ASN's Mission

To create a world without kidney diseases, the ASN Alliance for Kidney Health elevates care by educating and informing, driving breakthroughs and innovation, and advocating for policies that create transformative changes in kidney medicine throughout the world.

learn more

Contact ASN

1401 H St, NW, Ste 900, Washington, DC 20005

email@asn-online.org

202-640-4660

The Latest on X

Kidney Week

Abstract: TH-PO1122

Wearable Device for Noninvasive Blood Pressure Monitoring of ICU Patients

Session Information

  • Late-Breaking Posters
    November 02, 2023 | Location: Exhibit Hall, Pennsylvania Convention Center
    Abstract Time: 10:00 AM - 12:00 PM

Category: Hypertension and CVD

  • 1602 Hypertension and CVD: Clinical

Author

  • Miller, Forrest, Alio, Broomfield, Colorado, United States
Background

Blood pressure (BP) is a cardinal vital sign used in cardiovascular clinical decision-making. The traditional approach for BP measurement in intensive care units (ICU) involves the use of an invasive arterial line (A-line). A-line measurements require technique and practice and introduce the risk of clinical complications that could result in thrombosis or sepsis. This study evaluated the performance of cuffless BP monitoring with a novel wearable device (“SmartPatch”) compared to the gold standard A-line.

Methods

A retrospective IRB-approved study was conducted to evaluate the performance of an algorithm to track BP metrics-systolic blood pressure (SBP), diastolic blood pressure (DBP) and mean arterial pressure (MAP)–noninvasively and compare them against invasive arterial line (on left radial) values in 26 subjects. Simultaneous arterial line BP and photoplethysmography (PPG) data from SmartPatch were collected from post-surgery patients admitted to a neuro-ICU unit over an average of 2 hours. The PPG data was pre-processed, assessed for signal quality, and fed into an Artificial Neural Network (ANN) model to train with the A-line BP data as reference.

Results

A total of 6.07 hours of data was segmented into 6 sec PPG recordings resulting in ~1900 data points to be analyzed. An ANN model was trained and validated with leave one out-cross validation (LOO-CV) to tune the model parameters and assess the performance. Mean of errors and Pearson correlation coefficient r were used to assess the performance of the ANN model. The mean of errors and the experimental standard deviation for SBP was: -1.207 (SD: 9.17) mmHg, MAP: -0.144 (SD: 5.09) mmHg and DBP: -0.161 (SD: 5.10) mmHg. These values fall within the limits set by the ISO 81060-2 (2018) standard. The ANN-generated BP values were correlated to the A-line with Pearson r = 0.81 (SBP), 0.68 (DBP) and 0.79 (MAP).

Conclusion

The ANN model was trained using LOO-CV to predict SBP, DBP & MAP. The results demonstrated quantitative accuracy within the limits set by the ISO 81060-2 (2018) standard when validated against the A-line BP. This noninvasive cuffless BP measurement from a wearable device could enable more consistent, accurate, and cost-effective patient care in remote monitoring settings.