Regression or Classification? Reflection on BP prediction from PPG data using Deep Neural Networks in the scope of practical applications

TL;DR

This study compares blood pressure estimation from PPG signals using regression and classification neural network models, finding classification often outperforms regression after personalization, suggesting it may be more practical in clinical scenarios.

Contribution

It provides a comparative analysis of BP regression and classification methods using neural networks on PPG data, highlighting the advantages of classification after personalization.

Findings

Classification models outperform regression models after personalization.

Both approaches perform similarly before personalization.

BP classification can be sufficient for clinical applications requiring coarser BP segmentation.

Abstract

Photoplethysmographic (PPG) signals offer diagnostic potential beyond heart rate analysis or blood oxygen level monitoring. In the recent past, research focused extensively on non-invasive PPG-based approaches to blood pressure (BP) estimation. These approaches can be subdivided into regression and classification methods. The latter assign PPG signals to predefined BP intervals that represent clinically relevant ranges. The former predict systolic (SBP) and diastolic (DBP) BP as continuous variables and are of particular interest to the research community. However, the reported accuracies of BP regression methods vary widely among publications with some authors even questioning the feasibility of PPG-based BP regression altogether. In our work, we compare BP regression and classification approaches. We argue that BP classification might provide diagnostic value that is equivalent to regression in many clinically relevant scenarios while being similar or even superior in terms of performance. We compare several established neural architectures using publicly available PPG data for SBP regression and classification with and without personalization using subject-specific data. We found that classification and regression models perform similar before personalization. However, after personalization, the accuracy of classification based methods outperformed regression approaches. We conclude that BP classification might be preferable over BP regression in certain scenarios where a coarser segmentation of the BP range is sufficient.