Objective: Until now, traditional invasive approaches have been the only means being leveraged to diagnose spinal disorders. Traditional manual diagnostics require a high workload, and diagnostic errors are likely to occur due to the prolonged work of physicians. In this research, we develop an expert system based on a hybrid inference algorithm and comprehensive integrated knowledge for assisting the experts in the fast and high-quality diagnosis of spinal disorders. Methods: First, for each spinal anomaly, the accurate and integrated knowledge was acquired from related experts and resources. Second, based on probability distributions and dependencies between symptoms of each anomaly, a unique numerical value known as certainty effect value was assigned to each symptom. Third, a new hybrid inference algorithm was designed to obtain excellent performance, which was an incorporation of the Backward Chaining Inference and Theory of Uncertainty. Results: The proposed expert system was evaluated in two different phases, real-world samples, and medical records evaluation. Evaluations show that in terms of real-world samples analysis, the system achieved excellent accuracy. Application of the system on the sample with anomalies revealed the degree of severity of disorders and the risk of development of abnormalities in unhealthy and healthy patients. In the case of medical records analysis, our expert system proved to have promising performance, which was very close to those of experts. Conclusion: Evaluations suggest that the proposed expert system provides promising performance, helping specialists to validate the accuracy and integrity of their diagnosis. It can also serve as an intelligent educational software for medical students to gain familiarity with spinal disorder diagnosis process, and related symptoms.

翻译：目的：迄今为止，传统侵入性方法仍是诊断脊柱疾病的唯一手段。传统人工诊断工作负荷大，且因医生长期工作容易产生诊断误差。本研究开发了一种基于混合推理算法和综合集成知识的专家系统，旨在辅助专家快速、高质量地诊断脊柱疾病。方法：首先，针对每种脊柱异常，从相关专家和资源中获取准确且集成的知识。其次，根据每种异常症状的概率分布及症状间依赖关系，为每个症状分配称为确定效应值的唯一数值。第三，设计了一种融合反向链推理与不确定性理论的新型混合推理算法，以获得优异性能。结果：所提出的专家系统通过两个不同阶段进行评估：真实世界样本评估和医疗记录评估。评估显示，在真实世界样本分析中，该系统实现了卓越的准确性。对存在异常的样本应用该系统后，揭示了疾病严重程度以及不健康与健康患者出现异常的风险。在医疗记录分析中，我们的专家系统展现出有前景的性能，与专家诊断结果高度接近。结论：评估表明，所提出的专家系统提供了有前景的性能，有助于专家验证其诊断的准确性和完整性。该系统还可作为医学生熟悉脊柱疾病诊断流程及相关症状的智能教育软件。