lancet-header

Preprints with The Lancet is part of SSRN´s First Look, a place where journals identify content of interest prior to publication. Authors have opted in at submission to The Lancet family of journals to post their preprints on Preprints with The Lancet. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early stage research papers that have not been peer-reviewed. The findings should not be used for clinical or public health decision making and should not be presented to a lay audience without highlighting that they are preliminary and have not been peer-reviewed. For more information on this collaboration, see the comments published in The Lancet about the trial period, and our decision to make this a permanent offering, or visit The Lancet´s FAQ page, and for any feedback please contact preprints@lancet.com.

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

26 Pages Posted: 21 Oct 2021

See all articles by Davide Benedetti

Davide Benedetti

University of Pisa - Department of Translational Research and of New Surgical and Medical Technologies

Umberto Olcese

University of Amsterdam - Cognitive and Systems Neuroscience Group

Simone Bruno

University of Pisa - Department of Translational Research and of New Surgical and Medical Technologies

Marta Barsotti

University Hospital of Pisa - Neurological Clinics

Michelangelo Maestri Tassoni

University Hospital of Pisa - Neurological Clinics

Enrica Bonanni

University Hospital of Pisa - Neurological Clinics

Gabriele Siciliano

University Hospital of Pisa - Neurological Clinics

Ugo Faraguna

University of Pisa - Department of Translational Research and of New Surgical and Medical Technologies

More...

Abstract

Background. A large portion of the adult population is thought to suffer from Obstructive Sleep Apnoea Syndrome (OSAS). Screening the general population for this syndrome is therefore crucial since this pathology has been associated with increased morbidity and mortality. However, current screening methods are based on questionnaires that intrinsically lack of objectivity. On the other hand, wrist-worn smartbands are non-invasive and economically convenient devices, which allow for prolonged monitoring of physiological parameters.

Methods. We used accelerometric and photoplethysmographic data collected via commercial smartbands to train a machine-learning (ML) classifier assessing the presence and severity of OSAS. Each of the 78 patients who participated in this study underwent cardiorespiratory monitoring (CRM), a diagnostic method used to assess OSAS and its severity according to the Apnoea-Hypopnoea Index (AHI).

Findings. According to the Matthews Correlation Coefficients (MCC), the proposed algorithms reached an overall good correlation with the ground truth (CRM) for AHI<5 vs AHI≥5 (MCC: 0.4) and AHI<30 vs AHI≥30 (MCC: 0.3) classifications. AHI<5 vs AHI≥5 and AHI<30 vs AHI≥30 classifiers’ sensitivity, specificity, positive predictive values (PPV), negative predictive values (NPV) and diagnostic odds ratio (DOR) are in line with the ones of the STOP-Bang questionnaire, a OSAS screening tool widely adopted in the clinical practise.

Interpretation. The consumer accelerometric and photoplethysmographic data, continuously collected and stored, could guide OSAS large scale screening also in a retroactive way, ideally triggering an alert for those users in need of further diagnostic investigation of the risk of OSAS.Funding. Arpa Foundation.

Declaration of Interest: Ugo Faraguna and Umberto Olcese are co-founders of sleepActa S.r.l, a spin-off company of the University of Pisa operating in the field of sleep medicine. All other
authors declare no competing interests.

Ethical Approval: This study was approved by the Pisa University Hospital Bioethical Committee
(CEAVNO protocol No: 42714). Participants provided written informed consent to take
part in the study.

Keywords: artificial intelligence, Machine-Learning, Screening, Wearable devices, Smartbands, Sleep Apnoea, OSAS, Sleep Medicine

Suggested Citation

Benedetti, Davide and Olcese, Umberto and Bruno, Simone and Barsotti, Marta and Maestri Tassoni, Michelangelo and Bonanni, Enrica and Siciliano, Gabriele and Faraguna, Ugo, Obstructive Sleep Apnoea Syndrome Screening Through Wrist-Worn Smartbands: A Machine-Learning Approach. Available at SSRN: https://ssrn.com/abstract=3946986 or http://dx.doi.org/10.2139/ssrn.3946986

Davide Benedetti

University of Pisa - Department of Translational Research and of New Surgical and Medical Technologies ( email )

Pisa
Italy

Umberto Olcese

University of Amsterdam - Cognitive and Systems Neuroscience Group ( email )

Amsterdam
Netherlands

Simone Bruno

University of Pisa - Department of Translational Research and of New Surgical and Medical Technologies ( email )

Pisa
Italy

Marta Barsotti

University Hospital of Pisa - Neurological Clinics ( email )

Pisa
Italy

Michelangelo Maestri Tassoni

University Hospital of Pisa - Neurological Clinics ( email )

Pisa
Italy

Enrica Bonanni

University Hospital of Pisa - Neurological Clinics ( email )

Pisa
Italy

Gabriele Siciliano

University Hospital of Pisa - Neurological Clinics ( email )

Pisa
Italy

Ugo Faraguna (Contact Author)

University of Pisa - Department of Translational Research and of New Surgical and Medical Technologies ( email )

Pisa
Italy