Comparison of random forests and SARIMA in Predicting Brucellosis Incidence / 公共卫生与预防医学

Objective To compare the effects of random forest and SARIMA (Seasonal Autoregressive Integrated Moving Average) on predicting incidence rate of brucellosis. Methods Using Brucellosis cases reported in the China Disease Prevention and Control Information System from 2005 to 2017, two models, random forest and SARIMA, were established for training and forecasting, and the forecasting results of the two models were compared. Results The R2 (R Squared) and RMSE (Root Mean Squared Error) of SARIMA model and random forest model are 0.904, 0.034351, 0.927 and 0.03345 respectively. Conclusion Both models have high prediction accuracy and can predict the incidence of brucellosis. Random forest prediction is a little bit better than SARIMA model and has more practical value.

Progress and prospect of machine learning in research of acupuncture and moxibustion / 中国针灸

The application progress of machine learning in research of acupuncture and moxibustion was reviewed from three aspects: mining of acupuncture and moxibustion prescription and indications, acupuncture efficacy prediction and its influencing factors, acupoint specificity and acupuncture manipulation research, and the existing problems in current research and future research trends were discussed. It is believed that the appropriate machine learning algorithm should be selected to build the model according to the research purpose and data characteristics in the future research; attention should be paid to feature design, feature selection and feature cleaning; sample data collection should be a priority, and data sharing platform and standardized data collection should be developed to improve the data quality.