Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Prediction formulae for sleep-disordered breathing.

S M Harding1

  • 1Division of Pulmonary, Allergy, and Critical Care Medicine, University of Alabama at Birmingham, Medical Director, UAB Sleep-Wake Disorders Center, Birmingham, Alabama 35294, USA. sharding@uab.edu

Current Opinion in Pulmonary Medicine
|November 14, 2001
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Review article: reflux and its consequences--the laryngeal, pulmonary and oesophageal manifestations. Conference held in conjunction with the 9th International Symposium on Human Pepsin (ISHP) Kingston-upon-Hull, UK, 21-23 April 2010.

Alimentary pharmacology & therapeutics·2011
Same author

Spironolactone reduces severity of obstructive sleep apnoea in patients with resistant hypertension: a preliminary report.

Journal of human hypertension·2009
Same author

Pharmacokinetics of ceftazidime in normal subjects.

The Journal of antimicrobial chemotherapy·2009
Same author

The comparative pharmacokinetics of ceftazidime and cefotaxime in healthy volunteers.

The Journal of antimicrobial chemotherapy·2009
Same author

The penetration of ceftazidime into extravascular fluid.

The Journal of antimicrobial chemotherapy·2009
Same author

Using saline solutions for ACE washouts.

Archives of disease in childhood·2007
Same journal

Nonsteroid treatment options in (pulmonary) sarcoidosis. When to consider and why?

Current opinion in pulmonary medicine·2026
Same journal

Multidisciplinary approach in cardiac sarcoidosis: to biopsy or not?

Current opinion in pulmonary medicine·2026
Same journal

Low diffusion capacity in pulmonary hypertension.

Current opinion in pulmonary medicine·2026
Same journal

Toward precision imaging in interstitial lung disease: advances in quantitative imaging and artificial intelligence.

Current opinion in pulmonary medicine·2026
Same journal

Oxygen therapy in interstitial lung disease - navigating benefit and burden.

Current opinion in pulmonary medicine·2026
Same journal

Preclinical and clinical advances in pulmonary hypertension associated with systemic sclerosis.

Current opinion in pulmonary medicine·2026
See all related articles

Prediction formulas help identify patients with sleep-disordered breathing. A regression neural network showed high accuracy, improving diagnosis and testing prioritization for conditions like obstructive sleep apnea.

Area of Science:

  • Medical Diagnostics
  • Respiratory Medicine
  • Machine Learning in Healthcare

Background:

  • Prediction formulas for sleep-disordered breathing (SDB) aid in diagnosis exclusion, probability assessment, and test prioritization.
  • Existing models often exhibit high sensitivity but low specificity, impacting clinical utility.
  • The Berlin Questionnaire has demonstrated effectiveness in primary care for identifying high-risk individuals.

Purpose of the Study:

  • To evaluate the performance of various prediction models for sleep-disordered breathing.
  • To identify accurate diagnostic tools for conditions like obstructive sleep apnea (OSA).
  • To explore risk factors for central sleep apnea in specific patient populations.

Main Methods:

  • Analysis of four previously described prediction models for SDB.

Related Experiment Videos

  • Evaluation of the Berlin Questionnaire in primary care settings.
  • Assessment of a regression neural network and a regression model for OSA prediction.
  • Identification of risk factors for central sleep apnea in congestive heart failure patients.
  • Examination of risk factors and racial anthropomorphic differences in pediatric and adult OSA patients.

    • Main Results:

    • Previous models showed sensitivities from 76%–96% and specificities from 13%–54%.
    • A regression neural network achieved 99% sensitivity, 80% specificity, 88% positive predictive value, and 98% negative predictive value.
    • Specific regression models effectively excluded OSA in obese snorers and identified central sleep apnea risk factors in heart failure patients.
    • Risk factors for sleep apnea in children include obesity, African-American race, sinus issues, and wheezing.

    Conclusions:

    • Prediction models are valuable for SDB diagnosis, particularly when refined.
    • Regression neural networks offer high accuracy for diagnosing sleep-disordered breathing.
    • Understanding specific risk factors in diverse populations (e.g., heart failure patients, children, different races) is crucial for accurate diagnosis and management of sleep apnea.