Real-Time PPG Signal Conditioning with Long Short-Term Memory (LSTM) Network for Wearable Devices.
Ontology highlight
ABSTRACT:
SUBMITTER: Wojcikowski M
PROVIDER: S-EPMC8749621 | biostudies-literature | 2021 Dec
REPOSITORIES: biostudies-literature
Publications
Real-Time PPG Signal Conditioning with Long Short-Term Memory (LSTM) Network for Wearable Devices.
Sensors (Basel, Switzerland) 20211227 1
This paper presents an algorithm for real-time detection of the heart rate measured on a person's wrist using a wearable device with a photoplethysmographic (PPG) sensor and accelerometer. The proposed algorithm consists of an appropriately trained LSTM network and the Time-Domain Heart Rate (TDHR) algorithm for peak detection in the PPG waveform. The Long Short-Term Memory (LSTM) network uses the signals from the accelerometer to improve the shape of the PPG input signal in a time domain that i ...[more]
Similar Datasets
Project description:BackgroundThe accurate temporal analysis of muscle activation is of great interest in many research areas, spanning from neurorobotic systems to the assessment of altered locomotion patterns in orthopedic and neurological patients and the monitoring of their motor rehabilitation. The performance of the existing muscle activity detectors is strongly affected by both the SNR of the surface electromyography (sEMG) signals and the set of features used to detect the activation intervals. This work aims at introducing and validating a powerful approach to detect muscle activation intervals from sEMG signals, based on long short-term memory (LSTM) recurrent neural networks.MethodsFirst, the applicability of the proposed LSTM-based muscle activity detector (LSTM-MAD) is studied through simulated sEMG signals, comparing the LSTM-MAD performance against other two widely used approaches, i.e., the standard approach based on Teager-Kaiser Energy Operator (TKEO) and the traditional approach, used in clinical gait analysis, based on a double-threshold statistical detector (Stat). Second, the effect of the Signal-to-Noise Ratio (SNR) on the performance of the LSTM-MAD is assessed considering simulated signals with nine different SNR values. Finally, the newly introduced approach is validated on real sEMG signals, acquired during both physiological and pathological gait. Electromyography recordings from a total of 20 subjects (8 healthy individuals, 6 orthopedic patients, and 6 neurological patients) were included in the analysis.ResultsThe proposed algorithm overcomes the main limitations of the other tested approaches and it works directly on sEMG signals, without the need for background-noise and SNR estimation (as in Stat). Results demonstrate that LSTM-MAD outperforms the other approaches, revealing higher values of F1-score (F1-score > 0.91) and Jaccard similarity index (Jaccard > 0.85), and lower values of onset/offset bias (average absolute bias < 6 ms), both on simulated and real sEMG signals. Moreover, the advantages of using the LSTM-MAD algorithm are particularly evident for signals featuring a low to medium SNR.ConclusionsThe presented approach LSTM-MAD revealed excellent performances against TKEO and Stat. The validation carried out both on simulated and real signals, considering normal as well as pathological motor function during locomotion, demonstrated that it can be considered a powerful tool in the accurate and effective recognition/distinction of muscle activity from background noise in sEMG signals.
| S-EPMC8532313 | biostudies-literature
Project description:BackgroundRecent studies have proposed deep learning techniques, namely recurrent neural networks, to improve biomedical text mining tasks. However, these techniques rarely take advantage of existing domain-specific resources, such as ontologies. In Life and Health Sciences there is a vast and valuable set of such resources publicly available, which are continuously being updated. Biomedical ontologies are nowadays a mainstream approach to formalize existing knowledge about entities, such as genes, chemicals, phenotypes, and disorders. These resources contain supplementary information that may not be yet encoded in training data, particularly in domains with limited labeled data.ResultsWe propose a new model to detect and classify relations in text, BO-LSTM, that takes advantage of domain-specific ontologies, by representing each entity as the sequence of its ancestors in the ontology. We implemented BO-LSTM as a recurrent neural network with long short-term memory units and using open biomedical ontologies, specifically Chemical Entities of Biological Interest (ChEBI), Human Phenotype, and Gene Ontology. We assessed the performance of BO-LSTM with drug-drug interactions mentioned in a publicly available corpus from an international challenge, composed of 792 drug descriptions and 233 scientific abstracts. By using the domain-specific ontology in addition to word embeddings and WordNet, BO-LSTM improved the F1-score of both the detection and classification of drug-drug interactions, particularly in a document set with a limited number of annotations. We adapted an existing DDI extraction model with our ontology-based method, obtaining a higher F1 score than the original model. Furthermore, we developed and made available a corpus of 228 abstracts annotated with relations between genes and phenotypes, and demonstrated how BO-LSTM can be applied to other types of relations.ConclusionsOur findings demonstrate that besides the high performance of current deep learning techniques, domain-specific ontologies can still be useful to mitigate the lack of labeled data.
| S-EPMC6323831 | biostudies-literature
Project description:Since December 2019, cases of COVID-19 have spread globally, caused millions of deaths and huge economic losses. To investigate the impact of different factors and predict the future trend, this study collects relevant data for 15 countries, containing 44 features in about 900 days, which can be classified into four groups: pandemic information, the characteristics of countries, climate, and prevention policies. Through the selection of several important features, we identified the factors that have stronger impact on the increase of new cases in different groups. Then, we use a long-time span data to predict the future COVID-19 new cases by training a long short-term memory (LSTM) model, a support vector regressor (SVR) and a temporal convolutional network (TCN), among which LSTM possessed the best performance and offered a good generalization ability. Under the metric of explained variance scores (EVS), the prediction performances were the most accurate for Germany (0.864), Italy (0.860) and the United States (0.766). Overall, the results of this study may provide insight for predictions of number of COVID-19 new cases in more countries/regions and offer some insightful recommendation for governments to carry out more effective policies to prevent COVID-19.
| S-EPMC11811167 | biostudies-literature
Project description:Cardiac rhythm disorders can manifest in various ways, such as the heart rate being too fast (tachycardia) or too slow (bradycardia), irregular heartbeats (like atrial fibrillation-AF, ventricular fibrillation-VF), or the initiation of heartbeats in different areas from the norm (extrasystole). Arrhythmias can disrupt the balanced circulation, leading to serious complications like heart attacks, strokes, and sudden death. Medical devices like electrocardiography (ECG) and Holter monitors are commonly used for diagnosing and monitoring cardiac rhythm disorders. However, in recent years, the development of wearable devices has played a significant role in the detection and diagnosis of rhythm disorders through the use of photoplethysmography (PPG) signals. Wearable devices enable patients to continuously monitor their health status and allow doctors to provide earlier diagnoses and interventions. In this study, a 1D-CNN model is proposed to detect arrhythmias using PPG signals. A dataset prepared by the University of Massachusetts Medical Center (UMMC) containing both ECG and PPG signal data was utilized. In this dataset, ECG signals are filtered with a bandpass filter and raw PPG signals are divided into 30-second segments. Accuracy values were obtained by classifying ECG and PPG signals using a 1D CNN model. ECG signals were used as a reference. The proposed model achieved a 95.17% accuracy rate in detecting normal sinus rhythm (NSR), atrial fibrillation (AF), and premature atrial contractions (PAC) from PPG signals. Datasets are available for download on https://www.synapse.org/pulsewatch. The codes used in this study are available on the https://github.com/miraygunay/PPG-Code.git website.
| S-EPMC11819536 | biostudies-literature
Project description:A three-terminal synaptic transistor enables more accurate controllability over the conductance compared with traditional two-terminal synaptic devices for the synaptic devices in hardware-oriented neuromorphic systems. In this work, we fabricated IGZO-based three-terminal devices comprising HfAlOx and CeOx layers to demonstrate the synaptic operations. The chemical compositions and thicknesses of the devices were verified by transmission electron microscopy and energy dispersive spectroscopy in cooperation. The excitatory post-synaptic current (EPSC), paired-pulse facilitation (PPF), short-term potentiation (STP), and short-term depression (STD) of the synaptic devices were realized for the short-term memory behaviors. The IGZO-based three-terminal synaptic transistor could thus be controlled appropriately by the amplitude, width, and interval time of the pulses for implementing the neuromorphic systems.
| S-EPMC9919079 | biostudies-literature
Project description:The National Institute of Environmental Research, under the Ministry of Environment of Korea, provides two-day forecasts, through AirKorea, of the concentration of particulate matter with diameters of ≤ 2.5 μm (PM2.5) in terms of four grades (low, moderate, high, and very high) over 19 districts nationwide. Particulate grades are subjectively designated by human forecasters based on forecast results from the Community Multiscale Air Quality (CMAQ) and artificial intelligence (AI) models in conjunction with weather patterns. This study evaluates forecasts from the long short-term memory (LSTM) algorithm relative to those from CMAQ-solely and AirKorea using observations from 2019. The skills of the one-day PM2.5 forecasts over the 19 districts were 39-70% for CMAQ, 72-79% for LSTM, and 73-80% for AirKorea; the AI forecasts showed comparable skills to the human forecasters at AirKorea. The one-day forecast skill levels of high and very high PM2.5 pollution grades are 31-98%, 31-74%, and 39-81% for the CMAQ-solely, the LSTM, and the AirKorea forecasts, respectively. Despite good skills for forecasting the high and very high events, CMAQ-solely forecasts also generate substantially higher false alarm rates (up to 86%) than the LSTM and AirKorea forecasts (up to 58%). Hence, applying only the LSTM model to the CMAQ forecasts can yield reasonable forecast skill levels comparable to the operational AirKorea forecasts that elaborately combine the CMAQ model, AI models, and human forecasters. The present results suggest that applications of appropriate AI models can greatly enhance PM2.5 forecast skills for Korea in a more objective way.Supplementary informationThe online version contains supplementary material available at 10.1007/s13143-022-00293-2.
| S-EPMC9483905 | biostudies-literature
Project description:Seizure prediction could improve quality of life for patients through removing uncertainty and providing an opportunity for acute treatments. Most seizure prediction models use feature engineering to process the EEG recordings. Long-Short Term Memory (LSTM) neural networks are a recurrent neural network architecture that can display temporal dynamics and, therefore, potentially analyze EEG signals without performing feature engineering. In this study, we tested if LSTMs could classify unprocessed EEG recordings to make seizure predictions. Long-term intracranial EEG data was used from 10 patients. 10-s segments of EEG were input to LSTM models that were trained to classify the EEG signal. The final seizure prediction was generated from 5 outputs of the LSTM model over 50 s and combined with time information to account for seizure cycles. The LSTM models could make predictions significantly better than a random predictor. When compared to other publications using the same dataset, our model performed better than several others and was comparable to the best models published to date. Furthermore, this framework could still produce predictions significantly better than chance when the experimental paradigm design was altered, without the need to reperform feature engineering. Removing the need to perform feature engineering is an advancement on previously published models. This framework can be applied to many different patients' needs and a variety of acute interventions. Also, it opens the possibility of personalized seizure predictions that can be altered to meet daily needs.
| S-EPMC11604808 | biostudies-literature
Project description:ObjectiveTo develop and test an accurate deep learning model for predicting new onset delirium in hospitalized adult patients.MethodsUsing electronic health record (EHR) data extracted from a large academic medical center, we developed a model combining long short-term memory (LSTM) and machine learning to predict new onset delirium and compared its performance with machine-learning-only models (logistic regression, random forest, support vector machine, neural network, and LightGBM). The labels of models were confusion assessment method (CAM) assessments. We evaluated models on a hold-out dataset. We calculated Shapley additive explanations (SHAP) measures to gauge the feature impact on the model.ResultsA total of 331 489 CAM assessments with 896 features from 34 035 patients were included. The LightGBM model achieved the best performance (AUC 0.927 [0.924, 0.929] and F1 0.626 [0.618, 0.634]) among the machine learning models. When combined with the LSTM model, the final model's performance improved significantly (P = .001) with AUC 0.952 [0.950, 0.955] and F1 0.759 [0.755, 0.765]. The precision value of the combined model improved from 0.497 to 0.751 with a fixed recall of 0.8. Using the mean absolute SHAP values, we identified the top 20 features, including age, heart rate, Richmond Agitation-Sedation Scale score, Morse fall risk score, pulse, respiratory rate, and level of care.ConclusionLeveraging LSTM to capture temporal trends and combining it with the LightGBM model can significantly improve the prediction of new onset delirium, providing an algorithmic basis for the subsequent development of clinical decision support tools for proactive delirium interventions.
| S-EPMC9748586 | biostudies-literature
Project description:This research presents a reverse engineering approach to discover the patterns and evolution behavior of SARS-CoV-2 using AI and big data. Accordingly, we have studied five viral families (Orthomyxoviridae, Retroviridae, Filoviridae, Flaviviridae, and Coronaviridae) that happened in the era of the past one hundred years. To capture the similarities, common characteristics, and evolution behavior for prediction concerning SARS-CoV-2. And how reverse engineering using Artificial intelligence (AI) and big data is efficient and provides wide horizons. The results show that SARS-CoV-2 shares the same highest active amino acids (S, L, and T) with the mentioned viral families. As known, that affects the building function of the proteins. We have also devised a mathematical formula representing how we calculate the evolution difference percentage between each virus concerning its phylogenic tree. It shows that SARS-CoV-2 has fast mutation evolution concerning its time of arising. Artificial Intelligence (AI) is used to predict the next evolved instance of SARS-CoV-2 by utilizing the phylogenic tree data as a corpus using Long Short-term Memory (LSTM). This paper has shown the evolved viral instance prediction process on ORF7a protein from SARS-CoV-2 as the first stage to predict the complete mutant virus. Finally, in this research, we have focused on analyzing the virus to its primary factors by reverse engineering using AI and big data to understand the viral similarities, patterns, and evolution behavior to predict future viral mutations of the virus artificially in a systematic and logical way.
| S-EPMC8016547 | biostudies-literature
Project description:Are the information processing steps that support short-term sensory memory common to all the senses? Systematic, psychophysical comparison requires identical experimental paradigms and comparable stimuli, which can be challenging to obtain across modalities. Participants performed a recognition memory task with auditory and visual stimuli that were comparable in complexity and in their neural representations at early stages of cortical processing. The visual stimuli were static and moving Gaussian-windowed, oriented, sinusoidal gratings (Gabor patches); the auditory stimuli were broadband sounds whose frequency content varied sinusoidally over time (moving ripples). Parallel effects on recognition memory were seen for number of items to be remembered, retention interval, and serial position. Further, regardless of modality, predicting an item's recognizability requires taking account of (1) the probe's similarity to the remembered list items (summed similarity), and (2) the similarity between the items in memory (inter-item homogeneity). A model incorporating both these factors gives a good fit to recognition memory data for auditory as well as visual stimuli. In addition, we present the first demonstration of the orthogonality of summed similarity and inter-item homogeneity effects. These data imply that auditory and visual representations undergo very similar transformations while they are encoded and retrieved from memory.
| S-EPMC1800308 | biostudies-literature