RESUMO
OBJECTIVES: Due to the narrow therapeutic range and high drug-to-drug interactions (DDIs), improving the adequate use of warfarin for the elderly is crucial in clinical practice. This study examines whether the effectiveness of using warfarin among elderly inpatients can be improved when machine learning techniques and data from the laboratory information system are incorporated. METHODS: Having employed 288 validated clinical cases in the DDI group and 89 cases in the non-DDI group, we evaluate the prediction performance of seven classification techniques, with and without an Adaptive Boosting (AdaBoost) algorithm. Measures including accuracy, sensitivity, specificity and area under the curve are used to evaluate model performance. RESULTS: Decision tree-based classifiers outperform other investigated classifiers in all evaluation measures. The classifiers supplemented with AdaBoost can generally improve the performance. In addition, weight, congestive heart failure, and gender are among the top three critical variables affecting prediction accuracy for the non-DDI group, while age, ALT, and warfarin doses are the most influential factors for the DDI group. CONCLUSION: Medical decision support systems incorporating decision tree-based approaches improve predicting performance and thus may serve as a supplementary tool in clinical practice. Information from laboratory tests and inpatients' history should not be ignored because related variables are shown to be decisive in our prediction models, especially when the DDIs exist.
Assuntos
Anticoagulantes/efeitos adversos , Anticoagulantes/uso terapêutico , Árvores de Decisões , Melhoria de Qualidade , Varfarina/efeitos adversos , Varfarina/uso terapêutico , Idoso , Idoso de 80 Anos ou mais , Algoritmos , Anticoagulantes/administração & dosagem , Inteligência Artificial , Peso Corporal , Sistemas de Informação em Laboratório Clínico , Comorbidade , Comparação Transcultural , Relação Dose-Resposta a Droga , Interações Medicamentosas , Etnicidade , Feminino , Insuficiência Cardíaca/diagnóstico , Humanos , Masculino , Anamnese , Pessoa de Meia-Idade , Fatores de Risco , Taiwan , Tireotoxicose/diagnóstico , Varfarina/administração & dosagemRESUMO
AIMS: To develop a real-time polymerase chain reaction (PCR) hybridization probe assay for rapid and specific detection of thermostable direct haemolysin-producing Vibrio parahaemolyticus. METHODS AND RESULTS: Primers and hybridization probes were designed to target the toxR and tdh2 genes. Mismatches were introduced in the tdh2 primers for specific amplification of the target. The 3' ends of donor probes for both genes were labelled with fluorescein. The 5' ends of recipient probes for tdh2 and toxR were labelled with LC Red 640 and LC Red 705, respectively. The real-time assay was evaluated against conventional biochemical tests and the KAP-RPLA kit (Kanagawa phenomenon detection kit by reverse passive latex agglutination). toxR and tdh2 were detected in 100% and 91% of clinical V. parahaemolyticus isolates (n = 118), respectively. Specificity and sensitivity of the real-time assay for toxR and tdh2 were 100%, respectively. Dynamic range of detection for toxR was 10(7)-10(1) CFU ml(-1) and that for tdh2 was 10(7)-10(4) CFU ml(-1). CONCLUSIONS: The LightCycler assay described is sensitive and highly specific for detection of pathogenic V. parahaemolyticus in a single reaction tube within 80 min. SIGNIFICANCE AND IMPACT OF THE STUDY: The assay developed allows accurate detection of pathogenic V. parahaemolyticus, which is valuable for rapid tracing of infection source during outbreaks.