895. Prediction of Occurrence for Surgical Site Infection in Infected Surgeries

BACKGROUND: A survey was carried out in five hospitals, between July 2016 and June 2018, on surgical site infection (SSI) in patients undergoing infected surgery procedures, in the city of Belo Horizonte (3,000,000 inhabitants). The general objective is to statistically evaluate such incidences and enable an analysis of the SSI predictive power, through MLP (Multilayer Perceptron) pattern recognition algorithms. METHODS: Through the Hospital Infection Control Committees (CCIH) of the hospitals, a data collection on SSI was carried out. Such data is used in the analysis during your routine SSI surveillance procedures. So, three procedures were performed: a treatment of the collected database for use of intact samples; a statistical analysis on the profile of the collected hospitals and; an assessment of the predictive power of five types of MLPs (Backpropagation Standard, Momentum, Resilient Propagation, Weight Decay and Quick Propagation) for SSI prediction. The MLPs were tested with 3, 5, 7 and 10 neurons in the hidden layer and with a division of the database for the resampling process (65% or 75% for testing, 35% or 25% for validation). They were compared by measuring the AUC (Area Under the Curve - ranging from 0 to 1) presented for each of the configurations. RESULTS: From 1770 records, 810 were intact for analysis. It was found that: the average age is 53 years old (from 0 to 98 years old); the surgeries had an average time of approximately 140 minutes; the average hospital stay is 19 days, the death rate reached 10.86% and the SSI rate was 6.04%. A maximum prediction power of 0.729 was found. CONCLUSION: There was a loss of 54% of the database samples due to the presence of noise. However, it was possible to have a relevant sample to assess the profile of these five hospitals. The predictive process, presented some configurations with results that reached 0.729, which promises the use of the structure for the monitoring of automated SSI for patients submitted to infected surgeries. To optimize data collection, enable other hospitals to use the prediction tool and minimize noise from the database, two mobile application were developed: one for monitoring the patient in the hospital and another for monitoring after hospital discharge. The SSI prediction analysis tool is available at www.nois.org.br. DISCLOSURES: All Authors: No reported disclosures