Dataset Information

Improving the Accuracy in Classification of Blood Pressure from Photoplethysmography Using Continuous Wavelet Transform and Deep Learning.

ABSTRACT:

Background

Continuous wavelet transform (CWT) based scalogram can be used for photoplethysmography (PPG) signal transformation to classify blood pressure (BP) with deep learning. We aimed to investigate the determinants that can improve the accuracy of BP classification based on PPG and deep learning and establish a better algorithm for the prediction.

Methods

The dataset from PhysioNet was accessed to extract raw PPG signals for testing and its corresponding BPs as category labels. The BP category of normal or abnormal followed the criteria of the 2017 American College of Cardiology/American Heart Association (ACC/AHA) Hypertension Guidelines. The PPG signals were transformed into 224 ∗ 224 ∗ 3-pixel scalogram via different CWTs and segment units. All of them are fed into different convolutional neural networks (CNN) for training and validation. The receiver-operating characteristic and loss and accuracy curves were used to evaluate and compare the performance of different methods.

Results

Both wavelet type and segment length could affect the accuracy, and Cgau1 wavelet and segment-300 revealed the best performance (accuracy 90%) without obvious overfitting. This method performed better than previously reported MATLAB Morse wavelet transformed scalogram on both of our proposed CNN and CNN-GoogLeNet.

Conclusions

We have established a new algorithm with high accuracy to predict BP classification from PPG via matching of CWT type and segment length, which is a promising solution for rapid prediction of BP classification from real-time processing of PPG signal on a wearable device.

SUBMITTER: Wu J

PROVIDER: S-EPMC8360747 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Remotely estimating leaf phosphorus concentration (LPC) is crucial for fertilization management, crop growth monitoring, and the development of precision agricultural strategy. This study aimed to explore the best prediction model for the LPC of rice (Oryza sativa L.) using machine learning algorithms fed with full-band (OR), spectral indices (SIs), and wavelet features. To obtain the LPC and leaf spectra reflectance, the pot experiments with four phosphorus (P) treatments and two rice cultivars were carried out in a greenhouse in 2020-2021. The results indicated that P deficiency increased leaf reflectance in the visible region (350-750 nm) and decreased the reflectance in the near-infrared (NIR, 750-1350 nm) regions compared to the P-sufficient treatment. Difference spectral index (DSI) composed of 1080 nm and 1070 nm showed the best performance for LPC estimation in calibration (R2 = 0.54) and validation (R2 = 0.55). To filter and denoise spectral data effectively, continuous wavelet transform (CWT) of the original spectrum was used to improve the accuracy of prediction. The model based on Mexican Hat (Mexh) wavelet function (1680 nm, Scale 6) demonstrated the best performance with the calibration R2 of 0.58, validation R2 of 0.56 and RMSE of 0.61 mg g-1. In machine learning, random forest (RF) had the best model accuracy in OR, SIs, CWT, and SIs + CWT compared with other four algorithms. The SIs and CWT coupling with the RF algorithm had the best results of model validation, the R2 was 0.73 and the RMSE was 0.50 mg g-1, followed by CWT (R2 = 0.71, RMSE = 0.51 mg g-1), OR (R2 = 0.66, RMSE = 0.60 mg g-1), and SIs (R2 = 0.57, RMSE = 0.64 mg g-1). Compared with the best performing SIs based on the linear regression models, the RF algorithm combining SIs and CWT improved the prediction of LPC with R2 increased by 32%. Our results provide a valuable reference for spectral monitoring of rice LPC under different soil P-supplying levels in a large scale.

Project description:Recent advances in molecular machine learning, especially deep neural networks such as graph neural networks (GNNs), for predicting structure-activity relationships (SAR) have shown tremendous potential in computer-aided drug discovery. However, the applicability of such deep neural networks is limited by the requirement of large amounts of training data. In order to cope with limited training data for a target task, transfer learning for SAR modeling has been recently adopted to leverage information from data of related tasks. In this work, in contrast to the popular parameter-based transfer learning such as pretraining, we develop novel deep transfer learning methods TAc and TAc-fc to leverage source domain data and transfer useful information to the target domain. TAc learns to generate effective molecular features that can generalize well from one domain to another and increase the classification performance in the target domain. Additionally, TAc-fc extends TAc by incorporating novel components to selectively learn feature-wise and compound-wise transferability. We used the bioassay screening data from PubChem and identified 120 pairs of bioassays such that the active compounds in each pair are more similar to each other compared to their inactive compounds. Overall, TAc achieves the best performance with an average ROC-AUC of 0.801; it significantly improves the ROC-AUC of 83% of target tasks with an average task-wise performance improvement of 7.102%, compared to the best baseline dmpna. Our experiments clearly demonstrate that TAc achieves significant improvement over all baselines across a large number of target tasks. Furthermore, although TAc-fc achieves slightly worse ROC-AUC on average compared to TAc (0.798 vs 0.801), TAc-fc still achieves the best performance on more tasks in terms of PR-AUC and F1 compared to other methods. In summary, TAc-fc is also found to be a strong model with competitive or even better performance than TAc on a notable number of target tasks.