A Time-Series Feature-Based Recursive Classification Model to Optimize Treatment Strategies for Improving Outcomes and Resource Allocations of COVID-19 Patients

Abstract

This paper presents a novel Lasso Logistic Regression model based on feature-based time series data to determine disease severity and when to administer drugs or escalate intervention procedures in patients with coronavirus disease 2019 (COVID-19). Advanced features were extracted from highly enriched and time series vital sign data of hospitalized COVID-19 patients, including oxygen saturation readings, and with a combination of patient demographic and comorbidity information, as inputs into the dynamic feature-based classification model. Such dynamic combinations brought deep insights to guide clinical decision-making of complex COVID-19 cases, including prognosis prediction, timing of drug administration, admission to intensive care units, and application of intervention procedures like ventilation and intubation. The COVID-19 patient classification model was developed utilizing 900 hospitalized COVID-19 patients in a leading multi-hospital system in Texas, United States. By providing mortality prediction based on time-series physiologic data, demographics, and clinical records of individual COVID-19 patients, the dynamic feature-based classification model can be used to improve efficacy of the COVID-19 patient treatment, prioritize medical resources, and reduce casualties. The uniqueness of our model is that it is based on just the first 24 hours of vital sign data such that clinical interventions can be decided early and applied effectively. Such a strategy could be extended to prioritize resource allocations and drug treatment for future pandemic events.

A COVID-19 Detection Model Based on Convolutional Neural Network and Residual Learning

“…By providing mortality prediction according to the time-series physiological data, demographics and clinical records of patients with COVID-19, the classification model based on dynamic characteristics can be used to improve the efficacy of treatment of patients with COVID-19, give priority to medical resources and reduce casualties. In the literature [28], for the twitter classification, four different aspects (policy, health, media and others) and four different Bert models (Mbert base [29], biobert [30], clinicalbert [31] and berturk [32]) were used. Six different COVID-19 vaccines with the highest frequency were selected in the data set, and twitter posts were used for emotional analysis of these vaccines.…”

Using time-series chest radiographs and laboratory data by machine learning for identifying pulmonary infection and colonization of Acinetobacter baumannii

“…In recent years, the use of machine learning in healthcare has garnered increasing attention, particularly in areas such as lesion prediction, personalized patient treatment, and objective evaluation of patient conditions [ 19 – 21 ]. For instance, Wang at al.…”

“…For instance, Wang at al. proposed an innovative Lasso Logistic Regression model that utilizes feature-based time series data to determine the optimal timing for drug administration or escalating intervention procedures in COVID-19 patients [ 19 ]. However, there have been limited studies focusing specifically on the application of machine learning in assessing the pulmonary status of A. baumannii .…”

Time series analysis for financial indices using optical reservoir computing

“…In sectors such as climate science, 1 , 2 epidemiology, 3 , 4 and energy forecasting, 5 , 6 time series analysis empowers researchers to model temporal dependencies, predict future outcomes, and develop strategies for effective resource allocation 7 – 9 By discerning patterns in historical data, decision-makers gain invaluable insights into the behavior of dynamic systems, aiding in the formulation of proactive strategies to mitigate risks, 10 , 11 optimize resource utilization, 12 , 13 and enhance overall operational efficiency 14 . However, the energy consumed in this analysis is a subject of growing concern as the demand for increasingly sophisticated machine learning models rises 15 , 16 .…”