A novel skin temperature estimation system for predicting pressure injury occurrence based on continuous body sensor data: A pilot study

• Published in: Clinical biomechanics (Bristol) 2024-12, Vol.122, p.106413, Article 106413
• Main Authors: Shinkawa, Minami, Mugita, Yuko, Takahashi, Toshiaki, Haba, Daijiro, Sanada, Hiromi, Nakagami, Gojiro
• Format: Article
• Language: English
• Subjects: Heathy participant; Non-constrained skin temperature estimation; Non-invasive body sensor monitoring; Pressure injury prediction; Simulation study
• ISSN: 0268-0033; 1879-1271; 1879-1271
• DOI: 10.1016/j.clinbiomech.2024.106413

Pressure injury prevention is important in older patients with immobility. This requires an accurate and efficient prediction of the development of pressure injuries. We aimed to develop a method for estimating skin temperature changes due to ischemia and inflammation using temperature sensors placed under bedsheets to provide an objective, non-invasive, and non-constrained risk assessment tool. This study consisted of a thermal skin simulation study and a descriptive correlation study in healthy participants. A thermal skin simulation study was conducted using a model reproducing the body surface (underwear, diaper, or wet diaper conditions) and bed environment. In a descriptive-correlational study, the participants lay supine on a mattress with a temperature sensor attached to their sacral skin. The thermal skin simulation study showed that temperature changes in the skin can be estimated under the sheets by inputting time-shifted temperature data into machine learning (R2 = 0.9967 for underwear, 0.9950 for diapers, and 0.9869 for wet diapers). It was also demonstrated that the absolute skin temperature of a healthy individual (N = 17) could be estimated with the best accuracy by inputting time-shifted data into an extra-tree regressor (R2 = 0.8145). A combination of interface pressure and temperature sensors can be used to estimate skin temperature changes. These findings contribute to the development of a skin temperature measurement method that can capture temperature changes over time in clinical settings. •Skin temperature of person on bed estimated by sensors placed under the sheet.•Thermal simulation was established to artificially reproduce skin thermal changes.•Input of time-shifted data into machine learning can estimate skin temperature.•Extra-tree regressor can estimate skin temperature with high accuracy.•This skin temperature estimation could be useful for predicting pressure injuries.