Granted Patent B2

US 12,658,320 · App. 17/493,159 · Granted Jun 16, 2026

Inventor: Kenneth Neumann (Lakewood, CO)

Assignee: KPN INNOVATIONS, LLC

G16H50/20G06F18/2113G06N5/022G06N20/00G16H10/60G16H50/70

Abstract

Claims (73)

1 . A system for prioritizing user symptom complaint inputs, the system comprising at least a computing device, wherein the at least a computing device is configured to:

receive a plurality of symptom complaint datums generated by a user;

determine a frequency element as a function of the plurality of symptom complaint datums;

generate an optimal vector output using a K-nearest neighbor (KNN) module,

wherein the KNN module is configured to:

receive suspected disease state training data correlating symptom complaint data to suspected disease state vectors;

determine similarity between the plurality of symptom complaint datums and suspected disease states using a distance metric;

modify suspected disease state training data by normalizing vector entries to contain consistent variance;

generate a suspected disease state output by selecting a k-nearest neighbors and aggregating results using component-wise addition followed by normalization;

display, using a graphical user interface, the generated optimal vector output;

receive a user entry generated as a function of the displayed optimal vector output, wherein the user entry comprises a datum of user genetic history, wherein the user genetic history comprises a sample extracted from the user;

update, as a function of the user entry, the generated optimal vector output;

produce a disease criticality score as a function of the frequency element and a criticality machine-learning model, wherein producing further comprises:

iteratively training the criticality machine-learning model as a function of a criticality training set comprising exemplary frequency element inputs, and exemplary expert inputs correlated to exemplary disease criticality score outputs, wherein the updated optimal vector output is used to refine a suspected disease state ranking, wherein the suspected disease state refined ranking is utilized in selecting and updating the criticality training set;

obtaining an expert input;

determining the disease criticality score as a function of the expert input and the frequency element using the trained criticality machine learning model;

receiving a user-entered valuation of the disease criticality score; and

updating the criticality training set as a function of the user-entered valuation;

generate a suspected disease state as a function of the disease criticality score, wherein the suspected disease state comprises a probable current disease state and at least one future disease state associated with the probable current disease state; and

display the suspected disease state using the graphical user interface.

2 . The system of claim 1 , wherein receiving the plurality of symptom complaint datums further comprises identifying a body symptom associated to the user.

3 . The system of claim 1 , wherein determining the frequency element further comprises identifying a user frequency.

4 . The system of claim 1 , wherein determining the frequency element further comprises identifying a symptom complaint datum frequency.

5 . The system of claim 1 , wherein producing the disease criticality score further comprises:

generating a validation signature as a function of the symptom complaint datum and the expert input; and

producing the disease criticality score as a function of the validation signature.

6 . The system of claim 1 , wherein producing the disease criticality score further comprises:

receiving a criticality training set, wherein the criticality training set correlates a plurality of frequency elements and a plurality of expert inputs to criticality scores; and

producing the disease criticality score as a function of a criticality machine-learning model, wherein the criticality machine-learning model is trained as a function of the criticality training set.

7 . The system of claim 1 , wherein the expert input is obtained as a function of an expert knowledge database.

8 . The system of claim 1 , wherein generating the suspected disease state further comprises:

producing a first disease criticality score as a function of a first frequency element;

receiving an updated symptom complaint datum;

generating a second disease criticality score as a function of the updated symptom complaint datum; and

determining the suspected disease state as a function of the second disease criticality score.

9 . The system of claim 8 , wherein generating the suspected disease state further comprises determining the suspected disease state as a function of ranking the first disease criticality score and the second disease criticality score.

10 . The system of claim 1 , wherein generating the suspected disease state further comprises transmitting the suspected disease state to a graphical user interface.

11 . A method for prioritizing user symptom complaint inputs, the method comprises:

receiving, by a computing device, a plurality of symptom complaint datums generated by a user;

determining, by the computing device, a frequency element as a function of the plurality of symptom complaint datums;

generating, by the computing device, an optimal vector output using a K-nearest neighbor (KNN) module, wherein the KNN module is configured to:

receive suspected disease state training data correlating symptom complaint data to suspected disease state vectors;

determine similarity between the plurality of symptom complaint datums and suspected disease states using a distance metric;

modify suspected disease state training data by normalizing vector entries to contain consistent variance;

generate a suspected disease state output by selecting a k-nearest neighbors and aggregating results using component-wise addition followed by normalization;

displaying, using a graphical user interface, the generated optimal vector output;

receiving, by the computing device, a user entry generated as a function of the displayed optimal vector output, wherein the user entry comprises a datum of user genetic history, wherein the user genetic history comprises a sample extracted from the user;

update, by the computing device, as a function of the user entry, the generated optimal vector output;

producing, by the computing device, a disease criticality score as a function of the frequency element and a criticality machine-learning model, wherein producing further comprises:

iteratively training the criticality machine-learning model as a function of a criticality training set comprising exemplary frequency element inputs, and exemplary expert inputs correlated to exemplary disease criticality score outputs, wherein the updated optimal vector output is used to refine a suspected disease state ranking, wherein the suspected disease state refined ranking is utilized in selecting and updating the criticality training set;

obtaining an expert input; and

determining the disease criticality score as a function of the expert input and the frequency element using the trained criticality machine learning model;

receiving a user-entered valuation of the disease criticality score; and

updating the criticality training set as a function of the user-entered valuation;

generating, by the computing device, a suspected disease state as a function of the disease criticality score, wherein the suspected disease state comprises a probable current disease state and at least one future disease state associated with the probable current disease state; and

display the suspected disease state using the graphical user interface.

12 . The method of claim 11 , wherein receiving the plurality of symptom complaint datums further comprises identifying a body symptom associated to the user.

13 . The method of claim 11 , wherein determining the frequency element further comprises identifying a user frequency.

14 . The method of claim 11 , wherein determining the frequency element further comprises identifying a symptom complaint datum frequency.

15 . The method of claim 11 , wherein producing the disease criticality score further comprises:

generating a validation signature as a function of the symptom complaint datum and the expert input; and

producing the disease criticality score as a function of the validation signature.

16 . The method of claim 11 , wherein producing the disease criticality score further comprises:

receiving a criticality training set, wherein the criticality training set correlates a plurality of frequency elements and a plurality of expert inputs to criticality scores; and

producing the disease criticality score as a function of a criticality machine-learning model, wherein the criticality machine-learning model is trained as a function of the criticality training set.

17 . The method of claim 11 , wherein the expert input is obtained as a function of an expert knowledge database.

18 . The method of claim 11 , wherein generating the suspected disease state further comprises:

producing a first disease criticality score as a function of a first frequency element;

receiving an updated symptom complaint datum;

generating a second disease criticality score as a function of the updated symptom complaint datum; and

determining the suspected disease state as a function of the second disease criticality score.

19 . The method of claim 18 , wherein generating the suspected disease state further comprises determining the suspected disease state as a function of ranking the first disease criticality score and the second disease criticality score.

20 . The method of claim 11 , wherein generating the suspected disease state further comprises transmitting the suspected disease state to a graphical user interface.

Assignments (1)

Continuity (2)

References Cited (16)