imPulse™ Tor System Self-Directed Cuffless Blood Pressure Monitoring

AI/ML Algorithm Training and Validation for the imPulse™ Tor System Self-Directed Systolic & Diastolic Blood Pressure Monitor.

Self-measured, non-invasive accurate blood pressure monitoring continues to be a major challenge for automated vital sign measurement systems. The general notion is that with reliable, self-administered BP monitoring in the clinic and at home, health care providers will be able to diagnose hypertension among individuals at an early stage, including high risk patients in the community, and more quickly assess if prescribed treatment plans are working. The imPulse™ Tor System detects 1) audible and inaudible low-frequency, low-amplitude sounds generated by the body, including arterial pulse waveforms, and 2) ECG-derived heart cycle identification, which can be combined with the vibroacoustic data to estimate blood pressure. The imPulse™ Tor has undergone preliminary testing. In this pilot study, we collect data from health care workers for algorithm training and validation study to achieve medical grade device AAMI/ISO and IEEE standards compliance.

Study Overview

• Status: Completed
• Conditions: AI-driven, Self-directed Blood Pressure Monitoring
• Intervention / Treatment: Device: imPulse™ Tor System

Detailed Description

Hypertension (HTN) is a major risk factor for cerebrovascular morbidity and mortality, yet its identification can be delayed due to lack of overt symptoms, relying on Blood Pressure (BP) measurements for diagnosis. Several BP monitoring techniques are used in clinics and hospitals, and there is also an outpatient method that is used for 24-hour BP monitoring, based on a sphygmomanometer. The general notion is that with frequent, reliable, self-directed BP monitoring in the clinic and at home, health care providers will be able to diagnose hypertension among individuals at an early stage, including high-risk patients in the community, and more quickly assess if prescribed treatment plans are working. However, non-invasive self-administered blood pressure monitoring continues to be a major challenge for automated vital sign measurement systems.

To circumvent the limitations of current systems of interval hemodynamic measurement and increasing demands on healthcare providers, a non-invasive automated self- directed vital sign monitor that can integrate into hospital early warning systems and warn healthcare providers of deteriorating vital sign parameters would be of significant value. This study aims to provide proof of concept for a portable device that measures vital signs (blood pressure, heart rate, and blood oxygen saturation) using biophysical pneumatics and hydraulics, vibroacoustics, and multi-lead ECG that aims to produce results that are as good as a sphygmomanometer-based device and pulse oximeter, without the need for a circumferential pressure device/sphygmomanometer on the arm.

• Study Type: Observational
• Enrollment (Actual): 15

Contacts and Locations

Study Locations

• United States
  • California
    • Sacramento, California, United States, 95816
      • UCD Sports Medicine

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: Yes
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

Healthy volunteer healthcare worker cohort

Description

Inclusion Criteria:

• Participants are limited to clinical staff and first-responders who work at the UC Davis C Street Clinics in the Sports and Spine suites.

Exclusion Criteria:

• History of major neck surgeries
• Unable to sit and stand upright comfortably for 2 minutes
• Unable to obtain or has contraindication to upper extremity blood pressure reading
• Unable to perform self-measurements using the imPulse™ Tor device
• Adults unable to consent
• Individuals who are not yet adults (infants, children, teenagers)
• Pregnant women

Study Plan

How is the study designed?

Design Details

• Observational Models: Cohort
• Time Perspectives: Prospective

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
imPulse™ Tor System Blood Pressure Prediction	Following AI/ML algorithm training and validation the difference between predicted systolic, diastolic, and mean arterial pressure predictions of the imPulse™ Tor and gold-standard measurement of an electronic blood pressure cuff will be less than 2.5 mmHg in at least 90% of the measurements, less than 5 mmHg in at least 92.5% of the measurements and less than 10 mmHg in at least 95% of the measurements.	bid/1week

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
imPulse™ Tor Heart Rate Prediction	Following AI/ML algorithm training and validation, there is no significant difference (p-values >0.05) in the comparisons of electronic blood pressure cuff pulse measurement and imPulse™ Tor estimations for HR measurements (BPM).	bid/1week
imPulse™ Tor Oxygen Saturation Prediction	Following AI/ML algorithm training and validation, the imPulse™ Tor can predict oxygen saturation (a proposed fifth vital sign) with an overall classification accuracy > 85% for the SpO2 class "< 84%", "85 to 91%" and "> 92%", respectively.	bid/1week

Collaborators and Investigators

• Sponsor: Level 42 AI, Inc.
• Collaborators: University of California, Davis

Study record dates

Study Major Dates

• Study Start (Actual): May 16, 2022
• Primary Completion (Actual): August 23, 2022
• Study Completion (Actual): August 30, 2022

Study Registration Dates

• First Submitted: May 18, 2022
• First Submitted That Met QC Criteria: May 18, 2022
• First Posted (Actual): May 23, 2022

Study Record Updates

• Last Update Posted (Actual): March 23, 2023
• Last Update Submitted That Met QC Criteria: March 22, 2023
• Last Verified: March 1, 2023

More Information

Terms related to this study

• Keywords: infrasound; vibroacoustic; capacitive ECG; electric potential sensor
• Other Study ID Numbers: L42CVP-0005

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Pilot study data for algorithm training using different AI/ML approaches.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No