Evaluation of the AudibleHealth Dx AI/ML-Based Dx SaMD Using FCV-SDS in the Diagnosis of COVID-19 Illness: Clinical Validation

Sponsor

AudibleHealth AI, Inc. (Industry)

Overall Status

Completed

CT.gov ID

NCT05364268

Collaborator

Sunrise Research Institute (Other), Analytical Solutions Group, Inc. (Other), Kelley Medical Consultants LLC (Other), R. P. Chiacchierini Consulting, LLC (Other)

514

Enrollment

Location

Actual Duration (Days)

558.7

Patients Per Site Per Month

Study Details

Study Description

Brief Summary

The AudibleHealth Dx is a diagnostic software as a medical device (Dx SaMD) consisting of an ensemble of software subroutines that interacts with a proprietary database of Signal Data Signatures (SDS), using Artificial Intelligence/Machine Learning (AI/ML) to analyze forced cough vocalization signal data signatures (FCV-SDS) for diagnostic purposes.

This study will evaluate the performance of the AudibleHealth Dx in comparison to a standard of care Reverse Transcriptase Polymerase Chain Reaction (RT-PCR) test for the diagnosis of COVID-19.

A secondary purpose of the study will be usability testing of the device for participants and providers.

Condition or Disease	Intervention/Treatment	Phase
2019 Novel Coronavirus Disease 2019 Novel Coronavirus Infection 2019-nCoV Disease COVID-19 Pandemic COVID-19 Virus Disease COVID-19 Virus Infection Coronavirus Disease 2019 Coronavirus Disease-19 SARS-CoV-2 Infection	Device: Diagnostic Test: Diagnostic Software as Medical Device

Detailed Description

The study is a prospective, multi-site, non-inferiority trial comparing the AudibleHealth Dx to FDA approved COVID-19 RT-PCR testing to demonstrate non-inferiority of the PPA and NPA when using this device to diagnose COVID-19 illness. The AudibleHealth Dx test and the "BioFire Respiratory 2.1 (RP2.1)" (brand name) test will be performed for each participant during a single encounter. Participants and staff will be blinded to AudibleHealth Dx results and the RT-PCR status at the time of testing. No one will know both results in real-time except for the Site Coordinators and unblinded statistician specifically authorized to have these results for enrollment, audit, data tracking, and data compiling purposes. • Unblinding of the results will occur after the AudibleHealth Dx, RT-PCR, and the second RT-PCR results (if necessary for discordance) have been obtained. Results for the RT-PCR test will be received by the participant according to the clinical site's protocol.

Target enrollment for this trial will be 65 COVID-19 positive cases and 152 COVID-19 negative cases, presuming a prevalence of 0.30 for a total of 217 subjects meeting all inclusion criteria.

Study Design

Study Type:

Observational

Actual Enrollment :

514 participants

Observational Model:

Case-Only

Time Perspective:

Prospective

Official Title:

Evaluation of the Artificial Intelligence/Machine Learning-Based Diagnostic Software as a Medical Device Using Forced Cough Vocalization Signal Data Signatures in the Diagnosis of COVID-19 Illness: A Prospective, Two-Arm Non-Inferiority Clinical Validation Trial of AudibleHealth Dx Software as a Medical Device (EUA-US)

Actual Study Start Date :

May 4, 2022

Actual Primary Completion Date :

Jun 1, 2022

Actual Study Completion Date :

Jun 1, 2022

Arms and Interventions

Arm	Intervention/Treatment
Trial Population The trial population will be enrolled from adults presenting for elective, outpatient COVID-19 testing at a single center, potentially with multiple testing locations (subject to local needs at the time of the trial). The investigational device will be provided to Participants via a cell phone preloaded with Common off-the-shelf original equipment manufacturer (COTS OEM) software and the investigational Dx SaMD. The investigational device will be evaluated during a single encounter in which an FCV-SDS will be collected. No follow-up visits or participant contacts will be involved in this trial.	Device: Diagnostic Test: Diagnostic Software as Medical Device AudibleHealth Dx is an investigational Dx SaMD consisting of an ensemble of software subroutines that interacts with a proprietary database of signal data signatures (SDS) using Artificial Intelligence/Machine Learning (AI/ML) to analyze forced cough vocalization signal data signatures (FCV-SDS) for diagnostic purposes. The intended use for the AudibleHealth Dx AI/ML-based Dx SaMD using FCV-SDS is for the diagnosis of acute and chronic illnesses, specifically COVID-19 illness for this study.

Arm

Intervention/Treatment

Trial Population

The trial population will be enrolled from adults presenting for elective, outpatient COVID-19 testing at a single center, potentially with multiple testing locations (subject to local needs at the time of the trial). The investigational device will be provided to Participants via a cell phone preloaded with Common off-the-shelf original equipment manufacturer (COTS OEM) software and the investigational Dx SaMD. The investigational device will be evaluated during a single encounter in which an FCV-SDS will be collected. No follow-up visits or participant contacts will be involved in this trial.

Device: Diagnostic Test: Diagnostic Software as Medical Device

AudibleHealth Dx is an investigational Dx SaMD consisting of an ensemble of software subroutines that interacts with a proprietary database of signal data signatures (SDS) using Artificial Intelligence/Machine Learning (AI/ML) to analyze forced cough vocalization signal data signatures (FCV-SDS) for diagnostic purposes. The intended use for the AudibleHealth Dx AI/ML-based Dx SaMD using FCV-SDS is for the diagnosis of acute and chronic illnesses, specifically COVID-19 illness for this study.

Outcome Measures

Primary Outcome Measures

Non-inferiority of the positive percent agreement (PPA) [Participants will have a single encounter lasting less than one hour; anticipated study duration is 6 weeks. Target enrollment is 65 positive and 152 negative participants.]
To demonstrate non-inferiority of the positive percent agreement (PPA) of the AudibleHealth Dx when compared to FDA approved SARS CoV-2 RT-PCR testing for the diagnosis of COVID-19 illness
Non-inferiority of the negative percent agreement (NPA) [Participants will have a single encounter lasting less than one hour; anticipated study duration is 6 weeks. Target enrollment is 65 positive and 152 negative participants.]
2. To demonstrate non-inferiority of the negative percent agreement (NPA) of the AudibleHealth Dx when compared to FDA approved SARS-CoV-2 RT-PCR testing for the diagnosis of COVID-19 illness.

Eligibility Criteria

Criteria

Ages Eligible for Study:

18 Years to 100 Years

Sexes Eligible for Study:

All

Accepts Healthy Volunteers:

Yes

Inclusion Criteria:

18 years of age or older
Present for elective, outpatient COVID-19 RT-PCR testing
Meet the FDA EUA approved indications for use for RT-PCR nasal swab testing for COVID-19
Stated willingness to comply with all trial procedures and availability for the duration of the trial
Informed consent must be obtained prior to testing
Ability to complete both the informed consent form and the screens on the medical device app in English (no translation to other languages is currently available)

Exclusion Criteria:

Any individual who was a part of the AudibleHealth Dx Development, Training, and Usability trial (Training and test data sets are to be kept strictly separate.)
Less than 18 years of age
Unable to produce a voluntary forced cough vocalization (FCV)
Recent acute traumatic injury to the head, neck, throat, chest, abdomen or trunk
Patent tracheostomy stoma
Recent chest / abdomen / trunk trauma or surgery, recent / persistent neurovascular injury or recent intracranial surgery
Medical history of cribriform plate injury or cribriform plate surgery, diaphragmatic hernia, external beam neck / throat / maxillofacial radiation, phrenic nerve injury/palsy, radical neck / throat / maxillofacial surgery, vocal cord trauma or nodules
Since persons with aphasia may have difficulty in producing an FCV-SDS in the time allotted by the app, this population also will be excluded from the current trial