896. Prediction of Surgical Site Infection Risk in Patients Undergoing Bariatric Surgery

Abstract

Background In the hospitals of Belo Horizonte (a city with more than 3,000,000 inhabitants), a survey was conducted between July 2016 and June 2018, focused on surgical site infection (SSI) in patients undergoing bariatric surgery procedures. The main objective is to statistically evaluate such incidences and enable a study of the prediction power of SSI through MLPs (Multilayer Perceptron), a pattern recognition algorithm. Methods Data were collected on SSI by the Hospital Infection Control Committees (CCIH) of the hospitals involved in the research. After data collection, three procedures were performed: a treatment of the database collected for the use of intact samples; a statistical analysis on the profile of the hospitals collected and; an assessment of the predictive power of five types of MLP (Backpropagation Standard, Momentum, Resilient Propagation, Weight Decay, and Quick Propagation) for SSI prediction. MLPs were tested with 3, 5, 7, and 10 hidden layer neurons and a database split for the resampling process (65% or 75% for testing, 35% or 25% for validation). They were compared by measuring AUC (Area Under the Curve - ranging from 0 to 1) presented for each of the configurations. Results From 3473 initial data, only 2491 were intact for analysis. Statistically, it was found that: the average age of the patients was 39 years (ranging from 16 to 65); the average duration of surgery was 138 minutes; and 0.8% of patients had SSI. Regarding the predictive power of SSI, the experiments have a minimum value of 0.350 and a maximum of 0.756. Conclusion Despite the loss rate of almost 30% of the database samples due to the presence of noise, it was possible to have a relevant sampling for the profile evaluation of Belo Horizonte hospitals. Moreover, for the predictive process, although some configurations have results that reached 0.755, which makes promising the use of the structure for automated SSI monitoring for patients undergoing bariatric surgery. To optimize data collection and enable other hospitals to use the SSI prediction tool (available in www.sacihweb.com), two mobile application were developed: one for monitoring the patient in the hospital and the other for monitoring after hospital discharge. Disclosures All Authors: No reported disclosures