# Feasibility of applying infrared thermal imaging for home monitoring of arthritis in children

## TL;DR

This study shows that infrared thermal imaging can be used at home to monitor arthritis in children, with results comparable to in-office evaluations.

## Contribution

The study demonstrates the feasibility of using smartphone-based thermal imaging for arthritis monitoring in a home setting.

## Key findings

- Home thermal imaging showed mild to moderate correlation with in-office measurements when using TAWiC calibration.
- Sensitivity and specificity for arthritis detection were similar between home and office settings.
- Thirty-eight out of fifty-three patients successfully completed home imaging with analyzable results.

## Abstract

Telemedicine has improved access to pediatric rheumatology care. A disadvantage to using virtual modality for evaluation of children with arthritis is the lack of an in-person, hands-on physical exam. Thermal imaging has been studied in the clinical setting with promising results. This study aims to determine the feasibility of procuring at-home thermal imaging, measuring the variability of in-home skin temperature measurements over three consecutive days, and to compare these measurements at home to ones obtained in the clinic setting.

Children with knee pain and/or swelling for a week or longer were enrolled and imaged with a smartphone-attached FLIR ONE PRO and Fluke handheld cameras followed by imaging with a FLIR camera at home for 3 consecutive days. Joint exam performed in the office was used as gold standard for joint assessment. A previously validated metric of temperature after within-limb calibration (TAWiC), defined as the temperature differences between the knee joint and ipsilateral mid-tibia, was used for all imaging studies.

Fifty-three patients were enrolled and thirty-eight completed the imaging acquisition at home with analyzable images. When evaluating images of the knee and mid-tibia regions, images collected at home compared to in-office demonstrated consistently lower absolute temperatures. However, the calibrated temperatures (TAWiC) of the anterior and lateral views of the knee showed mild to moderate correlation across 3 days between home-acquired images and office-acquired images (r = 0.58, 0.26, 0.24 and r = 0.36, 0.41, 0.42, respectively). The sensitivity and specificity of detecting arthritis of the knee using TAWiC adjustments from previously defined thresholds were similar regardless of the setting of image acquisition (0.44 and 0.79).

This study demonstrates the feasibility of applying TAWiC for arthritis detection through a smartphone-based infrared thermal camera operated by families at home. Further investigation on a larger scale is needed prior to implementation of this process in the telemedicine setting.

The online version contains supplementary material available at 10.1186/s12969-025-01096-1.