Artificial neural networks: useful aid in diagnosing acute appendicitis.

摘要: The purpose of the study was to assess role artificial neural networks (ANNs) in diagnosis appendicitis patients presenting with acute right iliac fossa (RIF) pain and comparing its performance assessment made by experienced clinicians Alvarado score. After training testing an ANN, data from 60 suspected over a 6-month period teaching hospital collected prospectively. Accuracy diagnosing clinician, score, ANN compared. sensitivity, specificity, positive negative predictive values were 100%, 97.2%, 96.0%, 100% respectively. ability exclude accurately without true statistically significant compared clinical (p = 0.031) score ≥6 (p = 0.004) nearly ≥7 (p = 0.063). ANNs can be effective tool for may reduce unnecessary appendectomies.