Development of a revisit prediction model for the outpatient in a hospital / 대한의료정보학회지

OBJECTIVES: This study is for developing the prediction model of outpatient's revisit in target hospital. Using this model, hospital managers can make efficient customer relationship. METHODS: This is based on the medical record data of patients in target hospital (with 967 beds). They are divided into two groups, which are used each for different purpose. One(raw data) is used to make the prediction model of revisit and the other(test data) is used to evaluate the model. For raw data were used the 4,273 outpatient cases, where patients visited the first time between august and september in 2000, and visited till december in 2003. For the test data were used 9,392 outpatient cases, where patients visited the first time between august and september in 2003, and visited till december in 2006. That is, each data was selected from the outpatient's medical records for three-years. RESULTS: The decision tree model is better than the logistic regression model as prediction model of outpatient's revisit in target hospital. The decision tree model is evaluated more excellent in ROC curve and classification accuracy in test data. For predicting the outpatient's revisit, it is more useful to have 4 variables - non-insured expenses, special medical service, cooperation service with oriental medicine and visit via ER. We can predict the revisit of outpatients over 39.5% rate by these variables. CONCLUSIONS: By using decision tree model, target hospital can make more accurate prediction of outpatient's revisit and make good customer relation management. So, target hospital can use some CRM program including 4 variables. To make more useful model for other hospitals in Korea, each hospital managers need to understand more their hospital environment and patient's characteristics.

Decision Tree Approach Characterizing the Non-Examinees of Health Screening Services / 대한의료정보학회지

OBJECTIVE: The purpose of this study was to develop the decision tree models to classify the characteristics of those who had not undergone the health screening tests provided by the National Health Insurance Corporation. METHODS: Total of 5,102,761 subjects of health screening services in the year of 2002 was used. The data was divided into two data-sets (disease VS. non-disease group). The target variable was whether they took the health screening services. The number of input variables was 25 in total. RESULTS: The decision trees were classified into fourteen different types of non-examinees in the non-disease group and nineteen in the disease group. The ROC curve areas in the non-disease and disease groups were .761 and .714, respectively. CONCLUSION: The different types of non-examinees classified by the decision tree models would facilitate the foundation for the further analysis of individual characteristics and the effective health screening service management in future.

Study and Application of New Hospital Customer Service Platform-"Doctor-Patient Communication" Platform / 医疗卫生装备

Objective The setting of "doctor-patient communication" platform aims to innovate service pattern for hospital customers by constructing the communication bridge between hospital and patients via digital ways. Methods The platform was based on electronic patient records system and hospital information system. The internal information could interchange with social communication platform (cell phone, PHS, internet) via that system to realize the communication between doctors and patients. Results The platform could easily realize immediate interaction and group administration to customers in the form of manual communication, short massage, voice service and email. Conclusion The platform innovates both the service pattern for hospital customers and hospital customer relationship management (CRM) mode, and it has a bright application future.