Using Artificial Neural Networks to Predict Intra-Abdominal Abscess Risk Post-Appendectomy.

Objective: To determine if artificial neural networks (ANN) could predict the risk of intra-abdominal abscess (IAA) development post-appendectomy. Background: IAA formation occurs in 13.6% to 14.6% of appendicitis cases with "complicated" appendicitis as the most common cause of IAA. There remains inconsistency in describing the severity of appendicitis with variation in treatment with respect to perforated appendicitis. Methods: Two "reproducible" ANN with different architectures were developed on demographic, clinical, and surgical information from a retrospective surgical dataset of 1574 patients less than 19 years old classified as either negative (n = 1,328) or positive (n = 246) for IAA post-appendectomy for appendicitis. Of 34 independent variables initially, 12 variables with the highest influence on the outcome selected for the final dataset for ANN model training and testing. Results: A total of 1574 patients were used for training and test sets (80%/20% split). Model 1 achieved accuracy of 89.84%, sensitivity of 70%, and specificity of 93.61% on the test set. Model 2 achieved accuracy of 84.13%, sensitivity of 81.63%, and specificity of 84.6%. Conclusions: ANN applied to selected variables can accurately predict patients who will have IAA post-appendectomy. Our reproducible and explainable ANNs potentially represent a state-of-the-art method for optimizing post-appendectomy care.

Extensive Mycobacterium abscessus Pneumonia in an Immunocompetent Infant with No Underlying Lung Pathology.

Pulmonary infection due to Mycobacterium abscessus occurs in patients with cystic fibrosis, but rarely in immunocompetent children without underlying lung pathology. Treatment is complicated by frequent resistance to many antibiotics. We present a case report of a 4-month-old female infant with 2 months of cough, difficulty feeding, and failure to thrive, with extensive culture-confirmed M. abscessus pulmonary infection without identified immunodeficiency or underlying lung pathology following multidisciplinary evaluation. We describe our complete evaluation including immunodeficiency evaluation incorporating whole-exome sequencing, describe our antibiotic selection and treatment duration given complicated susceptibility pattern of the M. abscessus isolate, and review literature for nontuberculous mycobacterial pulmonary disease in immunocompetent children. A complete multidisciplinary evaluation for underlying lung disease and primary and acquired immunodeficiency should be undertaken in pediatric patients with M. abscessus pneumonia. Confirming macrolide susceptibility through erm(41) gene evaluation is clinically important for isolates with complicated susceptibility pattern.