# Dual Bayesian ResNet: A Deep Learning Approach to Heart Murmur Detection

arXiv: https://arxiv.org/abs/2305.16691 · HTML: https://mlsanity.com/paper/2305.16691/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 14 references that are in the map.
- First posted on arXiv 26 May 2023.

## Builds on (most cited first, 4 of 4)

- [Rethinking CNN Models for Audio Classification](https://mlsanity.com/paper/2007.11154/) (2020)
- [The CirCor DigiScope Dataset: From Murmur Detection to Murmur Classification](https://mlsanity.com/paper/2108.00813/) (2021)
- [Loss-Calibrated Approximate Inference in Bayesian Neural Networks](https://mlsanity.com/paper/1805.03901/) (2018)
- [HumBugDB: A Large-scale Acoustic Mosquito Dataset](https://mlsanity.com/paper/2110.07607/) (2021)

## Built on by (most cited first, 6 of 6)

- [Review of multimodal machine learning approaches in healthcare](https://mlsanity.com/paper/2402.02460/) (2024)
- [Multimodal deep learning approach to predicting neurological recovery from coma after cardiac arrest](https://mlsanity.com/paper/2403.06027/) (2024)
- [A Method for Detecting Murmurous Heart Sounds based on Self-similar Properties](https://mlsanity.com/paper/2306.05283/) (2023)
- [Comprehensive and Reliable Feature Attribution for Diverse Modalities and Models via Frequency-Domain Insights](https://mlsanity.com/paper/2411.18343/) (2024)
- [HD3C: Efficient Medical Data Classification for Edge Devices](https://mlsanity.com/paper/2509.14617/) (2025)
- [SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation](https://mlsanity.com/paper/2510.10719/) (2025)

## Abstract (arXiv)

This study presents our team PathToMyHeart's contribution to the George B. Moody PhysioNet Challenge 2022. Two models are implemented. The first model is a Dual Bayesian ResNet (DBRes), where each patient's recording is segmented into overlapping log mel spectrograms. These undergo two binary classifications: present versus unknown or absent, and unknown versus present or absent. The classifications are aggregated to give a patient's final classification. The second model is the output of DBRes integrated with demographic data and signal features using XGBoost.DBRes achieved our best weighted accuracy of 0.771 on the hidden test set for murmur classification, which placed us fourth for the murmur task. (On the clinical outcome task, which we neglected, we scored 17th with costs of 12637.) On our held-out subset of the training set, integrating the demographic data and signal features improved DBRes's accuracy from 0.762 to 0.820. However, this decreased DBRes's weighted accuracy from 0.780 to 0.749. Our results demonstrate that log mel spectrograms are an effective representation of heart sound recordings, Bayesian networks provide strong supervised classification performance, and treating the ternary classification as two binary classifications increases performance on the weighted accuracy.