JMIR Publications

ABSTRACT

Background:

Oropharyngeal dysphagia (OD) commonly occurs in COVID-19 patients, posing diagnostic challenges due to isolation protocols. The study evaluated AIMS-OD, a machine-learning software for real-time OD screening, comparing OD prevalence and clinical outcomes using OD ICD-10 R13 codes (R13-OD) and high-risk AIMS-OD scores (>0.5) (H-AIMS-OD), in hospital and primary care COVID-19 patients. It explored clinical characteristics, OD risk factors and clinical outcomes.

Objective:

The aims of this study are to demonstrate the underdiagnosis of OD in COVID-19 patients across both hospitalized and primary care settings, to compare the prevalence of OD in patients with COVID-19 according to ICD-10 coding (R13), group called R13-OD, or AIMS-OD high risk (>0.5), group called H-AIMS-OD, in hospitalization patients and primary care settings, and to study the clinical characteristics, risk factors for OD and clinical outcomes associated with two age groups: patients aged 18-69 years and those aged 70 years and older.

Methods:

This retrospective, observational study analyzed SARS-CoV-2 patients aged 18 years and over in Catalonia from January 1st to August 31st 2020, including hospital and primary care data on clinical information, ICD-10 codes, hospital stay, discharge destination, and mortality. AIMS-OD assessed OD risk, stratifying patients by age (18-69 and ≥70 years).

Results:

Among 257,541 COVID-19 patients, 59.3% were 18-69 and 40.7% 70 years old and over. Hospital and primary care R13-OD prevalence was 3.5% and 4.3%, respectively; AIMS-OD showed 34.8% and 15.4%, with True prevalence at 16.7% and 7.4%. Patients 70 years and over had worse clinical outcomes and worse prognosis. R13-OD patients experienced significantly worse clinical outcomes than H-AIMS-OD patients, who in turn fared worse than those without R13-OD and with low AIMS-OD risk. Risk factors for COVID-19 R13-OD patients included age, neuroleptic use, stroke, dementia, and delirium.

Conclusions:

AIMS-OD screening revealed high prevalence and significant underdiagnosis in COVID-19 patients across settings. Early detection and risk stratification using AIMS-OD could improve clinical decision making, diagnosis and management, particularly in older patients with comorbidities.