| CPC G16H 50/30 (2018.01) [A61B 5/7275 (2013.01); A61B 5/7435 (2013.01)] | 12 Claims |
|
1. A healthcare support system comprising:
a memory,
a hardware processor connected to the memory, and
a display device connected to the hardware processor,
wherein the hardware processor is configured to:
predict a risk value of a disease based on medical checkup data stored in the memory for a medical examinee;
set a reduction target for the risk value of the disease;
set a plurality of second factors constituting search targets among a plurality of first factors relating to the disease and a search range for each of the second factors;
search, by using a random method or a Bayesian method, in the search range for each of the second factors, for a target value candidate of each of the second factors so that the risk value of the disease is brought close to the reduction target;
execute search processing to reduce a loss value calculated based on the risk value of the disease and the reduction target, for each target value candidate of the second factors;
calculate a third loss using a calculation formula for each target value candidate of the second factors;
output, as a final value, a target value of each of the second factors with which the third loss is equal to or less than a preset threshold value; and
generate a graphical user interface and display the graphical user interface on the display device, the graphical user interface displaying the target value for each of the second factors which is finally obtained by the search processing, displaying a current risk value predicted from the medical checkup data and a post-reduction risk value such that the current risk value is comparable with the post-reduction risk value, and displaying the reduction target, the graphical user interface displaying the current risk value and the post-reduction risk value side-by-side in a graph format or a table format and displaying the reduction target as a numerical value adjacent to the current risk value and the post-reduction risk value, and
wherein the calculation formula adds together a first loss and a second loss using fixed weighting, the first loss being calculated from a difference between the current risk value and a risk value constituting the reduction target, and the second loss being calculated from the difference between an examination value for each of the second factors and the target value candidate of each of the second factors.
|