RÉSUMÉ
Clinical cases of TCM are used as important clinical data to record the whole process of the interaction between doctors and patients in the form of text.However,in the context of big data,there is a lack of research on the use of information covered in clinical cases.Therefore,we studied the method of extracting the symptom term from the history of present illness in TCM clinic in this paper,in order to lay the foundation for the further use of clinical cases.First,twelve thousand,three hundred and sixty-seven history data of present illness were obtained by random selection and expert review.According to the different disease types,they were divided into the two groups of the experiments:4,838 data in the diabetes group,7,529 data in the spleen and stomach disease group and 12,367 data in the mixed or combined group.A glossary of symptom terms covering 22,996 words were compiled.Then,five feature templates,such as sliding window feature,prefix and suffix character and lexical features,were selected.CRFs model was adopted to carry out named entity extraction experiment.As a result,in the open test,the performance of diabetes,spleen and stomach disease and mixed group were (0.83,0.8,0.82),(0.9,0.9,0.89) and (0.88,0.87,0.87),respectively,while the results were (0.83,0.82,0.83),(0.95,0.95,0.95) and (0.93,0.92,0.92) in the ten-fold cross validation.In conclusion,the results showed that the CRFs algorithm was an excellent sequence labeling algorithm and applied to the named entity extraction task of symptom history.
RÉSUMÉ
We studied the disease status by question-naire in seoul of the pupils in two primary schools on May, 1991 and carried out statistical analysis of their results. The following results were observed: 1) Total number of answered pupil was 2330; 1103 were male and 1227 were female and the ratio of male to female was 1:1.1. Average age was 9.27 years. 2) Number of the pupil with any present described was 499(21.4%) Majority was as follows: (1) Respiratory system diseases; 358(71.1%) (2) Skin & Subcutaneous tissue diseases; 36(7.2%) (3) Circulatory system diseases; 14 (2.8%) (4) Infectious diseases; 11 (2.2%) (5) Trauma; 7 (1.4%) 3) Number of the pupil with any disease on treatment was 225 (9.7%). Majority was as follows: (1) Respiratory system diseases; 108 among 358 (2) Skin & Subcutaneous diseases; 22 among 36 (3) Infectious diseases; 11 among 11 (4) Trauma; 3 among 7 (5) Mental disorders; 1 among 6 4) Number of the pupils with the past history of diseases described was 561 (24.1%). Majority was as follows: (1) Respiratory system diseases; 217 (38.7%) (2) Infectious diseases; 105 (18.7%) (3)Trauma; 74 (13.2%) (4) Nervous system & Sense organ diseases; 39 (7.0%) (5) Digestive system diseases; 27 (4.8%) 5) Number of the pupils with the past hospitalization history was 190 (8.2%). Majority was as follows: (1) Respiratory system diseases; 48 (25.3%) (2) Trauma; 41 (21.6%) (3) Infectious diseases; 18 (9.5%) (4) Genitourinary system diseases; 9 (4.7%) (5) Digestive system diseases; 6 (3.2%) 6) Number of the pupils with the past history fo sugery was 362 (15.5%). The types of surgery of the causative diseases requiring surgery were as follows: (1) Circumcision; 98 (4.2%) (2) Trauma; 73 (3.1%) (3) Tonsillectomy & Adenectomy; 46 (2.0%) (4) Inguinal herniectomy; 25 (1.1%) (5) Appendictomy; 10 (0.4%) (6) Intussusception; 10 (0.4%) 7) Number of the pupils with hearing disturbance was 498 (21.4%), with present illness of otitis media 19 (0.82%) and with the past history of otitis media 15 (0.64). 8) Number of the pupils with visual disturbance was 498 (21.4%), with myopia 233 (10%), with hyperopia 49 (2.1%), with strabismus 16 (0.7%), color blindness 7 (0.3%). 9) Number of the pupils hoping to consult with the physicians were 446 (19.1%). The contents of their consultation were as follows: (1) Dental problems; 81 (18.0%) (2) Extremity pain; 56 (13.0%)(3) Abdominal pain; 52 (12.0%) (4) Skin disease; 34 (7.6%) (5) Headache; 30 (6.7%) 10) Number of the pupil sttended to school inspite of disease was 846 (36.3%). The caustive diseases were as follows: (1) Upper respiratory infection; 217 (25,7%) (2) Abdominal pain; 27 (3.2%) (3) Fever; 24 (2.8%) (4) Trauma; 8 (0.9%) (5) Infection (Measles, Mumps, Chicken pox et.); 6 (0.7%) .