Oriel — AI & technology worth noticing, every day.

Towards Automatic Heart Murmur Characterization from Multi-spot Phonocardiograms

Paper · https://arxiv.org/abs/2611.03654

arXiv:2611.03654v1 Announce Type: new Abstract: Cardiac auscultation traditionally detects the presence of a heart murmur, but clinicians further characterize it by timing, shape, pitch, quality, and grade. Most automatic phonocardiogram analysis systems stop at binary detection and do not estimate this richer description. In this work, we formulate automatic murmur characterization as five patient-level classification tasks and compare three multi-spot strategies on recordings from the aortic, pulmonary, mitral, and tricuspid auscultation locations. First, classical and deep-learning classifiers are trained independently at each location, and predictions are combined via a maximum-severity late-fusion rule. Second, a synchronous multi-input CNN jointly processes one representative segment per location for a single task. Third, a unified multi-input, multi-output CNN predicts all five attributes from one shared multi-spot representation. Using 735 patients from the CirCor DigiScope dataset with complete four-spot recordings, the best late-fusion configurations reach an unweighted mean sensitivity between 85.56% and 93.81% across the five tasks, with class-specific recalls between 80.00% and 100.00% for every relevant category. The multi-input CNN trails late fusion by 7-16 points depending on the task, while the multi-output model reaches values between 72.59% and 79.40%, estimating all five attributes from one shared representation. We further show that naively balancing training data by adding all minority-class segments degrades patient-level performance under the maximum-severity rule, since it introduces non-representative, noisy segments not filtered by the clustering-based segment selection used for evaluation. These results indicate multi-spot murmur characterization is feasible with both fusion-based and jointly learned architectures, outlining a path toward automatic, structured murmur reports complementing binary screening.

First seen by Oriel on .

AI summary

The study evaluates three multi-spot phonocardiogram strategies for automatically classifying five heart-murmur attributes, finding late fusion performs best across 735 patients.

  • The tasks characterize murmur timing, shape, pitch, quality, and grade at the patient level using aortic, pulmonary, mitral, and tricuspid recordings.
  • Late fusion combines independently trained location-specific classifiers using a maximum-severity rule and achieves 85.56%–93.81% unweighted mean sensitivity.
  • A synchronous multi-input CNN trails late fusion by 7–16 points depending on the task, while the multi-output CNN reaches 72.59%–79.40%.
  • Class-specific recalls range from 80.00% to 100.00% for every relevant category in the best late-fusion configurations.
  • Adding all minority-class segments for naive training-data balancing reduces patient-level performance by introducing non-representative, noisy segments.

#phonocardiograms #heart murmurs #deep learning #medical classification

Generated by gpt-5.6-sol. Check the original for details.

Aliases

SourceExternal IDURL
arXiv AI Papersoai:arXiv.org:2611.03654v1https://arxiv.org/abs/2611.03654 Read discussion