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.

Diagnostic value and influencing factors for amplitude-integrated EEG in brain injury in preterm infants / 中国当代儿科杂志

<p><b>OBJECTIVE</b>To study the diagnostic value and influencing factors for amplitude-integrated EEG (aEEG) in brain injury in preterm infants.</p><p><b>METHODS</b>One hundred and sixteen preterm infants with a gestational age (GA) between 27 weeks and 36(+6) weeks were enrolled as subjects. The aEEG scores of all preterm infants were obtained within 6 hours after birth. According to the diagnostic results, the 116 preterm infants were divided into two groups: brain injury (n=63) and non-brain injury (n=53). The risk factors for brain injury were evaluated using logistic regression analysis. According to the aEEG results, the 116 preterm infants were divided into two groups: normal aEEG (n=58) and abnormal aEEG (n=58). The influencing factors for aEEG results in preterm infants were determined using univariate analysis.</p><p><b>RESULTS</b>The brain injury group had a significantly higher rate of abnormal aEEG than the non-brain injury group (83% vs 11%; P<0.05). The infants in the brain injury group from two different GA subgroups (27-33(+6) weeks and 34-36(+6) weeks) had significantly lower aEEG scores than the non-brain injury group from corresponding GA subgroups (P<0.01). Logistic regression analysis showed that low GA (<32 weeks), low birth weight (<1 500 g), abnormal placenta, fetal membranes, and umbilical cord, and hypertension during pregnancy were high-risk factors for brain injury (P<0.05). There were significant differences in GA, birth weight, abnormal placenta, fetal membranes, and umbilical cord, and hypertension during pregnancy between the normal and abnormal aEEG groups (P<0.05).</p><p><b>CONCLUSIONS</b>The risk factors for brain injury are consistent with the influencing factors for aEEG results in preterm infants, suggesting that aEEG contributes to the early diagnosis of brain injury.</p>