Sleep apnea: a review of diagnostic sensors, algorithms, and therapies

Sleep Apnea Events Recognition Based on Polysomnographic Recordings: A Large-Scale Multi-Channel Machine Learning approach

Goal: The gold standard for detecting the presence of apneic events is a time and effort-consuming manual evaluation of type I polysomnographic recordings by experts, often not error-free. Such acquisition protocol requires dedicated facilities resulting in high costs and long waiting lists. The usage of artificial intelligence models assists the clinician's evaluation overcoming the aforementioned limitations and increasing healthcare quality. Methods: The present work proposes a machine learning-based approach for automatically recognizing apneic events in subjects affected by sleep apnea-hypopnea syndrome. It embraces a vast and diverse pool of subjects, the Wisconsin Sleep Cohort (WSC) database. Results: An overall accuracy of 87.2[Formula: see text]1.8% is reached for the event detection task, significantly higher than other works in literature performed over the same dataset. The distinction between different types of apnea was also studied, obtaining an overall accuracy of 62.9[Formula: see text]4.1%. Conclusions: The proposed approach for sleep apnea events recognition, validated over a wide pool of subjects, enlarges the landscape of possibilities for sleep apnea events recognition, identifying a subset of signals that improves State-of-the-art performance and guarantees simple interpretation.

Assessing the effects of HMGCR, LPL, and PCSK9 inhibition on sleep apnea: Mendelian randomization analysis of drug targets

To investigate the use of lipid-lowering drugs and abnormal serum lipid levels in patients at risk of sleep apnea syndrome. Three types of Mendelian randomization (MR) analyses were used. First, a 2-sample Mendelian randomization (TSMR) analysis was used to investigate the association between sleep apnea syndrome risk and serum lipid levels. Multivariate Mendelian randomization (MVMR) analysis was subsequently used to investigate the effects of confounding variables on SAS incidence of sleep apnea syndrome. Finally, drug-target Mendelian randomization (DMR) analysis was used to analyze the association between lipid-lowering drug use and sleep apnea syndrome risk. According to the TSMR analysis, the serum HDL-C concentration was negatively correlated with sleep apnea syndrome (OR = 0.904; 95% CI = 0.845-0.967; P = .003). Serum TG levels were positively correlated with sleep apnea syndrome (OR = 1.081; 95% CI = 1.003-1.163; P = .039). The association between serum HDL-C levels and sleep apnea syndrome in patients with MVMR was consistent with the results in patients with TSMR (OR = 0.731; 95% CI = 0.500-1.071; P = 3.94E-05). According to our DMR analysis, HMGCR and PCSK9, which act by lowering serum LDL-C levels, were inversely associated with the risk of sleep apnea syndrome (OR = 0.627; 95% CI = 0.511-0.767; P = 6.30E-06) (OR = 0.775; 95% CI = 0.677-0.888; P = .0002). LPL, that lowered serum TG levels, was positively associated with the risk of sleep apnea syndrome (OR = 1.193; 95% CI = 1.101-1.294; P = 1.77E-05). Our analysis suggested that high serum HDL-C levels may reduce the risk of sleep apnea syndrome. Low serum TG levels have a protective effect against sleep apnea syndrome. The DMR results suggested that the use of HMGCR lipid-lowering drugs (such as statins) and PCSK9 inhibitors has a protective effect against sleep apnea syndrome. However, LPL-based lipid-lowering drugs may increase the risk of sleep apnea syndrome.

Deep learning approaches for assessing pediatric sleep apnea severity through SpO2 signals

Pediatric Sleep Apnea-Hypopnea (SAH) presents a significant health challenge, particularly in diagnostic contexts, where conventional Polysomnography (PSG) testing, although effective, can be distressing for children. Addressing this, our research proposes a less invasive method to assess pediatric SAH severity by analyzing blood oxygen saturation (SpO2) signals. We adopted two advanced deep learning architectures, namely ResNet-based and attention-augmented hybrid CNN-BiGRU models, to process SpO2 signals in a one-dimensional (1D) format for Apnea-Hypopnea Index (AHI) estimation in pediatric subjects. Employing the CHAT dataset, which includes 844 SpO2 signals, the data was partitioned into training (60%), testing (30%), and validation (10%) sets. A predefined validation subset was randomly selected to ensure the models' robustness via a threefold cross-validation approach. Comparative analysis revealed that while the ResNet model attained an average accuracy of 72.9% across four SAH severity categories with a kappa score of 0.57, the CNN-BiGRU-Attention model demonstrated superior performance, achieving an average accuracy of 75.95% and a kappa score of 0.63. This distinction underscores our method's efficacy in both estimating AHI and categorizing SAH severity levels with notable precision. Further, to evaluate diagnostic capabilities, the models were benchmarked against common AHI thresholds (1, 5, and 10 events/hour) in each test fold, affirming their effectiveness in identifying pediatric SAH. This study marks a significant advance in the field, offering a non-invasive, child-friendly alternative for pediatric SAH diagnosis. Although challenges persist in accurately estimating AHI, particularly in severe cases, our findings represent a critical stride towards improving diagnostic processes in pediatric SAH.

Highly Sensitive and Fast Responding Flexible Force Sensors Using ZnO/ZnMgO Coaxial Nanotubes on Graphene Layers for Breath Sensing

The authors report the fabrication of highly sensitive, rapidly responding flexible force sensors using ZnO/ZnMgO coaxial nanotubes grown on graphene layers and their applications in sleep apnea monitoring. Flexible force sensors are fabricated by forming Schottky contacts to the nanotube array, followed by the mechanical release of the entire structure from the host substrate. The electrical characteristics of ZnO and ZnO/ZnMgO nanotube-based sensors are thoroughly investigated and compared. Importantly, in force sensor applications, the ZnO/ZnMgO coaxial structure results in significantly higher sensitivity and a faster response time when compared to the bare ZnO nanotube. The origin of the improved performance is thoroughly discussed. Furthermore, wireless breath sensing is demonstrated using the ZnO/ZnMgO pressure sensors with custom electronics, demonstrating the feasibility of the sensor technology for health monitoring and the potential diagnosis of sleep apnea.

Validity study of a multiscaled fusion network using single-lead electrocardiogram signals for obstructive sleep apnea diagnosis

STUDY OBJECTIVES

We evaluated the validity of a squeeze-and-excitation and multiscaled fusion network (SE-MSCNN) using single-lead electrocardiogram (ECG) signals for obstructive sleep apnea detection and classification.

METHODS

Overnight polysomnographic data from 436 participants at the Sleep Center of the First Affiliated Hospital of Sun Yat-sen University were used to generate a new FAH-ECG dataset comprising 260, 88, and 88 single-lead ECG signal recordings for training, validation, and testing, respectively. The SE-MSCNN was employed for detection of apnea-hypopnea events from the acquired ECG segments. Sensitivity, specificity, accuracy, and F1 scores were assigned to assess algorithm performance. We also used the SE-MSCNN to estimate the apnea-hypopnea index, classify obstructive sleep apnea severity, and compare the agreement between 2 sleep technicians.

RESULTS

The SE-MSCNN's accuracy, sensitivity, specificity, and F1 score on the FAH-ECG dataset were 86.6%, 83.3%, 89.1%, and 0.843, respectively. Although slightly inferior to previously reported results using public datasets, it is superior to state-of-the-art open-source models. Furthermore, the SE-MSCNN had good agreement with manual scoring, such that the Spearman's correlations for the apnea-hypopnea index between the SE-MSCNN and 2 technicians were 0.93 and 0.94, respectively. Cohen's kappa scores in classifying the SE-MSCNN and the 2 sleep technicians were 0.72 and 0.78, respectively.

CONCLUSIONS

In this study, we validated the use of the SE-MSCNN in a clinical environment, and despite some limitations the network appeared to meet the performance standards for generalizability. Therefore, updating algorithms based on single-lead ECG signals can facilitate the development of novel wearable devices for efficient obstructive sleep apnea screening.

CITATION

Yue H, Li P, Li Y, et al. Validity study of a multiscaled fusion network using single-lead electrocardiogram signals for obstructive sleep apnea diagnosis. J Clin Sleep Med. 2023;19(6):1017-1025.

Bio-Inspired Micromachined Volumetric Flow Sensor with a Big Dynamic Range for Intravenous Systems

Real-time monitoring of drug delivery in an intravenous infusion system can prevent injury caused by improper drug doses. As the medicine must be administered into the vein at different rates and doses in different people, an ideal intravenous infusion system requires both a low flow rate and large dynamic range monitoring. In this study, a bio-inspired and micromachined volumetric flow sensor is presented for the biomedical application of an intravenous system. This was realized by integrating two sensing units with different sensitivities on one silicon die to achieve a large dynamic range of the volumetric flow rate. The sensor was coated with a parylene layer for waterproofing and biocompatibility purposes. A new packaging scheme incorporating a silicon die into a flow channel was employed to demonstrate the working prototype. The test results indicate that the sensor can detect a volumetric flow rate as low as 2 mL/h, and its dynamic range is from 2 mL/h to 200 mL/h. The sensor performed better than the other two commercial sensors for low-flow detection. The high sensitivity, low cost, and small size of this flow sensor make it promising for intravenous applications.

[Morphological changes of upper airway in patients with obstructive sleep apnea hypopnea syndrome after H-UPPP]

Objective:To investigate the morphological changes of the upper airway palatepharyngeal plane after modified uvulopalatopharyngoplasty（H-UPPP） in patients with obstructive sleep apnea hypopnea syndrome（OSAHS） and efficacy of the surgery. Methods:Thirty-six patients diagnosed as moderate to severe OSAHS in the Central Hospital of Wuhan from January 2016 to September 2019 were treated with H-UPPP. PSG and 64 slice spiral CT were performed before operation, 1 month, 3 months, 6 months, 1 year and 2 years after operation to evaluate the changes of AHI, LSaO₂, CT90, BMI and the minimum anterior and posterior axis diameter, left and right axis diameter and cross-sectional volume of velopharyngeal plane, respectively. Results:The AHI, LSaO₂, CT90, BMI were significantly improved, while the minimum anterior posterior axis diameter, left and right axis diameter and cross-sectional volume of velopharyngeal plane were enlarged in the maximum extent at one month after operation. The alteration of left and right axis diameter could be maintained until half a year after operation, but gradually retracted after 1 year after operation. The improvement of anterior and posterior axis diameter can only be maintained until 3 months after operation, and return to the preoperative level 2 years after operation; The minimum cross-sectional area improved significantly at 1 month after operation and decreased after 3 months, but there was still a significant improvement at 2 years after operation（P<0.05）. The change of AHI was similar to that of the minimum cross-sectional area, and there was still a significant difference at 2 years after operation（P<0.001）; The improvement of LSaO₂ was the most significant at 1 month after operation, which could be maintained until 3 months after operation, and then gradually recovered. The improvement of CT90 could be maintained until half a year after operation, and decreased significantly at 1 year after operation. BMI was still better than that before operation at 1 year after operation, but returned to the preoperative level at 2 years after operation. The improvement of AHI was mainly related to the minimum anterior posterior axis diameter and cross-sectional area of velopharyngeal plane, but not to the left and right axis diameters. Conclusion:The morphological changes of upper airway in patients with OSAHS after H-UPPP are mainly the improvement of anterior posterior diameter, left and right diameter and minimum cross-sectional area caused by removing the anatomical load of upper airway within 3 months after operation, but the reduction of anterior posterior diameter and minimum cross-sectional area gradually occurs after 3 months, resulting in the weakening of surgical effect.

The Current State of Optical Sensors in Medical Wearables

Optical sensors play an increasingly important role in the development of medical diagnostic devices. They can be very widely used to measure the physiology of the human body. Optical methods include PPG, radiation, biochemical, and optical fiber sensors. Optical sensors offer excellent metrological properties, immunity to electromagnetic interference, electrical safety, simple miniaturization, the ability to capture volumes of nanometers, and non-invasive examination. In addition, they are cheap and resistant to water and corrosion. The use of optical sensors can bring better methods of continuous diagnostics in the comfort of the home and the development of telemedicine in the 21st century. This article offers a large overview of optical wearable methods and their modern use with an insight into the future years of technology in this field.

Deep-Learning Model Based on Convolutional Neural Networks to Classify Apnea–Hypopnea Events from the Oximetry Signal

Automated analysis of the blood oxygen saturation (SpO₂) signal from nocturnal oximetry has shown usefulness to simplify the diagnosis of obstructive sleep apnea (OSA), including the detection of respiratory events. However, the few preceding studies using SpO₂ recordings have focused on the automated detection of respiratory events versus normal respiration, without making any distinction between apneas and hypopneas. In this sense, the characteristics of oxygen desaturations differ between obstructive apnea and hypopnea episodes. In this chapter, we use the SpO₂ signal along with a convolutional neural network (CNN)-based deep-learning architecture for the automatic identification of apnea and hypopnea events. A total of 398 SpO₂ signals from adult OSA patients were used for this purpose. A CNN architecture was trained using 30-s epochs from the SpO₂ signal for the automatic classification of three classes: normal respiration, apnea, and hypopnea. Then, the apnea index (AI), the hypopnea index (HI), and the apnea-hypopnea index (AHI) were obtained by aggregating the outputs of the CNN for each subject (AI_CNN, HI_CNN, and AHI_CNN). This model showed a promising diagnostic performance in an independent test set, with 80.3% 3-class accuracy and 0.539 3-class Cohen's kappa for the classification of respiratory events. Furthermore, AI_CNN, HI_CNN, and AHI_CNN showed a high agreement with the values obtained from the standard PSG: 0.8023, 0.6774, and 0.8466 intra-class correlation coefficients (ICCs), respectively. This suggests that CNN can be used to analyze SpO₂ recordings for the automated diagnosis of OSA in at-home oximetry tests.

MOF based flexible, low-cost chemiresistive device as a respiration sensor for sleep apnea diagnosis

The monitoring of respiratory disorders requires breath sensors that are fast, robust, and convenient to use and can function under real time conditions. A MOF based flexible sensor is reported for the first time for breath sensing applications. The properties of a highly porous HKUST-1 MOF and a conducting MoS2 material have been combined to fabricate an electronic sensor on a flexible paper support for studying sleep apnea problems. Extensive breath sensing experiments have been performed and interestingly the fabricated sensor is efficient in detecting various kinds of breaths such as deep, fast, slow and hydrated breath. The MOF breath sensor shows a fast response time of just ∼0.38 s and excellent stability with no decline in its performance even after a month. A plausible mechanism has been proposed and a smartphone based prototype has been prepared to demonstrate the real time applications of the hybrid device. This work demonstrates great potential for the application of MOFs in healthcare with a special focus on breath sensing and sleep apnea diagnosis.

The Importance of Respiratory Rate Monitoring: From Healthcare to Sport and Exercise

Respiratory rate is a fundamental vital sign that is sensitive to different pathological conditions (e.g., adverse cardiac events, pneumonia, and clinical deterioration) and stressors, including emotional stress, cognitive load, heat, cold, physical effort, and exercise-induced fatigue. The sensitivity of respiratory rate to these conditions is superior compared to that of most of the other vital signs, and the abundance of suitable technological solutions measuring respiratory rate has important implications for healthcare, occupational settings, and sport. However, respiratory rate is still too often not routinely monitored in these fields of use. This review presents a multidisciplinary approach to respiratory monitoring, with the aim to improve the development and efficacy of respiratory monitoring services. We have identified thirteen monitoring goals where the use of the respiratory rate is invaluable, and for each of them we have described suitable sensors and techniques to monitor respiratory rate in specific measurement scenarios. We have also provided a physiological rationale corroborating the importance of respiratory rate monitoring and an original multidisciplinary framework for the development of respiratory monitoring services. This review is expected to advance the field of respiratory monitoring and favor synergies between different disciplines to accomplish this goal.

Convolutional Neural Networks to Detect Pediatric Apnea-Hypopnea Events from Oximetry

Pediatric sleep apnea-hypopnea syndrome (SAHS) is a highly prevalent breathing disorder that is related to many negative consequences for the children's health and quality of life when it remains untreated. The gold standard for pediatric SAHS diagnosis (overnight polysomnography) has several limitations, which has led to the search for alternative tests. In this sense, automated analysis of overnight oximetry has emerged as a simplified technique. Previous studies have focused on the extraction of ad-hoc features from the blood oxygen saturation (SpO₂) signal, which may miss useful information related to apnea and hypopnea (AH) events. In order to overcome this limitation of traditional approaches, we propose the use of convolutional neural networks (CNN), a deep learning technique, to automatically detect AH events from the SpO₂ raw data. CHAT-baseline dataset, composed of 453 SpO₂ recordings, was used for this purpose. A CNN model was trained using 60-s segments from the SpO₂ signal using a training set (50% of subjects). Optimum hyperparameters of the CNN architecture were obtained using a validation set (25% of subjects). This model was applied to a third test set (25% of subjects), reaching 93.6% accuracy to detect AH events. These results suggest that the application of CNN may be useful to detect changes produced in the oximetry signal by AH events in pediatric SAHS patients.

A machine learning-based test for adult sleep apnoea screening at home using oximetry and airflow

The most appropriate physiological signals to develop simplified as well as accurate screening tests for obstructive sleep apnoea (OSA) remain unknown. This study aimed at assessing whether joint analysis of at-home oximetry and airflow recordings by means of machine-learning algorithms leads to a significant diagnostic performance increase compared to single-channel approaches. Consecutive patients showing moderate-to-high clinical suspicion of OSA were involved. The apnoea-hypopnoea index (AHI) from unsupervised polysomnography was the gold standard. Oximetry and airflow from at-home polysomnography were parameterised by means of 38 time, frequency, and non-linear variables. Complementarity between both signals was exhaustively inspected via automated feature selection. Regression support vector machines were used to estimate the AHI from single-channel and dual-channel approaches. A total of 239 patients successfully completed at-home polysomnography. The optimum joint model reached 0.93 (95%CI 0.90–0.95) intra-class correlation coefficient between estimated and actual AHI. Overall performance of the dual-channel approach (kappa: 0.71; 4-class accuracy: 81.3%) significantly outperformed individual oximetry (kappa: 0.61; 4-class accuracy: 75.0%) and airflow (kappa: 0.42; 4-class accuracy: 61.5%). According to our findings, oximetry alone was able to reach notably high accuracy, particularly to confirm severe cases of the disease. Nevertheless, oximetry and airflow showed high complementarity leading to a remarkable performance increase compared to single-channel approaches. Consequently, their joint analysis via machine learning enables accurate abbreviated screening of OSA at home.

System for Monitoring User Engagement with Personalized Medical Devices to Improve Use and Health Outcomes

Medical devices used in a home setting for treating a variety of chronic diseases lack the ability to convey meaningful information to the patients directly about how they are engaging with their devices in real-time. This research is focused on the development of a monitoring system that addresses this need. For this initial design and testing, the research team applied the technology to a positive airway pressure (PAP) system used in the treatment of those suffering from obstructive sleep apnea (OSA). Data from experimental testing showed results of 93.6% accuracy, 98.7% sensitivity, and 90.9% specificity in the monitoring system detecting events that are typical of issues occurring during standard PAP therapy use. Results indicate this technology can be considered as a viable solution for providing more meaningful information to users about their engagement with their prescribed medical devices.

Plasma Extracellular Vesicles in Children with OSA Disrupt Blood-Brain Barrier Integrity and Endothelial Cell Wound Healing in Vitro

Pediatric obstructive sleep apnea (P-OSA) is associated with neurocognitive deficits and endothelial dysfunction, suggesting the possibility that disruption of the blood-brain barrier (BBB) may underlie these morbidities. Extracellular vesicles (EVs), which include exosomes, are small particles involved in cell-cell communications via different mechanisms and could play a role in OSA-associated end-organ injury. To examine the roles of EVs in BBB dysfunction, we recruited three groups of children: (a) absence of OSA or cognitive deficits (CL, n = 6), (b) OSA but no evidence of cognitive deficits (OSA-NC(-), n = 12), and (c) OSA with evidence of neurocognitive deficits (OSA-NC(+), n = 12). All children were age-, gender-, ethnicity-, and BMI-z-score-matched, and those with OSA were also apnea-hypopnea index (AHI)-matched. Plasma EVs were characterized, quantified, and applied on multiple endothelial cell types (HCAEC, HIAEC, human HMVEC-D, HMVEC-C, HMVEC-L, and hCMEC/D3) while measuring monolayer barrier integrity and wound-healing responses. EVs from OSA children induced significant declines in hCMEC/D3 transendothelial impedance compared to CL (p < 0.001), and such changes were greater in NC(+) compared to NC(-) (p < 0.01). The effects of EVs from each group on wound healing for HCAEC, HIAEC, HMVED-d, and hCMEC/D3 cells were similar, but exhibited significant differences across the three groups, with evidence of disrupted wound healing in P-OSA. However, wound healing in HMVEC-C was only affected by NC(+) (p < 0.01 vs. NC(-) or controls (CO). Furthermore, no significant differences emerged in HMVEC-L cell wound healing across all three groups. We conclude that circulating plasma EVs in P-OSA disrupt the integrity of the BBB and exert adverse effects on endothelial wound healing, particularly among OSA-NC(+) children, while also exhibiting endothelial cell type selectivity. Thus, circulating EVs cargo may play important roles in the emergence of end-organ morbidity in pediatric OSA.

Ruiz J, Buela-Casal G. Anxiety and Depression in Patients with Obstructive Sleep Apnoea before and after Continuous Positive Airway Pressure: The ADIPOSA Study

The prevalence and treatment response of depression and anxiety symptoms in obstructive sleep apnoea (OSA), although widely addressed in research and clinical settings, still remain unclear due to overlapping symptoms. The ADIPOSA study sought to elucidate the presence of non-overlapping symptoms of depression and anxiety in patients with moderate to severe OSA before and after continuous positive airway pressure (CPAP) treatment. Forty-eight adults aged 18-80 (68.75% men) with moderate to severe OSA were enrolled in this twelve-week longitudinal single-arm trial and completed a full-night ambulatory sleep diagnostic test and an assessment of cognitive-affective depression and anxiety symptoms using the Beck-Depression Inventory-Fast Screen (BDI-FS), the State-Trait Depression Inventory (IDER) and the State-Trait Anxiety Inventory (STAI). We found no cognitive-affective depression or anxiety symptoms of clinical relevance at baseline. The amelioration of depression and anxiety symptoms after CPAP use was only statistically significant when considering anxiety-trait (p < 0.01; d = 0.296) and euthymia (p < 0.05; d = 0.402), the distinctive component of depression. Although dysthymia or high negative affect remained unchanged, CPAP may be effective at reducing the lack of positive affect, a well-established health-protective factor. However, not until depression and anxiety disorders related to OSA are accurately measured in clinical and research settings will it be possible to obtain robust conclusions on the occurrence and amelioration of these symptoms after treatment.

Technology to Detect Driver Sleepiness

This article reports on sleepiness, drowsiness, tiredness, and fatigue. An assessment of sleepiness can be done with electroencephalograms, electrooculograms, and electromyograms in validated tests, such as the multiple sleep latency test and the maintenance of wakefulness test. These 2 tests serve as references for quantitative assessment of daytime sleepiness and drowsiness. Correlates for sleepiness, such as reaction time tests, can be used but are less reliable. Questionnaires are self-administered and popular measures for perceived sleepiness. Driver drowsiness assessment is an important part of sleep laboratory testing, because European Union regulations require assessments due to risk of accidents in patients with sleep disorders.

A Sleep Apnea Therapy Device Uses No Added Pressure

Sleep Apnea is a common sleeping disorder that affects over 25 million Americans. Due to the complex nature of sleep apnea, and the human body, neither an effective nor comfortable treatment option for sleep apnea has been developed. Accordingly, we describe a novel alternative to current sleep apnea therapies, including CPAP therapy. A comfortable device for treating sleep apnea incorporates a mask, a flexible hose and a chamber for collecting expired air containing CO₂. A sensor detects apnea and a control system automatically adjusts the amount of rebreathed CO₂ minimize apnea and also minimize arousal.

A review on wearable photoplethysmography sensors and their potential future applications in health care

Photoplethysmography (PPG) is an uncomplicated and inexpensive optical measurement method that is often used for heart rate monitoring purposes. PPG is a non-invasive technology that uses a light source and a photodetector at the surface of skin to measure the volumetric variations of blood circulation. Recently, there has been much interest from numerous researchers around the globe to extract further valuable information from the PPG signal in addition to heart rate estimation and pulse oxymetry readings. PPG signal’s second derivative wave contains important health-related information. Thus, analysis of this waveform can help researchers and clinicians to evaluate various cardiovascular-related diseases such as atherosclerosis and arterial stiffness. Moreover, investigating the second derivative wave of PPG signal can also assist in early detection and diagnosis of various cardiovascular illnesses that may possibly appear later in life. For early recognition and analysis of such illnesses, continuous and real-time monitoring is an important approach that has been enabled by the latest technological advances in sensor technology and wireless communications. The aim of this article is to briefly consider some of the current developments and challenges of wearable PPG-based monitoring technologies and then to discuss some of the potential applications of this technology in clinical settings.

Phenotype-Based and Self-Learning Inter-Individual Sleep Apnea Screening With a Level IV-Like Monitoring System

Purpose: We propose a phenotype-based artificial intelligence system that can self-learn and is accurate for screening purposes and test it on a Level IV-like monitoring system.

Methods: Based on the physiological knowledge, we hypothesize that the phenotype information will allow us to find subjects from a well-annotated database that share similar sleep apnea patterns. Therefore, for a new-arriving subject, we can establish a prediction model from the existing database that is adaptive to the subject. We test the proposed algorithm on a database consisting of 62 subjects with the signals recorded from a Level IV-like wearable device measuring the thoracic and abdominal movements and the SpO2.

Results: With the leave-one-subject-out cross validation, the accuracy of the proposed algorithm to screen subjects with an apnea-hypopnea index greater or equal to 15 is 93.6%, the positive likelihood ratio is 6.8, and the negative likelihood ratio is 0.03.

Conclusion: The results confirm the hypothesis and show that the proposed algorithm has potential to screen patients with SAS.

A Novel Intracranial Pressure Readout Circuit for Passive Wireless LC Sensor

We present a wide frequency range, low cost, wireless intracranial pressure monitoring system, which includes an implantable passive sensor and an external reader. The passive sensor consists of two spiral coils and transduces the pressure change to a resonant frequency shift. The external portable reader reads out the sensor's resonant frequency over a wide frequency range (35 MHz-2.7 GHz). We propose a novel circuit topology, which tracks the system's impedance and phase change at a high frequency with low-cost components. This circuit is very simple and reliable. A prototype has been developed, and measurement results demonstrate that the device achieves a suitable measurement distance (>2 cm), sufficient sample frequency (>6 Hz), fine resolution, and good measurement accuracy for medical practice. Responsivity of this prototype is 0.92 MHz/mmHg and resolution is 0.028 mmHg. COMSOL specific absorption rate simulation proves that this system is safe. Considerations to improve the device performance have been discussed, which include the size of antenna, the power radiation, the Analog-to-digital converter (ADC) choice, and the signal processing algorithm.