Vital Signs Prediction for COVID-19 Patients in ICU

Abstract

This study introduces machine learning predictive models to predict the future values of the monitored vital signs of COVID-19 ICU patients. The main vital sign predictors include heart rate, respiration rate, and oxygen saturation. We investigated the performances of the developed predictive models by considering different approaches. The first predictive model was developed by considering the following vital signs: heart rate, blood pressure (systolic, diastolic and mean arterial, pulse pressure), respiration rate, and oxygen saturation. Similar to the first approach, the second model was developed using the same vital signs, but it was trained and tested based on a leave-one-subject-out approach. The third predictive model was developed by considering three vital signs: heart rate (HR), respiration rate (RR), and oxygen saturation (SpO2). The fourth model was a leave-one-subject-out model for the three vital signs. Finally, the fifth predictive model was developed based on the same three vital signs, but with a five-minute observation rate, in contrast with the aforementioned four models, where the observation rate was hourly to bi-hourly. For the five models, the predicted measurements were those of the three upcoming observations (on average, three hours ahead). Based on the obtained results, we observed that by limiting the number of vital sign predictors (i.e., three vital signs), the prediction performance was still acceptable, with the average mean absolute percentage error (MAPE) being 12%,5%, and 21.4% for heart rate, oxygen saturation, and respiration rate, respectively. Moreover, increasing the observation rate could enhance the prediction performance to be, on average, 8%,4.8%, and 17.8% for heart rate, oxygen saturation, and respiration rate, respectively. It is envisioned that such models could be integrated with monitoring systems that could, using a limited number of vital signs, predict the health conditions of COVID-19 ICU patients in real-time.

Vital signs and work of breathing assessment in the emergency department as predictor for acute respiratory failure in COVID-19 pneumonia

“…Several studies have demonstrated associations among reduced oxygen saturation, increased glucose levels, and elevated respiratory rate on admission with an unfavourable outcome in patients with COVID-19 [41][42][43][44]. RR was found to be an important parameter for predicting ARF in COVID-19 pneumonia patients within 72 hours.…”

Clinical prediction rules for adverse evolution in patients with COVID-19 by the Omicron variant

“…We defined heart rate-diastolic/systolic pressure as the combination of heart rate and diastolic-systolic pressure as presented in Online Table 1 . [20] , [21] , [22] .…”

“…Given the large sample size (n train = 120,534 and n test = 120,533 in the general population sample and n train = 19,672 and n test = 19,672 in the ED sample), variable selection was performed by means of a multivariate Lasso logistic regression model (1.- Hospital admission; 2.- Death; and 3.- Adverse evolution) which employs penalized likelihood for parameter estimates and variable selection in the train subsample [19] , [20] . The final models were adjusted by means of a multilevel logistic regression considering that patients were nested in the IHOs.…”

Nonadverse COVID-19 evolution predictors: the CoNAE scale

“…Todos los datos de los pacientes bajo la atención de Osakidetza se registran en una única base de datos electrónica unificada y se mantuvieron de forma confidencial. Expertos analistas recuperaron datos de todos los casos positivos detectados durante el periodo de estudio, incluidos datos sociodemográficos (edad, sexo, lugar de residencia), vacunación frente a la COVID-19 (fecha, dosis, tipo de vacuna), comorbilidades basales (todas las incluidas en el índice de comorbilidad de Charlson, más angina de pecho, arritmia, hipertensión arterial, dislipidemia, asma, bronquiectasias, fibrosis quística, enfermedad pulmonar intersticial, linfoma, leucemia, coagulopatía, enfermedad inflamatoria intestinal, hemorragia gastrointestinal), tratamientos basales prescritos (basados en el sistema de clasificación anatómica, terapéutica, química o código ATC), signos vitales (temperatura corporal, presión arterial, frecuencia cardiaca y saturación de oxígeno -SatO 2 ) [10][11][12] , otros datos de referencia relacionados con la atención prestada en entornos hospitalarios o de atención primaria, (incluyendo las fechas de ingreso y alta hospitalaria, y si los pacientes fueron ingresados en una unidad de cuidados intensivos -UCI-) y el estado vital. Con respecto a los signos vitales, definimos clases de riesgo de la combinación de frecuencia cardiaca y presión arterial diastólica-sistólica tal y como se presenta en https://emergencias.portalsemes.org/images/MATERIAL-SUPLEMENTARIO-4200.…”