ABSTRACT
PURPOSE: The purposes of this study were to apply data mining tool to nursing specific knowledge discovery process and to identify the utilization of data mining skill for clinical decision making. METHODS: Data mining based on rough set model was conducted on a large clinical data set containing NMDS elements. Randomized 1000 patient data were selected from year 1998 database which had at least one of the five most frequently used nursing diagnoses. Patient characteristics and care service characteristics including nursing diagnoses, interventions and outcomes were analyzed to derive the meaningful decision rules. RESULTS: Number of comorbidity, marital status, nursing diagnosis related to risk for infection and nursing intervention related to infection protection, and discharge status were the predictors that could determine the length of stay. Four variables (age, impaired skin integrity, pain, and discharge status) were identified as valuable predictors for nursing outcome, relived pain. Five variables (age, pain, potential for infection, marital status, and primary disease) were identified as important predictors for mortality. CONCLUSIONS: This study demonstrated the utilization of data mining method through a large data set with stan-dardized language format to identify the contribution of nursing care to patient's health.
Subject(s)
Adult , Aged , Aged, 80 and over , Female , Humans , Male , Middle Aged , Decision Making, Computer-Assisted , Hospital Information Systems , Information Storage and Retrieval , Midwestern United States , Nursing Records , Outcome Assessment, Health Care/methods , ROC CurveABSTRACT
BACKGROUND AND OBJECTIVES: Cancer is a genetic disease in which several genetic events are required to induce normal cells to convert to malignancy. Functional loss of tumor suppressor genes is related to these events, but the molecular mechanism is not well known. This study was designed to identify whether the tumor suppressor genes, Fragile Histidine Triad (FHIT), p16, Retinoblastoma (Rb), and p53 were involved in the carcinogenesis of laryngeal squamous cell carcinoma and to determine whether FHIT alterations play a role in laryngeal squamous cell carcinoma. MATERIALS AND METHOD: The loss of heterozygosity (LOH) was analysed by using microsatellite markers D3S1285 and D3S1481 for FHIT, microsatellite marker D9S171 for p16, investigation of AccII restriction fragment length polymorphism (RFLP) and investigation of variable number of tandem repeat (VNTR) for p53, Xba I RFLP and VNTR for Rb. The FHIT gene was examined by polymerase chain reaction-single strand conformation polymorphism (PCR-SSCP). RESULTS: The results of LOH analysis by using microsatellite markers D3S1285 and D3S1481 for FHIT, microsatellite marker D9S171 for p16, investigation of AccII RFLP and investigation of VNTR for p 53, VNTR for Rb were 8% (1/12), 0% (0/13), 18% (2/11), 14% (1/7), 22% (2/9), 17% (1/6), respectively. As a result of analysis of genomic DNA of FHIT gene by SSCP, two cases showed that the polymorphic change occurs at exon 8 codon 98 (CAT-->CAC), and that it is a silent substitution. CONCLUSION: Based on the experimental result of the change in tumor suppressor genes in laryngeal squamous cell carcinoma, the genetic alterations were most frequently observed in p53 followed by Rb, p16 and FHIT but it is not significant. It is also expected that FHIT has little influence on the process of carcinogenesis of laryngeal squamous cell carcinoma.