Related Experiment Video
Updated: Jun 6, 2025
A Detailed Protocol for Physiological Parameters Acquisition and Analysis in Neurosurgical Critical Patients
Published on: October 17, 2017
Assessing the Predictive Capabilities of Autoregressive Integrated Moving Average and Linear Regression Models for
Sharmin Nahar Sharwardy1, Hasan Sarwar2, Mohammad Nurul Akhtar Hasan3
1Department of Computer Science and Engineering, Jahangirnagar University, Savar 1342, Bangladesh.
Insights
This study identifies key clinical factors for predicting intensive care unit (ICU) patient status in pediatric congenital heart defect cases. The ARIMA model accurately forecasts patient conditions, enabling early intervention and improved outcomes.
Area of Science:
- Pediatric Cardiology
- Intensive Care Medicine
- Biomedical Engineering
Background:
- Congenital heart defects (CHDs) pose significant challenges for pediatric patients undergoing intensive care unit (ICU) surgery.
- Monitoring clinical factors is crucial for managing post-operative outcomes in these vulnerable patients.
- A study was conducted at the National Heart Foundation Hospital and Research Institute in Dhaka, Bangladesh, involving 288 pediatric ICU patients.
Purpose of the Study:
- To assess clinical factors associated with the condition of pediatric patients with CHDs after ICU surgery.
- To identify predictive parameters for patient status monitoring and early warning systems.
- To compare the predictive accuracy of linear regression and ARIMA models for ICU patient status.
Main Methods:
- Data from 288 pediatric ICU patients (under 12 years, >24h ICU stay) with CHDs were analyzed.
- Pearson correlation, linear regression, and Autoregressive Integrated Moving Average (ARIMA) modeling were employed.
- Key ICU parameters including Central Venous Pressure (CVP), Blood Pressure (BP), Positive End-Expiratory Pressure (PEEP), Fraction of Inspired Oxygen (FiO2), pH, and Partial Pressure of Oxygen (PO2) were assessed.
Main Results:
- Statistically significant relationships were found between CVP and BP (p < 0.001), and PEEP and FiO2 (p < 0.001).
- Minor but significant relationships were observed between pH and PO2 (p < 0.001).
- The ARIMA model demonstrated a lower error rate than the linear regression model in forecasting patient status using BP, FiO2, and PO2.
Conclusions:
- Identifying critical parameters aids in predicting and monitoring ICU patient status, facilitating early detection of deterioration.
- The ARIMA model offers a more accurate forecasting tool for patient conditions compared to linear regression.
- Accurate forecasting enables proactive interventions, potentially improving patient outcomes and reducing adverse events in pediatric CHD cases.
Abstract:
(1) Background: The main objective of this research was to assess the clinical factors related to the condition of pediatric patients with congenital heart defects after they underwent intensive care unit surgery. The information was gathered from the Congenital Heart Disease Surgery Unit at the National Heart Foundation Hospital and Research Institute in Dhaka, Bangladesh. We gathered and examined data from 288 ICU patients. Patients under the age of twelve who required more than a 24-h ICU stay were selected. (2) Methods: The dependent and independent variables were chosen in advance based on expert opinion. The relationships between these pre-specified ICU parameters were determined using the Pearson correlation model and assessed through linear regression and ARIMA modeling to predict subsequent acute changes in the patients' ICU statuses. (3) Results: A statistically significant relationship (p value < 0.001) was found between CVP and BP (95% CI = 0.2113; 0.353 r = 0.2841249) and between PEEP and FiO2 (95% CI = 0.6992; 0.770 r = 0.7367744). Although the relationships between pH and PO2 were minor (95% CI = 0.161; 0.308 r = 0.2362575), they were statistically significant. The parameters considered statistically significant (p < 0.001) were chosen for forecasting. In this work, the linear regression model and the ARIMA model used the parameters BP, FiO2, and PO2 for prediction. We forecasted the patients' statuses for the next hour. It was found that the ARIMA model had a lower error rate than the linear regression model. (4) Conclusions: This study helps identify the important parameters for predicting and monitoring patients' statuses in the ICU, with the ultimate goal of providing physicians with an early warning system to anticipate deterioration in clinical and biochemical parameters. The ability to accurately forecast future patients' conditions can enable proactive, targeted interventions, potentially improving outcomes and reducing the risk of adverse events.
