RESUMEN
PURPOSE: The objective was to develop a natural language processing (NLP) algorithm to identify vaccine-related anaphylaxis from plain-text clinical notes, and to implement the algorithm at five health care systems in the Vaccine Safety Datalink. METHODS: The NLP algorithm was developed using an internal NLP tool and training dataset of 311 potential anaphylaxis cases from Kaiser Permanente Southern California (KPSC). We applied the algorithm to the notes of another 731 potential cases (423 from KPSC; 308 from other sites) with relevant codes (ICD-9-CM diagnosis codes for anaphylaxis, vaccine adverse reactions, and allergic reactions; Healthcare Common Procedure Coding System codes for epinephrine administration). NLP results were compared against a reference standard of chart reviewed and adjudicated cases. The algorithm was then separately applied to the notes of 6 427 359 KPSC vaccination visits (9 402 194 vaccine doses) without relevant codes. RESULTS: At KPSC, NLP identified 12 of 16 true vaccine-related cases and achieved a sensitivity of 75.0%, specificity of 98.5%, positive predictive value (PPV) of 66.7%, and negative predictive value of 99.0% when applied to notes of patients with relevant diagnosis codes. NLP did not identify the five true cases at other sites. When NLP was applied to the notes of KPSC patients without relevant codes, it captured eight additional true cases confirmed by chart review and adjudication. CONCLUSIONS: The current study demonstrated the potential to apply rule-based NLP algorithms to clinical notes to identify anaphylaxis cases. Increasing the size of training data, including clinical notes from all participating study sites in the training data, and preprocessing the clinical notes to handle special characters could improve the performance of the NLP algorithms. We recommend adding an NLP process followed by manual chart review in future vaccine safety studies to improve sensitivity and efficiency.
Asunto(s)
Anafilaxia/inducido químicamente , Anafilaxia/epidemiología , Bases de Datos Factuales , Atención a la Salud/métodos , Procesamiento de Lenguaje Natural , Vacunas/efectos adversos , Anafilaxia/diagnóstico , California/epidemiología , Registros Electrónicos de Salud , Humanos , Vacunas/administración & dosificaciónRESUMEN
AIMS AND OBJECTIVES: The aim of this study was to test the Chinese version of the Critical Thinking Disposition Inventory (CTDI-CV) among nurses in Taiwan. BACKGROUND: Critical thinking is the use of purposeful self-regulatory judgments to identify patient's problems and provide patient care. Critical thinking influences nurses' decision making. To date, no inventory to understand nurse's critical thinking disposition has been developed. DESIGN: This was a survey design with a stratified random sampling to test the reliability and validity of the CTDI-CV. METHODS: The participants comprised 864 registered nurses who were chosen by stratified random sampling from seven hospitals in Taiwan. Data were collected through self-administered structured questionnaires. RESULTS: A new scale, short form (SF) CTDI-CV, contains 18 items with three subscales: 'systematic analysis', 'thinking within the box' and 'thinking out of the box', was generated from the analysis with 44% explained variance. Cronbach's alpha coefficients and intra-class correlation coefficients for overall and subscale were above 0.8. Goodness-of-fit test for the final model of SF-CTDI-CV revealed an acceptable result in the overall fit (χ(2)/df = 4.04, p < 0.05, GFI = 0.93, AGFI = 0.91, SRMR = 0.076, RMSEA = 0.059). CONCLUSION: On the basis of these results, the SF-CTDI-CV is a reliable instrument for assessing critical thinking disposition for nurses. RELEVANCE TO CLINICAL PRACTICE: A short and valid critical thinking instrument for nurses will facilitate critical thinking research in the clinical practice arena. When designing continuing education activities, clinical educators will be able to efficiently and effectively evaluate the quality of critical thinking among practicing nurses.