So far, major wearable manufacturers have been reluctant to offer body temperature data via wristbands. Some of them, such as Xiaomi, aim to include the estimation of body temperature from heart rate, on the basis that heart rate increases when a person has a fever. However, the company, as of the date of publication of this article, has not launched any device with this feature on the market.

At Intelligent Data we are already working, within the wearables market, on the development of an innovative solution focused on this current market need. Today, the technology used to measure temperature with wrist wearables is based on a thermistor, a type of resistor that varies its value depending on the temperature. This makes it possible to measure the temperature of the skin on the wrist.

1-. Theory and state of research.

Currently, when measuring temperature, there is a difference of a few degrees between skin temperature (Tp) and body temperature (Tc). The relationship between them is directly affected by the following factors:

  • Ambient temperature.
  • Location of the sensor on the skin.
  • Evaporation of sweat.
  • Heart rate.
  • Skin type of the person.
  • Thermal conductivity of the skin.
Illustration 1. Relationship of typical skin temperatures according to body location and ambient temperature [4].
Illustration 1. Ratio of typical skin temperatures according to body location and ambient temperature [4].

Heat produced inside the human body is transferred through the tissues to the skin surface by conduction, then dissipated from the skin to the environment with a heat loss rate HF (heat flux).

Generically, we can describe the relationship between body and skin temperatures with the following equation, a solution of the differential heat diffusion equation [1]:

𝑇𝑐 (𝑡) = 𝑇𝑝(𝑡) + Δ (𝑡)

Where Δ corresponds to the difference, in degrees, between the two temperatures and depends, like skin temperature, on time. In the steady state, the diffusion equation has the following solution:

𝑇𝑐 = 𝑇𝑝 + 𝐻𝐹 𝑑/𝜆 = 𝑇𝑝 + 𝐻𝐹 𝑑/𝜆

Where d is the thickness of the diffusion layer and λ is the thermal conductivity of the skin in Wm-1°C-1 and typically ranges from 0.20 - 0.70 [5]. In reference [2], neural networks are used to identify hidden variables and perform the conversion.

The graph on the left shows a schematic of the data fed into the neural network, which are related to each other and to other hidden variables to obtain body temperature as an output. On the right is a graph showing the results.

Other studies have demonstrated the usefulness of skin temperature as a parameter, for example, being able to predict future infections in hospitalised patients [6].

2.- Solution proposed by Intelligent Data: Customised calibration.

In the first stage of the pilot phase of the project, it is proposed to perform a personalised measurement calibration for each patient. That is, when a patient is given the bracelet, the skin temperature is automatically taken by the bracelet and, simultaneously, the nursing staff measures the body temperature. The difference between them is a first calibration of the personalised and unique increment for each patient:

Δ(𝑡 = 0) = 𝑇𝑐(0) - 𝑇𝑝(0)

The increment is variable over time and several calibrations can be performed during the patient's stay in hospital.

 In the following stages of the pilot phase, the calibration can be adjusted by including the following variables in its calculation which, as this document has shown, affect the time variation of the customised increment:

  • Ambient temperature.
  • Heart rate.

The values of these variables are collected by the wristband at the same time as the skin temperature, so there would be no time lag between them.

Bibliography

[1] X. Xu, A. J. Karis, M. J. Buller, and W. R. Santee, "Relationship between core temperature,
skin temperature, and heat flux during exercise in heat," Eur. J. Appl. Physiol., vol. 113, no.
9, pp. 2381-2389, 2013, doi: 10.1007/s00421-013-2674-z.
[2] Y. T. Kwak, J. Yang, and Y. You, "Conversion of Body Temperature from Skin Temperature
using Neural Network for Smart Band," 2019 7th Int. Conf. Robot Intell. Technol. Appl. RiTA
2019, pp. 67-71, 2019, doi: 10.1109/RITAPP.2019.8932736.
[3] K. Malhi, S. C. Mukhopadhyay, J. Schnepper, M. Haefke, and H. Ewald, "A zigbee-based wearable physiological parameters monitoring system," IEEE Sens. J., vol. 12, no. 3, pp. 423-430, 2012, doi: 10.1109/JSEN.2010.2091719.
[4] P. Webb, "Temperatures of skin, subcutaneous tissue, muscle and core in resting men in cold, comfortable and hot conditions," Eur. J. Appl. Physiol. Occup. Physiol., vol. 64, no. 5,pp. 471-476, 1992, doi: 10.1007/BF00625070.
[5] J. Werner and M. Buse, "Temperature profiles with respect to inhomogeneity and geometry of the human body," J. Appl. Physiol., vol. 65, no. 3, pp. 1110-1118, 1988, doi: 10.1152/jappl.1988.65.3.1110.
[6] S. G. Holt et al., "Monitoring skin temperature at the wrist in hospitalised patients may assist in the detection of infection," Intern. Med. J., vol. 50, no. 6, pp. 685-690, 2020, doi:10.1111/imj.14748.