Automated Algorithm Based Analysis of Phonocardiograms of Newborns

NCT02105480 | Completed DMC

• 1 other identifier: GRZ02 (AAAPN)
• Study Type: observational
• Target: 220
• Locations: 1 country
• Sites: 1

Brief Summary

The purpose of this double-blind pivotal clinical utility study is to determine on a large patient population whether heart murmurs can be reliably detected with high sensitivity and specificity using a locked, automated algorithm-based phonocardiogram analysis (also referred to as computer aided auscultation (CAA)). Each patient is auscultated and diagnosed independently by a medical specialist. Additionally, for each patient, an echocardiogram is performed as the gold-standard for determining heart pathologies. The CAA results are compared to the findings of the medical professionals as well as to the echocardiogram findings. Hypothesis: The specific (locked) CAA algorithms used in this study are able to automatically diagnose pathological heart murmurs in premature babies and newborns with at least the same accuracy as experienced medical specialists.

Conditions

Heart Murmurs; Mitral Valve Prolapse; Systolic Murmurs

Keywords

Computer aided auscultation (CAA); Phonocardiogram analysis; Murmur detection; Heart auscultation

Outcome Measures

Primary Outcomes (1)

• Number of correctly diagnosed heart murmurs through locked, independent algorithm based auscultation and traditional stethoscope based auscultation by medical experts

  Each patient is screened and diagnosed regarding a potential heart murmur by a medical expert through standard stethoscope based auscultation. Heart sounds are recorded using an electronic stethoscope and analyzed and diagnosed independently (with no external input) by a locked algorithm. A final diagnoses for each patient is made by a medical expert by performing an echocardiogram, the gold standard method for heart murmur detection. The diagnoses of both the medical expert and the algorithm are finally compared to the echocardiogram based diagnosis (after completion of patient recruitment).

  2 years (expected)

Interventions

Computer aided auscultation (CAA) DEVICE

Also known as: Phonocardiogram analysis, Automated heart murmur classification, Murmur screening

Eligibility Criteria

• Age: 1 Minute - 5 Days
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17)
• Sampling Method: Non-Probability Sample

Study Population

Premature babies and newborns stationed at the department of neonatology

You may qualify if:

• any premature baby or newborn
• parental approval for study participation

You may not qualify if:

• none

Sponsors & Collaborators

• CSD Labs GmbH: lead

Study Sites (1)

University Hospital

Graz, Styria, 8010, Austria

Location

MeSH Terms

Conditions

Heart Murmurs; Mitral Valve Prolapse; Systolic Murmurs

Condition Hierarchy (Ancestors)

Signs and Symptoms; Pathological Conditions, Signs and Symptoms; Heart Valve Prolapse; Heart Valve Diseases; Heart Diseases; Cardiovascular Diseases

Study Officials

• Gerhard Pichler, MD

  Medical University of Graz

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: CROSS SECTIONAL
• Target Duration: 1 Day
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: March 31, 2014
• First Posted: April 7, 2014
• Study Start: November 1, 2013
• Primary Completion: January 25, 2016
• Study Completion: January 18, 2017
• Last Updated: July 17, 2018

Record last verified: 2018-07

Locations

AU (1)