# "Can't Take the Pressure?": Examining the Challenges of Blood Pressure Estimation via Pulse Wave Analysis

arXiv: https://arxiv.org/abs/2304.14916 · HTML: https://mlsanity.com/paper/2304.14916/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 68 references that are in the map.
- First posted on arXiv 23 Apr 2023.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement](https://mlsanity.com/paper/2006.03790/) (2020)
- [PPG2ABP: Translating Photoplethysmogram (PPG) Signals to Arterial Blood Pressure (ABP) Waveforms using Fully Convolutional Neural Networks](https://mlsanity.com/paper/2005.01669/) (2020)
- [A Deep Learning Approach to Predict Blood Pressure from PPG Signals](https://mlsanity.com/paper/2108.00099/) (2021)
- [A Shallow U-Net Architecture for Reliably Predicting Blood Pressure (BP) from Photoplethysmogram (PPG) and Electrocardiogram (ECG) Signals](https://mlsanity.com/paper/2111.08480/) (2021)
- [MobilePhys: Personalized Mobile Camera-Based Contactless Physiological Sensing](https://mlsanity.com/paper/2201.04039/) (2022)
- [SmartKC: Smartphone-based Corneal Topographer for Keratoconus Detection](https://mlsanity.com/paper/2111.01354/) (2021)
- [Towards Automating Retinoscopy for Refractive Error Diagnosis](https://mlsanity.com/paper/2208.05552/) (2022)

## Built on by (most cited first, 2 of 2)

- [Uncertainty quantification with approximate variational learning for wearable photoplethysmography prediction tasks](https://mlsanity.com/paper/2505.11412/) (2025)
- [Hypertension Detection From High-Dimensional Representation of Photoplethysmogram Signals](https://mlsanity.com/paper/2308.02425/) (2023)

## Abstract (arXiv)

The use of observed wearable sensor data (e.g., photoplethysmograms [PPG]) to infer health measures (e.g., glucose level or blood pressure) is a very active area of research. Such technology can have a significant impact on health screening, chronic disease management and remote monitoring. A common approach is to collect sensor data and corresponding labels from a clinical grade device (e.g., blood pressure cuff), and train deep learning models to map one to the other. Although well intentioned, this approach often ignores a principled analysis of whether the input sensor data has enough information to predict the desired metric. We analyze the task of predicting blood pressure from PPG pulse wave analysis. Our review of the prior work reveals that many papers fall prey data leakage, and unrealistic constraints on the task and the preprocessing steps. We propose a set of tools to help determine if the input signal in question (e.g., PPG) is indeed a good predictor of the desired label (e.g., blood pressure). Using our proposed tools, we have found that blood pressure prediction using PPG has a high multi-valued mapping factor of 33.2% and low mutual information of 9.8%. In comparison, heart rate prediction using PPG, a well-established task, has a very low multi-valued mapping factor of 0.75% and high mutual information of 87.7%. We argue that these results provide a more realistic representation of the current progress towards to goal of wearable blood pressure measurement via PPG pulse wave analysis.