Multi-parameter patient monitoring in intensive care units (ICU) remains unsatisfactory as evidenced by the well-known alarm fatigue problem. It has been reported that a critical care patient could generate 700 alarms per day. At UCSF, a daily average of 187 audible alarms per bed occurred in ICUs during one month of assessment. Improving signal processing algorithms, fine-tuning alarm thresholds, and downgrading some alarms to an inaudible category are some ways to address alarm fatigue. However, these interventions attempt to solve the problem within the context of conventional patient monitoring practice (i.e., the focus is on an individual alarm while ignoring the relationships among alarms, the contextual information established by other data available in electronic health record (EHR), and the sequential patterns of all of these variables). In fact, we argue that alarm fatigue reflecs a deeper challenge for critical care clinicians who are overloaded with increasingly available raw data but do not have appropriate tools to leverage the potential of these data to treat their patients. As a first step to support clinicians to overcome data overload, our goal is to precisely detect gross patient state changes by recognizing combinatorial and sequential patterns among individual alarms, physiological variables, and EHR data. Achieving this goal will lead to developing additional decision support tools to understand the causes and select potential interventions for the detected patient state changes. Our group has done preliminary studies that demonstrate the feasibility of achieving this goal. In particular, we have evolved a specific algorithm to identify co-occurring monitor alarms, which frequently precede in-hospital cardiopulmonary arrests (CPA) but rarely occur among control patients, to a data fusion framework. This framework is capable of recognizing predictive combinations of a much richer set of variables including lab tests and additional physiological variables not available from monitors. We term these combinations SuperAlarm patterns. By construction, SuperAlarm triggers will occur much less frequently than monitor alarms, yet be more precise in detecting patient state changes. Thus, the objective of this application is to develop and validate further algorithm improvement under this SuperAlarm data fusion framework using prospective data. We will pursue the following three aims: 1) To enrich SuperAlarm patterns by novel analysis of Electrocardiographic (ECG) signals; 2) To develop sequential pattern recognition methods for sequences of SuperAlarm triggers. 3) To conduct prospective data collection to develop and validate SuperAlarm model.

Public Health Relevance

Critical care patient monitoring remains unsatisfactory as evidenced by the alarm fatigue problem it has created. We propose to develop a data fusion framework to integrate monitor alarms, laboratory test results, and other non-monitored physiological variables to realize a more precise way of monitoring patients to provide early detection of patient crisis events with few false alarms. Our project will lead to a potentially transformative paradigm change of critical care patient monitoring towards a more integrated and precise system for recognizing crisis events and enabling early interventions and produce a database to the community to propel further development of predictive models.

Agency
National Institute of Health (NIH)
Institute
National Heart, Lung, and Blood Institute (NHLBI)
Type
Research Project (R01)
Project #
1R01HL128679-01
Application #
8943567
Study Section
Biomedical Computing and Health Informatics Study Section (BCHI)
Program Officer
Lee, Albert
Project Start
2015-07-20
Project End
2019-04-30
Budget Start
2015-07-20
Budget End
2016-04-30
Support Year
1
Fiscal Year
2015
Total Cost
$531,284
Indirect Cost
$196,089
Name
University of California San Francisco
Department
Other Health Professions
Type
Schools of Nursing
DUNS #
094878337
City
San Francisco
State
CA
Country
United States
Zip Code
94143
Shahriari, Yalda; Fidler, Richard; Pelter, Michele M et al. (2018) Electrocardiogram Signal Quality Assessment Based on Structural Image Similarity Metric. IEEE Trans Biomed Eng 65:745-753
Gadhoumi, Kais; Do, Duc; Badilini, Fabio et al. (2018) Wavelet leader multifractal analysis of heart rate variability in atrial fibrillation. J Electrocardiol 51:S83-S87
Xiao, Ran; Xu, Yuan; Pelter, Michele M et al. (2018) Monitoring significant ST changes through deep learning. J Electrocardiol 51:S78-S82
Fidler, Richard L; Pelter, Michele M; Drew, Barbara J et al. (2017) Understanding heart rate alarm adjustment in the intensive care units through an analytical approach. PLoS One 12:e0187855
Harris, Patricia R; Z├Ęgre-Hemsey, Jessica K; Schindler, Daniel et al. (2017) Patient characteristics associated with false arrhythmia alarms in intensive care. Ther Clin Risk Manag 13:499-513
Tinoco, Adelita; Drew, Barbara J; Hu, Xiao et al. (2017) ECG-derived Cheyne-Stokes respiration and periodic breathing in healthy and hospitalized populations. Ann Noninvasive Electrocardiol 22:
Bai, Yong; Do, Duc; Ding, Quan et al. (2017) Is the Sequence of SuperAlarm Triggers More Predictive Than Sequence of the Currently Utilized Patient Monitor Alarms? IEEE Trans Biomed Eng 64:1023-1032
Ding, Quan; Bai, Yong; Erol, Yusuf Bugra et al. (2016) Robust QRS peak detection by multimodal information fusion of ECG and blood pressure signals. Physiol Meas 37:N84-N95
Arroyo-Palacios, Jorge; Rudz, Maryna; Fidler, Richard et al. (2016) Characterization of Shape Differences Among ICP Pulses Predicts Outcome of External Ventricular Drainage Weaning Trial. Neurocrit Care 25:424-433
Ding, Quan; Bai, Yong; Tinoco, Adelita et al. (2015) Developing new predictive alarms based on ECG metrics for bradyasystolic cardiac arrest. Physiol Meas 36:2405-22