Introduction: Diagnosing appendicitis in young children (0-12 years) still poses a special difficulty despite the advent of radiological investigations. Few scoring models have evolved and been applied worldwide, but with significant fluctuations in accuracy upon validation. Aim: To utilize Artificial Intelligence (AI) techniques to develop and validate a diagnostic model based on clinical and laboratory parameters only (without imaging), in addition to prospective validation to confirm the findings. Methods: In Stage-I, observational data of children (0-12 years), referred for acute appendicitis (1/3/2016 to 28/2/2019, n=166), was used for model development and evaluation using 10-fold Cross-Validation (XV) technique to simulate a prospective validation. In Stage-II, prospective validation of the model and the XV estimates were carried out (1/3/2019 to 30/11/2021, n=139). Results: The developed model, AiPAD, is both accurate and explainable, with an XV estimation of average accuracy to be 93.5% ±5.8 (91.4% PPV, 94.8% NPV). Prospective validation revealed that the model was indeed accurate and close to the XV evaluations, with an overall accuracy of 97.1% (96.7% PPV and 97.4% NPV). Conclusions : The AiPAD is validated, highly accurate, easy to comprehend, and offers an invaluable tool to use in diagnosing appendicitis in children without the need for imaging. Ultimately, this would lead to significant practical benefits, improved outcomes, and reduced costs.

简介：尽管放射学检查已经出现，但诊断幼儿（0-12 岁）阑尾炎仍然是一个特殊的困难。很少有评分模型在全球范围内得到发展和应用，但验证后的准确性却存在显着波动。目标：利用人工智能 (AI) 技术开发和验证仅基于临床和实验室参数（无成像）的诊断模型，并进行前瞻性验证以确认研究结果。方法：在第一阶段，将因急性阑尾炎转介的儿童（0-12岁）的观察数据（2016年1月3日至2019年2月28日，n=166）用于模型开发和评估，使用10-折叠交叉验证（XV）技术来模拟前瞻性验证。在第二阶段，对模型和 XV 估计进行了前瞻性验证（2019 年 1 月 3 日至 2021 年 11 月 30 日，n=139）。结果：开发的模型 AiPAD 既准确又可解释，XV 估计平均准确度为 93.5% ±5.8（91.4% PPV，94.8% NPV）。前瞻性验证表明，该模型确实准确且接近 XV 评估，总体准确率为 97.1%（96.7% PPV 和 97.4% NPV）。结论：AiPAD 经过验证、高度准确、易于理解，为诊断儿童阑尾炎提供了宝贵的工具，无需进行影像学检查。最终，这将带来显着的实际效益、改善结果并降低成本。