Data structure, method, and system for predicting medical conditions

• US 8,868,436 B2
• Filed: 01/17/2011
• Issued: 10/21/2014
• Est. Priority Date: 03/11/2010
• Status: Active Grant

• Current Assignee: Adrian Spalka, CompuGroup Medical SE
• Original Assignee: Compugroup Medical AG (CompuGroup Medical SE & Co. KGaA)
• Inventors: Gotthardt, Frank
• Primary Examiner(s): NGUYEN, HIEP VAN
• Application Number:
  US13/007,855
• Publication Number:
  US 20110225114A1
• Time in Patent Office: 1,373 Days
• Field of Search: 705/2
• US Class Current: 705/2
• CPC Class Codes: G06F 21/6245 Protecting personal data, e.g. for financial or medical purposes
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 70/60 relating to pathologies
• CPC Class Codes: H04L 9/0816 Key establishment, i.e. cryptographic processes or cryptographic protocols whereby a shared secret becomes available to two or more parties, for subsequent use

Abstract

The invention relates to a data structure comprising a plurality of biomedical parameters for providing a plurality of biomedical parameter values as input to a medical decision support system.

Claims

1. A computer-implemented method for generating a specification of a data structure, the data structure to be used as input for a medical decision support system, the data structure comprising a plurality of biomedical parameters, the method comprising the following steps performed on a processor:

determining, for a particular population of persons received via a communications device, a first set of diseases, each disease being represented by a data object, wherein each disease belonging to the determined set of diseases has assigned an absolute or relative frequency value within said population,

storing each data object on a non-transitory computer readable medium, said each data object representing a disease of the first set of diseases in association with the determined frequency value of the represented disease,

sorting the diseases of the first set of disease according to their assigned frequency values,

determining a second set of diseases, wherein the second set of diseases is a sub-set of the first set of diseases, the sub-set being created by leaving out all diseases of the first set of diseases which are biomechanical diseases,

determining a third set of diseases, the third set of diseases being built by executing the sub-steps;

A) determining, for each disease of the second set of diseases, a number of predictive parameters of said disease,

B) assigning a score value to each disease, the score value positively correlating with the frequency value of a disease and negatively correlating with the number of parameters correlating with or characterizing said disease, and sorting the diseases of the second set of diseases according to their assigned score values,

C) adding a disease of the second set of diseases which has assigned the highest score value and which in addition has not yet been added to the third set of diseases to the third set of diseases,

D) calculating a first sum, the first sum being calculated by summing up all frequency values of the diseases having yet being added to the third set of diseases,

E) if the first sum is below a coverage threshold value, repeating steps C and D, and if the first sum equals or exceeds said coverage threshold value, continuing with step F and using the third set of diseases and the first sum as result, and

F) compiling the plurality of biomedical parameters by determining, for each of the diseases in the third set of diseases, at least one biomedical parameter being indicative of the presence of said disease, whereby the compilation of the biomedical parameters constitutes the specification of the data structure wherein the plurality of biomedical parameter values comprises a first set of parameter values, each parameter value of the first set of biomedical parameter values being a laboratory value having been derived by analyzing a body fluid or tissue of a person, the first set of parameter values comprising;

glucose concentration,

LDL concentration,

HDL concentration,

triglyceride concentration,

creatinine concentration,

cholesterol concentration,

Hba1c concentration, and

C Reactive Peptide (CRP) concentration,

wherein the plurality of biomedical parameter values comprises a second set of parameter values of the person, the second set of data values comprising;

age,

gender,

body mass index (BMI),

waist/hip ratio,

blood pressure, and

smoking history

wherein the parameter set is the minimum parameter set required to allow monitoring of a wide range of the most common diseases.

2. The computer-implemented method according to claim 1, further comprising the step of instantiating the specified data structure by assigning each biomedical parameter of the data structure at least one biomedical parameter value of a person.

3. The computer-implemented method according to claim 2, wherein the instantiated data structure is assigned a pseudonym of the person, the method further comprising the steps:

entering a user-selected secret,

storing the user-selected secret in memory,

computing a private key by applying an embedding and randomizing function onto the secret,

storing the private key in the memory,

computing a public key using the private key, the public key and the private key forming an asymmetric cryptographic key,

erasing the secret and the private key from the memory,

outputting the public key for providing the pseudonym, and

assigning the pseudonym to the data structure.

4. The computer-implemented method according to claim 1, the method further comprising the step of adding to at least one biomedical parameter value a timestamp value, the timestamp value being indicative of the time and date the biomedical parameter value was received or created.

5. The computer-implemented method according to claim 1, wherein at least one biomedical parameter of the data structure is assigned a parameter value by executing the steps of:

receiving at least one biomedical catalog;

presenting a tree to a user via a graphical user interface, the nodes of the tree being a graphical representation of the elements of the received biomedical catalog, the tree providing the user with means to navigate in the tree structure;

receiving, upon selection of a tree node by the user, information being indicative of the element of the catalog represented by the selected tree node; and

assigning the identifier of the indicated catalog element as parameter value to the at least one biomedical parameter.

6. The computer-implemented method according to claim 1, wherein at least one biomedical parameter of the data structure is assigned a parameter value by executing the steps:

displaying on a graphical user interface a first list of first selectable Graphic User Interface (GUI) elements, each first selectable GUI element representing a laboratory parameter,

displaying, upon selection of a laboratory parameter of the first list by a user, a list of second parameter names having a similar parameter name like the selected laboratory parameter, each second parameter name being automatically determined and being represented as a second selectable GUI element,

displaying on the graphical user interface;

third selectable GUI elements for selecting a Logical Observation Identifiers Names and Codes (LOINC) name,

fourth selectable GUI elements for selecting a system of units,

fifth selectable GUI elements for selecting the tissue the selected laboratory parameter was derived from, and

a display element, the display element displaying a LOINC code, the LOINC code being determined automatically based on the selected third, fourth and fifth selectable GUI elements,

using the LOINC code as identifier of the laboratory parameter value.

7. The method of claim 1, wherein the first set of parameter values further comprises:

International Normalized Ratio (INR),

potassium concentration, and

at least one of Thyrotropic hormone or Thyroid stimulating hormone (collectively TSH) concentration.

8. The method of claim 7, wherein the first set of parameter values further comprises:

gamma-glutamyltransferase concentration,

alanine transaminase concentration, and

hemoglobin concentration.

9. The method of claim 8, wherein the first set of parameter values further comprises:

Leukocyte concentration,

Albumin concentration, and

Hä

mohapto value Stool,

and wherein the second set of parameter values further comprises;

body height,

body weight,

body temperature,

hip circumference,

waist circumference,

the systolic blood pressure,

the mean blood pressure,

the diastolic blood pressure,

the pulse rate,

allergies and intolerances, and

the medication history of the person.

10. The method of claim 1, wherein the second set of parameter values further comprises the ethnicity of the person.

11. The method of claim 1, wherein at least one parameter value of the plurality of parameter values has assigned at least one timestamp value, the at least one timestamp value being indicative of the time and date of having received, specified or measured the data value.

12. A non-transitory computer readable storage medium having stored therein instructions, which when executed by a computing device cause the computing device to perform a method of generating an access key, the method comprising the steps of:

accessing an input value;

calculating an asymmetric cryptographic key pair by applying a cryptographic one-way function to the input value, wherein the cryptographic key pair comprises a public key and a private key, wherein the cryptographic one-way function is an injective function; and

outputting the public key for providing the access key, and

storing a data structure into a database whereby the provided access key is used as database key, wherein the data structure comprises a plurality of biomedical parameter values for use in a medical decision support system, wherein the plurality of biomedical parameter values comprises a first set of parameter values, each parameter value of the first set of biomedical parameter values being a laboratory value having been derived by analyzing a body fluid or tissue of a person, the first set of parameter values comprising;

glucose concentration,

LDL concentration,

HDL concentration,

triglyceride concentration,

creatinine concentration,

cholesterol concentration,

Hba1c concentration, and

C Reactive Peptide (CRP) CRP concentration,

wherein the plurality of biomedical parameter values comprises a second set of parameter values of the person, the second set of data values comprising;

age,

gender,

body mass index (BMI),

waist/hip ratio,

blood pressure, and

smoking history

wherein the parameter set is the minimum parameter set required to allow monitoring of a wide range of the most common diseases.

13. The non-transitory computer-readable storage medium of claim 12, wherein the method further comprises the step of generating a digital signature for the data structure using the private key, and wherein the digital signature is stored into the database in association with the data structure.

14. A computer system comprising a server-computer system, the server-computer system comprising:

an interface configured to receive a data structure via a network connection from a client computer system, wherein the data structure comprises a plurality of biomedical parameter values for use in a medical decision support system, wherein the plurality of biomedical parameter values comprises a first set of parameter values, each parameter value of the first set of biomedical parameter values being a laboratory value having been derived by analyzing a body fluid or tissue of a person, the first set of parameter values comprising;

glucose concentration,

LDL concentration,

HDL concentration,

triglyceride concentration,

creatinine concentration,

cholesterol concentration,

Hba1c concentration, and

C Reactive Peptide (CRP) concentration,

wherein the plurality of biomedical parameter values comprises a second set of parameter values of the person, the second set of data values comprising;

age,

gender,

body mass index (BMI),

waist/hip ratio,

blood pressure, and

smoking history

wherein the parameter set is the minimum parameter set required to allow monitoring of a wide range of the most common diseases

a processor,

a first non-transitory computer-readable storage medium comprising instructions which, when executed by the processor, provide for a decision support system, the decision support system in operation receiving the data structure from the interface and calculating a medical decision based on the received data structure,

wherein the decision support system in operation calculates a medical decision based on the biomedical parameters contained in the received data structure.

15. The computer system according to claim 14, wherein the decision support system is a modular decision support system comprising one or more modules, each module being operable to calculate a different medical decision.

16. The computer system according to claim 14, wherein the client-computer system comprises a second computer-readable storage medium, the second computer readable storage medium comprising instructions which, when executed by the processor, causes said processor to perform a method of generating an access key, the method comprising the steps of:

accessing an input value;

calculating an asymmetric cryptographic key pair by applying a cryptographic one-way function to the input value, wherein the cryptographic key pair comprises a public key and a private key, wherein the cryptographic one-way function is an injective function; and

outputting the public key for providing the access key,

depositing the data structure together with the medical decision into a database using the provided access key via the interface, the database being operatively coupled to the decision support system.