CoChat
Sign Up
Cited by 99Obstructive Sleep Apnea ResearchArtificial Intelligence in HealthcareSleep and related disorders

Clinical Prediction Models for Sleep Apnea: The Importance of Medical History over Symptoms

Open access
Ustun, Berk, Westover, M. Brandon, Rudin, Cynthia, Bianchi, Matt T.·2016·Journal of Clinical Sleep Medicine
DOI 10.5664/jcsm.5476PMC PMC4751423
Open this paper in CoChat — free accountOpen PDF

Abstract

Study objective Obstructive sleep apnea (OSA) is a treatable contributor to morbidity and mortality. However, most patients with OSA remain undiagnosed. We used a new machine learning method known as SLIM (Supersparse Linear Integer Models) to test the hypothesis that a diagnostic screening tool based on routinely available medical information would be superior to one based solely on patient-reported sleep-related symptoms.Methods We analyzed polysomnography (PSG) and self-reported clinical information from 1,922 patients tested in our clinical sleep laboratory. We used SLIM and 7 state-of-the-art classification methods to produce predictive models for OSA screening using features from: (i) self-reported symptoms; (ii) self-reported medical information that could, in principle, be extracted from electronic health records (demographics, comorbidities), or (iii) both.Results For diagnosing OSA, we found that model performance using only medical history features was superior to model performance using symptoms alone, and similar to model performance using all features. Performance was similar to that reported for other widely used tools: sensitivity 64.2% and specificity 77%. SLIM accuracy was similar to state-of-the-art classification models applied to this dataset, but with the benefit of full transparency, allowing for hands-on prediction using yes/no answers to a small number of clinical queries.Conclusion To predict OSA, variables such as age, sex, BMI, and medical history are superior to the symptom variables we examined for predicting OSA. SLIM produces an actionable clinical tool that can be applied to data that is routinely available in modern electronic health records, which may facilitate automated, rather than manual, OSA screening.Commentary A commentary on this article appears in this issue on page 159.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.5664/jcsm.5476

Cites

36 of 36 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • In general, increasing frequency of each symptom occurs with increasing AHI and OSA severity.

    “In general, increasing frequency of each symptom occurs with increasing AHI and OSA severity.”

    From International Consensus Statement on Obstructive Sleep Apnea (2023) · cites this paper as [505]

    The Clinical Implications section says symptom–severity dissociation is prominent in OSA patients, contrary to the claimed general increase in symptoms with severity. The Database section also says the questionnaire did not measure symptom frequency and the analysis did not subdivide OSA by severity category. Page numbers are unavailable in our copy. (LLM, conf=0.85)

    Checked by a reasoning model — may be wrong.

    Experimental — accuracy not yet measured

  • Among individuals diagnosed with OSA, 38%-80% report snoring, 10%-67% report witnessed apneas, and 32%-40% report excessive daytime sleepiness (ESS ≥ 11).

    “Among individuals diagnosed with OSA, 38%–80% report snoring, 10%–67% report witnessed apneas, and 32%–40% report excessive daytime sleepiness (ESS ≥ 11).”

    From International Consensus Statement on Obstructive Sleep Apnea (2023) · cites this paper as [505]

    The Results (page not available in our copy) report that patients with OSA more often reported snoring and witnessed apneas than patients without OSA. The Introduction also discusses sleepiness as an OSA symptom, but the passages found do not give the claimed 38%–80%, 10%–67%, or 32%–40% ranges or an ESS ≥ 11 threshold. (LLM, conf=0.78)

    Experimental — accuracy not yet measured

  • Findings from population-based and retrospective studies have demonstrated that habitual snoring and witnessed apneas are predictors for OSA.

    “Findings from several population-based and retrospective studies have demonstrated that habitual snoring and witnessed apneas are predictors for OSA.”

    From International Consensus Statement on Obstructive Sleep Apnea (2023) · cites this paper as [505]

    The Results (page not provided) report that patients with OSA more often reported snoring and witnessed apneas, supporting an association with OSA. But the Database section says the questionnaire did not measure snoring frequency, and the study examined a referred sleep-laboratory cohort—not several population-based and retrospective studies. The Introduction also cautions that classic symptoms are not strongly predictive. (LLM, conf=0.87)

    Experimental — accuracy not yet measured

  • Anthropometric and other objective variables such as age, sex, body mass index, neck circumference and co-morbidities may be more reliable than subjective variables such as snoring and excessive daytime sleepiness in predicting obstructive sleep apnea.

    “Anthropometric and other objective variables such as age, sex, body mass index (BMI), neck circumference and co‐morbidities may be more reliable than subjective variables such as snoring and EDS in predicting OSA (Ustun et al., 2016).”

    From Obstructive sleep apnea: transition from pathophysiology to an integrative disease model (2022) · cites this paper as Ustun et al., 2016

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

1 of the 37 references couldn’t be matched to a known paper.

Research works printed but not linked: 2

  1. [23]23. Somers VK, White DP, Amin R, et al. Sleep apnea and cardiovascular disease: an American Heart Association/American College of Cardiology Foundation Scientific Statement from the American Heart Association Council for High Blood Pressure Research Professional Education Committee, Council on Clinical Cardiology, Stroke Council, and Council On Cardiovascular Nursing. In collaboration with the National Heart, Lung, and Blood Institute National Center on Sleep Disorders Research (National Institutes of Health). Circulation 2008;118:1080-111.
  2. [30]30. Levendowski D, Olmstead R, Popovic D, Carper DL, Berka C, Westbrook P. Assessment of obstructive sleep apnea risk and severity in truck drivers: validation of a screening questionnaire. Sleep Diagn Ther 2007;2:20-6.

Cited by

Sorted by citations

Related

Authors
Ustun, B., Westover, M. B., Rudin, C., & Bianchi, M. T.
Affiliations
  • Massachusetts Institute of Technology (US)
  • Massachusetts General Hospital (US)
  • Harvard University (US)
ORCID
Venue
Journal of Clinical Sleep Medicine
Publisher
Springer Science and Business Media LLC
Published
2016-02-15
Volume
12
Issue
2
Pages
161-168
ISSN
  • 1550-9389 (ISSN-L)
  • 1550-9397
DOI
10.5664/jcsm.5476
PMC
PMC4751423
OpenAlex
W2396120831
Semantic Scholar
e70a1dcb580773f20133e974dc47a8e7b4b7d59a
Cited by
99
References
37
Citations by year
2026: 4 · 2025: 5 · 2024: 9 · 2023: 10 · 2022: 19 · 2021: 11 · 2020: 11 · 2019: 4 · 2018: 10 · 2017: 9 · 2016: 4 · 2015: 3
FWCI
7.24
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal of Clinical Sleep Medicine (publishedVersion)
  • Europe PMC (PubMed Central) (publishedVersion)
  • PubMed Central (publishedVersion)
  • PubMed (publishedVersion)
  • eScholarship (California Digital Library) (submittedVersion)
Funders
National Institute of Neurological Disorders and Stroke (K23NS090900)
Topics
  • Health Sciences › Medicine › Physiology › Obstructive Sleep Apnea Research
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Sleep and related disorders
Keywords
obstructive sleep apnea, OSA screening, clinical prediction model, medical history, sleep symptoms, electronic health records, polysomnography, automated screening, model interpretability
MeSH terms
Adult, Decision Support Techniques, Female, Humans, Male, Medical History Taking, Middle Aged, Sensitivity and Specificity, Reproducibility of Results, Models, Statistical, Polysomnography, Sleep Apnea, Obstructive, Self Report

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review