change is of great significance for optimizing regional ecological environment and coordinating human-land relationship. Based on three periods of land use data from 2000 to 2020 in Yili Valley, we used ArcGIS 10.8 and Origin to analyze the characteristics of land use change, temporal and spatial variations of ESV, and the synergy and trade-offs of ecosystem services, and explored the driving factors affecting the spatial differentiation of ESV and the interaction among factors by using Geo-Detector. The results showed that land use change in the study area was obvious from 2000 to 2020, with the area of grassland and water area being greatly reduced and the largest increase for the area of construction land. The ESV of grassland and water area and the service function of water resource supply decreased significantly. ESV high value areas were transformed to low value areas. Synergy was the dominant relationship among ecosystem services in the study area, which showed an increasing trend. Elevation was the main driving factor of ESV spatial differentiation in Yili Valley, and the low elevation plain area suitable for human activities on both sides of the basin was the low ESV value area. The interaction between all factors was manifested as enhanced relationship, while the explanatory power of natural factors was higher than that of social and economic factors.
Asunto(s)
Conservación de los Recursos Naturales , Ecosistema , Humanos , China , Abastecimiento de Agua , AguaRESUMEN
OBJECTIVE: To explore the relationship between portal vein hemodynamics and the severity of fibrosis in patients with chronic hepatitis. METHODS: Portal vein blood flow velocity (PBFVe) and volume (PBFVo) along with the serum fibrosis markers were examined in 71 patients with chronic viral hepatitis B, and hepatic pathological changes were routinely observed. RESULTS: As the hepatitis progressed, the PBFVe decreased in close inverse relation to the degree of liver fibrosis (P<0.01) and the levels of the serum fibrosis markers hyaluronic (HA) and collagen IV (IV-C). The PBFVo, however, was not related with the fibrotic status in the patients, but was reduced as the hepatic inflammatory reaction escalated. CONCLUSION: PBFVe is a more sensitive indicator for assessing portal hemodynamics than PBFVo in chronic hepatitis progression, and when combined with serum HA and IV-C levels, it may demonstrate the severity of hepatic fibrosis. PBFVo together with procollagen III level, however, can be meaningful for deciding the intrahepatic inflammation activity.