Automated Algorithm Based Analysis of Phonocardiograms of Newborns

Sponsor

CSD Labs GmbH (Other)

Overall Status

Completed

CT.gov ID

NCT02105480

Collaborator

(none)

220

Enrollment

Location

38.6

Actual Duration (Months)

5.7

Patients Per Site Per Month

Study Details

Study Description

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.

Condition or Disease	Intervention/Treatment	Phase
Heart Murmurs Mitral Valve Prolapse Systolic Murmurs	Device: Computer aided auscultation (CAA)

Detailed Description

The following registry procedures and quality factors have been implemented:

Quality assurance plan, including
data validation
proper registration procedures
regular site monitoring
regular auditing
Data checks to compare data entered into the registry against predefined rules for range or consistency with other data fields in the registry.
Source data verification to assess the accuracy, completeness, or representativeness of registry data by comparing the data to external data sources (medical records and paper case report forms).
Standard Operating Procedures to address registry operations and analysis activities, such as patient recruitment, data collection, data management, data analysis, reporting for adverse events, and change management.
Sample size assessment to specify the number of participants or participant years necessary to demonstrate an effect.
Statistical analysis plan describing the analytical principles and statistical techniques to be employed in order to address the primary and secondary objectives, as specified in the study protocol or plan.
Plan for missing data to address situations where variables are reported as missing, unavailable, "non-reported," uninterpretable, or considered missing because of data inconsistency or out-of-range results.

Study Design

Study Type:

Observational [Patient Registry]

Actual Enrollment :

220 participants

Observational Model:

Cohort

Time Perspective:

Cross-Sectional

Official Title:

Automated Algorithm Based Analysis of Phonocardiograms of Newborns

Actual Study Start Date :

Nov 1, 2013

Actual Primary Completion Date :

Jan 25, 2016

Actual Study Completion Date :

Jan 18, 2017

Outcome Measures

Primary Outcome Measures

Number of correctly diagnosed heart murmurs through locked, independent algorithm based auscultation and traditional stethoscope based auscultation by medical experts [2 years (expected)]
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).