Screening for obstructive sleep apnea with novel hybrid acoustic smartphone app technology

Abstract

Background: Obstructive sleep apnea (OSA) has a high prevalence, with an estimated 425 million adults with apnea hypopnea index (AHI) of ≥15 events/hour, and is significantly underdiagnosed. This presents a significant pain point for both the sufferers, and for healthcare systems, particularly in a post COVID-19 pandemic world. As such, it presents an opportunity for new technologies that can enable screening in both developing and developed countries. In this work, the performance of a non-contact OSA screener App that can run on both Apple and Android smartphones is presented. Methods: The subtle breathing patterns of a person in bed can be measured via a smartphone using the "Firefly" app technology platform [and underpinning software development kit (SDK)], which utilizes advanced digital signal processing (DSP) technology and artificial intelligence (AI) algorithms to identify detailed sleep stages, respiration rate, snoring, and OSA patterns. The smartphone is simply placed adjacent to the subject, such as on a bedside table, night stand or shelf, during the sleep session. The system was trained on a set of 128 overnights recorded at a sleep laboratory, where volunteers underwent simultaneous full polysomnography (PSG), and "Firefly" smartphone app analysis. A separate independent test set of 120 recordings was collected across a range of Apple iOS and Android smartphones, and withheld for performance evaluation by a different team. An operating point tuned for mid-sensitivity (i.e., balancing sensitivity and specificity) was chosen for the screener. Results:The performance on the test set is comparable to ambulatory OSA screeners, and other smartphone screening apps, with a sensitivity of 88.3% and specificity of 80.0% [with receiver operating characteristic (ROC) area under the curve (AUC) of 0.92], for a clinical threshold for the AHI of ≥15 events/ hour of detected sleep time. Conclusions: The "Firefly" app based sensing technology offers the potential to significantly lower the barrier of entry to OSA screening, as no hardware (other than the user's personal smartphone) is required.Additionally, multi-night analysis is possible in the home environment, without requiring the wearing of a portable PSG or other home sleep test (HST).

Accuracy of a Smartphone Application Measuring Snoring in Adults—How Smart Is It Actually?

“…Focusing on those which solely use the smartphone without any supplementary external devices, two studies can be extrapolated [ 25 , 26 ]: Regarding the correlation between the snoring time measured by the smartphone compared to the respective gold standard, Nakano et al [ 25 ] revealed a higher correlation than the present study (r = 0.93 versus r = 0.754/0.780). Moreover, both studies [ 25 , 26 ] found also higher correlations comparing the respiratory disturbance indices created by the apps with the AHI obtained by PSG/PG (r = 0.94 [ 25 ] versus r = 0.81 [ 26 ] versus r = 0.495). It has to be kept in mind, that the “Snore Score” calculated by SnoreLab is based on an unknown algorithm and thus cannot be directly compared to specific scores which are associated to respiratory events.…”

“…In contrast to commercial snoring apps, which are available at the common app stores, some research groups developed and tested their own smartphone apps for measurement of snoring and screening of OSA [ 25 , 26 , 35 , 36 ]. Focusing on those which solely use the smartphone without any supplementary external devices, two studies can be extrapolated [ 25 , 26 ]: Regarding the correlation between the snoring time measured by the smartphone compared to the respective gold standard, Nakano et al [ 25 ] revealed a higher correlation than the present study (r = 0.93 versus r = 0.754/0.780). Moreover, both studies [ 25 , 26 ] found also higher correlations comparing the respiratory disturbance indices created by the apps with the AHI obtained by PSG/PG (r = 0.94 [ 25 ] versus r = 0.81 [ 26 ] versus r = 0.495).…”

“…Another validation study [ 24 ] used a paid smartphone application and included 11 patients with snoring problems wearing an oral appliance at night, which could have influenced snoring during the investigation. Two research groups [ 25 , 26 ] described their development of audio-based snoring apps and validated them in 40 [ 25 ] and 120 [ 26 ] subjects, respectively. Nevertheless, both apps are not available in the common mobile app stores until now.…”

Prototype of Customized Mobile Application for Obstructive Sleep Apnea (OSA) Risk Assessment During the COVID-19 Pandemic

“…Scope for prescreening in orthodontic clinics, primary healthcare centers, and hospitals; 6. Automated initial assessment in schools, educational institutions, and driving license authorities; and have been tested previously for screening OSA, including "SleepAp" 9 and "Firefly App," 10 to name a couple of them. However, these are commercial applications that may present cost limitations in a developing country like India.…”

“…For example, SleepAp uses actigraphy, position of the body, photoplethysmography, and audio for inputs in a vector machine classifier, as well as a standardized STOP-BANG questionnaire. 9 The "Firefly" app, 10 on the other hand, utilizes AI and advanced digital signal processing (DSP) for identifying stages of sleep, snoring, OSA patterns, and respiration rate. Additionally, the questionnaire used in "SleepAp" 9 has clinical validity only in adults, and hence pediatric OSA cannot be screened, while our mobile application would be applicable for all age groups.…”