Search

Introduction There have been significant advances in machine learning in recent years. This means that powerful methods are now available for classification problems, such as scoring sleep stages from neurological or cardiorespiratory signals. In the present work, validation studies for both applications are presented. Methods To determine the 5 sleep stages from the neurological signals, 54 sleep-wake-related features were calculated and classified by a bidirectional long short-term memory (LSTM) network which had been trained on 1956 manual scorings of 588 PSGs from 294 subjects (supervised deep learning). To determine the 4 stages (wake, light sleep, deep sleep, REM) from cardiorespiratory signals, a convolutional neural network combined with LSTM layers was used for feature extraction and classification. This network had been trained on 685 PSGs from 391 subjects (Bakker et al. JCSM 2021). The networks obtained were validated in 428 PSGs with one and 10 PSGs with 12 manual scorings (neurological staging) as well as in 2 two datasets, each containing 296 ambulatory recordings (cardiorespiratory staging). Results Cohen’s kappa between autoscoring based on neurological signals and manual scoring was 0.74 (95%-confidence interval: 0.74-0.74) for the 428 PSGs. The intraclass correlation coefficient (ICC) for absolute agreement between autoscoring and manual scoring was for the AHI 0.97 (0.96-0.98), for the arousal index 0.79 (0.67-0.86) and for the PLMSI 0.91 (0.88-0.93). The ICC between the sleep stage probabilities derived from the 12 manual scorings and the artificial intelligence (AI) derived hypnodensity was 0.91 (0.91-0.91). Cohen’s kappa values for the cardiorespiratory sleep staging were 0.68 (0.68-0.68) and 0.64 (0.63-0.64) for the 2 datasets with 296 ambulatory recordings each. Conclusion All metrics from the PSG validation studies show substantial (Cohen’s kappa > 0.6) as well as good to excellent agreement (ICC > 0.75 or > 0.90) compared to manual scorings. As an added value of the AI-supported PSG evaluation, the probabilities of the sleep stages per epoch are determined (hypnodensity graph). The valid estimation of the sleep stages from cardiorespiratory signals by means of AI may result in improved clinical interpretation of home sleep apnea tests, which are increasingly used in the sleep-disordered breathing diagnostic pathway. Support (If Any)

UNSTRUCTURED Digital medicine is an interdisciplinary field, drawing together stakeholders with expertise in engineering, manufacturing, clinical science, data science, biostatistics, regulatory considerations, ethics, patient advocacy, and healthcare policy, to name a few. While this diversity is undoubtedly valuable, it can lead to confusion regarding terminology and best practices. There are many instances, as we detail in this paper, where a single term is used by different groups to mean different things, as well as cases where multiple terms are used to describe essentially the same concept. Our intent is to clarify core terminology and best practices for the evaluation of Biometric Monitoring Technologies (BioMeTs), without unnecessarily introducing new terms. We propose and describe a three-component framework intended to provide a foundational evaluation framework for BioMeTs. This framework includes 1) verification, 2) analytical validation, and 3) clinical validation. We aim for this common vocabulary to enable more effective communication and collaboration, generate a common and meaningful evidence base for BioMeTs, and improve the accessibility of the digital medicine field.

Auto-adjusting positive airway pressure (APAP) devices are being increasingly used to treat obstructive sleep apnoea (OSA). Anecdotal encounters of obese patients requiring high therapeutic pressure whose OSA was inadequately controlled by APAP led to this study aiming to compare the effectiveness of continuous positive airway pressure (CPAP) and APAP (S8 Autoset II(®) , ResMed, NSW, Australia) in a randomised, single-blinded crossover trial. Twelve morbidly obese patients with severe OSA [mean±SD apnoea-hypopnoea index (AHI) 75.8±32.7, body mass index 49.9±5.2 kg m(-2) , mean pressure 16.4 cmH(2)O] were consecutively recruited, and received CPAP or APAP in random order for six nights at home, separated by a four-night washout. Polysomnographic (PSG) indices of OSA were recorded at baseline and following each treatment arm. Both therapies substantially reduced the AHI (APAP 9.8±9.5 and CPAP 7.3±6.6 events h(-1) ; P=0.35), but residual PSG measures of disease (AHI5) were common. APAP delivered a significantly lower 95th percentile pressure averaged over the home-use arm than CPAP (14.2±2.7 and 16.1±1.8 cmH(2)O, respectively, P=0.02). The machine-scored AHI significantly overestimated the level of residual disease compared with the laboratory-scored AHI (using Chicago criteria); however, when the machine-scored AHI was ≤5 and ≤10 this was always confirmed by the PSG data. In morbidly obese OSA patients without significant co-morbid disease requiring high therapeutic pressure, our data provide support for the use of either APAP or manually titrated CPAP. We recommend objective assessment by sleep study if the S8 Autoset II indicates a high level of residual disease.