Boosting Phonocardiogram Classification Performance with Function Generated Data

Naoki Nonaka, Hiroshi Seki, Tomohiro Komatsu, Jun Seita
Proceedings of the Fifth Machine Learning for Health Symposium, PMLR 297:473-524, 2026.

Abstract

Deep neural networks require large datasets, yet medical phonocardiogram ({PCG}) data are scarce due to privacy and disease rarity. To address this challenge in {PCG} analysis, we present a function-generated {PCG} pipeline that synthesizes {S1}/{S2} heart sounds with modulated noise to emulate aortic stenosis ({AS}), aortic regurgitation ({AR}), and mitral regurgitation ({MR}). Across eight architectures, we compare real-only training, synthetic-only, and synthetic pretraining followed by real fine-tuning ({Syn}$\to${Real}). {Syn}$\to${Real} consistently improves {AUROC} with average gains of +15.3% ({AS}), +17.0% ({AR}), +17.1% ({MR}) on {BMD-HS}, and +7.1%, +8.8%, +6.1% on a private cohort (8,564 recordings). Furthermore, we show {Syn}$\to${Real} is competitive with pretraining on out-of-domain real data, and combining it with multi-stage real fine-tuning yields the best overall performance, highlighting the complementary value of synthetic and real {PCG}s. While synthetic-only training generalizes poorly, pretraining on function-generated {PCG}s consistently improves {PCG} classification over training from scratch, offering a practical path to mitigate data-collection burdens and potentially reduce privacy and ethical exposure.

Cite this Paper

BibTeX
@InProceedings{pmlr-v297-nonaka26a, title = {Boosting Phonocardiogram Classification Performance with Function Generated Data}, author = {Nonaka, Naoki and Seki, Hiroshi and Komatsu, Tomohiro and Seita, Jun}, booktitle = {Proceedings of the Fifth Machine Learning for Health Symposium}, pages = {473--524}, year = {2026}, editor = {Argaw, Peniel and Zhang, Haoran and Jabbour, Sarah and Chandak, Payal and Ji, Jerry and Mukherjee, Sumit and Salaudeen, Olawale and Chang, Trenton and Healey, Elizabeth and Gröger, Fabian and Adibi, Amin and Hegselmann, Stefan and Wild, Benjamin and Noori, Ayush}, volume = {297}, series = {Proceedings of Machine Learning Research}, month = {13--14 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v297/main/assets/nonaka26a/nonaka26a.pdf}, url = {https://proceedings.mlr.press/v297/nonaka26a.html}, abstract = {Deep neural networks require large datasets, yet medical phonocardiogram ({PCG}) data are scarce due to privacy and disease rarity. To address this challenge in {PCG} analysis, we present a function-generated {PCG} pipeline that synthesizes {S1}/{S2} heart sounds with modulated noise to emulate aortic stenosis ({AS}), aortic regurgitation ({AR}), and mitral regurgitation ({MR}). Across eight architectures, we compare real-only training, synthetic-only, and synthetic pretraining followed by real fine-tuning ({Syn}$\to${Real}). {Syn}$\to${Real} consistently improves {AUROC} with average gains of +15.3% ({AS}), +17.0% ({AR}), +17.1% ({MR}) on {BMD-HS}, and +7.1%, +8.8%, +6.1% on a private cohort (8,564 recordings). Furthermore, we show {Syn}$\to${Real} is competitive with pretraining on out-of-domain real data, and combining it with multi-stage real fine-tuning yields the best overall performance, highlighting the complementary value of synthetic and real {PCG}s. While synthetic-only training generalizes poorly, pretraining on function-generated {PCG}s consistently improves {PCG} classification over training from scratch, offering a practical path to mitigate data-collection burdens and potentially reduce privacy and ethical exposure.} }
Endnote
%0 Conference Paper %T Boosting Phonocardiogram Classification Performance with Function Generated Data %A Naoki Nonaka %A Hiroshi Seki %A Tomohiro Komatsu %A Jun Seita %B Proceedings of the Fifth Machine Learning for Health Symposium %C Proceedings of Machine Learning Research %D 2026 %E Peniel Argaw %E Haoran Zhang %E Sarah Jabbour %E Payal Chandak %E Jerry Ji %E Sumit Mukherjee %E Olawale Salaudeen %E Trenton Chang %E Elizabeth Healey %E Fabian Gröger %E Amin Adibi %E Stefan Hegselmann %E Benjamin Wild %E Ayush Noori %F pmlr-v297-nonaka26a %I PMLR %P 473--524 %U https://proceedings.mlr.press/v297/nonaka26a.html %V 297 %X Deep neural networks require large datasets, yet medical phonocardiogram ({PCG}) data are scarce due to privacy and disease rarity. To address this challenge in {PCG} analysis, we present a function-generated {PCG} pipeline that synthesizes {S1}/{S2} heart sounds with modulated noise to emulate aortic stenosis ({AS}), aortic regurgitation ({AR}), and mitral regurgitation ({MR}). Across eight architectures, we compare real-only training, synthetic-only, and synthetic pretraining followed by real fine-tuning ({Syn}$\to${Real}). {Syn}$\to${Real} consistently improves {AUROC} with average gains of +15.3% ({AS}), +17.0% ({AR}), +17.1% ({MR}) on {BMD-HS}, and +7.1%, +8.8%, +6.1% on a private cohort (8,564 recordings). Furthermore, we show {Syn}$\to${Real} is competitive with pretraining on out-of-domain real data, and combining it with multi-stage real fine-tuning yields the best overall performance, highlighting the complementary value of synthetic and real {PCG}s. While synthetic-only training generalizes poorly, pretraining on function-generated {PCG}s consistently improves {PCG} classification over training from scratch, offering a practical path to mitigate data-collection burdens and potentially reduce privacy and ethical exposure.
APA
Nonaka, N., Seki, H., Komatsu, T. & Seita, J.. (2026). Boosting Phonocardiogram Classification Performance with Function Generated Data. Proceedings of the Fifth Machine Learning for Health Symposium, in Proceedings of Machine Learning Research 297:473-524 Available from https://proceedings.mlr.press/v297/nonaka26a.html.

Related Material