-
PloS One 2024Sedatives are commonly used to promote sleep in intensive care unit patients. However, it is not clear whether sedation-induced states are similar to the biological...
Do all sedatives promote biological sleep electroencephalogram patterns? A machine learning framework to identify biological sleep promoting sedatives using electroencephalogram.
BACKGROUND
Sedatives are commonly used to promote sleep in intensive care unit patients. However, it is not clear whether sedation-induced states are similar to the biological sleep. We explored if sedative-induced states resemble biological sleep using multichannel electroencephalogram (EEG) recordings.
METHODS
Multichannel EEG datasets from two different sources were used in this study: (1) sedation dataset consisting of 102 healthy volunteers receiving propofol (N = 36), sevoflurane (N = 36), or dexmedetomidine (N = 30), and (2) publicly available sleep EEG dataset (N = 994). Forty-four quantitative time, frequency and entropy features were extracted from EEG recordings and were used to train the machine learning algorithms on sleep dataset to predict sleep stages in the sedation dataset. The predicted sleep states were then compared with the Modified Observer's Assessment of Alertness/ Sedation (MOAA/S) scores.
RESULTS
The performance of the model was poor (AUC = 0.55-0.58) in differentiating sleep stages during propofol and sevoflurane sedation. In the case of dexmedetomidine, the AUC of the model increased in a sedation-dependent manner with NREM stages 2 and 3 highly correlating with deep sedation state reaching an AUC of 0.80.
CONCLUSIONS
We addressed an important clinical question to identify biological sleep promoting sedatives using EEG signals. We demonstrate that propofol and sevoflurane do not promote EEG patterns resembling natural sleep while dexmedetomidine promotes states resembling NREM stages 2 and 3 sleep, based on current sleep staging standards.
Topics: Humans; Electroencephalography; Machine Learning; Hypnotics and Sedatives; Male; Adult; Female; Sleep; Propofol; Sevoflurane; Dexmedetomidine; Sleep Stages; Young Adult
PubMed: 38954679
DOI: 10.1371/journal.pone.0304413 -
Brain : a Journal of Neurology Jul 2024The ability to initiate volitional action is fundamental to human behaviour. Loss of dopaminergic neurons in Parkinson's disease is associated with impaired action...
The ability to initiate volitional action is fundamental to human behaviour. Loss of dopaminergic neurons in Parkinson's disease is associated with impaired action initiation, also termed akinesia. Both dopamine and subthalamic deep brain stimulation (DBS) can alleviate akinesia, but the underlying mechanisms are unknown. An important question is whether dopamine and DBS facilitate de novo build-up of neural dynamics for motor execution or accelerate existing cortical movement initiation signals through shared modulatory circuit effects. Answering these questions can provide the foundation for new closed-loop neurotherapies with adaptive DBS, but the objectification of neural processing delays prior to performance of volitional action remains a significant challenge. To overcome this challenge, we studied readiness potentials and trained brain signal decoders on invasive neurophysiology signals in 25 DBS patients (12 female) with Parkinson's disease during performance of self-initiated movements. Combined sensorimotor cortex electrocorticography (ECoG) and subthalamic local field potential (LFP) recordings were performed OFF therapy (N = 22), ON dopaminergic medication (N = 18) and ON subthalamic deep brain stimulation (N = 8). This allowed us to compare their therapeutic effects on neural latencies between the earliest cortical representation of movement intention as decoded by linear discriminant analysis classifiers and onset of muscle activation recorded with electromyography (EMG). In the hypodopaminergic OFF state, we observed long latencies between motor intention and motor execution for readiness potentials and machine learning classifications. Both, dopamine and DBS significantly shortened these latencies, hinting towards a shared therapeutic mechanism for alleviation of akinesia. To investigate this further, we analysed directional cortico-subthalamic oscillatory communication with multivariate granger causality. Strikingly, we found that both therapies independently shifted cortico-subthalamic oscillatory information flow from antikinetic beta (13-35 Hz) to prokinetic theta (4-10 Hz) rhythms, which was correlated with latencies in motor execution. Our study reveals a shared brain network modulation pattern of dopamine and DBS that may underlie the acceleration of neural dynamics for augmentation of movement initiation in Parkinson's disease. Instead of producing or increasing preparatory brain signals, both therapies modulate oscillatory communication. These insights provide a link between the pathophysiology of akinesia and its' therapeutic alleviation with oscillatory network changes in other non-motor and motor domains, e.g. related to hyperkinesia or effort and reward perception. In the future, our study may inspire the development of clinical brain computer interfaces based on brain signal decoders to provide temporally precise support for action initiation in patients with brain disorders.
PubMed: 38954651
DOI: 10.1093/brain/awae219 -
The Journal of Physical Chemistry. A Jul 2024Machine learning is capable of effectively predicting the potential energies of molecules in the presence of high-quality data sets. Its application in the construction...
Machine learning is capable of effectively predicting the potential energies of molecules in the presence of high-quality data sets. Its application in the construction of ground- and excited-state potential energy surfaces is attractive to accelerate nonadiabatic molecular dynamics simulations of photochemical reactions. Because of the huge computational cost of excited-state electronic structure calculations, the construction of a high-quality data set becomes a bottleneck. In the present work, we first built two data sets. One was obtained from surface hopping dynamics simulations at the semiempirical OM2/MRCI level. Another was extracted from the dynamics trajectories at the CASSCF level, which was reported previously. The ground- and excited-state potential energy surfaces of ethylene-bridged azobenzene at the CASSCF computational level were constructed based on the former low-level data set. Although non-neural network machine learning methods can achieve good or modest performance during the training process, only neural network models provide reliable predictions on the latter external test data set. The BPNN and SchNet combined with the Δ-ML scheme and the force term in the loss functions are recommended for dynamics simulations. Then, we performed excited-state dynamics simulations of the photoisomerization of ethylene-bridged azobenzene on machine learning potential energy surfaces. Compared with the lifetimes of the first excited state (S) estimated at different computational levels, our results on the isomer are in good agreement with the high-level estimation. However, the overestimation of the isomer is unimproved. It suggests that smaller errors during the training process do not necessarily translate to more accurate predictions on high-level potential energies or better performance on nonadiabatic dynamics simulations, at least in the present case.
PubMed: 38954640
DOI: 10.1021/acs.jpca.4c02028 -
IEEE Journal of Biomedical and Health... Jul 2024Presents corrections to the paper, Multi-View Feature Transformation Based SVM+ for Computer-Aided Diagnosis of Liver Cancers With Ultrasound Image.
Presents corrections to the paper, Multi-View Feature Transformation Based SVM+ for Computer-Aided Diagnosis of Liver Cancers With Ultrasound Image.
Topics: Humans; Liver Neoplasms; Ultrasonography; Image Interpretation, Computer-Assisted; Support Vector Machine; Liver; Diagnosis, Computer-Assisted
PubMed: 38954561
DOI: 10.1109/JBHI.2024.3404528 -
IEEE Journal of Biomedical and Health... Jul 2024Major depressive disorder (MDD) is a chronic mental illness which affects people's well-being and is often detected at a later stage of depression with a likelihood of...
Major depressive disorder (MDD) is a chronic mental illness which affects people's well-being and is often detected at a later stage of depression with a likelihood of suicidal ideation. Early detection of MDD is thus necessary to reduce the impact, however, it requires monitoring vitals in daily living conditions. EEG is generally multi-channel and due to difficulty in signal acquisition, it is unsuitable for home-based monitoring, whereas, wearable sensors can collect single-channel ECG. Classical machine-learning based MDD detection studies commonly use various heart rate variability features. Feature generation, which requires domain knowledge, is often challenging, and requires computation power, often unsuitable for real time processing, MDDBranchNet is a proposed parallel-branch deep learning model for MDD binary classification from a single channel ECG which uses additional ECG-derived signals such as R-R signal and degree distribution time series of horizontal visibility graph. The use of derived branches was able to increase the model's accuracy by around 7%. An optimal 20-second overlapped segmentation of ECG recording was found to be beneficial with a 70% prediction threshold for maximum MDD detection with a minimum false positive rate. The proposed model evaluated MDD prediction from signal excerpts, irrespective of location (first, middle or last one-third of the recording), instead of considering the entire ECG signal with minimal performance variation stressing the idea that MDD phenomena are likely to manifest uniformly throughout the recording.
Topics: Humans; Deep Learning; Electrocardiography; Depressive Disorder, Major; Signal Processing, Computer-Assisted; Algorithms; Adult; Male
PubMed: 38954560
DOI: 10.1109/JBHI.2024.3390847 -
IEEE Journal of Biomedical and Health... Jul 2024Magnetic resonance imaging (MRI)-based deep neural networks (DNN) have been widely developed to perform prostate cancer (PCa) classification. However, in real-world...
Magnetic resonance imaging (MRI)-based deep neural networks (DNN) have been widely developed to perform prostate cancer (PCa) classification. However, in real-world clinical situations, prostate MRIs can be easily impacted by rectal artifacts, which have been found to lead to incorrect PCa classification. Existing DNN-based methods typically do not consider the interference of rectal artifacts on PCa classification, and do not design specific strategy to address this problem. In this study, we proposed a novel Targeted adversarial training with Proprietary Adversarial Samples (TPAS) strategy to defend the PCa classification model against the influence of rectal artifacts. Specifically, based on clinical prior knowledge, we generated proprietary adversarial samples with rectal artifact-pattern adversarial noise, which can severely mislead PCa classification models optimized by the ordinary training strategy. We then jointly exploited the generated proprietary adversarial samples and original samples to train the models. To demonstrate the effectiveness of our strategy, we conducted analytical experiments on multiple PCa classification models. Compared with ordinary training strategy, TPAS can effectively improve the single- and multi-parametric PCa classification at patient, slice and lesion level, and bring substantial gains to recent advanced models. In conclusion, TPAS strategy can be identified as a valuable way to mitigate the influence of rectal artifacts on deep learning models for PCa classification.
Topics: Humans; Artifacts; Male; Prostatic Neoplasms; Magnetic Resonance Imaging; Rectum; Neural Networks, Computer; Image Interpretation, Computer-Assisted; Deep Learning
PubMed: 38954559
DOI: 10.1109/JBHI.2024.3384970 -
IEEE Journal of Biomedical and Health... Jul 2024Electroencephalogram (EEG) has been widely utilized in emotion recognition due to its high temporal resolution and reliability. However, the individual differences and...
Electroencephalogram (EEG) has been widely utilized in emotion recognition due to its high temporal resolution and reliability. However, the individual differences and non-stationary characteristics of EEG, along with the complexity and variability of emotions, pose challenges in generalizing emotion recognition models across subjects. In this paper, an end-to-end framework is proposed to improve the performance of cross-subject emotion recognition. A novel evolutionary programming (EP)-based optimization strategy with neural network (NN) as the base classifier termed NN ensemble with EP (EPNNE) is designed for cross-subject emotion recognition. The effectiveness of the proposed method is evaluated on the publicly available DEAP, FACED, SEED, and SEED-IV datasets. Numerical results demonstrate that the proposed method is superior to state-of-the-art cross-subject emotion recognition methods. The proposed end-to-end framework for cross-subject emotion recognition aids biomedical researchers in effectively assessing individual emotional states, thereby enabling efficient treatment and interventions.
Topics: Humans; Electroencephalography; Emotions; Signal Processing, Computer-Assisted; Neural Networks, Computer; Machine Learning; Algorithms; Pattern Recognition, Automated; Databases, Factual; Adult; Female; Male
PubMed: 38954558
DOI: 10.1109/JBHI.2024.3384816 -
IEEE Journal of Biomedical and Health... Jul 2024Efficient medical image segmentation aims to provide accurate pixel-wise predictions with a lightweight implementation framework. However, existing lightweight networks...
Efficient medical image segmentation aims to provide accurate pixel-wise predictions with a lightweight implementation framework. However, existing lightweight networks generally overlook the generalizability of the cross-domain medical segmentation tasks. In this paper, we propose Generalizable Knowledge Distillation (GKD), a novel framework for enhancing the performance of lightweight networks on cross-domain medical segmentation by generalizable knowledge distillation from powerful teacher networks. Considering the domain gaps between different medical datasets, we propose the Model-Specific Alignment Networks (MSAN) to obtain the domain-invariant representations. Meanwhile, a customized Alignment Consistency Training (ACT) strategy is designed to promote the MSAN training. Based on the domain-invariant vectors in MSAN, we propose two generalizable distillation schemes, Dual Contrastive Graph Distillation (DCGD) and Domain-Invariant Cross Distillation (DICD). In DCGD, two implicit contrastive graphs are designed to model the intra-coupling and inter-coupling semantic correlations. Then, in DICD, the domain-invariant semantic vectors are reconstructed from two networks (i.e., teacher and student) with a crossover manner to achieve simultaneous generalization of lightweight networks, hierarchically. Moreover, a metric named Fréchet Semantic Distance (FSD) is tailored to verify the effectiveness of the regularized domain-invariant features. Extensive experiments conducted on the Liver, Retinal Vessel and Colonoscopy segmentation datasets demonstrate the superiority of our method, in terms of performance and generalization ability on lightweight networks.
Topics: Humans; Image Processing, Computer-Assisted; Algorithms; Neural Networks, Computer; Databases, Factual; Deep Learning
PubMed: 38954557
DOI: 10.1109/JBHI.2024.3385098 -
Proceedings of the National Academy of... Jul 2024Standard deep learning algorithms require differentiating large nonlinear networks, a process that is slow and power-hungry. Electronic (CLLNs) offer potentially fast,...
Standard deep learning algorithms require differentiating large nonlinear networks, a process that is slow and power-hungry. Electronic (CLLNs) offer potentially fast, efficient, and fault-tolerant hardware for analog machine learning, but existing implementations are linear, severely limiting their capabilities. These systems differ significantly from artificial neural networks as well as the brain, so the feasibility and utility of incorporating nonlinear elements have not been explored. Here, we introduce a nonlinear CLLN-an analog electronic network made of self-adjusting nonlinear resistive elements based on transistors. We demonstrate that the system learns tasks unachievable in linear systems, including XOR (exclusive or) and nonlinear regression, without a computer. We find our decentralized system reduces modes of training error in order (mean, slope, curvature), similar to in artificial neural networks. The circuitry is robust to damage, retrainable in seconds, and performs learned tasks in microseconds while dissipating only picojoules of energy across each transistor. This suggests enormous potential for fast, low-power computing in edge systems like sensors, robotic controllers, and medical devices, as well as manufacturability at scale for performing and studying emergent learning.
PubMed: 38954545
DOI: 10.1073/pnas.2319718121 -
Proceedings of the National Academy of... Jul 2024Artificial skins or flexible pressure sensors that mimic human cutaneous mechanoreceptors transduce tactile stimuli to quantitative electrical signals. Conventional...
Artificial skins or flexible pressure sensors that mimic human cutaneous mechanoreceptors transduce tactile stimuli to quantitative electrical signals. Conventional trial-and-error designs for such devices follow a forward structure-to-property routine, which is usually time-consuming and determines one possible solution in one run. Data-driven inverse design can precisely target desired functions while showing far higher productivity, however, it is still absent for flexible pressure sensors because of the difficulties in acquiring a large amount of data. Here, we report a property-to-structure inverse design of flexible pressure sensors, exhibiting a significantly greater efficiency than the conventional routine. We use a reduced-order model that analytically constrains the design scope and an iterative "jumping-selection" method together with a surrogate model that enhances data screening. As an exemplary scenario, hundreds of solutions that overcome the intrinsic signal saturation have been predicted by the inverse method, validating for a variety of material systems. The success in property design on multiple indicators demonstrates that the proposed inverse design is an efficient and powerful tool to target multifarious applications of flexible pressure sensors, which can potentially advance the fields of intelligent robots, advanced healthcare, and human-machine interfaces.
PubMed: 38954542
DOI: 10.1073/pnas.2320222121