Dataset Information

A Novel Artificial Neural Network Based Sleep-Disordered Breathing Screening Tool.

ABSTRACT:

Study objectives

This study evaluated a novel artificial neural network (ANN) based sleep-disordered breathing (SDB) screening tool incorporating nocturnal pulse oximetry with demographic, anatomic, and clinical data. The tool was compatible with 6 categories of apnea-hypopnea index (AHI) with 4% oxyhemoglobin desaturation threshold, ≥ 5, 10, 15, 20, 25, and 30 events/h.

Methods

Using a general population dataset, the training set included 2,280 subjects, whereas the test set included 470 subjects. The input of this tool was a set of 22 variables. The tool had six neural network models for each AHI threshold. Several metrics were explored to evaluate the performance of the tool: area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value, and 95% confidence interval (CI).

Results

The AUC was 0.904, 0.912, 0.913, 0.926, 0.930, and 0.954, respectively, with models of AHI ≥ 5, 10, 15, 20, 25, and 30 events/h thresholds. The sensitivities of all neural network models were higher than 95%. The AHI ≥ 30 events/h model had the maximum sensitivity: 98.31% (95% CI: 95.01%-100%).

Conclusions

The results of this study suggested that the ANN based SDB screening tool can be used to identify the presence or absence of SDB. Future validation should be performed in other populations to determine the practicability of this screening tool in sleep clinics and other at-risk populations.

SUBMITTER: Li A

PROVIDER: S-EPMC5991950 | biostudies-literature | 2018 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Novel Artificial Neural Network Based Sleep-Disordered Breathing Screening Tool.

Li Ao A Quan Stuart F SF Silva Graciela E GE Perfect Michelle M MM Roveda Janet M JM

Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine 20180615 6

<h4>Study objectives</h4>This study evaluated a novel artificial neural network (ANN) based sleep-disordered breathing (SDB) screening tool incorporating nocturnal pulse oximetry with demographic, anatomic, and clinical data. The tool was compatible with 6 categories of apnea-hypopnea index (AHI) with 4% oxyhemoglobin desaturation threshold, ≥ 5, 10, 15, 20, 25, and 30 events/h.<h4>Methods</h4>Using a general population dataset, the training set included 2,280 subjects, whereas the test set incl ...[more]

PMID: 29852901

Similar Datasets

Project description:Sleep disordered breathing (SDB) is highly prevalent, but frequently unrecognized among stroke patients. Polysomnography (PSG) is difficult to perform soon after a stroke. We evaluated the use of screening questionnaires and portable sleep testing (PST) for patients with acute stroke, subarachnoid hemorrhage, or transient ischemic attack to expedite SDB diagnosis and management. We performed a single-center retrospective analysis of a quality improvement study on SDB screening of consecutive daytime, weekday, adult admissions to a stroke unit. We excluded patients who were unable to communicate and lacked available family members. Patients were screened with the Epworth Sleepiness Scale, Berlin Questionnaire, and STOP-BANG Questionnaire and underwent overnight PST and/or outpatient PSG. The 4-item STOP Questionnaire was derived from STOP-BANG for a secondary analysis. We compared the sensitivity and specificity of the questionnaires for the diagnosis of at least mild SDB (apnea hypopnea index (AHI) ≥5) on PST and correlated AHI measurements between PST and PSG using the Spearman correlation. Out of sixty-eight patients included in the study, 54 (80%) were diagnosed with SDB. Only one (1.5%) had a previous SDB diagnosis. Thirty-three patients completed all questionnaires and a PST. The STOP-BANG questionnaire had the highest sensitivity for at least mild SDB (0.81, 95% CI (confidence interval): 0.65-0.92) but a low specificity (0.33, 95% CI 0.10, 0.65). The discrimination of all questionnaires was overall poor (C statistic range 0.502-0.640). There was a strong correlation (r = 0.71) between the AHI results estimated using PST and outpatient PSG among 28 patients. The 4-item STOP Questionnaire was the easiest to administer and had a comparable or better sensitivity than the other questionnaires. Inpatient PSTs were useful for screening in the acute setting to facilitate an early diagnosis of SDB and to establish further outpatient evaluations with sleep medicine.

Dataset Information

A Novel Artificial Neural Network Based Sleep-Disordered Breathing Screening Tool.

Study objectives

Methods

Results

Conclusions

Publications

A Novel Artificial Neural Network Based Sleep-Disordered Breathing Screening Tool.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets