Ivashchenko A S, Dudchenko L Sh, Kaladze N N, Mizin V I
I.M. Sechenov Academic Research Institute of Physical Methods of Treatment, Medical Climatology and Rehabilitation, Yalta, Republic of Crimea, Russia.
S.I. Georgievskiy Medical Academy, V.I. Vernadskiy Crimean Federal University, Simpheropol, Republic of Crimea, Russia.
Vopr Kurortol Fizioter Lech Fiz Kult. 2020;97(1):13-24. doi: 10.17116/kurort20209701113.
Bronchial asthma (BA) is a relevant social and medical problem in our country and around the world. Currently, phenotypes of the disease are distinguished. One of the original decisions in phenotypes distinguishing is the use of cluster analysis. However, the concept of BA phenotypes at the health resort period of rehabilitation has not yet been formed.
To determine the BA phenotypes upon admission of patients to a health resort medical rehabilitation (HRMR) using cluster analysis and to offer personalized rehabilitation programs.
518 patients with asthma who underwent HRMR on the southern coast of Crimea were examined. Each patient received clinical, functional and laboratory examination. HRMR included correction of long-term treatment according to the severity of asthma, climate therapy, respiratory therapy, educational programs, and physiotherapeutic procedures. We applied cluster analysis in order to identify BA phenotypes. Description statistics methods were used for phenotype-cluster characterization, comparative analysis - for determination of reliable phenotypic characteristics and relation of the effectiveness of HRMR and phenotypes.
A model of three phenotype-clusters was developed. The first cluster included patients with BA of moderate severity, uncontrolled course, frequent exacerbations, history of atopy, a tendency to obesity, moderately reduced external respiration function, fixed airway obstruction, high adherence to long-term therapy with medium doses of inhaled glucocorticoids (ICS) combined with long-acting β-2 agonists (LABA). Cluster 2 included patients with mild asthma, controlled or partially controlled course of the disease, with rare short exacerbations, late onset, preserved external respiration function and exercise tolerance, but low adherence to long-term therapy with medium and low doses of ICS. Cluster 3 included patients with moderate to severe BA, uncontrolled course, with early onset, frequent and prolonged exacerbations, severe symptoms, significantly reduced external respiration function with fixed obstruction, decreased exercise tolerance, but low adherence to long-term therapy (4th stage) with high doses of ICS in combination with LABA and long-acting anticholinergics. A close relationship was found between phenotypes-clusters and the achieved effects: a significant increase in the control of BA and a high efficiency of rehabilitation in patients of the 1st and especially 3rd clusters and low in the 2nd cluster. The optimal rehabilitation programs for each of the selected cluster phenotypes were determined.
The cluster model developed with the help of artificial intelligence has demonstrated high prognostic value in the determination of the effectiveness and change of control over the course of asthma as a result of HRMR. Personalized HRMR programs are suggested.
支气管哮喘（BA）在我国乃至全球都是一个重要的社会和医学问题。目前，该疾病的表型已得到区分。区分表型的最初决策之一是使用聚类分析。然而，康复疗养期BA表型的概念尚未形成。
采用聚类分析确定患者入住疗养医学康复（HRMR）机构时的BA表型，并提供个性化康复方案。
对518例在克里米亚南岸接受HRMR的哮喘患者进行检查。每位患者均接受了临床、功能和实验室检查。HRMR包括根据哮喘严重程度调整长期治疗、气候疗法、呼吸治疗、教育项目和物理治疗程序。我们应用聚类分析来识别BA表型。描述性统计方法用于表型聚类特征描述，比较分析用于确定可靠的表型特征以及HRMR效果与表型的关系。
建立了一个包含三个表型聚类的模型。第一类包括中度严重度、病程未得到控制、频繁发作、有特应性病史、有肥胖倾向、外呼吸功能中度降低、存在固定性气道阻塞、对中等剂量吸入糖皮质激素（ICS）联合长效β2受体激动剂（LABA）的长期治疗依从性高的BA患者。第二类包括轻度哮喘、疾病得到控制或部分控制、发作罕见且短暂、起病较晚、外呼吸功能和运动耐力保留，但对中低剂量ICS长期治疗依从性低的患者。第三类包括中度至重度BA、病程未得到控制、起病早、发作频繁且持续时间长、症状严重、外呼吸功能显著降低且存在固定性阻塞、运动耐力下降，但对高剂量ICS联合LABA和长效抗胆碱能药物的长期治疗（第4阶段）依从性低的患者。发现表型聚类与所取得的效果之间存在密切关系：第一类尤其是第三类患者的BA控制显著改善且康复效率高，而第二类患者的康复效率低。确定了针对每个选定聚类表型的最佳康复方案。
借助人工智能开发的聚类模型在确定HRMR对哮喘病程的控制效果和变化方面显示出较高的预后价值。建议采用个性化的HRMR方案。
