RESUMO
BACKGROUND: Early identification of sepsis remains the greatest barrier to compliance with recommended evidence-based bundles. PURPOSE: The purpose was to improve the early identification and treatment of sepsis by developing an automated screening tool. METHODS: Six variables associated with sepsis were identified. Logistic regression was used to weigh the variables, and a predictive model was developed to help identify patients at risk. A retrospective review of 10 792 records of hospitalizations was conducted including 339 cases of sepsis to retrieve data for the model. RESULTS: The final model resulted an area under the curve of 0.857 (95% CI, 0.850-0.863), suggesting that the screening tool may assist in the early identification of patients developing sepsis. CONCLUSION: By using artificial intelligence capabilities, we were able to screen 100% of our inpatient population and deliver results directly to the caregiver without any manual intervention by nursing staff.
Assuntos
Hospitais Comunitários , Sepse , Inteligência Artificial , Humanos , Programas de Rastreamento , Estudos RetrospectivosRESUMO
BACKGROUND: Clostridium difficile infection (CDI) continues to cause significant morbidity and mortality among hospitalized patients. Early diagnosis, contact precautions, and prompt therapy are crucial to the control of the disease and its spread. This study aims to develop an electronic screening tool to help identify patients who are at risk of CDI. METHODS: Six variables associated with CDI including antibiotic usage, age, and admission from another facility were identified. Logistic regression was used to weigh the variables, and then a predictive model was devised to help identify which patients may be at risk for developing CDI. A retrospective review of 29,453 records of hospitalizations was conducted including 274 cases of C difficile toxin positive patients to retrieve data for the model. RESULTS: The final model resulted in an area under the curve of 0.929, which suggests that the electronic screening tool will be an accurate predictor of predisposition to the disease. Model testing suggests a positive relationship between the total weight or score and the probability of developing the disease. CONCLUSION: An electronic screening tool may be an effective tool to assist in the accurate and timely identification of patients who may be predisposed to CDI during hospitalization.