PulseDB: A large, cleaned dataset based on MIMIC-III and VitalDB for benchmarking cuff-less blood pressure estimation methods

Wang, Weinan; Mohseni, Pedram; Kilgore, Kevin L.; Najafizadeh, Laleh

doi:10.3389/fdgth.2022.1090854

Cited by 18 publications

(6 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, spectral features can be combined with temporal features for predicting BP [83][84][85]. The impact of data cleaning is highlighted in [86,87]. The problem may be formulated as a regression or classification problem [88].…”

Section: A Machine Learning and Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

Video-based beat-by-beat blood pressure monitoring via transfer deep-learning

Omer,

Salah,

Hassan

et al. 2024

Appl Intell

View full text Add to dashboard Cite

Currently, learning physiological vital signs such as blood pressure (BP), hemoglobin levels, and oxygen saturation, from Photoplethysmography (PPG) signal, is receiving more attention. Despite successive progress that has been made so far, continuously revealing new aspects characterizes that field as a rich research topic. It includes a diverse number of critical points represented in signal denoising, data cleaning, employed features, feature format, feature selection, feature domain, model structure, problem formulation (regression or classification), and model combinations. It is worth noting that extensive research efforts are devoted to utilizing different variants of machine learning and deep learning models while transfer learning is not fully explored yet. So, in this paper, we are introducing a per-beat rPPG-to-BP mapping scheme based on transfer learning. An interesting representation of a 1-D PPG signal as a 2-D image is proposed for enabling powerful off-the-shelf image-based models through transfer learning. It resolves limitations about training data size due to strict data cleaning. Also, it enhances model generalization by exploiting underlying excellent feature extraction. Moreover, non-uniform data distribution (data skewness) is partially resolved by introducing logarithmic transformation. Furthermore, double cleaning is applied for training contact PPG data and testing rPPG beats as well. The quality of the segmented beats is tested by checking some of the related quality metrics. Hence, the prediction reliability is enhanced by excluding deformed beats. Varying rPPG quality is relaxed by selecting beats during intervals of the highest signal strength. Based on the experimental results, the proposed system outperforms the state-of-the-art systems in the sense of mean absolute error (MAE) and standard deviation (STD). STD for the test data is decreased to 5.4782 and 3.8539 for SBP and DBP, respectively. Also, MAE decreased to 2.3453 and 1.6854 for SBP and DBP, respectively. Moreover, the results for BP estimation from real video reveal that the STD reaches 8.027882 and 6.013052 for SBP and DBP, respectively. Also, MAE for the estimated BP from real videos reaches 7.052803 and 5.616028 for SBP and DBP, respectively. Graphical abstract Proposed camera-based blood pressure monitoring system

show abstract

Section: A Machine Learning and Deep Learningmentioning

confidence: 99%

“…In this paper, we prefer to operate on MIMIC-II. While the MIMIC dataset represents the universal common source of the dataset for almost all the related work, the essential difference resides in the applied cleaning strategy [86,117]. However, we follow our cleaned version [87].…”

Section: Datasetmentioning

confidence: 99%

Video-based beat-by-beat blood pressure monitoring via transfer deep-learning

Omer,

Salah,

Hassan

et al. 2024

Appl Intell

View full text Add to dashboard Cite

show abstract

“…2) The PulseDB dataset 52 : This dataset contains a large number of filtered PPG and ECG signals. It also contains the ground truth labels for HR and BP.…”

Section: Benchmark Ppg Datasetsmentioning

confidence: 99%

Your smartphone could act as a pulse-oximeter and as a single-lead ECG

Mehmood,

Sarouji,

Rahman

et al. 2023

Preprint

View full text Add to dashboard Cite

In the post-covid19 era, every new wave of the pandemic causes an increased concern/interest among the masses to learnmore about their state of well-being. Therefore, it is the need of the hour to come up with ubiquitous, low-cost, non-invasivetools for rapid and continuous monitoring of body vitals that reflect the status of one’s overall health. In this backdrop, this workproposes a deep learning approach to turn a smartphone—the popular hand-held personal gadget—into a diagnostic tool tomeasure/monitor the three most important body vitals, i.e., pulse rate (PR), blood oxygen saturation level (aka SpO2), andrespiratory rate (RR). Furthermore, we propose another method that could extract a single-lead electrocardiograph (ECG)of the subject. The proposed methods include the following core steps: subject records a small video of his/her fingertip byplacing his/her finger on the rear camera of the smartphone, and the recorded video is pre-processed to extract the filteredand/or detrended video-photoplethysmography (vPPG) signal, which is then fed to custom-built convolutional neural networks(CNN), which eventually spit-out the vitals (PR, SpO2, and RR) as well as a single-lead ECG of the subject. To be precise,the contribution of this paper is two-fold: 1) estimation of the three body vitals (PR, SpO2, RR) from the vPPG data usingcustom-built CNNs, vision transformer, and most importantly by CLIP model (a popular image-caption-generator model); 2) anovel discrete cosine transform+feedforward neural network-based method that translates the recorded video-PPG signal to asingle-lead ECG signal. The significance of this work is two-fold: i) it allows rapid self-testing of body vitals (e.g., self-monitoringfor covid19 symptoms), ii) it enables rapid self-acquisition of a single-lead ECG, and thus allows early detection of atrialfibrillation (abormal heart beat or arrhythmia), which in turn could enable early intervention in response to a range of cardiovascular diseases,and could help save many precious lives. Our work could help reduce the burden on healthcare facilities and could lead toreduction in health insurance costs.

show abstract

“…One of our previous works proposed a high-performance deep learning model, UTransBPNet [17] . Due to its strong capability in short-and long-range feature representation due to the combined structure of Unet and Transformer, it demonstrated superior performance over popular models such as CNN-LSTM-attention [17] and CNN-BiGRU [18] , in scenarios with significant intra-subject BP variations. However, this validation was limited to a small, self-collected dataset with a narrow demographic range.…”

Section: Introductionmentioning

confidence: 99%

Validation of deep learning models for cuffless blood pressure estimation on a large benchmarking dataset

Huang,

He,

Song

et al. 2024

Conn Health Telemed

View full text Add to dashboard Cite

Objective: This study aims to evaluate the effectiveness of deep learning techniques in estimating cuffless blood pressure (BP) across a diverse patient population in intensive care units (ICUs). Methods: A comprehensive ICU benchmarking dataset encompassing 2,154 patients with a wide demographic range (18-97 years old) and varied cardiovascular status was employed to validate several deep learning models in predicting continuous BP waveforms. Three methods were developed to enhance the model's generalizability to this heterogeneous dataset. Ten-fold subject-independent cross-validation was performed and the model performance was assessed through mean absolute error (MAE), Pearson’s correlation coefficient (PCC), and compared with significance analysis. Results: The UTransBPNet_Demo_In model, which incorporated demographic and physiological signals as inputs, achieved a PCC of 0.89 and a MAE of 10.38 mmHg in predicting arterial BP waveforms, demonstrating the highest tracking capability among all models. Notably, the performance of UTransBPNet_Demo_In remained robust across variations in demographic and cardiovascular status. Conclusion: The UTransBPNet_Demo_In model demonstrates robust predictive capabilities across a broad spectrum of demographics and cardiovascular conditions. Although the performance still needs further improvement, this study offers a benchmark in the field of cuffless BP monitoring in critical care settings for future studies.

show abstract

PulseDB: A large, cleaned dataset based on MIMIC-III and VitalDB for benchmarking cuff-less blood pressure estimation methods

Cited by 18 publications

References 54 publications

Video-based beat-by-beat blood pressure monitoring via transfer deep-learning

Video-based beat-by-beat blood pressure monitoring via transfer deep-learning

Your smartphone could act as a pulse-oximeter and as a single-lead ECG

Validation of deep learning models for cuffless blood pressure estimation on a large benchmarking dataset

Contact Info

Product

Resources

About