Search

Spatially resolved transcriptomics (SRT) is a pioneering method for simultaneously studying morphological contexts and gene expression at single-cell precision. Data emerging from SRT are multifaceted, presenting researchers with intricate gene expression matrices, precise spatial details and comprehensive histology visuals. Such rich and intricate datasets, unfortunately, render many conventional methods like traditional machine learning and statistical models ineffective. The unique challenges posed by the specialized nature of SRT data have led the scientific community to explore more sophisticated analytical avenues. Recent trends indicate an increasing reliance on deep learning algorithms, especially in areas such as spatial clustering, identification of spatially variable genes and data alignment tasks. In this manuscript, we provide a rigorous critique of these advanced deep learning methodologies, probing into their merits, limitations and avenues for further refinement. Our in-depth analysis underscores that while the recent innovations in deep learning tailored for SRT have been promising, there remains a substantial potential for enhancement. A crucial area that demands attention is the development of models that can incorporate intricate biological nuances, such as phylogeny-aware processing or in-depth analysis of minuscule histology image segments. Furthermore, addressing challenges like the elimination of batch effects, perfecting data normalization techniques and countering the overdispersion and zero inflation patterns seen in gene expression is pivotal. To support the broader scientific community in their SRT endeavors, we have meticulously assembled a comprehensive directory of readily accessible SRT databases, hoping to serve as a foundation for future research initiatives. [ABSTRACT FROM AUTHOR]

Prostate cancer (PC) is the most frequently diagnosed non-skin cancer in the world. Previous studies have shown that genomic alterations represent the most common mechanism for molecular alterations responsible for the development and progression of PC. This highlights the importance of identifying functional genomic variants for early detection in high-risk PC individuals. Great efforts have been made to identify common protein-coding genetic variations; however, the impact of non-coding variations, including regulatory genetic variants, is not well understood. Identification of these variants and the underlying target genes will be a key step in improving the detection and treatment of PC. To gain an understanding of the functional impact of genetic variants, and in particular, regulatory variants in PC, we developed an integrative pipeline (AGV) that uses whole genome/exome sequences, GWAS SNPs, chromosome conformation capture data, and ChIP-Seq signals to investigate the potential impact of genomic variants on the underlying target genes in PC. We identified 646 putative regulatory variants, of which 30 significantly altered the expression of at least one protein-coding gene. Our analysis of chromatin interactions data (Hi-C) revealed that the 30 putative regulatory variants could affect 131 coding and non-coding genes. Interestingly, our study identified the 131 protein-coding genes that are involved in disease-related pathways, including Reactome and MSigDB, for most of which targeted treatment options are currently available. Notably, our analysis revealed several non-coding RNAs, including RP11-136K7.2 and RAMP2-AS1, as potential enhancer elements of the protein-coding genes CDH12 and EZH1, respectively. Our results provide a comprehensive map of genomic variants in PC and reveal their potential contribution to prostate cancer progression and development. [ABSTRACT FROM AUTHOR]

Objective. In this study, we test the hypothesis that if, as demonstrated in a previous study, brachial arteries exhibit hysteresis as the occluding cuff is deflated and fail to open until cuff pressure (CP) is well below true intra-arterial blood pressure (IABP). Approach Estimating systolic (SBP) and diastolic blood pressure (DBP) from the presence of Korotkoff sounds as CP increases may eliminate these errors and give more accurate estimates of SBP relative to IABP readings. Main Results. In 63 subjects of varying age 45.4 ± 19.9 years (range 21–76 years), including 44 men (45.2 ± 19.5, range 21–76 years) and 19 women (45.6 ± 21.4, range 21 – 75 years), there was a significant (p < 0.0001) increase in SBP from 124.4 ± 15.7 to 129.2 ± 16.3 mmHg and a significant (p < 0.0001) increase in DBP from 70.2 ± 10.7 to 73.6 ± 11.5 mmHg. Of the 63 subjects, 59 showed a positive increase in SBP (1–19 mmHg) and 5 subjects showed a reduction (−5 to −1 mmHg). The average differences for SBP estimates derived as the cuff inflates and estimates derived as the cuff deflates were 4.9 ± 4.7 mmHg, not dissimilar to the differences observed between IABP and NIBP measurements. Although we could not develop multiparameter linear or nonlinear models to explain this phenomenon we have clearly demonstrated through analysis of variance test that both body mass index (BMI) and pulse wave velocity are implicated, supporting the hypothesis that the phenomenon is associated with age, higher BMI and stiffer arteries. Significance. The implications of this study are potentially profound requiring the implementation of a new paradigm for NIBP measurement and a revision of the international standards for their calibration. [ABSTRACT FROM AUTHOR]

Objective. In this study, we test the hypothesis that if, as demonstrated in a previous study, brachial arteries exhibit hysteresis as the occluding cuff is deflated and fail to open until cuff pressure (CP) is well below true intra-arterial blood pressure (IABP). Approach Estimating systolic (SBP) and diastolic blood pressure (DBP) from the presence of Korotkoff sounds as CP increases may eliminate these errors and give more accurate estimates of SBP relative to IABP readings. Main Results. In 63 subjects of varying age 45.4 ± 19.9 years (range 21â€"76 years), including 44 men (45.2 ± 19.5, range 21â€"76 years) and 19 women (45.6 ± 21.4, range 21 â€" 75 years), there was a significant (p < 0.0001) increase in SBP from 124.4 ± 15.7 to 129.2 ± 16.3 mmHg and a significant (p < 0.0001) increase in DBP from 70.2 ± 10.7 to 73.6 ± 11.5 mmHg. Of the 63 subjects, 59 showed a positive increase in SBP (1â€"19 mmHg) and 5 subjects showed a reduction (âˆ'5 to âˆ'1 mmHg). The average differences for SBP estimates derived as the cuff inflates and estimates derived as the cuff deflates were 4.9 ± 4.7 mmHg, not dissimilar to the differences observed between IABP and NIBP measurements. Although we could not develop multiparameter linear or nonlinear models to explain this phenomenon we have clearly demonstrated through analysis of variance test that both body mass index (BMI) and pulse wave velocity are implicated, supporting the hypothesis that the phenomenon is associated with age, higher BMI and stiffer arteries. Significance. The implications of this study are potentially profound requiring the implementation of a new paradigm for NIBP measurement and a revision of the international standards for their calibration. [ABSTRACT FROM AUTHOR]

Cardiovascular disease is known as the number one cause of death globally, with elevated blood pressure (BP) being the single largest risk factor. Hence, BP is an important physiological parameter used as an indicator of cardiovascular health. The use of automated non-invasive blood pressure (NIBP) measurement devices is growing, as they can be used without expertise and BP measurement can be performed by patients at home. Non-invasive cuff-based monitoring is the dominant method for BP measurement. While the oscillometric technique is most common, some automated NIBP measurement methods have been developed based on the auscultatory technique. By utilizing (relatively) large BP data annotated by experts, models can be trained using machine learning and statistical concepts to develop novel NIBP estimation algorithms. Amongst artificial intelligence (AI) techniques, deep learning has received increasing attention in different fields due to its strength in data classification and feature extraction problems. This paper reviews AI-based BP estimation methods with a focus on recent advances in deep learning-based approaches within the field. Various architectures and methodologies proposed todate are discussed to clarify their strengths and weaknesses. Based on the literature reviewed, deep learning brings plausible benefits to the field of BP estimation. We also discuss some limitations which can hinder the widespread adoption of deep learning in the field and suggest frameworks to overcome these challenges. [ABSTRACT FROM AUTHOR]

It is well known that non-invasive blood pressure measurements significantly underestimate true systolic blood pressure (SBP), and overestimate diastolic blood pressure (DBP). The aetiology for these errors has not yet been fully established. This study aimed to investigate the accuracy of Korotkoff sounds for detection of SBP and DBP points as used in brachial cuff sphygmomanometry. Brachial cuff pressure and Korotkoff sounds were obtained in 11 patients (6 males: 69.0 ± 6.2 years, 5 females: 71.8 ± 5.5 years) undergoing diagnostic coronary angiography. K2 Korotkoff sounds were obtained by high-pass filtering (>20 Hz) the microphone-recorded signal to eliminate low frequency components. Analysis of the timing of K2 Korotkoff sounds relative to cuff pressure and intra-arterial pressure shows that the onset of K2 Korotkoff sounds reliably detect the start of blood flow under the brachial cuff and their termination, marks the cuff pressure closely coincident with DBP. We have made the critical observation that blood flow under the cuff does not begin when cuff pressure falls just below SBP as is conventionally assumed, and that the delay in the opening of the artery following occlusion, and the consequent delay in the generation of K2 Korotkoff sounds, may lead to significant errors in the determination of SBP of up to 24 mmHg. Our data suggest a potential role of arterial stiffness as a major component of the errors recorded, with underestimation of SBP much more significant for subjects with stiff arteries than for subjects with more compliant arteries. [ABSTRACT FROM AUTHOR]

This paper aims to improve the performance of an electromyography (EMG) decoder based on a switching mechanism in controlling a rehabilitation robot for assisting human-robot cooperation arm movements. For a complex arm movement, the major difficulty of the EMG decoder modeling is to decode EMG signals with high accuracy in real-time. Our recent study presented a switching mechanism for carving up a complex task into simple subtasks and trained different submodels with low nonlinearity. However, it was observed that a “bump” behavior of decoder output (i.e., the discontinuity) occurred during the switching between two submodels. The bumps might cause unexpected impacts on the affected limb and thus potentially injure patients. To improve this undesired transient behavior on decoder outputs, we attempt to maintain the continuity of the outputs during the switching between multiple submodels. A bumpless switching mechanism is proposed by parameterizing submodels with all shared states and applied in the construction of the EMG decoder. Numerical simulation and real-time experiments demonstrated that the bumpless decoder shows high estimation accuracy in both offline and online EMG decoding. Furthermore, the outputs achieved by the proposed bumpless decoder in both testing and verification phases are significantly smoother than the ones obtained by a multimodel decoder without a bumpless switching mechanism. Therefore, the bumpless switching approach can be used to provide a smooth and accurate motion intent prediction from multi-channel EMG signals. Indeed, the method can actually prevent participants from being exposed to the risk of unpredictable loads. [ABSTRACT FROM AUTHOR]

The use of automated non-invasive blood pressure (NIBP) measurement devices is growing, as they can be used without expertise, and BP measurement can be performed by patients at home. Non-invasive cuff-based monitoring is the dominant method for BP measurement. While the oscillometric technique is most common, a few automated NIBP measurement methods have been developed based on the auscultatory technique. Amongst artificial intelligence (AI) techniques, deep learning has received increasing attention in different fields due to its strength in data classification, and feature extraction problems. This paper proposes a novel automated AI-based technique for NIBP estimation from auscultatory waveforms (AWs) based on converting the NIBP estimation problem to a sequence-to-sequence classification problem. To do this, a sequence of segments was first formed by segmenting the AWs, and their corresponding decomposed detail, and approximation parts obtained by wavelet packet decomposition method, and extracting features from each segment. Then, a label was assigned to each segment, i.e. (i) between systolic, and diastolic segments, and (ii) otherwise, and a bidirectional long short term memory recurrent neural network (BiLSTM-RNN) was devised to solve the resulting sequence-to-sequence classification problem. Adopting a 5-fold cross-validation scheme, and using a data base of 350 NIBP recordings gave an average mean absolute error of 1.7 ± 3.7 mmHg for systolic BP (SBP), and 3.4 ± 5.0 mmHg for diastolic BP (DBP) relative to reference values. Based on the results achieved, and comparisons made with the existing literature, it is concluded that the proposed automated BP estimation algorithm based on deep learning methods, and auscultatory waveform brings plausible benefits to the field of BP estimation. [ABSTRACT FROM AUTHOR]

This article presents a novel method for estimating systolic blood pressure (SBP) and diastolic blood pressure (DBP) from time-domain features extracted from oscillometric waveforms (OWs) using a long short-term memory (LSTM) recurrent neural network (RNN) method. First, we extract seven time-domain features from each cycle of OW, including the cuff pressure, the cardiac period, the trough-to-peak amplitude of OW, the time between the trough and the peak of the OW, the slopes of the oscillometric waveform envelope (OWE), and the maximum upslope of individual OWs. Second, we locate each feature vector in an noninvasive blood pressure (NIBP) record in one of three different phases (classes), namely, presystolic (PS), between systolic and diastolic (BSD), and after diastolic (AD), and form a target sequence. Then, we propose an LSTM-RNN approach to effectively learn the complex nonlinear relationship between the feature vector sequences and the target sequence. The SBP and DBP points are then obtained by mapping the beats at which the network output sequence switches from PS phase to BSD phase and from BSD phase to AD phase, respectively, to the deflation curve. Adopting a tenfold cross-validation scheme and using a database of 350 NIBP recordings gave an average mean error of −1.2 ± 5.9 mmHg for SBP and 1.8 ± 8.8 mmHg for DBP relative to reference values derived from a visual method of determining SBP and DBP. The proposed RNN-based approach uses all time-domain features available from each NIBP recording and can outperform traditional methods in blood pressure (BP) estimation. [ABSTRACT FROM AUTHOR]

This article presents a novel method of estimating systolic blood pressure (SBP) and diastolic BP (DBP) from time-domain features extracted from auscultatory and oscillometric waveforms and using Gaussian Mixture Models and Hidden Markov Model (GMM-HMM). The nine time-domain features selected include the cuff pressure (CP), the cardiac period (T), the energy of the Korotkoff pulses (KE), the oscillometric waveform envelope (OWE), the lag between the trough of the oscillometric waveforms (OWs) and the peak of the Korotkoff energy (Lag), the time between the trough and the peak of the OW (OWD), the slopes of the KE and OWE (SKE, SOWE), and the maximum upslope of individual OWs (MSOW). Adopting a fivefold cross-validation scheme and using a database of 350 noninvasive BP (NIBP) recordings gave an average mean error (± standard deviation of error) of −0.3 ± 4.2 mmHg for SBP and 2.9 ± 8.1 mmHg for DBP relative to reference values derived from a visual method of determining SBP and DBP. The significantly larger spread of DBP estimates relative to SBP, suggests that the criteria for determining DBP are poorly defined and would benefit from further experimental studies involving simultaneous invasive and noninvasive methods of measuring arterial pressure. We conclude that the proposed GMM-HMM BP estimation method outperforms previously reported methods in the literature and is a very promising method in improving the accuracy of automated noninvasive measurement of BP. [ABSTRACT FROM AUTHOR]

Post-stroke motor recovery highly relies on voluntarily participating in active rehabilitation as early as possible for promoting the reorganization of the patient’s brain. In this paper, a new method is proposed which manipulates cable-based rehabilitation robots to assist multi-joint body motions. This uses an electromyography (EMG) decoder for continuous estimation of voluntary motion intention to establish a cooperative human-machine interface for promoting the participation in rehabilitation exercises. In particular, for multi-joint complex tasks in three-dimensional space, a switching mechanism has been developed which can carve up tasks into separate simple motions. For each simple motion, a linear six-inputs and three-outputs time-invariant model is established respectively. The inputs are the processed muscle activations of six arm muscles, and the outputs are voluntary forces of participants when executing a multi-directional tracking task with visual feedback. The experiments for examining the decoder model and EMG-based controller include model training, testing and controller application phases with seven healthy participants. Experimental results demonstrate that the decoder model with the switching mechanism could effectively recognize arm movement intention and provide appropriate assistance to the participants. This study finds that the switching mechanism can improve both the model estimation accuracy and the completeness for executing complex tasks. [ABSTRACT FROM AUTHOR]

Summary: This paper is devoted to the design of a novel fault‐tolerant control (FTC) using the combination of a robust sliding‐mode control (SMC) strategy and a control allocation (CA) algorithm, referred to as a CA‐based sliding‐mode FTC (SMFTC). The proposed SMFTC can also be considered a modular‐design control strategy. In this approach, first, a high‐level SMC, designed without detailed knowledge of systems' actuators/effectors, commands a vector of virtual control signals to meet the overall control objectives. Then, a CA algorithm distributes the virtual control efforts among the healthy actuators/effectors using the real‐time information obtained from a fault detection and reconstruction mechanism. As the underlying system is not assumed to have a rank‐deficient input matrix, the control allocator module is visible to the SMC module resulting in an uncertainty. Hence, the virtual control, in this scheme, is designed to be robust against uncertainties emanating from the visibility of the control allocator to the controller and imperfections in the estimated effectiveness gain. The proposed CA‐based SMFTC scheme is a unified FTC, which does not need to reconfigure the control system in the case of actuator fault or failure. Additionally, to cope with actuator saturation limits, a novel redistributed pseudoinverse‐based CA mechanism is proposed. The effectiveness of the proposed schemes is discussed with a numerical example. [ABSTRACT FROM AUTHOR]

This paper describes a new framework for the design of a sliding surface for a given system while multi-channel performances of the closed-loop system are under control. In contrast to most of the current sliding surface design schemes, in this new method, the level of control effort required to maintain sliding is penalised. The proposed method for the design of optimal sliding mode control is implemented in two stages. In the first stage, a state feedback gain is derived using a linear matrix inequality (LMI)-based scheme that can assign a number of the closed-loop eigenvalues to a known value whilst satisfying performance specifications. The sliding function matrix related to the particular state feedback derived in the first stage is obtained in the second stage by using one of the two different methods developed for this goal. The proposed theory is evaluated by using numerical examples including the problem of steady-state output tracking via a state-feedback SMC for flight control. [ABSTRACT FROM AUTHOR]

When dealing with large-scale systems, manual selection of a subset of components (sensors/actuators), or equivalently identification of a favourable structure for the controller, that guarantees a certain closed-loop performance, is not very feasible. This paper is dedicated to the problem of concurrent optimal selection of actuators/sensors which can equivalently be considered as the structure identification for the controller. In the context of a multi-channel dynamic output feedback controller synthesis, we formulate and analyse a framework in which we incorporate two extra terms for penalising the number of actuators and sensors into the variational formulations of controller synthesis problems in order to induce a favourable controller structure. We then develop an explicit scheme as well as an iterative process for the purpose of dealing with the multi-objective problem of controller structure and control law co-design. It is also stressed that the immediate application of the proposed approach lies within the fault accommodation stage of a fault tolerant control scheme. By two numerical examples, we demonstrate the remarkable performance of the proposed approach. [ABSTRACT FROM AUTHOR]

Summary: This paper describes two novel schemes for fault tolerant control using robust suboptimal static output feedback design methods. These schemes can also be employed as actuator redundancy management for overactuated uncertain linear systems. In contrast to many existing methods in the literature that assume the control input matrix (i) is not of full‐rank such that it can be factorized into two matrices and (ii) it does not involve uncertainty, these schemes can be applied to systems whose control input matrix cannot be factorized and/or involve uncertainty. The so‐called virtual control, in these schemes, is calculated using suboptimal H2‐based static output feedback design schemes constructed to be robust against uncertainties emanating from inherent input matrix uncertainty and visibility of the control allocator to the controller. Then, using two proposed control allocation schemes (fixed and on‐line), the obtained virtual control signal is redistributed among remaining (redundant or nonfaulty) set of actuators. As the proposed schemes are modular‐based, they can be employed as real‐time fault tolerant control schemes with no need to reconfigure the controller in the case of actuator faults or failures. The effectiveness of the proposed schemes is discussed and compared with numerical examples. [ABSTRACT FROM AUTHOR]

We present a robust method for testing and calibrating the performance of oscillometric non-invasive blood pressure (NIBP) monitors, using an industry standard NIBP simulator to determine the characteristic ratios used, and to explore differences between different devices. Assuming that classical auscultatory sphygmomanometry provides the best approximation to intra-arterial pressure, the results obtained from oscillometric measurements for a range of characteristic ratios are compared against a modified auscultatory method to determine an optimum characteristic ratio, Rs for systolic blood pressure (SBP), which was found to be 0.565. We demonstrate that whilst three Chinese manufactured NIBP monitors we tested used the conventional maximum amplitude algorithm (MAA) with characteristic ratios Rs = 0.4624±0.0303 (Mean±SD) and Rd = 0.6275±0.0222, another three devices manufactured in Germany and Japan either do not implement this standard protocol or used different characteristic ratios. Using a reference database of 304 records from 102 patients, containing both the Korotkoff sounds and the oscillometric waveforms, we showed that none of the devices tested used the optimal value of 0.565 for the characteristic ratio Rs, and as a result, three of the devices tested would underestimate systolic pressure by an average of 4.8mmHg, and three would overestimate the systolic pressure by an average of 6.2 mmHg. [ABSTRACT FROM AUTHOR]

Summary: This paper describes 2 schemes for a fault‐tolerant control using a novel optimal sliding‐mode control, which can also be employed as actuator redundancy management for overactuated uncertain linear systems. By using the effectiveness level of the actuators in the performance indexes, 2 schemes for redistributing the control effort among the remaining (redundant or nonfaulty) set of actuators are constructed based on an ℋ 2‐based optimal sliding‐mode control. In contrast to the current sliding‐mode fault‐tolerant control design methods, in these new schemes, the level of control effort required to maintain sliding is penalised. The proposed optimal sliding‐mode fault‐tolerant control design schemes are implemented in 2 stages. In the first stage, a state feedback gain is derived using an LMI‐based scheme that can assign a number of the closed‐loop eigenvalues to a known value whilst satisfying performance specifications. The sliding function matrix related to the particular state feedback derived in the first stage is obtained in the second stage. The difference between the 2 schemes proposed for the sliding‐mode fault‐tolerant control is that the second one includes a separate control allocation module, which makes it easier to apply actuator constraints to the problem. Moreover, it will be shown that, with the second scheme, we can deal with actuator faults or even failures without controller reconfiguration. We further discuss the advantages and disadvantages of the 2 schemes in more details. The effectiveness of the proposed schemes are illustrated with numerical examples. [ABSTRACT FROM AUTHOR]

This paper is devoted to the problem of designing anand/orrow-sparse static output feedback controller for continuous linear time-invariant systems with polytopic uncertainty. The immediate application of the proposed approach lies within the problem of the optimal selection of a subset of available actuators during the fault accommodation stage of a fault-tolerant control scheme. Incorporating an extra term for penalising the number of actuators into the optimisation objective function, we propose an explicit scheme and two iterative procedures according to the reweighted ℓ1(REL1) and reweighted iterative support detection (RISD) algorithms for the purposes of identifying the favourable row-sparse feedback gains. Furthermore, this problem formulation allows us to incorporate additional constraints into the designing problem such as regional pole placement constraints which provide more control over the satisfactory transient behaviour and closed-loop pole locations. In this paper, we present two examples which demonstrate the remarkable performance and broad applicability of the proposed approaches. [ABSTRACT FROM PUBLISHER]

This paper is devoted to the problem of designing a sparsely distributed sliding mode control for networked systems. Indeed, this note uses a distributed sliding mode control framework by exploiting (some of) other subsystems' information to improve the performance of each local controller so that it can widen the applicability region of the given scheme. To do so, different from the traditional schemes in the literature, a novel approach is proposed to design the sliding surface, in which the level of required control effort is taken into account during the sliding surface design based on the [ABSTRACT FROM AUTHOR]

This paper develops a novel stabilising sliding mode for systems involving uncertainties as well as measurement data packet dropouts. In contrast to the existing literature that designs the switching function by using unavailable system states, a novel linear sliding function is constructed by employing only the available communicated system states for the systems involving measurement packet losses. This also equips us with the possibility to build a novel switching component for discrete-time sliding mode control (DSMC) by using only available system states. Finally, using a numerical example, we evaluate the performance of the designed DSMC for networked systems. [ABSTRACT FROM AUTHOR]

This study is devoted to the problem of designing a robust output-feedback discrete-time sliding mode control (ODSMC) for the networked systems involving both measuring and actuating data packet losses. Packet losses in the networked control systems (NCSs) have been modelled by utilising the probability and the characteristics of the sources and the destinations. Here, the well-known Bernoulli random binary distribution is used to model consecutive packet losses in the NCSs. In this study, first, a robust observer-based discrete-time sliding mode control is proposed for the NCSs including random packet losses. The packet losses occur in the channels from the sensors to the controller and the channels from the controller to the actuators. Then, using the notion of exponential mean square stability, the boundedness of the obtained closed-loop system is analysed with a linear matrix inequality approach. Our proposed robust ODSMC can be applied to unstable NCSs, and there is no need to stabilise the underlying system in advance. Illustrative examples are presented to show the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Background: In a home telemonitoring trial, patient adherence with scheduled vital signs measurements is an important aspect that has not been thoroughly studied and for which data in the literature are limited. Levels of adherence have been reported as varying from approximately 40% to 90%, and in most cases, the adherence rate usually dropped off steadily over time. This drop is more evident in the first few weeks or months after the start. Higher adherence rates have been reported for simple types of monitoring and for shorter periods of intervention. If patients do not follow the intended procedure, poorer results than expected may be achieved. Hence, analyzing factors that can influence patient adherence is of great importance. Objective: The goal of the research was to present findings on patient adherence with scheduled vital signs measurements in the recently completed Commonwealth Scientific and Industrial Research Organisation (CSIRO) national trial of home telemonitoring of patients (mean age 70.5 years, SD 9.3 years) with chronic conditions (chronic obstructive pulmonary disease, coronary artery disease, hypertensive diseases, congestive heart failure, diabetes, or asthma) carried out at 5 locations along the east coast of Australia. We investigated the ability of chronically ill patients to carry out a daily schedule of vital signs measurements as part of a chronic disease management care plan over periods exceeding 6 months (302 days, SD 135 days) and explored different levels of adherence for different measurements as a function of age, gender, and supervisory models. Methods: In this study, 113 patients forming the test arm of a Before and After Control Intervention (BACI) home telemonitoring trial were analyzed. Patients were required to monitor on a daily basis a range of vital signs determined by their chronic condition and comorbidities. Vital signs included noninvasive blood pressure, pulse oximetry, spirometry, electrocardiogram (ECG), blood glucose level, body temperature, and body weight. Adherence was calculated as the number of days during which at least 1 measurement was taken over all days where measurements were scheduled. Different levels of adherence for different measurements, as a function of age, gender, and supervisory models, were analyzed using linear regression and analysis of covariance for a period of 1 year after the intervention. Results: Patients were monitored on average for 302 (SD 135) days, although some continued beyond 12 months. The overall adherence rate for all measurements was 64.1% (range 59.4% to 68.8%). The adherence rates of patients monitored in hospital settings relative to those monitored in community settings were significantly higher for spirometry (69.3%, range 60.4% to 78.2%, versus 41.0%, range 33.1% to 49.0%, P<.001), body weight (64.5%, range 55.7% to 73.2%, versus 40.5%, range 32.3% to 48.7%, P<.001), and body temperature (66.8%, range 59.7% to 73.9%, versus 55.2%, range 48.4% to 61.9%, P=.03). Adherence with blood glucose measurements (58.1%, range 46.7% to 69.5%, versus 50.2%, range 42.8% to 57.6%, P=.24) was not significantly different overall. Adherence rates for blood pressure (68.5%, range 62.7% to 74.2%, versus 59.7%, range 52.1% to 67.3%, P=.04), ECG (65.6%, range 59.7% to 71.5%, versus 56.5%, range 48.7% to 64.4%, P=.047), and pulse oximetry (67.0%, range 61.4% to 72.7%, versus 56.4%, range 48.6% to 64.1%, P=.02) were significantly higher in males relative to female subjects. No statistical differences were observed between rates of adherence for the younger patient group (70 years and younger) and older patient group (older than 70 years). Conclusions: Patients with chronic conditions enrolled in the home telemonitoring trial were able to record their vital signs at home at least once every 2 days over prolonged periods of time. Male patients maintained a higher adherence than female patients over time, and patients supervised by hospital-based care coordinators reported higher levels of adherence with their measurement schedule relative to patients supervised in community settings. This was most noticeable for spirometry. Trial Registration: Australian New Zealand Clinical Trials Registry ACTRN12613000635763; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=364030&isReview=true (Archived by WebCite at http://www.webcitation.org/6xPOU3DpR). [ABSTRACT FROM AUTHOR]

Objective: Telehealth paradigms are essential for remotely managing patients with chronic conditions. To assist clinicians in handling the large volumes of data collected through these systems, clinical decision support systems (CDSSs) have been developed. However, the effectiveness of CDSSs depends on the quality of remotely recorded physiological data and the reliability of the algorithms used for processing this data. This study aims to reliably detect atrial fibrillation (AF) from short-term single-lead (STSL) electrocardiogram (ECG) recordings obtained in unsupervised telehealth environments., Methods: A novel deep ensemble-based method was developed for detecting AF from STSL ECG recordings. Following this, a postprocessing algorithm was created to assess uncertainty in classified STSL ECGs and to refrain from interpretation when confidence is low. The proposed method was validated through a 5-fold cross-validation on the Cardiology Challenge 2017 (CinC2017) dataset., Results: The deep ensemble method achieved 83.5 ± 1.5% sensitivity, 98.4 ± 0.2% specificity, and an F 1 -score of 0.847 ± 0.016in AF detection. Implementing the selective classification algorithm resulted in significant improvements, with sensitivity increasing to 92.8 ± 2.2%, specificity to 99.7 ± 0.0%, and an F 1 -score of 0.919 ± 0.016., Conclusion: The proposed method demonstrates the feasibility of accurately detecting AF from STSL ECG recordings. The selective classification approach offers a substantial enhancement to automated ECG interpretation algorithms in telehealth solutions., Significance: These findings highlight the potential for improving the utility of telehealth systems by integrating advanced CDSSs capable of managing uncertainty and ensuring higher accuracy, thereby improving patient outcomes in remote healthcare settings.

Objectives . In this study, we test the hypothesis that if, as demonstrated in a previous study, brachial arteries exhibit hysteresis as the occluding cuff is deflated and fail to open until cuff pressure (CP) is well below true intra-arterial blood pressure (IAPB), estimating systolic (SBP) and diastolic blood pressure (DBP) from the presence of Korotkoff sounds (KS) as CP increases may eliminate these errors and give more accurate estimates of SBP and DBP relative to IABP readings. Approach . In 62 subjects of varying ages (45.1 ± 19.8, range 20.6-75.8 years), including 44 men (45.3 ± 19.4, range 20.6-75.8 years) and 18 women (44.4 ± 21.4, range 20.9-75.3 years), we sequentially recorded SBP and DBP both during cuff inflation and cuff deflation using KS. Results . There was a significant ( p < 0.0001) increase in SBP from 122.8 ± 13.2 to 127.6 ± 13.0 mmHg and a significant ( p = 0.0001) increase in DBP from 70.0 ± 9.0 to 77.5 ± 9.7 mmHg. Of the 62 subjects, 51 showed a positive increase in SBP (0-14 mmHg) and 11 subjects showed a reduction (-0.3 to -7 mmHg). The average differences for SBP and DBP estimates derived as the cuff inflates and those derived as the cuff deflates were 4.8 ± 4.6 mmHg and 2.5 ± 4.6 mmHg, not dissimilar to the differences reported between IABP and non-invasive blood pressure measurements. Although we could not develop multiparameter linear or non-linear models to explain this phenomenon we have clearly demonstrated through ANOVA tests that both body mass index (BMI) and pulse wave velocity are implicated, supporting the hypothesis that the phenomenon is associated with age, higher BMI and stiffer arteries. Significance . The implications of this study are that brachial sphygmomanometry carried out during cuff inflation could be more accurate than measurements carried out as the cuff deflates. Further research is required to validate these results with IAPB measurements., (Creative Commons Attribution license.)

Background: Tuberculosis (TB) was the leading infectious cause of mortality globally prior to COVID-19 and chest radiography has an important role in the detection, and subsequent diagnosis, of patients with this disease. The conventional experts reading has substantial within- and between-observer variability, indicating poor reliability of human readers. Substantial efforts have been made in utilizing various artificial intelligence-based algorithms to address the limitations of human reading of chest radiographs for diagnosing TB., Objective: This systematic literature review (SLR) aims to assess the performance of machine learning (ML) and deep learning (DL) in the detection of TB using chest radiography (chest x-ray [CXR])., Methods: In conducting and reporting the SLR, we followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. A total of 309 records were identified from Scopus, PubMed, and IEEE (Institute of Electrical and Electronics Engineers) databases. We independently screened, reviewed, and assessed all available records and included 47 studies that met the inclusion criteria in this SLR. We also performed the risk of bias assessment using Quality Assessment of Diagnostic Accuracy Studies version 2 (QUADAS-2) and meta-analysis of 10 included studies that provided confusion matrix results., Results: Various CXR data sets have been used in the included studies, with 2 of the most popular ones being Montgomery County (n=29) and Shenzhen (n=36) data sets. DL (n=34) was more commonly used than ML (n=7) in the included studies. Most studies used human radiologist's report as the reference standard. Support vector machine (n=5), k-nearest neighbors (n=3), and random forest (n=2) were the most popular ML approaches. Meanwhile, convolutional neural networks were the most commonly used DL techniques, with the 4 most popular applications being ResNet-50 (n=11), VGG-16 (n=8), VGG-19 (n=7), and AlexNet (n=6). Four performance metrics were popularly used, namely, accuracy (n=35), area under the curve (AUC; n=34), sensitivity (n=27), and specificity (n=23). In terms of the performance results, ML showed higher accuracy (mean ~93.71%) and sensitivity (mean ~92.55%), while on average DL models achieved better AUC (mean ~92.12%) and specificity (mean ~91.54%). Based on data from 10 studies that provided confusion matrix results, we estimated the pooled sensitivity and specificity of ML and DL methods to be 0.9857 (95% CI 0.9477-1.00) and 0.9805 (95% CI 0.9255-1.00), respectively. From the risk of bias assessment, 17 studies were regarded as having unclear risks for the reference standard aspect and 6 studies were regarded as having unclear risks for the flow and timing aspect. Only 2 included studies had built applications based on the proposed solutions., Conclusions: Findings from this SLR confirm the high potential of both ML and DL for TB detection using CXR. Future studies need to pay a close attention on 2 aspects of risk of bias, namely, the reference standard and the flow and timing aspects., Trial Registration: PROSPERO CRD42021277155; https://www.crd.york.ac.uk/prospero/display&#95;record.php?RecordID=277155., (©Seng Hansun, Ahmadreza Argha, Siaw-Teng Liaw, Branko G Celler, Guy B Marks. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 03.07.2023.)

Transfer learning (TL) has been proven to be a good strategy for solving domain-specific problems in many deep learning (DL) applications. Typically, in TL, a pre-trained DL model is used as a feature extractor and the extracted features are then fed to a newly trained classifier as the model head. In this study, we propose a new ensemble approach of transfer learning that uses multiple neural network classifiers at once in the model head. We compared the classification results of the proposed ensemble approach with the direct approach of several popular models, namely VGG-16, ResNet-50, and MobileNet, on two publicly available tuberculosis datasets, i.e., Montgomery County (MC) and Shenzhen (SZ) datasets. Moreover, we also compared the results when a fully pre-trained DL model was used for feature extraction versus the cases in which the features were obtained from a middle layer of the pre-trained DL model. Several metrics derived from confusion matrix results were used, namely the accuracy (ACC), sensitivity (SNS), specificity (SPC), precision (PRC), and F1-score. We concluded that the proposed ensemble approach outperformed the direct approach. Best result was achieved by ResNet-50 when the features were extracted from a middle layer with an accuracy of 91.2698% on MC dataset.Clinical Relevance- The proposed ensemble approach could increase the detection accuracy of 7-8% for Montgomery County dataset and 4-5% for Shenzhen dataset.

Automated detection of atrial fibrillation (AF) from electrocardiogram (ECG) traces remains a challenging task and is crucial for telemonitoring of patients after stroke. This study aimed to quantify the generalizability of a deep learning (DL)-based automated ECG classification algorithm. We first developed a novel hybrid DL (HDL) model using the PhysioNet/CinC Challenge 2017 (CinC2017) dataset (publicly available) that can classify the ECG recordings as one of four classes: normal sinus rhythm (NSR), AF, other rhythms (OR), and too noisy (TN) recordings. The (pre)trained HDL was then used to classify 636 ECG samples collected by our research team using a handheld ECG device, CONTEC PM10 Portable ECG Monitor, from 102 (age: 68 ± 15 years, 74 male) outpatients of the Eastern Heart Clinic and inpatients in the Cardiology ward of Prince of Wales Hospital, Sydney, Australia. The proposed HDL model achieved average test F 1 -score of 0.892 for NSR, AF, and OR, relative to the reference values, on the CinC2017 dataset. The HDL model also achieved an average F 1 -score of 0.722 (AF: 0.905, NSR: 0.791, OR: 0.471 and TN: 0.342) on the dataset created by our research team. After retraining the HDL model on this dataset using a 5-fold cross validation method, the average F 1 -score increased to 0.961. We finally conclude that the generalizability of the HDL-based algorithm developed for AF detection from short-term single-lead ECG traces is acceptable. However, the accuracy of the pre-trained DL model was significantly improved by retraining the model parameters on the new dataset of ECG traces.

Noninvasive blood pressure (NIBP) devices are calibrated against validated auscultation sphygmomanometers using Korotkoff sounds. This study aimed to investigate the timing of Korotkoff sounds in relation to pulse appearance in the brachial artery and values of intra-arterial blood pressure. Experiments were carried out on 15 participants, (14 males, 64.3 ± 10.4 years; one female, 86 yo), undergoing coronary angiography. A conventional occluding cuff, with a microphone for Korotkoff sounds, was placed on the upper arm (on the brachial artery). Intra-arterial blood pressure (IABP) was measured below the cuff with a fluid-filled catheter inserted via the radial artery and an external transducer. Finger photoplethysmography was used to measure brachial pulse wave velocity (PWV). Korotkoff sounds were processed electronically and custom algorithms identified the cuff pressure (CP) at which the first and last Korotkoff sounds were heard. PWV and max slope of the IABP pressure pulse were recorded to estimate arterial stiffness. The brachial artery closed at a CP of 132.0 ± 17.1 mmHg. Systolic and diastolic blood pressure (SBP and DBP) were 147.6 ± 14.3 and 72.7 ± 10.1 mmHg; mean pressure (MP, 100.1 ± 10.4 mmHg) was similar to MP derived from the peak of the oscillogram (98.5 ± 13.6 mmHg). Difference between IABP and CP recorded at first and last occurrence of Korotkoff sounds were, SBP: 19.0 ± 8.3 (range 2-29) mmHg, DBP: 4.0 ± 4.3 (range 2-12) mmHg. SBP derived from the onset of Korotkoff sounds can underestimate IABP by up to 19 mmHg. Since Korotkoff sounds are the recommended method mandated by the universal standard for the validation of blood pressure measuring devices, these errors are propagated through to all NIBP measurement devices irrespective of whether they use auscultatory or oscillometric methods.

Given the aging population, healthcare systems need to be established to deal with health issues such as injurious falls. Wearable devices can be used to detect falls. However, most wearable devices are obtrusive, and patients generally do not like or may forget to wear them. In this study, we developed an unobtrusive monitoring system using infrared technology to unobtrusively detect locations and recognize human activities such as sitting, standing, walking, lying, and falling. We prototyped a system consisting of two 24×32 thermal array sensors and collected data from healthy young volunteers performing ten different scenarios. A supervised deep learning (DL)-based approach classified activities and detected locations from images. The performance of the DL approach was also compared with the machine learning (ML)-based methods. In addition, we fused the data of two sensors and formed a stereo system, which resulted in better performance compared to a single sensor. Furthermore, to detect critical activities such as falling and lying on floor, we performed a binary classification in which one class was falling plus lying on floor and another class was all the remaining activities. Using the DL-based algorithm on the stereo dataset to recognize activities, overall average accuracy and F1-score were achieved as 97.6%, and 0.935, respectively. These scores for location detection were 97.3%, and 0.927, respectively. These scores for binary classification were 97.9%, and 0.945, respectively. Our results suggest the proposed system recognized human activities, detected locations, and detected critical activities namely falling and lying on floor accurately.

Human activity recognition has many potential applications. In an aged care facility, it is crucial to monitor elderly patients and assist them in the case of falls or other needs. Wearable devices can be used for such a purpose. However, most of them have been proven to be obtrusive, and patients reluctate or forget to wear them. In this study, we used infrared technology to recognize certain human activities including sitting, standing, walking, laying in bed, laying down, and falling. We evaluated a system consisting of two 24×32 thermal array sensors. One infrared sensor was installed on side and another one was installed on the ceiling of an experimental room capturing the same scene. We chose side and overhead mounts to compare the performance of classifiers. We used our prototypes to collect data from healthy young volunteers while performing eight different scenarios. After that, we converted data coming from the sensors into images and applied a supervised deep learning approach. The scene was captured by a visible camera and the video from the visible camera was used as the ground truth. The deep learning network consisted of a convolutional neural network which automatically extracted features from infrared images. Overall average F1-score of all classes for the side mount was 0.9044 and for the overhead mount was 0.8893. Overall average accuracy of all classes for the side mount was 96.65% and for the overhead mount was 95.77%. Our results suggested that our infrared-based method not only could unobtrusively recognize human activities but also was reasonably accurate.

This paper presents a novel method to estimate systolic blood pressure (SBP) and diastolic blood pressure (DBP) from time domain features extracted from auscultatory waveforms (AWs) and using a Gaussian Mixture Models and Hidden Markov Model (GMM-HMM) classification approach. The three time domain features selected include the cuff pressure (CP), the energy of the Korotkoff pulses (KE), and the slope of the KE (SKE). The proposed GMM-HMM can effectively discover the latent structure in AW sequences and automatically learn such structures. The SBP and DBP points are then detected as the cuff pressures at which AW sequence changes its structure. We conclude that the proposed GMM-HMM estimation method is a very promising method improving the accuracy of automated non-invasive measurement of blood pressure.

By recruiting a modular organization of muscle with relative activities, the arm motion can be indicated by the neural system and generated for performing a variety of motor tasks. In this study, a Non-negative Matrix Factorization with initial estimation is applied to identify and extract primary muscle synergies and their activation patterns from the processed EMG recordings during three multidirectional tracking tasks with visual feedback interaction. The effects of task variety and tracking accuracy by visual feedback on muscle synergies and their activation patterns are explored by statistic analysis. The results showed that only the task variety affected what synergies were indicated by the neural system, but both task variety and visual feedback affected the duration and magnitude of the primary synergies. Thus, for active rehabilitation application, it is advised that if the purpose is to enhance the synergy indication from the neural system, the task completion accuracy should be emphasized, but if the purpose is to expand the motion area, the task variety should be diversified.

This paper presents a novel method to estimate systolic blood pressure (SBP) and diastolic blood pressure (DBP) from time domain features extracted on auscultatory waveforms (AWs) using a long short term memory (LSTM) recurrent neural network (RNN). The proposed LSTM-RNN can effectively discover the latent structure in AW sequences and automatically learn such structures. The SBP and DBP points are then detected as the cuff pressures at which AW sequence changes its structure. Our LSTM-RNN is a powerful technique for sequence learning and can be used in blood pressure estimation as an alternative way for replacing traditional approaches.

This study proposed a detection approach for the congestive heart failure (CHF) by short-time electrocardiographic monitoring. Recent literature only reported that RR intervals and Heart Rate Variability (HRV) indicated key hidden information to discriminate CHF groups from healthy controls. However whether it was possible to find certain short-time electrocardiographic monitoring duration for CHF clinical diagnoses, has not been well addressed. In the study, databases of 54 normal subjects and 15 CHF patients from PhysioNet were introduced. Signals were classified into variable assessment lengths. Based on R-R intervals in the assessment length, raw R-R intervals, mean and standard deviation (STD) of R-R intervals, and clinically standard features of shortterm (5-min) Heart Rate Variability (HRV), were comparatively analyzed, while combining with classifiers of Recurrent Neural Network (RNN), Random Forest (RF), and Support Vector Machine (SVM). The Leave-one-out Cross-Validation (LOOCV) was adopted for performance verification, by which the model extracted from certain assessment length was utilized to test measured data of a subject with the same length. Results showed that based on testing databases, a specific 30-minute duration can be achieved by choosing HRV features in full with sensitivity of 88.55% and specificity of 94.81%. It was believed that a short-time electrocardiographic monitoring for the CHF detection could be feasible if standard HRV features together with the classifier of RF or RNN are adopted. It implied that a short-time electrocardiographic monitoring can be applied for fast reference advice of CHF in urgent medical conditions.

This paper aims to present findings on seasonal variation in a recently completed Commonwealth Scientific and Industrial Research Organization (CSIRO) national trial of home telemonitoring of patients with chronic conditions, carried out at five locations along the east coast of Australia. Patients in this trial were selected from a list of eligible patients living with a range of chronic conditions. Each test patient was case matched with at least one control patient. A total of 114 test patients and 173 control patients were available in this trial. However, of the 287 patients, we only considered subjects who had one or more admissions in the years 2010-2012. Three different groups were analyzed because of substantially different climates, i.e., Queensland (QLD), Australian Capital Territory & Victoria (ACT + VIC), and Tasmania (TAS). Time series data were analyzed using linear regression for a period of 3 years before the intervention in order to obtain an average seasonal variation pattern.

Background: Seasonal variation has an impact on the hospitalization rate of patients with a range of cardiovascular diseases, including myocardial infarction and angina. This paper presents findings on the influence of seasonal variation on the results of a recently completed national trial of home telemonitoring of patients with chronic conditions, carried out at five locations along the east coast of Australia., Objective: The aim is to evaluate the effect of the seasonal timing of hospital admission and length of stay on clinical outcome of a home telemonitoring trial involving patients (age: mean 72.2, SD 9.4 years) with chronic conditions (chronic obstructive pulmonary disease coronary artery disease, hypertensive diseases, congestive heart failure, diabetes, or asthma) and to explore methods of minimizing the influence of seasonal variations in the analysis of the effect of at-home telemonitoring on the number of hospital admissions and length of stay (LOS)., Methods: Patients were selected from a hospital list of eligible patients living with a range of chronic conditions. Each test patient was case matched with at least one control patient. A total of 114 test patients and 173 control patients were available in this trial. However, of the 287 patients, we only considered patients who had one or more admissions in the years from 2010 to 2012. Three different groups were analyzed separately because of substantially different climates: (1) Queensland, (2) Australian Capital Territory and Victoria, and (3) Tasmania. Time series data were analyzed using linear regression for a period of 3 years before the intervention to obtain an average seasonal variation pattern. A novel method that can reduce the impact of seasonal variation on the rate of hospitalization and LOS was used in the analysis of the outcome variables of the at-home telemonitoring trial., Results: Test patients were monitored for a mean 481 (SD 77) days with 87% (53/61) of patients monitored for more than 12 months. Trends in seasonal variations were obtained from 3 years' of hospitalization data before intervention for the Queensland, Tasmania, and Australian Capital Territory and Victoria subgroups, respectively. The maximum deviation from baseline trends for LOS was 101.7% (SD 42.2%), 60.6% (SD 36.4%), and 158.3% (SD 68.1%). However, by synchronizing outcomes to the start date of intervention, the impact of seasonal variations was minimized to a maximum of 9.5% (SD 7.7%), thus improving the accuracy of the clinical outcomes reported., Conclusions: Seasonal variations have a significant effect on the rate of hospital admission and LOS in patients with chronic conditions. However, the impact of seasonal variation on clinical outcomes (rate of admissions, number of hospital admissions, and LOS) of at-home telemonitoring can be attenuated by synchronizing the analysis of outcomes to the commencement dates for the telemonitoring of vital signs., Trial Registration: Australian New Zealand Clinical Trial Registry ACTRN12613000635763; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=364030&isReview=true (Archived by WebCite at http://www.webcitation.org/ 6xLPv9QDb)., (©Ahmadreza Argha, Andrey Savkin, Siaw-Teng Liaw, Branko George Celler. Originally published in JMIR Medical Informatics (http://medinform.jmir.org), 16.03.2018.)

This paper investigates the modelling of oxygen consumption (VO 2 ) response to jogging exercise on treadmill. Unlike most of the previous methods, which often use simple parametric models, e.g., first order linear time invariant model, this study applied a nonparametric kernel based regularised method to estimate VO 2 to address the ill-conditioned modelling problem and achieve accurate estimation. In particular, it is worthy to be noted that the selection of kernels will affect the results for different modelling scenarios. Therefore, in this research, both radial basis kernel and stable spline kernel were selected for testing. In order to select the favourable kernel for this system, a simulation related to VO 2 -jogging speed was carried out. The results of simulation indicated that spline kernel can achieve higher accuracy comparing to radial basis function kernel. Experimentally, the kernel based estimation method and spline kernel were tested using six participants. From the results, an average impulse response is obtained. It showed the VO 2 estimation, based on the average finite impulse response, is fitted well to the six observations collected from the participants.