US 11,717,217 B2
Stress monitor and stress-monitoring method
Steffen Wirth, Munich (DE); Bernd Hälbig, Bobingen (DE); and Tina Schlereth, Erding (DE)
Assigned to Steffen Wirth, Munich (DE)
Filed by Steffen Wirth, Munich (DE)
Filed on Mar. 25, 2020, as Appl. No. 16/829,130.
Claims priority of application No. 19164972 (EP), filed on Mar. 25, 2019.
Prior Publication US 2020/0305791 A1, Oct. 1, 2020
Int. Cl. A61B 5/00 (2006.01)
CPC A61B 5/4884 (2013.01) [A61B 5/7264 (2013.01); A61B 5/749 (2013.01); A61B 2560/0431 (2013.01); A61B 2562/02 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A computer-implemented method for indicating a long-term stress level of a person using a computer comprising a processor and a memory, the method comprising the steps of:
acquiring stressor data having a set of stressor data items;
analyzing stressor data values of the stressor data items by generating, using an artificial neural network, data representing a stress level, wherein the artificial neural network is trained to provide output representing the stress level based on the stressor data values and an indication of previous stress state, wherein the artificial neural network is a recurrent neural network, wherein the indication of the previous stress state is considered via a feedback path to an input of the recurrent artificial neural network to consider the accumulating effect of stressors to which the person is exposed, wherein the artificial neural network is trained by available data of various persons who have developed a burnout syndrome, wherein the burnout syndrome defines a maximum value of a stress level; and
signaling the stress level, and
generating missing values of one or more particular stressor data by selecting relevant stressor data from the set of stressor data which have a positive correlation with the missing data above a given correlation threshold level so that a high-quality prediction of the missing stressor data can be obtained.