ITMO University, Saint Petersburg, Russia.
Stud Health Technol Inform. 2021 Oct 27;285:112-117. doi: 10.3233/SHTI210582.
Today pneumonia is one of the main problems of all countries around the world. This disease can lead to early disability, serious complications, and severe cases of high probabilities of lethal outcomes. A big part of cases of pneumonia are complications of COVID-19 disease. This type of pneumonia differs from ordinary pneumonia in symptoms, clinical course, and severity of complications. For optimal treatment of disease, humans need to study specific features of providing 19 pneumonia in comparison with well-studied ordinary pneumonia. In this article, the authors propose a new approach to identifying these specific features. This method is based on creating dynamic disease models for COVID and non-COVID pneumonia based on Bayesian Network design and Hidden Markov Model architecture and their comparison. We build models using real hospital data. We created a model for automatically identifying the type of pneumonia (COVID-19 or ordinary pneumonia) without special COVID tests. And we created dynamic models for simulation future development of both types of pneumonia. All created models showed high quality. Therefore, they can be used as part of decision support systems for medical specialists who work with pneumonia patients.
如今，肺炎是全球各国面临的主要问题之一。这种疾病可能导致早期残疾、严重并发症，在严重情况下，致死概率很高。肺炎病例的很大一部分是 COVID-19 疾病的并发症。这种类型的肺炎在症状、临床过程和并发症严重程度方面与普通肺炎不同。为了优化疾病治疗，人类需要研究提供 19 肺炎的具体特征，与研究充分的普通肺炎进行比较。在本文中，作者提出了一种新的方法来识别这些具体特征。该方法基于基于贝叶斯网络设计和隐马尔可夫模型架构创建 COVID 和非 COVID 肺炎的动态疾病模型，并对其进行比较。我们使用真实的医院数据来构建模型。我们创建了一个模型，用于在没有特殊 COVID 检测的情况下自动识别肺炎的类型（COVID-19 或普通肺炎）。我们还创建了用于模拟两种类型肺炎未来发展的动态模型。所有创建的模型都显示出高质量。因此，它们可以作为与肺炎患者一起工作的医疗专家的决策支持系统的一部分。
