OBJECTIVE: This paper presents a methodology to automatically screen for sleep apnea based on the detection of apnea and hypopnea events in the blood oxygen saturation (SpO2) signal. METHODS: It starts by detecting all desaturations in the SpO2 signal. From these desaturations, a total of 143 time-domain features are extracted. After feature selection, the six most discriminative features are used to construct classifiers to predict if desaturations are caused by respiratory events. From these, a random forest classifier yielded the best classification performance. The number of desaturations, classified as caused by respiratory events per hour of recording, can then be used as an estimate of the apnea-hypopnea index (AHI), and to predict whether or not a patient suffers from sleep apnea-hypopnea syndrome (SAHS). All classifiers were developed based on a subset of 500 subjects of the Sleep Heart Health Study (SHHS) and tested on three different datasets, containing 8052 subjects in total. RESULTS: An averaged desaturation classification accuracy of 82.8% was achieved over the different test sets. Subjects having SAHS with an AHI greater than 15 can be detected with an average accuracy of 87.6%. CONCLUSION: The achieved SAHS screening outperforms SpO2 methods from the literature on the SHHS test dataset. Moreover, the robustness of the method was shown when tested on different independent test sets. SIGNIFICANCE: These results show that an algorithm based on simple features of SpO2 desaturations can outperform more elaborate methods in the detection of apneic events and the screening of SAHS patients.
OBJECTIVE: This paper presents a methodology to automatically screen for sleep apnea based on the detection of apnea and hypopnea events in the blood oxygen saturation (SpO2) signal. METHODS: It starts by detecting all desaturations in the SpO2 signal. From these desaturations, a total of 143 time-domain features are extracted. After feature selection, the six most discriminative features are used to construct classifiers to predict if desaturations are caused by respiratory events. From these, a random forest classifier yielded the best classification performance. The number of desaturations, classified as caused by respiratory events per hour of recording, can then be used as an estimate of the apnea-hypopnea index (AHI), and to predict whether or not a patient suffers from sleep apnea-hypopnea syndrome (SAHS). All classifiers were developed based on a subset of 500 subjects of the Sleep Heart Health Study (SHHS) and tested on three different datasets, containing 8052 subjects in total. RESULTS: An averaged desaturation classification accuracy of 82.8% was achieved over the different test sets. Subjects having SAHS with an AHI greater than 15 can be detected with an average accuracy of 87.6%. CONCLUSION: The achieved SAHS screening outperforms SpO2 methods from the literature on the SHHS test dataset. Moreover, the robustness of the method was shown when tested on different independent test sets. SIGNIFICANCE: These results show that an algorithm based on simple features of SpO2 desaturations can outperform more elaborate methods in the detection of apneic events and the screening of SAHS patients.
Authors: Fernando Vaquerizo-Villar; Daniel Alvarez; Leila Kheirandish-Gozal; Gonzalo C Gutierrez-Tobal; Veronica Barroso-Garcia; Eduardo Santamaria-Vazquez; Felix Del Campo; David Gozal; Roberto Hornero Journal: IEEE J Biomed Health Inform Date: 2021-08-05 Impact factor: 7.021
Authors: Jeremy Levy; Daniel Álvarez; Aviv A Rosenberg; Alexandra Alexandrovich; Félix Del Campo; Joachim A Behar Journal: NPJ Digit Med Date: 2021-01-04