Reducing False Alarm Rates and Workload in ICUs by Improving Arrhythmia Detection Algorithms of Patient Monitoring Systems
Year: 2025
Type: article
Study design: Clinical Trial
Abstract: BACKGROUND Patient monitoring systems are widely used in intensive care units (ICUs) to monitor patient's conditions. A high false alarm rate can lead to alarm fatigue among nurses, increasing workload and stress. This study aimed to improve the accuracy of arrhythmia detection by enhancing the noise detection algorithm in patient monitoring systems and to determine whether false alarm rate and workload decreased through clinical trials. MATERIAL AND METHODS Trials were conducted on adult patients in the ICU at Yongin Severance Hospital who required continuous electrocardiogram (ECG) monitoring for at least 2 days. After the first trial, the noise detection algorithm of the M50 (investigational device) was improved, and a second trial was conducted to evaluate its performance. Both trials followed the same study design. During the study period, M50 and MX700 (comparator device) were applied simultaneously for 3 days. Arrhythmia alarms were reviewed by an independent evaluator who assessed false alarms by comparing them with the ECG signals. False alarm rates were compared between trials using the chi-square (χ²) test. RESULTS The clinical trial was conducted through 2 separate trials, with 17 and 11 participants, respectively. A comparative analysis of false alarm rates of the investigational device demonstrated a reduction from 71.75% to 27.61%. Statistical analysis using the chi-square test indicated a P value of 0.000 (<0.001), confirming a statistically significant difference. CONCLUSIONS The results of 2 trials demonstrated reductions in false alarm rate and NASA-TLX score. These findings suggest that enhancing the noise detection algorithm in the patient monitoring system improved arrhythmia detection accuracy and helped reduce nurses' workload.
Source: Medical Science Monitor
DOI: 10.12659/msm.949932
Authors: Jiyoon Oh, You Rim Kim, Yong Ju Lee, Dae Keun Jeon, Ji Soo Choi, Jae-Sun Uhm, Chul-Min Ahn, Won Seuk Jang
Language: English
Subfield: Surgery
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W4415296740
FWCI:
Cites:
Cited by:
Related to: