Beyond AHI: An Interpretable Causal-Discovery-Guided Framework for Sleep Recovery in Connected Health
Abstract
Objective sleep assessment relies on polysomnography (PSG), yet clinical impact is often better reflected in patient-reported outcomes (PROs) such as sleepiness and fatigue. Existing summary indices, including the Apnea-Hypopnea Index (AHI), provide limited insight into the multidomain physiology underlying functional recovery. We propose an interpretable, causal-discovery-guided framework for deriving a hierarchical Sleep Recovery Score (SRS) from multimodal PSG. Using two large population cohorts (MESA: n=1,540; MrOS: n=825), we apply directed acyclic graph (DAG) learning to identify candidate physiological drivers spanning respiratory burden, hypoxic burden, sleep fragmentation, sleep architecture, and autonomic regulation. Although derived from clinical PSG, these domains map naturally to sensing streams increasingly available in connected health technologies, including wearable ECG, oximetry, and sleep-stage estimation devices. To preserve mechanistic plausibility, we introduce a two-stage screening process that combines physiology-based constraints with constrained LLM-assisted auditing to identify and remove structural confounders and construct-overlapping variables. Across cohorts, these five domains emerge as recurrent physiological domains associated with recovery, and the resulting SRS shows up to 3.4× stronger alignment with perceived recovery than AHI. By linking multimodal sleep physiology to patient-centered outcomes through an interpretable, bias-aware, and domain-structured framework, this work provides a practical foundation for recovery modeling across both clinical sleep studies and emerging smart and connected health settings.
Related
- Interpretable Causal Discovery via Causal-Effect Constraints
- Interpretable Feature Discovery from Unstructured Data Using LLMs and Statistical Choice Models
- Equation discovery for climate impact: emulating impact models for unexplored climate scenario with interpretable symbolic regression
- Beyond χ2: Ensemble null tests for reliable scientific discovery
- Causal Discovery beyond Conditional Independence: Identifiability, Algorithms, and Statistical Inference for Directed Acyclic and Cyclic Graphs
BibTeX
@misc{farahani2026beyond,
title = {{Beyond AHI: An Interpretable Causal-Discovery-Guided Framework for Sleep Recovery in Connected Health}},
author = {Saba A. Farahani and Elahe Khatibi and Manoj Vishwanath and Amir M. Rahmani and Hung Cao},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2606.18506},
eprint = {2606.18506},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.18506},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Beyond AHI: An Interpretable Causal-Discovery-Guided Framework for Sleep Recovery in Connected Health
AU - Saba A. Farahani
AU - Elahe Khatibi
AU - Manoj Vishwanath
AU - Amir M. Rahmani
AU - Hung Cao
PY - 2026
DA - 2026/08/31
PB - arXiv
DO - 10.48550/arxiv.2606.18506
UR - https://arxiv.org/abs/2606.18506
AB - Objective sleep assessment relies on polysomnography (PSG), yet clinical impact is often better reflected in patient-reported outcomes (PROs) such as sleepiness and fatigue. Existing summary indices, including the Apnea-Hypopnea Index (AHI), provide limited insight into the multidomain physiology underlying functional recovery. We propose an interpretable, causal-discovery-guided framework for deriving a hierarchical Sleep Recovery Score (SRS) from multimodal PSG. Using two large population cohorts (MESA: n=1,540; MrOS: n=825), we apply directed acyclic graph (DAG) learning to identify candidate physiological drivers spanning respiratory burden, hypoxic burden, sleep fragmentation, sleep architecture, and autonomic regulation. Although derived from clinical PSG, these domains map naturally to sensing streams increasingly available in connected health technologies, including wearable ECG, oximetry, and sleep-stage estimation devices. To preserve mechanistic plausibility, we introduce a two-stage screening process that combines physiology-based constraints with constrained LLM-assisted auditing to identify and remove structural confounders and construct-overlapping variables. Across cohorts, these five domains emerge as recurrent physiological domains associated with recovery, and the resulting SRS shows up to 3.4× stronger alignment with perceived recovery than AHI. By linking multimodal sleep physiology to patient-centered outcomes through an interpretable, bias-aware, and domain-structured framework, this work provides a practical foundation for recovery modeling across both clinical sleep studies and emerging smart and connected health settings.
ER -