ABSTRACT
[Objective] To research the construction and optimization of natural language processing model for unstructured medical records,and using the model to extract structured data from medical records of stroke patients in Jiangxi Medical Big Data Platform.[Methods] According to the actual needs of clinical research,a stroke specialist entity annotation system and named entity annotation corpus were constructed based on 500 hospital admission records of stroke patients,which randomly selected between 2011 to 2016 from the Jiangxi provincial medical big data platform.The corpus is used to construct a named entity extraction model based on CRF and RUTA rules,and the recognition accuracy is improved by adjusting RUTA rules and parameters.[Results] Accuracy rate of extraction model was 0.960,recall rate was 0.916 and F-score was 0.939.The extraction model was used to extract 264 580 entities and 1 161 077 entity relation from 10 295 stroke patients' admission records of the medical big data platform.[Conclusions] The constructed natural language extraction model has a high recognition accuracy,which can accurately obtain valuable scientific research data of patients' past history,life history and clinical manifestations from a large number of unstructured medical records and effectively improve the clinical research efficiency and scientific research level of cerebrovascular diseases.
ABSTRACT
The risk factors of high trait anger of juvenile offenders were explored through question naire study in a youth correctional facility of Hubei province,China.A total of 1090 juvenile offenders in Hubei province were investigated by self-compiled social-demographic questionnaire,Childhood Trauma Questionnaire (CTQ),and State-Trait Anger Expression Inventory-Ⅱ (STAXI-Ⅱ).The risk factors were analyzed by chi-square tests,correlation analysis,and binary logistic regression analysis with SPSS 19.0.A total of 1082 copies of valid questionnaires were collected.High trait anger group (n=316) was defined as those who scored in the upper 27th percentile of STAXI-Ⅱ trait anger scale (TAS),and the rest were defined as low trait anger group (n=766).The risk factors associated with high level of trait anger included:childhood emotional abuse,childhood sexual abuse,step family,frequent drug abuse,and frequent internet using (P＜0.05 or P＜0.01).Birth sequence,number of sibling,ranking in the family,identity of the main care-taker,the education level of care-taker,educational style of care-taker,family income,relationship between parents,social atmosphere of local area,frequent drinking,and frequent smoking did not predict to high level of trait anger (P＞0.05).It was suggested that traumatic experience in childhood and unhealthy life style may significantly increase the level of trait anger in adulthood.The risk factors of high trait anger and their effects should be taken into consideration seriously.