Dataset Information

Misclassification of OSA severity with automated scoring of home sleep recordings.

ABSTRACT: The advent of home sleep testing has allowed for the development of an ambulatory care model for OSA that most health-care providers can easily deploy. Although automated algorithms that accompany home sleep monitors can identify and classify disordered breathing events, it is unclear whether manual scoring followed by expert review of home sleep recordings is of any value. Thus, this study examined the agreement between automated and manual scoring of home sleep recordings.Two type 3 monitors (ApneaLink Plus [ResMed] and Embletta [Embla Systems]) were examined in distinct study samples. Data from manual and automated scoring were available for 200 subjects. Two thresholds for oxygen desaturation (? 3% and ? 4%) were used to define disordered breathing events. Agreement between manual and automated scoring was examined using Pearson correlation coefficients and Bland-Altman analyses.Automated scoring consistently underscored disordered breathing events compared with manual scoring for both sleep monitors irrespective of whether a ? 3% or ? 4% oxygen desaturation threshold was used to define the apnea-hypopnea index (AHI). For the ApneaLink Plus monitor, Bland-Altman analyses revealed an average AHI difference between manual and automated scoring of 6.1 (95% CI, 4.9-7.3) and 4.6 (95% CI, 3.5-5.6) events/h for the ? 3% and ? 4% oxygen desaturation thresholds, respectively. Similarly for the Embletta monitor, the average difference between manual and automated scoring was 5.3 (95% CI, 3.2-7.3) and 8.4 (95% CI, 7.2-9.6) events/h, respectively.Although agreement between automated and manual scoring of home sleep recordings varies based on the device used, modest agreement was observed between the two approaches. However, manual review of home sleep test recordings can decrease the misclassification of OSA severity, particularly for those with mild disease.ClinicalTrials.gov; No.: NCT01503164; www.clinicaltrials.gov.

SUBMITTER: Aurora RN

PROVIDER: S-EPMC4347534 | biostudies-literature | 2015 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Misclassification of OSA severity with automated scoring of home sleep recordings.

Aurora R Nisha RN Swartz Rachel R Punjabi Naresh M NM

Chest 20150301 3

<h4>Background</h4>The advent of home sleep testing has allowed for the development of an ambulatory care model for OSA that most health-care providers can easily deploy. Although automated algorithms that accompany home sleep monitors can identify and classify disordered breathing events, it is unclear whether manual scoring followed by expert review of home sleep recordings is of any value. Thus, this study examined the agreement between automated and manual scoring of home sleep recordings.<h ...[more]

PMID: 25411804

Similar Datasets

Project description:PURPOSE:Home sleep testing devices are being widely used in diagnosis/screening for obstructive sleep apnea (OSA). We examined differences in OSA metrics obtained from two devices with divergent home monitoring strategies, the Apnea Risk Evaluation System (ARES™, multiple signals plus forehead reflectance oximetry) and the Nonin WristOx2™ (single channel finger transmission pulse oximeter), compared to differences from night-night variability of OSA. METHODS:One hundred fifty-two male/26 female subjects (BMI = 30.3 ± 5.6 kg/m2, age = 52.5 ± 8.9 years) were recruited without regard to OSA symptoms and simultaneously wore both ARES™ and Nonin WristOx2™ for two nights (n = 351 nights). Automated analysis of the WristOx2 yielded oxygen desaturation index (ODIOx2, ?4% O2 dips/h), and automated analysis with manual editing of ARES™ yielded AHI4ARES (apneas + hypopneas with ?4% O2 dips/h) and RDIARES (apneas + hypopneas with ?4% O2 dips/h or arousal surrogates). Baseline awake oxygen saturation, percent time < 90% O2 saturation (%time < 90%O2Sat), and O2 signal loss were compared between the two methods. RESULTS:Correlation between AHI4ARES and ODIOx2 was high (ICC = 0.9, 95% CI = 0.87-0.92, p < 0.001, bias ± SD = 0.7 ± 6.1 events/h). Agreement values for OSA diagnosis (77-85%) between devices were similar to those seen from night-to-night variability of OSA using a single device. Awake baseline O2 saturation was significantly higher in the ARES™ (96.2 ± 1.6%) than WristOx2™ (92.2 ± 2.1%, p < 0.01). There was a significantly lower %time < 90%O2Sat reported by the ARES™ compared to WristOx2 (median (IQR) 0.5 (0.0, 2.6) vs. 2.1 (0.3, 9.7), p < 0.001), and the correlation was low (ICC = 0.2). CONCLUSIONS:OSA severity metrics predominantly dependent on change in oxygen saturation and metrics used in diagnosis of OSA (AHI4 and ODI) correlated well across devices tested. However, differences in cumulative oxygen desaturation measures (i.e., %time < 90%O2Sat) between the devices suggest that caution is needed when interpreting this metric particularly in populations likely to have significant hypoxia.

Project description:BackgroundThe Psoriasis Area and Severity Index (PASI) score is commonly used in clinical practice and research to monitor disease severity and determine treatment efficacy. Automating the PASI score with deep learning algorithms, like Convolutional Neural Networks (CNNs), could enable objective and efficient PASI scoring.ObjectivesTo assess the performance of image-based automated PASI scoring in anatomical regions by CNNs and compare the performance of CNNs to image-based scoring by physicians.MethodsImaging series were matched to PASI subscores determined in real life by the treating physician. CNNs were trained using standardized imaging series of 576 trunk, 614 arm and 541 leg regions. CNNs were separately trained for each PASI subscore (erythema, desquamation, induration and area) in each anatomical region (trunk, arms and legs). The head region was excluded for anonymity. Additionally, PASI-trained physicians retrospectively determined image-based subscores on the test set images of the trunk. Agreement with the real-life scores was determined with the intraclass correlation coefficient (ICC) and compared between the CNNs and physicians.ResultsIntraclass correlation coefficients between the CNN and real-life scores of the trunk region were 0.616, 0.580, 0.580 and 0.793 for erythema, desquamation, induration and area, respectively, with similar results for the arms and legs region. PASI-trained physicians (N = 5) were in moderate-good agreement (ICCs 0.706-0.793) with each other for image-based PASI scoring of the trunk region. ICCs between the CNN and real-life scores were slightly higher for erythema (0.616 vs. 0.558), induration (0.580 vs. 0.573) and area scoring (0.793 vs. 0.694) than image-based scoring by physicians. Physicians slightly outperformed the CNN on desquamation scoring (0.580 vs. 0.589).ConclusionsConvolutional Neural Networks have the potential to automatically and objectively perform image-based PASI scoring at an anatomical region level. For erythema, desquamation and induration scoring, CNNs performed similar to physicians, while for area scoring CNNs outperformed physicians on image-based PASI scoring.

Dataset Information

Misclassification of OSA severity with automated scoring of home sleep recordings.

Publications

Misclassification of OSA severity with automated scoring of home sleep recordings.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets