RESUMEN
Oropharyngeal dysphagia (OD) is underdiagnosed and current screening is costly. We aimed: (a) to develop an expert system (ES) based on machine learning that calculates the risk of OD from the electronic health records (EHR) of all hospitalized older patients during admission, and (b) to implement the ES in a general hospital. In an observational, retrospective study, EHR and swallowing assessment using the volume-viscosity swallow test for OD were captured over 24 months in patients > 70 yr admitted to Mataró Hospital. We studied the predictive power for OD of 25,000 variables. ES was obtained using feature selection, the final prediction model was built with non-linear methods (Random Forest). The database included 2809 older patients (mean age 82.47 ± 9.33 yr), severely dependent (Barthel Index 47.68 ± 31.90), with multiple readmissions (4.06 ± 7.52); 75.76% had OD. The psychometrics of the ES built with a non-linear model were: Area under the ROC Curve of 0.840; sensitivity 0.940; specificity, 0.416; Positive Predictive Value 0.834; Negative Predictive Value 0.690; positive likelihood ratio (LH), 1.61 and negative LH, 0.146. The ES screens in 6 s all patients admitted to a 419-bed hospital, identifies patients at greater risk of OD, and shows the risk for OD in the clinician's workstation. It is currently in use at our institution. Our ES provides accurate, systematic and universal screening for OD in real time during hospital admission of older patients, allowing the most appropriate diagnostic and therapeutic strategies to be selected for each patient.
Asunto(s)
Trastornos de Deglución , Humanos , Anciano , Anciano de 80 o más Años , Trastornos de Deglución/diagnóstico , Inteligencia Artificial , Estudios Retrospectivos , Hospitalización , Gestión de RiesgosRESUMEN
BACKGROUND: The phenotype of patients affected by COVID-19 disease changed between the waves of the pandemic. We assessed the prevalence of oropharyngeal dysphagia (OD), malnutrition (MN), and mortality between the first three waves of COVID-19 patients in a general hospital. METHODS: a prospective observational study between April 2020-May 2021. Clinical assessment for OD was made with the volume-viscosity swallowing test; nutritional assessment was performed consistent with GLIM criteria. A multimodal intervention was implemented in the second and third wave, including (a) texturized diets-fork mashable (1900 kcal + 90 g protein) or pureed (1700 kcal + 75 g protein), (b) oral nutritional supplements (500-600 kcal + 25-30 g protein), and (c) fluid thickening (250 mPa·s or 800 mPa·s). RESULTS: We included 205 patients (69.3 ± 17.6 years) in the 1st, 200 (66.4 ± 17.5 years) in the 2nd, and 200 (72.0 ± 16.3 years;) in the 3rd wave (p = 0.004). On admission, prevalence of OD was 51.7%, 31.3% and 35.1%, and MN, 45.9%, 36.8% and 34.7%, respectively; mortality was 10.7%, 13.6% and 19.1%. OD was independently associated with age, delirium, and MN; MN, with age, OD, diarrhea and ICU admission; mortality, with age, OD and MN. (4) Conclusions: Prevalence of OD, MN and mortality was very high among COVID-19 patients. OD was independently associated with MN and mortality. An early and proactive multimodal nutritional intervention improved patients' nutritional status.