A study published in the British Medical Journal explores this misconception in-depth, highlighting that:
Individuals have varying baseline temperatures
Fevers should not be inferred by "absolute body temperature", but from deviations from baseline temperatures instead.
Why should someone's physiological state be compared with an absolute standard temperature? Body temperature deviations, after all, can have their roots in individual physiology, such as age, circadian, metabolic, and ovulatory cycles. These factors vary dramatically across individuals, raising the possibility that individuals have baseline temperatures that differ systematically from the population average. The same temperature that is normal for one person might be dangerously high for another.
(BMJ 2017;359;j5468)
Collecting and formulating a baseline temperature for an individual is a tedious task that is fraught with human error. Doing this at a large workplace with hundreds or thousands of employees is humanly impossible. Thankfully, Nirovision does this automatically for you. Simply set a deviation value, say 1°C, and we'll automatically alert you if a person has a temperature reading that is 1°C above their baseline.
Nirovision logs each time a person is seen on camera with a temperature reading. Over time, Nirovision learns what an appropriate temperature for each individual should be. Baseline temperatures are precise to the hour, as it is common for the human body to get warmer throughout the day. If an hourly baseline is not available, the individual's median is used instead.
We recommend starting with 1°C as per medical guidelines. You can use a lower number if you want more sensitivity, but anything less than 0.5°C is probably too sensitive.
If a new or unknown person registers a temperature reading, this reading will be compared to all other readings taken from that camera. This is obviously less accurate than using an individual baseline but still markedly more accurate than relying on an absolute temperature threshold.