# Pain Detection in Masked Faces during Procedural Sedation

arXiv: https://arxiv.org/abs/2211.06694 · HTML: https://mlsanity.com/paper/2211.06694/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 18 references that are in the map.
- First posted on arXiv 12 Nov 2022.

## Builds on (most cited first, 2 of 2)

- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Unobtrusive Pain Monitoring in Older Adults with Dementia using Pairwise and Contrastive Training](https://mlsanity.com/paper/2101.03251/) (2021)

## Built on by (most cited first, 1 of 1)

- [SynPAIN: A Synthetic Dataset of Pain and Non-Pain Facial Expressions](https://mlsanity.com/paper/2507.19673/) (2025)

## Abstract (arXiv)

Pain monitoring is essential to the quality of care for patients undergoing a medical procedure with sedation. An automated mechanism for detecting pain could improve sedation dose titration. Previous studies on facial pain detection have shown the viability of computer vision methods in detecting pain in unoccluded faces. However, the faces of patients undergoing procedures are often partially occluded by medical devices and face masks. A previous preliminary study on pain detection on artificially occluded faces has shown a feasible approach to detect pain from a narrow band around the eyes. This study has collected video data from masked faces of 14 patients undergoing procedures in an interventional radiology department and has trained a deep learning model using this dataset. The model was able to detect expressions of pain accurately and, after causal temporal smoothing, achieved an average precision (AP) of 0.72 and an area under the receiver operating characteristic curve (AUC) of 0.82. These results outperform baseline models and show viability of computer vision approaches for pain detection of masked faces during procedural sedation. Cross-dataset performance is also examined when a model is trained on a publicly available dataset and tested on the sedation videos. The ways in which pain expressions differ in the two datasets are qualitatively examined.