Mathieu Lemay
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Mathieu Lemay has a total of 71 co-authors. Here are the top co-authors by number of shared publications:
- Cilia Jäger
Brain Products GmbH, Gilching, Germany
2 shared publications - Cristina Sainz Martinez
CSEM - Swiss Center for Electronics and Microtechnology, Neuchâtel, Switzerland
2 shared publications - Fabian Braun
Swiss Centre for Electronics and Microtechnology (CSEM)
2 shared publications - Jessica A. M. Bastiaansen
Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital Bern University Hospital, University of Bern Bern Switzerland
2 shared publications - Jonathan Wirsich
EEG and Epilepsy Unit, University Hospitals and Faculty of Medicine of Geneva, University of Geneva
2 shared publications - João Jorge
CSEM - Swiss Center for Electronics and Microtechnology, Neuchâtel, Switzerland
2 shared publications
Latest Publications
- Open Access
- 4 November 2025
- Published by MIT Press in Imaging Neuroscience
- Vol. 3
An optimized framework for simultaneous EEG-fMRI at 7T enabling safe, high-quality human brain imaging with millisecond temporal resolution and sub-millimeter spatial resolution
The combination of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) at ultra-high field (7 Tesla) offers appealing new possibilities to probe human brain function non-invasively with high coverage, millisecond temporal precision and sub-millimeter spatial precision, unraveling cortical layers and small subcortical structures. Unfortunately, this technique has remained largely inaccessible at 7T, due to prohibitive cross-modal interference effects and physical constraints. Here, we developed a first-of-its-kind EEG-fMRI acquisition framework on a clinical 7T system combining key improvements from previous research: compact EEG transmission to reduce artifact incidence, reference sensors for artifact correction, and adapted leads for compatibility with a dense radiofrequency receive array allowing state-of-the-art fMRI sensitivity and acceleration. Two implementations were tested: one using an EEG cap adapted in-house, and another using a recently designed prototype from an industrial manufacturer, intended to be further developed into a commercial device accessible to the broader community. A comprehensive evaluation in humans showed that simultaneous acquisitions, including sub-millimeter fMRI resolution, could be conducted without detectable safety issues or major practical constraints. The EEG exerted relatively mild perturbations on fMRI quality (6–11% loss in temporal SNR), without measurably affecting the detection of resting-state networks and visual responses. The artifacts induced on EEG could be corrected to a degree where the spatial, spectral, and temporal characteristics were comparable with outside recordings, and hallmark features such as resting-state alpha and eyes-closing alpha modulation could be clearly detected. Altogether, these findings indicate excellent prospects for neuroimaging applications, which can leverage the unique possibilities achievable at 7T.
- 4 November 2025
- Published by MIT Press in Imaging Neuroscience
- Vol. 3
Open AccessAn optimized framework for simultaneous EEG-fMRI at 7T enabling safe, high-quality human brain imaging with millisecond temporal resolution and sub-millimeter spatial resolution
The combination of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) at ultra-high field (7 Tesla) offers appealing new possibilities to probe human brain function non-invasively with high coverage, millisecond temporal precision and sub-millimeter spatial precision, unraveling cortical layers and small subcortical structures. Unfortunately, this technique has remained largely inaccessible at 7T, due to prohibitive cross-modal interference effects and physical constraints. Here, we developed a first-of-its-kind EEG-fMRI acquisition framework on a clinical 7T system combining key improvements from previous research: compact EEG transmission to reduce artifact incidence, reference sensors for artifact correction, and adapted leads for compatibility with a dense radiofrequency receive array allowing state-of-the-art fMRI sensitivity and acceleration. Two implementations were tested: one using an EEG cap adapted in-house, and another using a recently designed prototype from an industrial manufacturer, intended to be further developed into a commercial device accessible to the broader community. A comprehensive evaluation in humans showed that simultaneous acquisitions, including sub-millimeter fMRI resolution, could be conducted without detectable safety issues or major practical constraints. The EEG exerted relatively mild perturbations on fMRI quality (6–11% loss in temporal SNR), without measurably affecting the detection of resting-state networks and visual responses. The artifacts induced on EEG could be corrected to a degree where the spatial, spectral, and temporal characteristics were comparable with outside recordings, and hallmark features such as resting-state alpha and eyes-closing alpha modulation could be clearly detected. Altogether, these findings indicate excellent prospects for neuroimaging applications, which can leverage the unique possibilities achievable at 7T.
- Open Access
An optimized framework for simultaneous EEG-fMRI at 7T enabling safe, high-quality human brain imaging with millisecond temporal resolution and sub-millimeter spatial resolution
The combination of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) at ultra-high field (7 Tesla) offers appealing new possibilities to probe human brain function non-invasively with high coverage, millisecond temporal precision and sub-millimeter spatial precision, unraveling cortical layers and small subcortical structures. Unfortunately, this technique has remained largely inaccessible at 7T, due to prohibitive cross-modal interference effects and physical constraints. Here, we developed a first-of-its-kind EEG-fMRI acquisition framework on a clinical 7T system combining key improvements from previous research: compact EEG transmission to reduce artifact incidence, reference sensors for artifact correction, and adapted leads for compatibility with a dense radiofrequency receive-array allowing state-of-the-art fMRI sensitivity and acceleration. Two implementations were tested: one using an EEG cap adapted in-house, and another using a recently-designed prototype from an industrial manufacturer, intended to be further developed into a commercial device accessible to the broader community. A comprehensive evaluation in humans showed that simultaneous acquisitions, including sub-millimeter fMRI resolution, could be conducted without detectable safety issues or major practical constraints. The EEG exerted relatively mild perturbations on fMRI quality (6–11% loss in temporal SNR), without measurably affecting the detection of resting-state networks and visual responses. The artifacts induced on EEG could be corrected to a degree where the spatial, spectral and temporal characteristics were comparable to outside recordings, and hallmark features such as resting-state alpha and eyes-closing alpha modulation could be clearly detected. Altogether, these findings indicate excellent prospects for neuroimaging applications, that can leverage the unique possibilities achievable at 7T.
Open AccessAn optimized framework for simultaneous EEG-fMRI at 7T enabling safe, high-quality human brain imaging with millisecond temporal resolution and sub-millimeter spatial resolution
The combination of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) at ultra-high field (7 Tesla) offers appealing new possibilities to probe human brain function non-invasively with high coverage, millisecond temporal precision and sub-millimeter spatial precision, unraveling cortical layers and small subcortical structures. Unfortunately, this technique has remained largely inaccessible at 7T, due to prohibitive cross-modal interference effects and physical constraints. Here, we developed a first-of-its-kind EEG-fMRI acquisition framework on a clinical 7T system combining key improvements from previous research: compact EEG transmission to reduce artifact incidence, reference sensors for artifact correction, and adapted leads for compatibility with a dense radiofrequency receive-array allowing state-of-the-art fMRI sensitivity and acceleration. Two implementations were tested: one using an EEG cap adapted in-house, and another using a recently-designed prototype from an industrial manufacturer, intended to be further developed into a commercial device accessible to the broader community. A comprehensive evaluation in humans showed that simultaneous acquisitions, including sub-millimeter fMRI resolution, could be conducted without detectable safety issues or major practical constraints. The EEG exerted relatively mild perturbations on fMRI quality (6–11% loss in temporal SNR), without measurably affecting the detection of resting-state networks and visual responses. The artifacts induced on EEG could be corrected to a degree where the spatial, spectral and temporal characteristics were comparable to outside recordings, and hallmark features such as resting-state alpha and eyes-closing alpha modulation could be clearly detected. Altogether, these findings indicate excellent prospects for neuroimaging applications, that can leverage the unique possibilities achievable at 7T.
- Open Access
- 24 May 2024
- Published by Oxford University Press (OUP) in EP Europace
- Vol. 26 (Supplement)
Non-invasive detection of cardiac arrhythmias using photoplethysmography signals
Cardiac arrhythmias (CAs) are associated with critical heart-related complications such as stroke or heart failure. Because of the intermittent and asymptomatic presentation of some CAs in their early stages, the screening remains limited using traditional methods based on ECG. Recent advances in photoplethysmography (PPG) have revealed substantial potential for wearable devices to detect CAs within large populations. Although PPG has demonstrated efficiency in discriminating atrial fibrillation (AF) from normal sinus rhythm, it remains unclear whether AF detection methods remains effective in the presence of CAs other than AF. In this study, we applied a recurrent neural network on a dataset containing eight different types of CAs (Table 1). The classifier processes sequences of interbeat intervals (IBIs) as input and discriminates between normal and abnormal rhythms. The algorithm was evaluated on 64 patients (45 males and 19 females , with a mean age of 55.9 ± 16.0) undergoing a diagnostic or therapeutic electrophysiological procedure. This dataset includes simultaneous recordings of PPG signals from a wrist-bracelet and 12-lead ECG, with the latter used as the gold-standard for annotating cardiac rhythms. The classifier achieved 84% accuracy, 77% sensitivity and 88% specificity in detecting abnormal rhythms. Table 1 shows that AF (99.6%), atrial tachycardia (100%) and AVRT (96.4%) were well classified as abnormal rhythm, whereas the reliability of the detection decreased for atrial flutter (65.4%), atrial or ventricular bigeminy (72.4%) and ventricular tachycardia (80.2%). Undetected abnormal rhythms were often characterized by a rather regular rhythm (illustrated by VT in Figure 1) and CAs for which PPG heartbeat detection was initially not optimal (Bigeminy in Figure 1). In conclusion, this study shows the capability of PPG-based technology to detect various CAs extending beyond AF. It highlights the merits and limitations of IBI-based detection of abnormal rhythms, highlighting the need for a better comprehension of the peripheral hemodynamic signature of CAs.
- 24 May 2024
- Published by Oxford University Press (OUP) in EP Europace
- Vol. 26 (Supplement)
Open AccessNon-invasive detection of cardiac arrhythmias using photoplethysmography signals
Cardiac arrhythmias (CAs) are associated with critical heart-related complications such as stroke or heart failure. Because of the intermittent and asymptomatic presentation of some CAs in their early stages, the screening remains limited using traditional methods based on ECG. Recent advances in photoplethysmography (PPG) have revealed substantial potential for wearable devices to detect CAs within large populations. Although PPG has demonstrated efficiency in discriminating atrial fibrillation (AF) from normal sinus rhythm, it remains unclear whether AF detection methods remains effective in the presence of CAs other than AF. In this study, we applied a recurrent neural network on a dataset containing eight different types of CAs (Table 1). The classifier processes sequences of interbeat intervals (IBIs) as input and discriminates between normal and abnormal rhythms. The algorithm was evaluated on 64 patients (45 males and 19 females , with a mean age of 55.9 ± 16.0) undergoing a diagnostic or therapeutic electrophysiological procedure. This dataset includes simultaneous recordings of PPG signals from a wrist-bracelet and 12-lead ECG, with the latter used as the gold-standard for annotating cardiac rhythms. The classifier achieved 84% accuracy, 77% sensitivity and 88% specificity in detecting abnormal rhythms. Table 1 shows that AF (99.6%), atrial tachycardia (100%) and AVRT (96.4%) were well classified as abnormal rhythm, whereas the reliability of the detection decreased for atrial flutter (65.4%), atrial or ventricular bigeminy (72.4%) and ventricular tachycardia (80.2%). Undetected abnormal rhythms were often characterized by a rather regular rhythm (illustrated by VT in Figure 1) and CAs for which PPG heartbeat detection was initially not optimal (Bigeminy in Figure 1). In conclusion, this study shows the capability of PPG-based technology to detect various CAs extending beyond AF. It highlights the merits and limitations of IBI-based detection of abnormal rhythms, highlighting the need for a better comprehension of the peripheral hemodynamic signature of CAs.
- Open Access
- 4 January 2024
- Published by MDPI AG in Methods and Protocols
- Vol. 7 (1) , 5
Introducing Artificial Intelligence in Interpretation of Foetal Cardiotocography: Medical Dataset Curation and Preliminary Coding—An Interdisciplinary Project
Artificial intelligence (AI) is gaining increasing interest in the field of medicine because of its capacity to process big data and pattern recognition. Cardiotocography (CTG) is widely used for the assessment of foetal well-being and uterine contractions during pregnancy and labour. It is characterised by inter- and intraobserver variability in interpretation, which depends on the observers’ experience. Artificial intelligence (AI)-assisted interpretation could improve its quality and, thus, intrapartal care. Cardiotocography (CTG) raw signals from labouring women were extracted from the database at the University Hospital of Bern between 2006 and 2019. Later, they were matched with the corresponding foetal outcomes, namely arterial umbilical cord pH and 5-min APGAR score. Excluded were deliveries where data were incomplete, as well as multiple births. Clinical data were grouped regarding foetal pH and APGAR score at 5 min after delivery. Physiological foetal pH was defined as 7.15 and above, and a 5-min APGAR score was considered physiologic when reaching ≥7. With these groups, the algorithm was trained to predict foetal hypoxia. Raw data from 19,399 CTG recordings could be exported. This was accomplished by manually searching the patient’s identification numbers (PIDs) and extracting the corresponding raw data from each episode. For some patients, only one episode per pregnancy could be found, whereas for others, up to ten episodes were available. Initially, 3400 corresponding clinical outcomes were found for the 19,399 CTGs (17.52%). Due to the small size, this dataset was rejected, and a new search strategy was elaborated. After further matching and curation, 6141 (31.65%) paired data samples could be extracted (cardiotocography raw data and corresponding maternal and foetal outcomes). Of these, half will be used to train artificial intelligence (AI) algorithms, whereas the other half will be used for analysis of efficacy. Complete data could only be found for one-third of the available population. Yet, to our knowledge, this is the most exhaustive and second-largest cardiotocography database worldwide, which can be used for computer analysis and programming. A further enrichment of the database is planned.
- 4 January 2024
- Published by MDPI AG in Methods and Protocols
- Vol. 7 (1) , 5
Open AccessIntroducing Artificial Intelligence in Interpretation of Foetal Cardiotocography: Medical Dataset Curation and Preliminary Coding—An Interdisciplinary Project
Artificial intelligence (AI) is gaining increasing interest in the field of medicine because of its capacity to process big data and pattern recognition. Cardiotocography (CTG) is widely used for the assessment of foetal well-being and uterine contractions during pregnancy and labour. It is characterised by inter- and intraobserver variability in interpretation, which depends on the observers’ experience. Artificial intelligence (AI)-assisted interpretation could improve its quality and, thus, intrapartal care. Cardiotocography (CTG) raw signals from labouring women were extracted from the database at the University Hospital of Bern between 2006 and 2019. Later, they were matched with the corresponding foetal outcomes, namely arterial umbilical cord pH and 5-min APGAR score. Excluded were deliveries where data were incomplete, as well as multiple births. Clinical data were grouped regarding foetal pH and APGAR score at 5 min after delivery. Physiological foetal pH was defined as 7.15 and above, and a 5-min APGAR score was considered physiologic when reaching ≥7. With these groups, the algorithm was trained to predict foetal hypoxia. Raw data from 19,399 CTG recordings could be exported. This was accomplished by manually searching the patient’s identification numbers (PIDs) and extracting the corresponding raw data from each episode. For some patients, only one episode per pregnancy could be found, whereas for others, up to ten episodes were available. Initially, 3400 corresponding clinical outcomes were found for the 19,399 CTGs (17.52%). Due to the small size, this dataset was rejected, and a new search strategy was elaborated. After further matching and curation, 6141 (31.65%) paired data samples could be extracted (cardiotocography raw data and corresponding maternal and foetal outcomes). Of these, half will be used to train artificial intelligence (AI) algorithms, whereas the other half will be used for analysis of efficacy. Complete data could only be found for one-third of the available population. Yet, to our knowledge, this is the most exhaustive and second-largest cardiotocography database worldwide, which can be used for computer analysis and programming. A further enrichment of the database is planned.
- 15 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 21 (1) , 1-13
PrivaTree: Collaborative Privacy-Preserving Training of Decision Trees on Biomedical Data
Biomedical data generation and collection have become faster and more ubiquitous. Consequently, datasets are increasingly spread across hospitals, research institutions, or other entities. Exploiting such distributed datasets simultaneously can be beneficial; in particular, classification using machine learning models such as decision trees is becoming increasingly common and important. However, given that biomedical data is highly sensitive, sharing data records across entities or centralizing them in one location are often prohibited due to privacy concerns or regulations. We design PrivaTree, an efficient and privacy-preserving protocol for collaborative training of decision tree models on distributed, horizontally partitioned, biomedical datasets. Although decision tree models may not always be as accurate as neural networks, they have better interpretability and are helpful in decision-making processes, which are crucial for biomedical applications. PrivaTree follows a federated learning approach, where raw data is not shared, and where every data provider computes updates to a global decision tree model being trained, on their private dataset. This is followed by privacy-preserving aggregation of these updates using additive secret-sharing, in order to collaboratively update the model. We implement PrivaTree, and evaluate its computational and communication efficiency on three different biomedical datasets, as well as the accuracy of the resulting models. Compared to the model centrally trained on all data records, the obtained collaborative model presents a modest loss of accuracy, while consistently outperforming the accuracy of the local models, trained separately by each data provider. Moreover, PrivaTree is more efficient than existing solutions, which makes it usable for training decision trees with numerous nodes, on large complex datasets, with both continuous and categorical attributes, as often found in the biomedical field.
- 15 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 21 (1) , 1-13
PrivaTree: Collaborative Privacy-Preserving Training of Decision Trees on Biomedical Data
Biomedical data generation and collection have become faster and more ubiquitous. Consequently, datasets are increasingly spread across hospitals, research institutions, or other entities. Exploiting such distributed datasets simultaneously can be beneficial; in particular, classification using machine learning models such as decision trees is becoming increasingly common and important. However, given that biomedical data is highly sensitive, sharing data records across entities or centralizing them in one location are often prohibited due to privacy concerns or regulations. We design PrivaTree, an efficient and privacy-preserving protocol for collaborative training of decision tree models on distributed, horizontally partitioned, biomedical datasets. Although decision tree models may not always be as accurate as neural networks, they have better interpretability and are helpful in decision-making processes, which are crucial for biomedical applications. PrivaTree follows a federated learning approach, where raw data is not shared, and where every data provider computes updates to a global decision tree model being trained, on their private dataset. This is followed by privacy-preserving aggregation of these updates using additive secret-sharing, in order to collaboratively update the model. We implement PrivaTree, and evaluate its computational and communication efficiency on three different biomedical datasets, as well as the accuracy of the resulting models. Compared to the model centrally trained on all data records, the obtained collaborative model presents a modest loss of accuracy, while consistently outperforming the accuracy of the local models, trained separately by each data provider. Moreover, PrivaTree is more efficient than existing solutions, which makes it usable for training decision trees with numerous nodes, on large complex datasets, with both continuous and categorical attributes, as often found in the biomedical field.
- Open Access
- 23 September 2022
- Published by MDPI AG in Journal of Personalized Medicine
- Vol. 12 (10) , 1571
Photoplethysmography-Based Blood Pressure Monitoring Could Improve Patient Outcome during Anesthesia Induction
During anesthesia, noncritical patients are routinely monitored via noninvasive cuff-based blood pressure (BP) monitors. Due to the noncontinuous nature of the monitoring, the BP values of the patient remain unavailable between consecutive cuff measurements, carrying the risk of missing rapid and sudden variations in BP. We evaluated the added value of using a photoplethysmography (PPG)-based continuous BP measurement device in addition to the standard cuff-based monitoring in a cohort of 40 patients in comparison with the current approach, in which only intermittent cuff-based measurements are available. When using a three-minute cuff measurement interval, using the PPG-based BP measurement in addition to the cuff-based monitor reduced the error (mean ± SD) of systolic (SBP) and mean (MBP) BP from 2.6 ± 19.6 mmHg and 1.2 ± 13.2 mmHg to 0.5 ± 11.2 mmHg and 0.0 ± 8.1 mmHg, respectively. Error grid analysis was also used to assess the improvement in patient safety. The additional use of the PPG-based BP measurement reduced the amount of data falling into higher risk categories. For SBP, points falling in the significant-, moderate-, and low-risk categories decreased from 1.1%, 8.7%, and 19.3% to 0.0%, 2.3%, and 9.6%, respectively. Similar results were obtained for MBP. These results suggest that using a PPG-based BP monitor—in addition to the standard cuff-based monitor—can improve patient safety during anesthesia induction, with no additional sensor needed.
- 23 September 2022
- Published by MDPI AG in Journal of Personalized Medicine
- Vol. 12 (10) , 1571
Open AccessPhotoplethysmography-Based Blood Pressure Monitoring Could Improve Patient Outcome during Anesthesia Induction
During anesthesia, noncritical patients are routinely monitored via noninvasive cuff-based blood pressure (BP) monitors. Due to the noncontinuous nature of the monitoring, the BP values of the patient remain unavailable between consecutive cuff measurements, carrying the risk of missing rapid and sudden variations in BP. We evaluated the added value of using a photoplethysmography (PPG)-based continuous BP measurement device in addition to the standard cuff-based monitoring in a cohort of 40 patients in comparison with the current approach, in which only intermittent cuff-based measurements are available. When using a three-minute cuff measurement interval, using the PPG-based BP measurement in addition to the cuff-based monitor reduced the error (mean ± SD) of systolic (SBP) and mean (MBP) BP from 2.6 ± 19.6 mmHg and 1.2 ± 13.2 mmHg to 0.5 ± 11.2 mmHg and 0.0 ± 8.1 mmHg, respectively. Error grid analysis was also used to assess the improvement in patient safety. The additional use of the PPG-based BP measurement reduced the amount of data falling into higher risk categories. For SBP, points falling in the significant-, moderate-, and low-risk categories decreased from 1.1%, 8.7%, and 19.3% to 0.0%, 2.3%, and 9.6%, respectively. Similar results were obtained for MBP. These results suggest that using a PPG-based BP monitor—in addition to the standard cuff-based monitor—can improve patient safety during anesthesia induction, with no additional sensor needed.
- 30 June 2022
- Published by Elsevier
- p. 59-93
Sensor technologies for mobile and wearable applications in mobile respiratory management
- 30 June 2022
- Published by Elsevier
- p. 59-93
Sensor technologies for mobile and wearable applications in mobile respiratory management
- Open Access
- 19 March 2022
- Published by MDPI AG in Diagnostics
- Vol. 12 (3) , 749
Comparability of a Blood-Pressure-Monitoring Smartphone Application with Conventional Measurements—A Pilot Study
(1) Background: New cuffless technologies attempting blood-pressure measurements (BPM) offer possibilities to improve hypertension awareness and control. The aim of this study was to compare a smartphone application (app)-based algorithm with office BPM (OBPM). (2) Methods: We included consecutive patients with an indication for ambulatory BPM. The smartphone app (RIVA digital) acquired the pulse wave in the fingers’ arterial bed using the phone’s camera and estimated BP based on photoplethysmographic (PPG) waveforms. Measurements were alternatingly taken with an oscillometric cuff-based device and smartphone BPM (AppBP) on two consecutive days. AppBP were calibrated to the first OBPM. Each AppBP was compared to its CuffBP (mean of the previous/following OBPM). (3) Results: 50 participants were included, resulting in 50 AppBP values on Day 1 and 33 on Day 2 after exclusion of 225 AppBP due to insufficient quality. The mean ± SD of the differences between AppBP and CuffBP was 0.7 ± 9.4/1.0 ± 4.5 mmHg (p-value 0.739/0.201) on Day 1 and 2.6 ± 8.2/1.3 ± 4.1 mmHg (p-value 0.106/0.091) on Day 2 for systolic/diastolic values, respectively. There were no significant differences between the deviations on Day 1 and Day 2 (p-value 0.297/0.533 for systolic/diastolic values). Overall, there were 10 (12%) systolic measurement pairs differing by >15 mmHg. (4) Conclusions: In this pilot evaluation, the RIVA Digital app shows promising results when compared to oscillometric cuff-based measurements, especially regarding diastolic values. Its differences between AppBP–CuffBP have a good stability one day after calibration. Before clinical use, signal acquisition needs improvement and the algorithm needs to undergo formal validation against a gold-standard BPM method.
- 19 March 2022
- Published by MDPI AG in Diagnostics
- Vol. 12 (3) , 749
Open AccessComparability of a Blood-Pressure-Monitoring Smartphone Application with Conventional Measurements—A Pilot Study
(1) Background: New cuffless technologies attempting blood-pressure measurements (BPM) offer possibilities to improve hypertension awareness and control. The aim of this study was to compare a smartphone application (app)-based algorithm with office BPM (OBPM). (2) Methods: We included consecutive patients with an indication for ambulatory BPM. The smartphone app (RIVA digital) acquired the pulse wave in the fingers’ arterial bed using the phone’s camera and estimated BP based on photoplethysmographic (PPG) waveforms. Measurements were alternatingly taken with an oscillometric cuff-based device and smartphone BPM (AppBP) on two consecutive days. AppBP were calibrated to the first OBPM. Each AppBP was compared to its CuffBP (mean of the previous/following OBPM). (3) Results: 50 participants were included, resulting in 50 AppBP values on Day 1 and 33 on Day 2 after exclusion of 225 AppBP due to insufficient quality. The mean ± SD of the differences between AppBP and CuffBP was 0.7 ± 9.4/1.0 ± 4.5 mmHg (p-value 0.739/0.201) on Day 1 and 2.6 ± 8.2/1.3 ± 4.1 mmHg (p-value 0.106/0.091) on Day 2 for systolic/diastolic values, respectively. There were no significant differences between the deviations on Day 1 and Day 2 (p-value 0.297/0.533 for systolic/diastolic values). Overall, there were 10 (12%) systolic measurement pairs differing by >15 mmHg. (4) Conclusions: In this pilot evaluation, the RIVA Digital app shows promising results when compared to oscillometric cuff-based measurements, especially regarding diastolic values. Its differences between AppBP–CuffBP have a good stability one day after calibration. Before clinical use, signal acquisition needs improvement and the algorithm needs to undergo formal validation against a gold-standard BPM method.
- 13 February 2020
- Published by Springer Nature
- p. 525-540
Sidecar: Augmenting Word Embedding Models with Expert Knowledge
- 13 February 2020
- Published by Springer Nature
- p. 525-540
Sidecar: Augmenting Word Embedding Models with Expert Knowledge
- Open Access
Classification of Cardiac Arrhythmias from Single Lead ECG with a Convolutional Recurrent Neural Network
While most heart arrhythmias are not immediately harmful, they can lead to severe complications. In particular, atrial fibrillation, the most common arrhythmia, is characterized by fast and irregular heart beats and increases the risk of suffering a stroke. To detect such abnormal heart conditions, we propose a system composed of two main parts: a smart vest with two cooperative sensors to collect ECG data and a neural network architecture to classify heart rhythms. The smart vest uses two dry bi-electrodes to record a single lead ECG signal. The biopotential signal is then streamed via a gateway to the cloud where a neural network detects and classifies the heart arrhythmias. We selected an architecture that combines convolutional and recurrent layers. The convolutional layers extract relevant features from sliding windows of ECG and the recurrent layer aggregates them for a final softmax layer that performs the classification. Our neural network achieves an accuracy of 87.50% on the dataset of the challenge of Computing in Cardiology 2017.
Open AccessClassification of Cardiac Arrhythmias from Single Lead ECG with a Convolutional Recurrent Neural Network
While most heart arrhythmias are not immediately harmful, they can lead to severe complications. In particular, atrial fibrillation, the most common arrhythmia, is characterized by fast and irregular heart beats and increases the risk of suffering a stroke. To detect such abnormal heart conditions, we propose a system composed of two main parts: a smart vest with two cooperative sensors to collect ECG data and a neural network architecture to classify heart rhythms. The smart vest uses two dry bi-electrodes to record a single lead ECG signal. The biopotential signal is then streamed via a gateway to the cloud where a neural network detects and classifies the heart arrhythmias. We selected an architecture that combines convolutional and recurrent layers. The convolutional layers extract relevant features from sliding windows of ECG and the recurrent layer aggregates them for a final softmax layer that performs the classification. Our neural network achieves an accuracy of 87.50% on the dataset of the challenge of Computing in Cardiology 2017.