Point-of-care prediction model of loop gain in patients with obstructive sleep apnea: development and validation.
Clinical decision rules
Precision medicine
Respiration
Sleep apnea, obstructive
Journal
BMC pulmonary medicine
ISSN: 1471-2466
Titre abrégé: BMC Pulm Med
Pays: England
ID NLM: 100968563
Informations de publication
Date de publication:
25 Apr 2022
25 Apr 2022
Historique:
received:
12
01
2022
accepted:
13
04
2022
entrez:
26
4
2022
pubmed:
27
4
2022
medline:
28
4
2022
Statut:
epublish
Résumé
High loop gain (unstable ventilatory control) is an important-but difficult to measure-contributor to obstructive sleep apnea (OSA) pathogenesis, predicting OSA sequelae and/or treatment response. Our objective was to develop and validate a clinical prediction tool of loop gain. A retrospective cohort of consecutive adults with OSA (apnea-hypopnea index, AHI > 5/hour) based on in-laboratory polysomnography 01/2017-12/2018 was randomly split into a training and test-set (3:1-ratio). Using a customized algorithm ("reference standard") loop gain was quantified from raw polysomnography signals on a continuous scale and additionally dichotomized (high > 0.7). Candidate predictors included general patient characteristics and routine polysomnography data. The model was developed (training-set) using linear regression with backward selection (tenfold cross-validated mean square errors); the predicted loop gain of the final linear regression model was used to predict loop gain class. More complex, alternative models including lasso regression or random forests were considered but did not meet pre-specified superiority-criteria. Final model performance was validated on the test-set. The total cohort included 1055 patients (33% high loop gain). Based on the final model, higher AHI (beta = 0.0016; P < .001) and lower hypopnea-percentage (beta = -0.0019; P < .001) predicted higher loop gain values. The predicted loop gain showed moderate-to-high correlation with the reference loop gain (r = 0.48; 95% CI 0.38-0.57) and moderate discrimination of patients with high versus low loop gain (area under the curve = 0.73; 95% CI 0.67-0.80). To our knowledge this is the first prediction model of loop gain based on readily-available clinical data, which may facilitate retrospective analyses of existing datasets, better patient selection for clinical trials and eventually clinical practice.
Sections du résumé
BACKGROUND
BACKGROUND
High loop gain (unstable ventilatory control) is an important-but difficult to measure-contributor to obstructive sleep apnea (OSA) pathogenesis, predicting OSA sequelae and/or treatment response. Our objective was to develop and validate a clinical prediction tool of loop gain.
METHODS
METHODS
A retrospective cohort of consecutive adults with OSA (apnea-hypopnea index, AHI > 5/hour) based on in-laboratory polysomnography 01/2017-12/2018 was randomly split into a training and test-set (3:1-ratio). Using a customized algorithm ("reference standard") loop gain was quantified from raw polysomnography signals on a continuous scale and additionally dichotomized (high > 0.7). Candidate predictors included general patient characteristics and routine polysomnography data. The model was developed (training-set) using linear regression with backward selection (tenfold cross-validated mean square errors); the predicted loop gain of the final linear regression model was used to predict loop gain class. More complex, alternative models including lasso regression or random forests were considered but did not meet pre-specified superiority-criteria. Final model performance was validated on the test-set.
RESULTS
RESULTS
The total cohort included 1055 patients (33% high loop gain). Based on the final model, higher AHI (beta = 0.0016; P < .001) and lower hypopnea-percentage (beta = -0.0019; P < .001) predicted higher loop gain values. The predicted loop gain showed moderate-to-high correlation with the reference loop gain (r = 0.48; 95% CI 0.38-0.57) and moderate discrimination of patients with high versus low loop gain (area under the curve = 0.73; 95% CI 0.67-0.80).
CONCLUSION
CONCLUSIONS
To our knowledge this is the first prediction model of loop gain based on readily-available clinical data, which may facilitate retrospective analyses of existing datasets, better patient selection for clinical trials and eventually clinical practice.
Identifiants
pubmed: 35468829
doi: 10.1186/s12890-022-01950-y
pii: 10.1186/s12890-022-01950-y
pmc: PMC9036750
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
158Subventions
Organisme : NHLBI NIH HHS
ID : R01 HL157985
Pays : United States
Organisme : NHLBI NIH HHS
ID : K23 HL151880
Pays : United States
Organisme : NHLBI NIH HHS
ID : T32 HL134632
Pays : United States
Organisme : NHLBI NIH HHS
ID : R01 HL085188
Pays : United States
Organisme : NIH HHS
ID : HL134632
Pays : United States
Organisme : NIA NIH HHS
ID : R01 AG063925
Pays : United States
Organisme : NIH HHS
ID : R01HL146697
Pays : United States
Organisme : NHLBI NIH HHS
ID : R01 HL154926
Pays : United States
Organisme : NHLBI NIH HHS
ID : R01 HL148436
Pays : United States
Informations de copyright
© 2022. The Author(s).
Références
Sleep. 2014 Jul 01;37(7):1227-36
pubmed: 25061251
J Appl Physiol (1985). 2013 Apr;114(7):911-22
pubmed: 23349453
Ann Am Thorac Soc. 2020 Apr;17(4):484-491
pubmed: 31821768
Ann Intern Med. 2015 Jan 6;162(1):W1-73
pubmed: 25560730
Sleep. 2019 Oct 21;42(11):
pubmed: 31418028
Eur Respir J. 2018 Sep 27;52(3):
pubmed: 30139771
Sleep. 2017 Jul 1;40(7):
pubmed: 28531336
J Clin Sleep Med. 2018 May 15;14(5):809-817
pubmed: 29734986
Sleep. 2021 Apr 9;44(4):
pubmed: 33057718
Biochem Med (Zagreb). 2015 Jun 05;25(2):141-51
pubmed: 26110027
Ann Am Thorac Soc. 2021 Apr;18(4):656-667
pubmed: 33064953
Chest. 2020 Jun;157(6):1626-1636
pubmed: 32006590
Crit Care Med. 2020 May;48(5):623-633
pubmed: 32141923
J Clin Sleep Med. 2012 Oct 15;8(5):597-619
pubmed: 23066376
Respir Physiol Neurobiol. 2008 Jul 31;162(2):144-51
pubmed: 18577470
Am J Respir Crit Care Med. 2018 May 15;197(10):1353-1355
pubmed: 29190428
N Engl J Med. 2016 Sep 8;375(10):1004-6
pubmed: 27602681
Sleep. 2021 Jan 21;44(1):
pubmed: 32929467
Am J Respir Crit Care Med. 2013 Oct 15;188(8):996-1004
pubmed: 23721582
Ann Am Thorac Soc. 2015 Sep;12(9):1351-7
pubmed: 26214564
Am J Respir Crit Care Med. 2014 Dec 1;190(11):1293-300
pubmed: 25321848
Am J Respir Crit Care Med. 2018 May 1;197(9):1187-1197
pubmed: 29327943
Chest. 2020 Dec;158(6):2632-2645
pubmed: 32768459
Am J Respir Crit Care Med. 2020 Dec 1;202(11):1592-1595
pubmed: 32673496
Lancet Respir Med. 2019 Aug;7(8):687-698
pubmed: 31300334
Ann Am Thorac Soc. 2019 Nov;16(11):1422-1431
pubmed: 31394914
Eur Respir J. 2015 Feb;45(2):408-18
pubmed: 25323235
Respirology. 2017 Jul;22(5):1015-1021
pubmed: 28303676
Crit Care Clin. 2015 Jul;31(3):473-95
pubmed: 26118916
Am J Respir Crit Care Med. 2019 Sep 15;200(6):691-703
pubmed: 31022356
Lancet. 2014 Feb 22;383(9918):736-47
pubmed: 23910433
J Clin Sleep Med. 2017 Sep 15;13(9):1029-1037
pubmed: 28818154
Neurol Clin Pract. 2013 Oct;3(5):366
pubmed: 30128170
Am J Respir Crit Care Med. 2021 Mar 15;203(6):746-755
pubmed: 32970962