Analysis of the Characteristics of the Older Adults with Depression Using Data Mining Decision Tree Analysis

PURPOSE: The purpose of this study was to develop a prediction model for the characteristics of older adults with depression using the decision tree method. METHODS: A large dataset from the 2008 Korean Elderly Survey was used and data of 14,970 elderly people were analyzed. Target variable was depression and 53 input variables were general characteristics, family & social relationship, economic status, health status, health behavior, functional status, leisure & social activity, quality of life, and living environment. Data were analyzed by decision tree analysis, a data mining technique using SPSS Window 19.0 and Clementine 12.0 programs. RESULTS: The decision trees were classified into five different rules to define the characteristics of older adults with depression. Classification & Regression Tree (C&RT) showed the best prediction with an accuracy of 80.81% among data mining models. Factors in the rules were life satisfaction, nutritional status, daily activity difficulty due to pain, functional limitation for basic or instrumental daily activities, number of chronic diseases and daily activity difficulty due to disease. CONCLUSION: The different rules classified by the decision tree model in this study should contribute as baseline data for discovering informative knowledge and developing interventions tailored to these individual characteristics.

Comorbidity Study on Type 2 Diabetes Mellitus Using Data Mining

BACKGROUND/AIMS: The aim of this study was to analyze comorbidity in patients with type 2 diabetes mellitus (T2DM) by using association rule mining (ARM). METHODS: We used data from patients who visited Keimyung University Dongsan Medical Center from 1996 to 2007. Of 411,414 total patients, T2DM was present in 20,314. The Dx Analyze Tool was developed for data cleansing and data mart construction, and to reveal associations of comorbidity. RESULTS: Eighteen associations reached threshold (support, > or = 3%; confidence, > or = 5%). The highest association was found between T2DM and essential hypertension (support, 17.43%; confidence, 34.86%). Six association rules were found among three comorbid diseases. Among them, essential hypertension was an important node between T2DM and stroke (support, 4.06%; confidence, 8.12%) as well as between T2DM and dyslipidemia (support, 3.44%; confidence, 6.88%). CONCLUSIONS: Essential hypertension plays an important role in the association between T2DM and its comorbid diseases. The Dx Analyze Tool is practical for comorbidity studies that have an enormous clinical database.

Diagnostic Analysis of Patients with Essential Hypertension Using Association Rule Mining / 대한의료정보학회지

OBJECTIVES: The purpose of this study was to analyze the records of patients diagnosed with essential hypertension using association rule mining (ARM). METHODS: Patients with essential hypertension (ICD code, I10) were extracted from a hospital's data warehouse and a data mart constructed for analysis. Apriori modeling of the ARM method and web node in the Clementine 12.0 program were used to analyze patient data. RESULTS: Patients diagnosed with essential hypertension totaled 5,022 and the diagnostic data extracted from those patients numbered 53,994. As a result of the web node, essential hypertension, non-insulin dependent diabetes mellitus (NIDDM), and cerebral infarction were shown to be associated. Based on the results of ARM, NIDDM (support, 35.15%; confidence, 100%) and cerebral infarction (support, 21.21%; confidence, 100%) were determined to be important diseases associated with essential hypertension. CONCLUSIONS: Essential hypertension was strongly associated with NIDDM and cerebral infarction. This study demonstrated the practicality of ARM in co-morbidity studies using a large clinic database.

Variable Threshold based Feature Selection using Spatial Distribution of Data / 대한의료정보학회지

OBJECTIVE: In processing high dimensional clinical data, choosing the optimal subset of features is important, not only for reduce the computational complexity but also to improve the value of the model constructed from the given data. This study proposes an efficient feature selection method with a variable threshold. METHODS: In the proposed method, the spatial distribution of labeled data, which has non-redundant attribute values in the overlapping regions, was used to evaluate the degree of intra-class separation, and the weighted average of the redundant attribute values were used to select the cut-off value of each feature. RESULTS: The effectiveness of the proposed method was demonstrated by comparing the experimental results for the dyspnea patients' dataset with 11 features selected from 55 features by clinical experts with those obtained using seven other classification methods. CONCLUSION: The proposed method can work well for clinical data mining and pattern classification applications.

The Paper-Based Medical Record Compared to the Electronic Medical Record: Documentation and Agreement of Information / 대한의료정보학회지

OBJECTIVE: This aim of this study was to evaluate the quality and agreement of electronic medical records with paper-based medical records. METHODS: Data was collected from the paper-based medical records generated during 2004 and electronic medical records during 2007, in patients hospitalized for arterial fibrillation. The categories evaluated included the chief complaint, history of present illness, past illness, medication history, admission history, family history, allergies, smoking history, and drinking history in admission record. RESULTS: The electronic medical records scored higher for: the existence of a medical record, level of information in the medical record and agreement of information. However, there were some categories of disagreement between the information from doctors and nurses, and there were several categories with no record by doctors or nurses. CONCLUSION: The results of this study confirmed that the quality of the electronic medical record is better than that of paper-based medical with regard to: the existence of the record, level and agreement of information. However, there are discrepancies in the information contained within both types of records.

Development of Critical Pathway for Laparoscopic Assisted Vaginal Hysterectomy by CPA program / 대한의료정보학회지

OBJECTIVE: The aim of this study was to develop critical pathway for post operation care of laparoscopic assisted vaginal hysterectomy with time and cost effectiveness using a clinical pathway assistant program (MDCPA(TM), MDware Co.) METHODS: Procedure was done with the following steps; establishment of conceptual framework, development of preliminary critical pathway using CPA program, expert validity test, and confirmation of final critical pathway. RESULTS: Preliminary critical pathway was extracted by CPA program, and this result was verified by expert validity test. The process of data collection and analysis to develop the preliminary critical pathway was accomplished automatically by CPA program. The patients' hospitalization period in the aspect of time and cost effectiveness was confirmed as 6 days, and each item of assessment, test, medication, treatment, diet, activity, and teaching were finalized. CONCLUSION: The CPA program can automate the complicated process, which contains collecting and cleaning the large size EMR data, classifying and confirming the items in critical pathway, so that the time and cost to develop a critical pathway can be reduced. This program is expected to be used for development of critical pathway in a variety of clinical settings in the aspect of time and cost effectiveness.

The Effects of Hope Intervention on the Hope and Quality of Life of Cancer Patients Staying at Home and Cared in Public Health Center

PURPOSE: This study was to identify the effects of hope intervention on the hope and quality of life of cancer patients staying at home. METHOD: The study adopted the randomized control group design. The subjects consisted of randomly selected forty cancer patients who were registered at S-Gu Public Health Center. Hope intervention which was composed of hope assessment, positive self identity formation, hope objective setting, therapeutic relationship and spiritual & transcendental process improving, and hope evaluation was provided from October 22, 2007 to November 30, 2007. RESULT: Hypothesis 1-1 "The experimental group that received hope intervention will have a higher score of hope than the control group", was supported(t=-3.108, p=.004). Hypothesis 1-2 "The experimental group that received hope intervention will have a higher level of hope index than the control group", was supported (t=-4.219, p=.000). Therefore, Hypothesis 1 "The experimental group that received hope intervention will have a higher level of hope than the control group" was supported. Hypothesis 2 "The experimental group that received hope intervention will have a higher level of quality of life than the control group", was not supported (t=-1.726, p=.092). CONCLUSION: Hope intervention is an effective nursing intervention to enhance hope for patients with cancer staying at home.

The Effects of Hope Intervention on Hope and Depression of Cancer Patients Staying at Home / 간호학회지

PURPOSE: This study was to identify the effects of hope intervention on hope and depression of cancer patients staying at home. METHODS: The study design was a randomized control group design. The subjects consisted of forty cancer patients randomly selected who were registered at S-Gu Public Health Center. Hope intervention, which was composed of hope assessment, hope objective setting, positive self identity formation, therapeutic relationships, spiritual & transcendental process improvement, positive environmental formation and hope evaluation, was provided from November 20, 2006 to January 26, 2007. RESULTS: The 1-1 hypothesis, "The experimental group which received hope intervention will have a higher score of hope than the control group", was supported(t=-3.253, p= .003). The 1-2 hypothesis, "The experimental group which received hope intervention will have a higher level of hope index than the control group", was supported (t=-4.001, p= .000). Therefore the 1st hypothesis, "The experimental group which received hope intervention will have a higher level of hope than the control group" was supported. The 2nd hypothesis, "The experimental group which received hope intervention will have a lower level of depression than the control group", was not supported (t=1.872, p= .070). CONCLUSION: Hope intervention is an effective nursing intervention to enhance hope for patient with cancer.