Uncovering Trajectory and Topological Signatures in Multimodal Pediatric Sleep Embeddings

Scott Ye, Harlin Lee
Proceedings of the Fifth Machine Learning for Health Symposium, PMLR 297:1392-1411, 2026.

Abstract

While generative models have shown promise in pediatric sleep analysis, the latent structure of their multimodal embeddings remains poorly understood. This work investigates session-wide diagnostic information contained in the sequences of 30-second pediatric {PSG} epochs embedded by a multimodal masked autoencoder. We test whether augmenting embeddings with (i) {PHATE}-derived per-epoch coordinates and whole-night movement descriptors, (ii) persistent homology summaries of the embedding cloud, and (iii) {EHR} yields task-relevant signals. Simple linear and {MLP} models, chosen for interpretability rather than state-of-the-art performance, show that geometric, topological, and clinical features each provide complementary gains. For binary predictions, feature importance is task-dependent, and more expressive late-fusion models generally perform better, with {AUPRC} improving 0.26$\rightarrow$0.34 for desaturation, 0.31$\rightarrow$0.48 for {EEG} arousal, 0.09$\rightarrow$0.22 for hypopnea, and 0.05$\rightarrow$0.14 for apnea. We also report Brier score and Expected Calibration Error, where the full fusion model yields the best calibration across all four binary tasks. Our study reveals that latent geometry/topology and {EHR} offer complementary, interpretable signals beyond embeddings, improving calibration and robustness under extreme imbalance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v297-ye26a, title = {Uncovering Trajectory and Topological Signatures in Multimodal Pediatric Sleep Embeddings}, author = {Ye, Scott and Lee, Harlin}, booktitle = {Proceedings of the Fifth Machine Learning for Health Symposium}, pages = {1392--1411}, 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/ye26a/ye26a.pdf}, url = {https://proceedings.mlr.press/v297/ye26a.html}, abstract = {While generative models have shown promise in pediatric sleep analysis, the latent structure of their multimodal embeddings remains poorly understood. This work investigates session-wide diagnostic information contained in the sequences of 30-second pediatric {PSG} epochs embedded by a multimodal masked autoencoder. We test whether augmenting embeddings with (i) {PHATE}-derived per-epoch coordinates and whole-night movement descriptors, (ii) persistent homology summaries of the embedding cloud, and (iii) {EHR} yields task-relevant signals. Simple linear and {MLP} models, chosen for interpretability rather than state-of-the-art performance, show that geometric, topological, and clinical features each provide complementary gains. For binary predictions, feature importance is task-dependent, and more expressive late-fusion models generally perform better, with {AUPRC} improving 0.26$\rightarrow$0.34 for desaturation, 0.31$\rightarrow$0.48 for {EEG} arousal, 0.09$\rightarrow$0.22 for hypopnea, and 0.05$\rightarrow$0.14 for apnea. We also report Brier score and Expected Calibration Error, where the full fusion model yields the best calibration across all four binary tasks. Our study reveals that latent geometry/topology and {EHR} offer complementary, interpretable signals beyond embeddings, improving calibration and robustness under extreme imbalance.} }
Endnote
%0 Conference Paper %T Uncovering Trajectory and Topological Signatures in Multimodal Pediatric Sleep Embeddings %A Scott Ye %A Harlin Lee %B Proceedings of the Fifth Machine Learning for Health Symposium %C Proceedings of Machine Learning Research %D 2026 %E Peniel Argaw %E Haoran Zhang %E Sarah Jabbour %E Payal Chandak %E Jerry Ji %E Sumit Mukherjee %E Olawale Salaudeen %E Trenton Chang %E Elizabeth Healey %E Fabian Gröger %E Amin Adibi %E Stefan Hegselmann %E Benjamin Wild %E Ayush Noori %F pmlr-v297-ye26a %I PMLR %P 1392--1411 %U https://proceedings.mlr.press/v297/ye26a.html %V 297 %X While generative models have shown promise in pediatric sleep analysis, the latent structure of their multimodal embeddings remains poorly understood. This work investigates session-wide diagnostic information contained in the sequences of 30-second pediatric {PSG} epochs embedded by a multimodal masked autoencoder. We test whether augmenting embeddings with (i) {PHATE}-derived per-epoch coordinates and whole-night movement descriptors, (ii) persistent homology summaries of the embedding cloud, and (iii) {EHR} yields task-relevant signals. Simple linear and {MLP} models, chosen for interpretability rather than state-of-the-art performance, show that geometric, topological, and clinical features each provide complementary gains. For binary predictions, feature importance is task-dependent, and more expressive late-fusion models generally perform better, with {AUPRC} improving 0.26$\rightarrow$0.34 for desaturation, 0.31$\rightarrow$0.48 for {EEG} arousal, 0.09$\rightarrow$0.22 for hypopnea, and 0.05$\rightarrow$0.14 for apnea. We also report Brier score and Expected Calibration Error, where the full fusion model yields the best calibration across all four binary tasks. Our study reveals that latent geometry/topology and {EHR} offer complementary, interpretable signals beyond embeddings, improving calibration and robustness under extreme imbalance.
APA
Ye, S. & Lee, H.. (2026). Uncovering Trajectory and Topological Signatures in Multimodal Pediatric Sleep Embeddings. Proceedings of the Fifth Machine Learning for Health Symposium, in Proceedings of Machine Learning Research 297:1392-1411 Available from https://proceedings.mlr.press/v297/ye26a.html.

Related Material