Portable Sleep Apnea Syndrome Screening and Event Detection Using Long Short-Term Memory Recurrent Neural Network.

Obstructive sleep apnea/hypopnea syndrome (OSAHS) is characterized by repeated airflow partial reduction or complete cessation due to upper airway collapse during sleep. OSAHS can induce frequent awake and intermittent hypoxia that is associated with hypertension and cardiovascular events. Full-channel Polysomnography (PSG) is the gold standard for diagnosing OSAHS; however, this PSG evaluation process is unsuitable for home screening. To solve this problem, a measuring module integrating abdominal and thoracic triaxial accelerometers, a pulsed oximeter (SpO2) and an electrocardiogram sensor was devised in this study. Moreover, a long short-term memory recurrent neural network model is proposed to classify four types of sleep breathing patterns, namely obstructive sleep apnea (OSA), central sleep apnea (CSA), hypopnea (HYP) events and normal breathing (NOR). The proposed algorithm not only reports the apnea-hypopnea index (AHI) through the acquired overnight signals but also identifies the occurrences of OSA, CSA, HYP and NOR, which assists in OSAHS diagnosis. In the clinical experiment with 115 participants, the performances of the proposed system and algorithm were compared with those of traditional expert interpretation based on PSG signals. The accuracy of AHI severity group classification was 89.3%, and the AHI difference for PSG expert interpretation was 5.0±4.5. The overall accuracy of detecting abnormal OSA, CSA and HYP events was 92.3%.

An integrated microfluidic system with field-effect-transistor sensor arrays for detecting multiple cardiovascular biomarkers from clinical samples.

Certain blood-borne biomarkers offer a potent methodology for understanding the risk of cardiovascular diseases (CVDs) with clinicians generally advocating the use of multiple biomarkers for proper risk assessment of CVDs. Herein four such CVDs biomarkers- C-reactive protein (CRP), N-terminal pro b-type natriuretic peptide (NT-proBNP), cardiac troponin I (cTnI), and fibrinogen- were rapidly (5 min) analyzed from clinical samples (~ 4 µL) on an integrated microfluidic platform equipped with 1) immobilized highly specific aptamer probes and 2) field-effect transistor (FET)-based sensor arrays. The calibration curve from the FET sensor arrays showed good agreement in the physiological concentration ranges for CRP (0.1-50 mg/L), NT-proBNP (50-10,000 pg/mL), cTnI (1-10,000 pg/mL), and fibrinogen (0.1-5 mg/mL). The developed prototype of this fully automated portable device requires minimal reagent and sample inputs and consequently shows great promise for next-generation point-of-care devices assaying multiple CVDs biomarkers in clinical samples.

A sample-to-answer, portable platform for rapid detection of pathogens with a smartphone interface.

Emerging and re-emerging infectious diseases pose global threats to human health. Although several conventional diagnostic methods have been widely adopted in the clinic, the long turn-around times of "gold standard" culture-based techniques, as well as the limited sensitivity of lateral-flow strip assays, thwart medical progress. In this study, a smartphone-controlled, automated, and portable system was developed for rapid molecular diagnosis of pathogens (including viruses and bacteria) via the use of a colorimetric loop-mediated isothermal amplification (LAMP) approach on a passive, self-driven microfluidic device. The system was capable of 1) purifying viral or bacterial samples with specific affinity reagents that had been pre-conjugated to magnetic beads, 2) lysing pathogens at low temperatures, 3) executing isothermal nucleic acid amplification, and 4) quantifying the results of colorimetric assays for detection of pathogens with an integrated color sensor. The entire, 40 min analytical process was automatically performed with a novel punching-press mechanism that could be controlled and monitored by a smartphone. As a proof of concept, the influenza A (H1N1) virus and methicillin-resistant Staphylococcus aureus bacteria were used to characterize and optimize the device, and the limits of detection were experimentally found to be 3.2 × 10-3 hemagglutinating units (HAU) per reaction and 30 colony-forming units (CFU) per reaction, respectively; both such values represent high enough sensitivity for clinical adoption. Moreover, the colorimetric assay could be both qualitative and quantitative for detection of pathogens. This is the first instance of an easy-to-use, automated, and portable system for accurate and sensitive molecular diagnosis of either viruses or bacteria, and it is envisioned that this smartphone-controlled apparatus may serve as a platform for clinical, point-of-care pathogen detection, particularly in resource-limited settings.

An integrated microfluidic platform to perform uninterrupted SELEX cycles to screen affinity reagents specific to cardiovascular biomarkers.

As cardiovascular diseases (CVD) are responsible for millions of deaths annually, there is a need for rapid and sensitive diagnosis of CVD at earlier stages. Aptamers generated by systematic evolution of ligands by exponential enrichment (SELEX) processes have been shown to be superior to conventional antibody-based cardiac biomarker detection. However, SELEX is a complicated, lengthy procedure requiring multiple rounds of extraction/amplification and well-trained personnel. To circumvent such issue, we designed an automated, miniaturized SELEX platform for the screening of aptamers towards three protein biomarkers associated with CVDs: N-terminal pro-peptide of B-type natriuretic peptide, human cardiac troponin I, and fibrinogen. The developed microfluidic platform was equipped with microfluidic devices capable of sample transport and mixing along with an on-chip nucleic acid amplification module such that the entire screening process (5 rounds of selection in 8 h.) could be performed consecutively on a single chip while consuming only 35 µL of reagents in each cycle. This system may therefore serve as a promising, sensitive, cost-effective platform for the selection of aptamers specific for CVD biomarkers.

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.

Detecting miRNA biomarkers from extracellular vesicles for cardiovascular disease with a microfluidic system.

According to World Health Organization reports, cardiovascular diseases (CVDs) are amongst the major causes of death globally and are responsible for over 18 million deaths every year. Traditional detection methods for CVDs include cardiac computerized tomography scans, electrocardiography, and myocardial perfusion imaging scans. Although diagnosis of CVDs through such bio-imaging techniques is common, these methods are relatively costly and cannot detect CVDs in their earliest stages. In contrast, the levels of certain micro RNA (miRNA) biomarkers extracted from extracellular vesicles (EVs) in the bloodstream have been recognized as promising indicators for early CVD detection. However, detection and quantification of miRNA using existing methods are relatively labor-intensive and time-consuming. In this study, a new integrated microfluidic system equipped with highly sensitive field-effect transistors (FETs) was capable of performing EV extraction, EV lysis, target miRNA isolation and miRNA detection within 5 h. The limit of detection was within the physiological range (femtomolar) for two targeted miRNAs, miR-21 and miR-126, meaning that this integrated microfluidic system has the potential to be used as a tool for early detection of CVDs.

Sleep Apnea Detection Based on Thoracic and Abdominal Movement Signals of Wearable Piezo-Electric Bands.

Physiologically, the thoracic (THO) and abdominal (ABD) movement signals, captured using wearable piezo-electric bands, provide information about various types of apnea, including central sleep apnea (CSA) and obstructive sleep apnea (OSA). However, the use of piezo-electric wearables in detecting sleep apnea events has been seldom explored in the literature. This study explored the possibility of identifying sleep apnea events, including OSA and CSA, by solely analyzing one or both the THO and ABD signals. An adaptive non-harmonic model was introduced to model the THO and ABD signals, which allows us to design features for sleep apnea events. To confirm the suitability of the extracted features, a support vector machine was applied to classify three categories - normal and hypopnea, OSA, and CSA. According to a database of 34 subjects, the overall classification accuracies were on average 75.9%±11.7% and 73.8%±4.4%, respectively, based on the cross validation. When the features determined from the THO and ABD signals were combined, the overall classification accuracy became 81.8%±9.4%. These features were applied for designing a state machine for online apnea event detection. Two event-byevent accuracy indices, S and I, were proposed for evaluating the performance of the state machine. For the same database, the S index was 84.01%±9.06%, and the I index was 77.21%±19.01%. The results indicate the considerable potential of applying the proposed algorithm to clinical examinations for both screening and homecare purposes.

A Battery-Less, Implantable Neuro-Electronic Interface for Studying the Mechanisms of Deep Brain Stimulation in Rat Models.

Although deep brain stimulation (DBS) has been a promising alternative for treating several neural disorders, the mechanisms underlying the DBS remain not fully understood. As rat models provide the advantage of recording and stimulating different disease-related regions simultaneously, this paper proposes a battery-less, implantable neuro-electronic interface suitable for studying DBS mechanisms with a freely-moving rat. The neuro-electronic interface mainly consists of a microsystem able to interact with eight different brain regions bi-directionally and simultaneously. To minimize the size of the implant, the microsystem receives power and transmits data through a single coil. In addition, particular attention is paid to the capability of recording neural activities right after each stimulation, so as to acquire information on how stimulations modulate neural activities. The microsystem has been fabricated with the standard 0.18 µm CMOS technology. The chip area is 7.74 mm (2) , and the microsystem is able to operate with a single supply voltage of 1 V. The wireless interface allows a maximum power of 10 mW to be transmitted together with either uplink or downlink data at a rate of 2 Mbps or 100 kbps, respectively. The input referred noise of recording amplifiers is 1.16 µVrms, and the stimulation voltage is tunable from 1.5 V to 4.5 V with 5-bit resolution. After the electrical functionality of the microsystem is tested, the capability of the microsystem to interface with rat brain is further examined and compared with conventional instruments. All experimental results are presented and discussed in this paper.

5×5 CMOS capacitive sensor array for detection of the neurotransmitter dopamine.

This work presents miniaturized CMOS (complementary metal oxide semiconductor) capacitive sensors for detection of the neurotransmitter dopamine (DA) down to the sub-fM range. Sensing resolution is significantly enhanced by monolithic sensor integration to reduce the parasitic effect and the use of sub-µm interdigitated microelectrodes as the sensing interface. The 5 × 5 sensor array contains five designs of different electrode sizes and each design has five sensors. The positive charges produced from protonation of boronate and amino group after immobilization of 4-carboxyphenylboronic acid (CPBA) result in an increase of the electrode-analyte capacitance. Then the negative charges produced after binding of CPBA and DA molecules decrease the electrode-analyte capacitance. Signal transduction is achieved through a CMOS readout circuit whose output frequency is inversely proportional to the capacitance. Experimental results showed the ratios of average percentage capacitance changes of the experiment groups over those of the control groups were all larger than one for the five designs at DA concentration of 0.1 fM. Selectivity against the non-analyte species, such as tyramine, has also been demonstrated.