Symptom Clustering of Dysphagia Phenotypes by Unsupervised Machine Learning Using Multidimensional Characteristics: A Cross-sectional Study of the Elderly Chinese Population

Background: Dysphagia severely affects the elderly population, but its signs and symptoms are variable. Existing assessment tools fall short in considering the coordination of relevant muscle groups in the pathology of dysphagia and fail to characterize dysphagia in a comprehensive manner. Methods: Senior dysphagia patients (>65 years old) diagnosed by Videofluoroscopic Swallow Study at several tertiary hospitals in Suzhou were enrolled from June 2022 to October 2024. They were clustered into different phenotypes by the k-means algorithm based on their respiratory, swallowing, and articulatory functions. The characteristics of demographics, medical history, and two dysphagia outcomes were compared across the different clustering results. Results: The 1,301 enrolled patients were divided into four distinct clusters (phenotypes) that featured minimal impairment (MN, n = 462, 35.5%), respiratory-dominant impairment (RD, n = 305, 23.4%), articulatory-dominant impairment (AD, n = 301, 23.2%), and multimodal impairment (MT, n = 233, 17.9%), respectively. Each phenotype exhibited a unique combination of respiratory, swallowing, and articulatory impairments, and the demographics and medical history differed significantly between phenotypes. The eating ability and the incidence of swallowing-related complications both differed significantly (P < .001) between phenotypes. The impairment ranked in the order of MT > RD > AD > MN. Discussion: This study identified different phenotypes of dysphagia based on multidimensional patient characteristics with unique clinical features and outcomes. The findings support the development of targeted therapeutic strategies to improve patient prognosis.