RESUMEN
OBJECTIVE: To develop a novel predictive model using primarily clinical history factors and compare performance to the widely used Rochester Low Risk (RLR) model. STUDY DESIGN: In this cross-sectional study, we identified infants brought to one pediatric emergency department from January 2014 to December 2016. We included infants age 0-90 days, with temperature ≥38°C, and documented gestational age and illness duration. The primary outcome was bacterial infection. We used 10 predictors to develop regression and ensemble machine learning models, which we trained and tested using 10-fold cross-validation. We compared areas under the curve (AUCs), sensitivities, and specificities of the RLR, regression, and ensemble models. RESULTS: Of 877 infants, 67 had a bacterial infection (7.6%). The AUCs of the RLR, regression, and ensemble models were 0.776 (95% CI 0.746, 0.807), 0.945 (0.913, 0.977), and 0.956 (0.935, 0.975), respectively. Using a bacterial infection risk threshold of .01, the sensitivity and specificity of the regression model was 94.6% (87.4%, 100%) and 74.5% (62.4%, 85.4%), compared with 95.5% (87.5%, 99.1%) and 59.6% (56.2%, 63.0%) using the RLR model. CONCLUSIONS: Compared with the RLR model, sensitivities of the novel predictive models were similar whereas AUCs and specificities were significantly greater. If externally validated, these models, by producing an individualized bacterial infection risk estimate, may offer a targeted approach to young febrile infants that is noninvasive and inexpensive.
Asunto(s)
Infecciones Bacterianas/diagnóstico , Reglas de Decisión Clínica , Fiebre/microbiología , Anamnesis/métodos , Infecciones Bacterianas/complicaciones , Estudios Transversales , Servicio de Urgencia en Hospital , Femenino , Humanos , Lactante , Recién Nacido , Modelos Lineales , Modelos Logísticos , Aprendizaje Automático , Masculino , Estudios Retrospectivos , Medición de Riesgo , Sensibilidad y EspecificidadRESUMEN
OBJECTIVE: To determine the frequency of medical problems in a large population of children with Down syndrome. STUDY DESIGN: Study population included 440 children with Down syndrome (ages 3-14 years) identified primarily through the New York Congenital Malformations Registry. Parents completed questionnaires on medical problems. RESULTS: Our study population was predominately White (92.3%), non-Hispanic (72.3%) with at least 1 college educated parent (72.3%). The prevalence of medical problems was as follows: heart disease (55%), hearing problem (39%), vision problem (39%), thyroid disease (27%), celiac disease (5%), alopecia (5%), seizures (7%), asthma/reactive airway disease (32%), diabetes (1%), and juvenile rheumatoid arthritis (0.2%). Of the children with heart disease, 58% needed surgery at a mean age of 9 months. Of the children with hearing loss, 29% were identified on newborn screening and 13% used an amplification device. Of the children with thyroid disease, 31% were diagnosed in the newborn period. Only 7% of these children with Down syndrome had no medical problem listed. CONCLUSION: Prevalence data of medical illnesses in a large population of children with Down syndrome provide us with data to support implementation of the American Academy of Pediatrics guidelines for health supervision for children with Down syndrome. The long-term health implications of the conditions we surveyed will be important for decreasing morbidity and increasing overall health and wellness into adulthood.