ChatPPG.
Join free

Paperdoi:10.2147/NSS.S352335

Obstructive Sleep Apnoea Syndrome Screening Through Wrist-Worn Smartbands: A Machine-Learning Approach

Venue listed2022Added Nov 9, 2026

  • DB
  • UO
  • SB
  • MB
  • MT
  • EB
  • GS
  • UF

Authors: Davide Benedetti, Umberto Olcese, Simone Bruno, Marta Barsotti, Michelangelo Maestri Tassoni, Enrica Bonanni, Gabriele Siciliano, Ugo Faraguna

Nature and Science of Sleep 2022;14:941–956 (published 2022-05-18)

Publisher (opens in a new tab) Cite
Dove Press OA

TL;DR

Supervised ML screens / grades OSAS severity from consumer wrist smartband (Fitbit Charge4 / AltaHR) data against home cardiorespiratory monitoring (CRM) in n=78 sleep-clinic adults. Sleepacta’s platform supplies minute sleep staging via DORMI; six DORMI-derived sleep metrics plus age/sex/BMI and HR features feed paired MLP/RandomForest classifiers at AHI cut-offs 5 / 15 / 30. Authors report performance comparable to STOP-Bang on several metrics, with higher specificity and lower sensitivity at the screening cut-off.

  • Form factor: wrist

Abstract

PurposeA large portion of the adult population is thought to suffer from obstructive sleep apnoea syndrome (OSAS), a sleep-related breathing disorder associated with increased morbidity and mortality. International guidelines include the polysomnography and the cardiorespiratory monitoring (CRM) as diagnostic tools for OSAS, but they are unfit for a large-scale screening, given their invasiveness, high cost and lengthy process of scoring. Current screening methods are based on self-reported questionnaires that suffer from lack of objectivity. On the contrary, commercial smartbands are wearable devices capable of collecting accelerometric and photoplethysmographic data in a user-friendly and objective way. We questioned whether machine-learning (ML) classifiers trained on data collected through these wearable devices would help predict OSAS severity.Patients and methodsEach of the patients (n = 78, mean age ± SD: 57.2 ± 12.9 years; 30 females) underwent CRM and concurrently wore a commercial wrist smartband. CRM's traces were scored, and OSAS severity was reported as apnoea hypopnoea index (AHI). We trained three pairs of classifiers to make the following prediction: AHI ResultsAccording to the Matthews correlation coefficient (MCC), the proposed algorithms reached an overall good correlation with the ground truth (CRM) for AHI ConclusionMachine learning algorithms showed an overall good performance. Unlike questionnaires, these are based on objectively collected data. Furthermore, these commercial devices are widely distributed in the general population. The aforementioned advantages of machine-learning algorithms applied to smartbands' data over questionnaires lead to the conclusion that they could serve a population-scale screening for OSAS.

Verbatim from Europe PMC (opens in a new tab) · Licence: cc by-nc

Results on ChatPPG leaderboards · 1

All leaderboards
LeaderboardMethodResultRank
own-pisa-crm-fitbit-benedetti-2022 mccSleep apnea (OSA) screeningDORMIAPNEA0.4mcc, higher is better#1 of 1

1 row is credited to this paper. Ranks apply within each leaderboard only, as reported by the source.

Tasks & signals

Tasks

Sleep apnea (OSA) screeningSleep stagingSleep apnea

Signals

PPGIMU

Keywords

OsaAHIScreeningFitbitSmartbandSleepactaDORMIDORMIAPNEA

How it works

How Method works: Setup → Method → TargetSetup: Signals (IMU, PPG); Form factor (wrist). Method: Method. Target: Sleep staging; Sleep apnea.SetupSignals: IMU, PPGxyzSignalsIMU, PPGForm factor: wristForm factorwristMethodMethodTargetSleep stagingSleep stagingSleep apneaSleep apnea

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Benedetti, D., Olcese, U., Bruno, S., Barsotti, M., Tassoni, M. M., Bonanni, E., Siciliano, G., & Faraguna, U. (2022). Obstructive Sleep Apnoea Syndrome Screening Through Wrist-Worn Smartbands: A Machine-Learning Approach. Nature and Science of Sleep 2022, 14, 941–956. https://doi.org/10.2147/NSS.S352335
Benedetti, Davide, Umberto Olcese, Simone Bruno, Marta Barsotti, Michelangelo Maestri Tassoni, Enrica Bonanni, Gabriele Siciliano, and Ugo Faraguna. 2022. "Obstructive Sleep Apnoea Syndrome Screening Through Wrist-Worn Smartbands: A Machine-Learning Approach." Nature and Science of Sleep 2022 14: 941–956. https://doi.org/10.2147/NSS.S352335.
Benedetti, D., Olcese, U., Bruno, S., Barsotti, M., Tassoni, M. M., Bonanni, E., Siciliano, G. and Faraguna, U. (2022) 'Obstructive Sleep Apnoea Syndrome Screening Through Wrist-Worn Smartbands: A Machine-Learning Approach', Nature and Science of Sleep 2022, 14, pp. 941–956. doi: 10.2147/NSS.S352335.
Benedetti, Davide, et al. "Obstructive Sleep Apnoea Syndrome Screening Through Wrist-Worn Smartbands: A Machine-Learning Approach." Nature and Science of Sleep 2022, vol. 14, 2022, pp. 941–956. https://doi.org/10.2147/NSS.S352335.
D. Benedetti et al., "Obstructive Sleep Apnoea Syndrome Screening Through Wrist-Worn Smartbands: A Machine-Learning Approach," Nature and Science of Sleep 2022, vol. 14, pp. 941–956, 2022, doi: 10.2147/NSS.S352335.
@article{benedetti2022obstructive,
  title         = {{Obstructive Sleep Apnoea Syndrome Screening Through Wrist-Worn Smartbands: A Machine-Learning Approach}},
  author        = {Benedetti, Davide and Olcese, Umberto and Bruno, Simone and Barsotti, Marta and Tassoni, Michelangelo Maestri and Bonanni, Enrica and Siciliano, Gabriele and Faraguna, Ugo},
  year          = {2022},
  journal       = {Nature and Science of Sleep 2022},
  volume        = {14},
  pages         = {941--956},
  doi           = {10.2147/NSS.S352335}
}

Added to the ChatPPG research hub

Same tasks, data and authors

Papers

Datasets