EUVIMEDEUVIMED entdecken
Crossref

Three-class obstructive sleep apnea severity assessment: a parallel AHI and ODI explainable artificial intelligence framework using craniofacial-enriched clinical data

Zahra Ameli Mazandarani, Mohammad Behnaz, Hamed AmiriFard, Asghar Ebadifar, Hoori Mirmohammadsadeghi, Kazem Dalaie, Shahab Kavousinejad

Sleep and Breathing · 2026-08 · 30 (4)

DOI: 10.1007/s11325-026-03774-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sleep and Breathing, online erschienen am 30.07.2026. Verfasst von Zahra Ameli Mazandarani und 6 weiteren Autor:innen. Beteiligte Einrichtung: Dentofacial Deformities Research Center, Research Institute of Dental Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran. Hauptthemen laut MEDLINE: Sleep Apnea, Obstructive, Severity of Illness Index, Artificial Intelligence. Die Arbeit nennt 101 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Machine learning models for Obstructive Sleep Apnea (OSA) diagnosis have largely inherited some structural limitations: reliance on generic, opportunistically collected feature sets; use of the Apnea-Hypopnea Index (AHI) as the sole ground truth; poor performance in multi-class severity grading; and predictions that offer clinicians no mechanistic insight. This study addresses these gaps by prospectively assembling a multi-domain dataset that, alongside established demographic, anthropometric, and questionnaire-based predictors, incorporates a panel of craniofacial and intraoral metrics specifically designed to capture the structural-anatomical contributors to OSA — integrating these into an interpretable framework for three-class severity classification evaluated against both AHI and the Oxygen Desaturation Index (ODI).

Methods

In this single-center study, 233 treatment-naïve adults from a tertiary referral cohort (61.8% severe OSA prevalence) underwent in-laboratory polysomnography (PSG). All predictor variables were collected prior to PSG outcome disclosure through a standardized clinical examination, requiring no overnight recording or specialized equipment. An Artificial Neural Network (ANN) was independently trained for three-class severity classification (No/Mild, Moderate, Severe) for each index. Model performance was evaluated on an independent test set ( n = 47; 20% of the sample), with interpretability assessed using SHapley Additive exPlanations (SHAP). Comparison with an anatomy-excluded ablation model was conducted to establish the added value of the full feature set.

Results

The AHI-based model achieved 87.2% overall accuracy (sensitivity/specificity: No/Mild 0.93/0.97, Moderate 0.80/0.91, Severe 0.88/0.93). The ODI-based model achieved 76.6% accuracy, offering reliable exclusion of severe desaturation burden (No/Mild specificity: 0.94). Univariate analyses confirmed significant associations between OSA severity and STOP-BANG score, age, BMI, neck circumference, observed apnea, loud snoring, high blood pressure, Cervico-Mental Angle, Mentocervical Distance, and submental fat (all p ≤ .034 for both indices). SHAP analysis further identified V-shaped maxillary arch, Mallampati score, increased overjet, and alcohol use as influential model predictors — several reaching high model rankings despite modest univariate significance. Notably, AHI and ODI models diverged in their feature weighting — anatomy-driven features dominated AHI prediction while body habitus and comorbidity markers dominated ODI. Against a conventional demographic and questionnaire-based ablation model, the full anatomy-inclusive ANN achieved substantially higher accuracy (87.2% vs. 72.3%), with the largest gain at the Moderate-class boundary (sensitivity: 0.80 vs. 0.58).

Conclusions

As a proof-of-concept, this study demonstrates that an interpretable ML framework integrating craniofacial and intraoral assessments with standard clinical predictors can classify OSA severity across three classes and provide feature-level explanations to support clinical reasoning. By developing parallel AHI and ODI models, the framework moves beyond AHI-only paradigms, though both remain frequency-based surrogates; hypoxic burden — quantifying the cumulative oxygen desaturation load per sleep period — is the more physiologically complete target toward which this line of work should progress. Findings are limited by single-center design, spectrum bias from a tertiary referral cohort, modest sample size, and absence of inter-rater reliability data. External validation in larger, more representative populations is needed to confirm the robustness and clinical utility of this approach.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Sleep Apnea, ObstructiveSeverity of Illness IndexArtificial IntelligenceHumansPolysomnographyFemaleMaleMiddle AgedAdultMachine LearningCephalometryNeural Networks, Computer

Stichwörter der Autor:innen

Artificial intelligenceCraniofacial phenotypingMachine learningObstructive sleep apneaOrthodonticsSeverity classificatio

Autor:innen und Institutionen

  • Dentofacial Deformities Research Center, Research Institute of Dental Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
  • Department of Orthodontics, School of Dentistry, Shahid Beheshti University of Medical Sciences, Daneshjou Blvd, Evin, Tehran, Tehran, 1983969411, Iran.
  • Iranian Center of Neurological Research, Neuroscience Institute, Tehran University of Medical Sciences, Tehran, Iran.
  • Dentofacial Deformities Research Center, Research Institute of Dental Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran. dr.shahab.k93@gmail.com.
  • Department of Orthodontics, School of Dentistry, Shahid Beheshti University of Medical Sciences, Daneshjou Blvd, Evin, Tehran, Tehran, 1983969411, Iran. dr.shahab.k93@gmail.com.

Zitieren

APA

Ameli Mazandarani, Z., Behnaz, M., AmiriFard, H., Ebadifar, A., Mirmohammadsadeghi, H., Dalaie, K., & Kavousinejad, S. (2026). Three-class obstructive sleep apnea severity assessment: a parallel AHI and ODI explainable artificial intelligence framework using craniofacial-enriched clinical data. Sleep and Breathing, 30(4). https://doi.org/10.1007/s11325-026-03774-0

Vancouver

Ameli Mazandarani Z, Behnaz M, AmiriFard H, Ebadifar A, Mirmohammadsadeghi H, Dalaie K, et al. Three-class obstructive sleep apnea severity assessment: a parallel AHI and ODI explainable artificial intelligence framework using craniofacial-enriched clinical data. Sleep and Breathing. 2026;30(4). doi:10.1007/s11325-026-03774-0

BibTeX
@article{AmeliMazandarani2026,
  author = {Ameli Mazandarani, Zahra and Behnaz, Mohammad and AmiriFard, Hamed and Ebadifar, Asghar and Mirmohammadsadeghi, Hoori and Dalaie, Kazem and Kavousinejad, Shahab},
  title = {Three-class obstructive sleep apnea severity assessment: a parallel AHI and ODI explainable artificial intelligence framework using craniofacial-enriched clinical data},
  journal = {Sleep and Breathing},
  year = {2026},
  volume = {30},
  number = {4},
  doi = {10.1007/s11325-026-03774-0}
}
Kostenlos starten →