Vilhena João, Rosário Martins M, Vicente Henrique, Grañeda José M, Caldeira Filomena, Gusmão Rodrigo, Neves João, Neves José
Departamento de Química, Escola de Ciências e Tecnologia, Universidade de Évora, 7000-671, Évora, Portugal.
Departamento de Química, Laboratório HERCULES, Escola de Ciências e Tecnologia, Universidade de Évora, 7000-671, Évora, Portugal.
J Med Syst. 2017 Mar;41(3):40. doi: 10.1007/s10916-017-0688-5. Epub 2017 Jan 23.
The AntiPhospholipid Syndrome (APS) is an acquired autoimmune disorder induced by high levels of antiphospholipid antibodies that cause arterial and veins thrombosis, as well as pregnancy-related complications and morbidity, as clinical manifestations. This autoimmune hypercoagulable state, usually known as Hughes syndrome, has severe consequences for the patients, being one of the main causes of thrombotic disorders and death. Therefore, it is required to be preventive; being aware of how probable is to have that kind of syndrome. Despite the updated of antiphospholipid syndrome classification, the diagnosis remains difficult to establish. Additional research on clinically relevant antibodies and standardization of their quantification are required in order to improve the antiphospholipid syndrome risk assessment. Thus, this work will focus on the development of a diagnosis decision support system in terms of a formal agenda built on a Logic Programming approach to knowledge representation and reasoning, complemented with a computational framework based on Artificial Neural Networks. The proposed model allows for improving the diagnosis, classifying properly the patients that really presented this pathology (sensitivity higher than 85%), as well as classifying the absence of APS (specificity close to 95%).
抗磷脂综合征（APS）是一种获得性自身免疫性疾病，由高水平的抗磷脂抗体引起，临床表现为动脉和静脉血栓形成以及与妊娠相关的并发症和发病情况。这种自身免疫性高凝状态通常被称为休斯综合征，对患者有严重后果，是血栓性疾病和死亡的主要原因之一。因此，需要进行预防，了解患那种综合征的可能性有多大。尽管抗磷脂综合征的分类有所更新，但诊断仍然难以确立。为了改进抗磷脂综合征风险评估，需要对临床相关抗体进行更多研究并对其定量进行标准化。因此，这项工作将侧重于开发一个诊断决策支持系统，该系统基于逻辑编程方法进行知识表示和推理构建正式议程，并辅以基于人工神经网络的计算框架。所提出的模型有助于改进诊断，正确分类真正患有这种疾病的患者（敏感性高于85%），以及分类不存在抗磷脂综合征的情况（特异性接近95%）。
