Use of Artificial Intelligence Predictive Analytics to Improve Early Detection of Clinical Deterioration in Hospitalized Patients
Advisor(s)
Megan Lieb
Confirmation
1
Document Type
Poster
Location
ONU McIntosh Center; Activities Room
Start Date
24-4-2026 11:00 AM
End Date
24-4-2026 11:50 AM
Abstract
Abstract
Problem: Hospitalized patients are at increased risk for rapidly developing life-threatening conditions such as sepsis, pulmonary embolism, and cardiac arrest. Despite the current standard practice of continuous vitals sign monitoring and use of Early Warning Scores (EWS's), early detection of subtle clinical deterioration remains a challenge. Recognition of these deteriorating patient conditions is essential for good patient outcomes. Some studies have found a potential solution in the use of artificial intelligence (AI) based predictive analysis Programs, finding them quicker and more successful at alerting for potential adverse events.
Purpose: The purpose of this project is to determine whether the use of AI predictive analytic programs improves early identification of deteriorating conditions in hospitalized patients compared to traditional EWS's and standard vital-sign monitoring. This project aims to evaluate whether AI technology enhances clinical decision-making and patient safety.
Methods: This project will use a quasi-experimental design including participants in an acute care hospital. Patients will be monitored using either an AI-driven predictive analysis program integrated into the electronic health record or traditional EWS's and routine vital-sign assessment. Outcome measures will include a chart review of the success rate of detecting adverse events, how quickly deteriorating conditions were recognized and the patient's outcome afterwards.
Conclusion: Implementation of AI predictive analytics may lead to earlier recognition of clinical deterioration and more timely interventions. Improved detection has the potential to reduce morbidity, mortality, and healthcare costs while enhancing patient safety. This project is significant to nursing practice because an improved patient monitoring system can strengthen clinical judgment and interventions to improve patient outcomes.
Recommended Citation
Highfield, Ashlynn, "Use of Artificial Intelligence Predictive Analytics to Improve Early Detection of Clinical Deterioration in Hospitalized Patients" (2026). ONU Student Research Colloquium. 32.
https://digitalcommons.onu.edu/student_research_colloquium/2026/Posters/32
Open Access
Available to all.
Use of Artificial Intelligence Predictive Analytics to Improve Early Detection of Clinical Deterioration in Hospitalized Patients
ONU McIntosh Center; Activities Room
Abstract
Problem: Hospitalized patients are at increased risk for rapidly developing life-threatening conditions such as sepsis, pulmonary embolism, and cardiac arrest. Despite the current standard practice of continuous vitals sign monitoring and use of Early Warning Scores (EWS's), early detection of subtle clinical deterioration remains a challenge. Recognition of these deteriorating patient conditions is essential for good patient outcomes. Some studies have found a potential solution in the use of artificial intelligence (AI) based predictive analysis Programs, finding them quicker and more successful at alerting for potential adverse events.
Purpose: The purpose of this project is to determine whether the use of AI predictive analytic programs improves early identification of deteriorating conditions in hospitalized patients compared to traditional EWS's and standard vital-sign monitoring. This project aims to evaluate whether AI technology enhances clinical decision-making and patient safety.
Methods: This project will use a quasi-experimental design including participants in an acute care hospital. Patients will be monitored using either an AI-driven predictive analysis program integrated into the electronic health record or traditional EWS's and routine vital-sign assessment. Outcome measures will include a chart review of the success rate of detecting adverse events, how quickly deteriorating conditions were recognized and the patient's outcome afterwards.
Conclusion: Implementation of AI predictive analytics may lead to earlier recognition of clinical deterioration and more timely interventions. Improved detection has the potential to reduce morbidity, mortality, and healthcare costs while enhancing patient safety. This project is significant to nursing practice because an improved patient monitoring system can strengthen clinical judgment and interventions to improve patient outcomes.