Epilepsy is a neurological disorder characterized by different symptoms, including seizures, stiffness of muscles, uncontrollable movement of the body, and multiple psychological abnormalities. Electroencephalogram (EEG) is extensively used in the diagnosis of epilepsy. The presence of abnormal wave complexes observed in the EEG signal helps in the diagnosis of epilepsy. There are multiple databases containing EEG signals from epileptic patients, which are used in developing support systems for neurologists to augment the diagnosis or prediction of epilepsy. However, few epilepsy databases are specific to the South-Asian region. Of these databases, no continuous recording of EEG signals with multiple wave complexes in unipolar and bipolar EEG signals is provided. This study aims to publish the first South-Asian database containing continuous EEG signals from chronic epileptic patients with multiple wave complexes in unipolar and bipolar formats. Moreover, apart from the wave complexes, the EEG recordings have also been marked for artifacts which may be used to train the system for automatic rejection of the artifact noise from the EEG epileptic signals.

This article presents an area and power-efficient system-on-chip (SoC) for vital signs monitoring to provide patients with remote monitoring. It measures five important vitals including blood oxygen saturation (SpO2), respiration rate (RR), heart rate (HR), HR variability (HRV), and temperature. The proposed SoC utilizes a photoplethysmography (PPG) signal to compute HR, HRV, SpO2, and RR. The PPG signal is amplified and filtered using a PPG readout that includes a transimpedance amplifier (TIA) with a switched integrator (SI) to filter and amplify the signal. A differential second-order, delta-sigma analog-to-digital converter ($\Delta \Sigma $-ADC) is adopted to digitize the PPG signal. The SoC also comprises a low-power LED driver for both red and infrared (IR) LEDs which operate in pulsed mode with a 0.625% duty cycle. A vital signs extractor performs feature extraction (FE) and computes the vital signs with a maximum absolute error of less than 1%. In this work, the temperature is also measured by employing a Wheatstone bridge (WhB)-based temperature sensor which integrates thermal resistors into a second-order$\Delta \Sigma $-ADC. The proposed system shares$\Delta \Sigma $-ADC for digitizing the PPG signal and the temperature readings to reduce both area and power consumption. The proposed system computes the temperature over the human’s temperature range ($32~^{\circ }$C to$42~^{\circ }$C) with an accuracy of +/$- 0.09~^{\circ }$C. The SoC is implemented using a 180 nm CMOS process with an area of 4.8 mm2 while consuming$206~\mu $W.

This paper presents an ensemble machine-learning approach to monitor the blood volume decomposition state for early hypovolemia detection. Hypovolemia is one of the major causes of preventable deaths in trauma cases. The proposed algorithm discriminates hypovolemia from normovolemia and further classifies hypovolemia into relative and absolute hypovolemia. The algorithms for blood volume classification are analyzed by extracting 13 distinct features from multi-modal physiological signals including Photoplethysmogram, Electrocardiogram, and Seismocardiogram. We compared different Machine Learning classifiers for the multi-class classification problem. We have validated our algorithm on a publicly available dataset collected from six animals undergoing normovolemia, relative hypovolemia, and absolute hypovolemia conditions. The best-performing algorithm is the Artificial Neural Network- (ANN) for the normovolemia/hypovolemia classifier with an accuracy of 93.2% and an F1-score of 0.97. For the absolute/relative hypovolemia (AH-RH) classifier, Long Short-Term Memory offers an accuracy of 95.1% and an F1-score of 0.97. The proposed classifiers outperform the state-of-the-art algorithms and achieve the highest accuracy and F1-score, serving as a potential decision-support tool to observe blood volume decomposition state and help develop context-sensitive hypovolemia therapeutic strategies.

Current electroencephalogram (EEG) measuring systems are bulky, impose constraints on patients, and require pre and post-measuring procedures. Usually, the EEG systems use either wet or dry EEG sensors, with the former suffers from skin preparation, the issues of adhesive conductive gels, and one-time usability whereas the latter causes skin irritation, abrasion, and pain upon pressure. Hence, these sensors are not suitable for long-term measurements. This paper presents a novel, wireless, behind-the-ear wearable EEG acquisition device that incorporates flexible dry EEG sensors. Silver ink-printed flexible sensors are fabricated using screen printing to overcome the above-mentioned drawbacks and limitations of conventional EEG sensors. The flexible sensors form a capacitive link with the skin via an adhesive layer between the sensor and the person's skin and are capable of acquiring the EEG without any skin preparation or gel. The performance of the printed flexible EEG sensors is tested by comparing them with the standard Ag/AgCl pre-gelled sensors. The alpha wave test and evoked potential EEG test are also performed for verification. The proposed device has a small form factor similar to a hearing aid and an in-house configurable Analog Front End (AFE) and Digital Back End (DBE) Processor and is capable of acquiring continuous EEG for a longer duration in a user-friendly and socially discrete manner.

Blood pressure (BP) is considered one of the key vital signs that provide valuable medical information about cardiovascular activity. Conventionally, cuff-based devices are used to measure BP which limits their usage for continuous monitoring. This paper presents a cuff-less BP estimation processor using photoplethysmography (PPG) signals with a Deep Neural Network (DNN). Spectral and temporal features are extracted from the PPG signals and then used to train and evaluate the machine learning (ML) algorithms. The proposed algorithm is evaluated using the MIMIC II database for systolic blood pressure (SBP) and diastolic blood pressure (SBP) estimation. The proposed BP estimation processor is implemented using a 180nm CMOS process with an area of 3.45mm2and consumes $73 \mu \mathrm{W}$. It achieves a mean absolute error in systolic BP of $0.0657 \pm 4.7$ mmHg and diastolic BP of $0.792 \pm 4.61$ mmHg which outperforms the state-of-the-art BP estimation algorithms.

Conventionally, monitoring the depth of anesthesia (DoA) is performed using the standard procedures of either observing the patient’s vitals or through commercial electroencephalogram (EEG)-based monitors. The reports of intraoperative awareness indicate that these methods are still unreliable for all patients and anesthetic agents. This paper proposes a novel approach for accurate DoA estimation based on Stationary Wavelet Transform (SWT) and fractal features while utilizing Multilayer Perceptron (MLP) Classifier, a class of Feed Forward Neural Network. The classifier utilizes an optimized temporal, fractal and spectral feature set to identify the patient conscious level irrespective of age and the type of anesthetic agent. The proposed algorithm is validated on 95 patients (age 5 months-67 years), (weight: 6 - 90 Kg). The anesthetic agents used in this study include Propofol, Sevoflurane, Isoflurane, Fentanyl, Ketamine, and Caudal. The proposed DoA classifier outperforms the state-of-the-art DoA prediction algorithms with the highest accuracy of 96.8% while utilizing minimized feature set and a deep learning-based MLP classifier for the first time in literature.

Asthma has been associated with a sharp increase in the global prevalence, morbidity, mortality, and economic burden over the past several years. This paper presents vitals monitoring system-on-chip (SoC) that measures the heart rate (HR), and its variability (HRV), blood oxygen saturation (SpO2), and respiratory rate (RR) from a Photoplethysmography signal (PPG). The proposed SoC integrates a direct current-to-digital analog front end for PPG signal acquisition, a vitals extraction processor, and a time-multiplexed LED driver for red and IR LEDs. The PPG readout employs a second-order, continuous-time, delta-sigma analog to digital converter (ΔΣ-ADC) with a 0.1% duty-cycled operation to reduce power consumption while achieving a 110dB dynamic range. The SoC is implemented in a 180nm CMOS process with an active area of 4.5mm2. The functionality of the proposed SoC is verified on patients’ recordings from Beth Israel Deaconess Medical Center (BIDMC). The proposed SoC achieves high accuracy measurements with a maximum absolute error percentage of <2% for all vitals while consuming 385μW.

Measuring the respiratory rate (RR) in a hospital setting involves wearing bulky uncomfortable sensors. Accurate measurement can be performed by extracting respiratory modulations from Photoplethysmogram (PPG) signal obtained from a pulse oximeter indirectly. Respiratory rate estimates from derived modulations are fused to get robust results. However, all the three extracted modulations are not true representative of the respiration activity all the time, subject to the patient's health condition and body position. Therefore, we propose novel modulation quality indices (MQI) to check the quality of the extracted modulations before computing the RR from it. We take the mean of only those estimates which pass an empirical quality threshold. This approach increases the robustness of the mean fusion methodology. We have validated our algorithm on a publicly available dataset: benchmark dataset CapnoBase. The proposed approach outperforms the current state-of-the-art with mean absolute errors (median, 25$^{th}$ 75$^{th}$ percentiles with 32-sec window size) of 0.4 (0.1-0.7) without discarding any PPG window, thus enabling accurate RR estimates.

Diagnostic testing plays an important role in modern medicine, helping physicians make informed decisions regarding disease diagnosis and treatment. Proteins’ biomarkers are utilized to detect disease onset, progression, efficacy of medicines, and patient susceptibility to get a specific kind of disease. Electrochemical impedance spectroscopy (EIS) is likely to underpin the progressive drive toward sensitive, miniaturized, and portable biomarker detection practices. The EIS is a highly sensitive detection method adopted to find the electrical response of chemical samples by applying low amplitude ac voltages/currents with tunable frequency. Conventional EIS systems use mixers and lock-in amplifiers to find both the real and imaginary components of the complex impedance. In this article, we present a partially integrated EIS measurement system to find the impedance of a biological sample. It includes a programmable sine-wave synthesizer (SWS) block with a frequency range of$500 \mu $Hz to 100 kHz. The implementation is based on switched-capacitor filters that adjust the cutoff frequency by changing the clock. The sample impedance is measured through mostly digital magnitude and phase-detection blocks. The proposed EIS system is realized using a 0.18-$\mu \text{m}$technology with a 0.35-mm2 active area and 380-$\mu \text{W}$power consumption. The proposed magnitude detection archives a differential nonlinearity (DNL) performance of −0.34/+0.3 LSB and an integral nonlinearity (INL) of −0.75/+2 LSB. The system is used to measure the impedance of biological samples containing tumor necrosis factor alpha (TNF-$\alpha$) protein at variable concentrations.

Electrical impedance spectroscopy (EIS) is a powerful technology for accurate disease detection at the point- of-care (POC) from biosensors. Nevertheless, EIS usually involves lock-in amplifiers and mixers to detect both the magnitude and phase of the complex impedances. This paper presents a highly digital impedance measurement system-on- chip, which can convert the magnitude and phase of impedance to 10-bits digital codes integrated with a filter-based wide-range programmable sinusoidal wave synthesizer (SWS). The proposed SWS utilizes switched-capacitor circuits such that the corner frequency can be adjusted by changing its switching frequency. The proposed EIS system was fabricated using a 180nm process with an active area of only 0.35 mm2. The SWS generates output frequency in the range of 579 μΗζ-48.9 kHz with measured total harmonic distortion of 0.152% at 100 Hz and 0.116% at 10 kHz. The DNL of the proposed magnitude converter is within -0.34/+0.3 LSB and the INL is around -0.75/+2 LSB. To validate the function of the proposed EIS measurement system, it is utilized to detect the tumor necrosis factor α in biological samples.

Most surgical procedures are not possible without general anesthesia which necessitates continuous and accurate monitoring of the patients' level of hypnosis (LoH). Currently, the LoH is monitored using the conventional methods of either observing the patient's physiological parameters or using electroencephalogram (EEG)-based monitors. To overcome the limitations of the conventional methods, this work implements an accurate EEG-based LoH monitoring processor using a bagged tree machine-learning (BTML) classifier. It is based on 12 temporal and spectral features to incorporate robustness against age variation and achieve high classification accuracy. Spectral features are computed using discrete wavelet transform (DWT) that uses time-multiplexed filter (TMF) architecture. The TMF DWT consumes 110.6-nJ/feature vector for a 100-tap filter while reducing the area by 11% compared with the conventional method. Moreover, the BTML is implemented using a pipelined approach which enables an efficient on-chip implementation to reduce the hardware cost by 15× compared with the parallel approach. The proposed processor is implemented using a 180-nm CMOS process with an active area of 0.9 mm2while consuming 1.6 mW. The accuracy of the proposed hypnotic state monitor is verified using two EEG databases with a total of 95 patients and achieves a sensitivity and specificity of 95.4% and 97.7%, respectively.

Long-term, continuous monitoring of human brain activity with closed-loop precise neurostimulation can potentially help to treat conditions such as epilepsy and Parkinson. These implantable devices are used to sense the brain signal, detect an abnormality, and stimulate once the abnormal activity is detected to mitigate the adverse effect. The target is to achieve the maximum efficacy while balancing the signal acquisition and intelligent processing to ensure minimize battery replacement frequency. This paper presents the design of the implantable Electrocorticography (ECoG) based system for intractable epileptic seizure treatment. The challenges, design choices, and trade-offs, related to the neurological disorder in the implantable environment are discussed. A multi-channel ultra-low-power instrumentation amplifier (IA) with digital electrode offset rejection loop (EORL) with a cutoff frequency of <; 0.5Hz to mitigate the electrode offset effect with a fast settling of <; 0.1 Sec to ensure real-time recording. The implantable system is realized in 180nm CMOS process to ensure area-and-power efficient design.

Accurate monitoring of the depth of anesthesia (DoA) is essential for intraoperative and postoperative patient's health. Commercially available electroencephalograph (EEG)-based DoA monitors are recommended only for certain anesthetic drugs and specific age-group patients. This paper presents a machine learning classification processor for accurate DoA estimation irrespective of the patient's age and anesthetic drug. The classification is solely based on six features extracted from EEG signal, i.e., spectral edge frequency (SEF), beta ratio, and four bands of spectral energy (FBSE). A machine learning fine decision tree classifier is adopted to achieve a four-class DoA classification (deep, moderate, and light DoA versus awake state). The feature selection and the classification processor are optimized to achieve the highest classification accuracy for the state of moderate anesthesia required for the surgical operations. The proposed 256-point fast Fourier transform accelerator is implemented to realize SEF, beta ratio, and FBSE that enables minimal latency and high accuracy feature extraction. The proposed DoA processor is implemented using a 65 nm CMOS technology and experimentally verified using field programming gate array (FPGA) based on the EEG recordings of 75 patients undergoing elective surgery with different types of anesthetic agents. The processor achieves an average accuracy of 92.2% for all DoA states, with a latency of 1s The 0.09 mm2DoA processor consumes 140nJ/classification.

This live demonstration showcases a noninvasive glucose monitoring device based on a single wavelength near-infrared (NIR) spectroscopy. The analog frontend record the Photoplethysmographic (PPG) signal from the fingertip. Ten discriminating features are extracted from the PPG signal to predict the blood glucose level using (Exponential Gaussian Process) machine learning regression. Visitors can easily insert their fingers into the finger-clip part of the system to measure their blood glucose level and display it on a mobile phone.

Continuous glucose monitoring is essential for patients to avoid complications of both hypoglycemia and hyperglycemia. This paper presents a novel non-invasive continuous blood glucose monitoring system based on a single wavelength near-infrared (NIR) spectroscopy. The analog frontend of the system is designed with a single NIR LED to record the Photoplethysmographic (PPG) signal from the fingertip with motion artifacts removal and a bias current rejection up to 20uA. The proposed digital backend extracts 10 discriminating features from the PPG signal to predict the blood glucose level using (Exponential Gaussian Process) machine learning regression. To realize the feature extraction on FPGA, a novel two-dimensional structure of 256-point Fast Fourier Transform (FFT) is implemented which achieves a 47% reduction in complex multiplications compared to the conventional Radix-2 algorithm. The performance of the proposed system is validated using 200 patients PPG recordings and glucose levels measured via a commercial glucometer. It successfully predicts the glucose level with a mean absolute relative difference (mARD) of 8.97%.

Cardiac arrhythmia (CA) is one of the most serious heart diseases that lead to a very large number of annual casualties around the world. The traditional electrocardiography (ECG) devices usually fail to capture arrhythmia symptoms during patients' hospital visits due to their recurrent nature. This paper presents a wearable long-term single-lead ECG processor for the CA detection at an early stage. To achieve on-sensor integration and long-term continuous monitoring, an ultra-low complexity feature extraction engine using reduced feature set of four (RFS4) is proposed. It reduces the area by >25% compared to the conventional QRS complex detection algorithms without compromising the accuracy. Moreover, RFS4 eliminates the need for complex machine learning decision logic for the detection of premature ventricular contraction (PVC) and nonsustained ventricular tachycardia (NVT). To ensure correct functional verification, the proposed system is implemented on FPGA and tested using the MIT-BIH ECG arrhythmia database. It achieves a sensitivity and specificity of 94.64% and 99.41%, respectively. The proposed processor is also synthesized using 0.18um CMOS technology with an overall energy efficiency of 139 nJ/detection.

Neurodegenerative disorders (NDDs) are chronic diseases of the human central nervous system that cause degradation in mobility and cognitive functioning. Continuous assessment of gait for patients with NDDs is a crucial element of future care and treatment. This paper presents a wearable NDD detection system that monitors the person's gait and infers 3 key gait features: stride time, its fluctuation and autocorrelation decay factor based on data extracted from an unobtrusive force resistive sensor embedded in patient's shoe. It is designed to distinguish between different NDDs: (Huntington's disease (HD), Parkinson Disease (PD), and Amyotrophic Lateral Sclerosis (ALS)) and healthy individuals using only 3 features. The proposed NDD classification algorithm is verified experimentally using a full FPGA implementation with patients' recordings from Physionet Gait Dynamics data set. It achieves a classification accuracy of 93.8%, 89.1%, 94% and 93.3%, for ALS, HD, PD, and healthy person, respectively, from a total set of 64 subjects.

An interference and multipath resilient Body Channel Communication transceiver with ground effect cancellation for binaural hearing aids application is presented. The channel characteristics are measured between the intended points of transmission and reception to measure the path loss. The energy efficient transceiver is based on Hybrid OFDM folded in FSK modulated signal to mitigate the multipath problem in binaural hearing aids. By eliminating the needs for DACs, ADCs and power amplifier, the proposed design is free from peak-to-average power ratio (PAPR) problem. It utilizes 4 channels Adaptive Frequency Hopping technique for resisting interference. A variable gain LNA is exploited in this implementation to overcome the variable ground effect of BCC. The transceiver is implemented in 65nm CMOS process with an active area of 2.28mm2for baseband OFDM and a data rate transmission of 1 Mbps while consuming 1.54mW.