# US 2018/0322953 A1 · Method for supporting medical personnel, support system, computer program and data carrier > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2018/0322953 A1 - Document ID: US20180322953A1 - Status: Published application - Kind: A1 - Application number: 15/963,395 - Filed: 2018-04-26 - Published: 2018-11-08 - Earliest claimed: 2017-05-02 - Assignees: Siemens Healthcare GmbH - Applicants: Siemens Healthcare GmbH - Inventors: Sebastian SCHMIDT - Web page: https://patentgrep.com/patent/US20180322953A1 ## CPC - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G16H 40/63: for local operation - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract A method is for supporting medical personnel. The method includes taking account of patient data of the patient in an electronic health record stored in a first database; determining at least one prevalence value, each relating to a diagnosis to be made for a group of people including the patient, to which the patient has been classified as belonging in dependence on at least one part of the patient data; generating, from the at least one prevalence value, at least one item of evaluation information based on at least one future examination procedure performable with respect to the diagnosis to be made, taking into account prediction information present in a second database describing at least one of sensitivity and specificity for the at least one future examination procedure with respect to the diagnosis to be made; and outputting the at least one item of evaluation information to the medical personnel. ## Claims ### Claim 1 A method for supporting medical personnel in examination of a patient by way of at least one examination procedure, the method comprising: taking account of patient data of the patient in an electronic health record stored in a first database, the patient data including at least one of at least one property of the patient and at least one examination result from at least one already concluded examination procedure, determining at least one prevalence value, each at least one prevalence value relating to a diagnosis to be made for a group of people including the patient, to which the patient has been classified as belonging in dependence on at least one part of the patient data; generating, from the at least one prevalence value determined, at least one item of evaluation information based on at least one future examination procedure performable with respect to the diagnosis to be made, taking into account prediction information present in a second database describing at least one of sensitivity and specificity for the at least one future examination procedure with respect to the diagnosis to be made; and outputting the at least one item of evaluation information generated to the medical personnel. ### Claim 2 (depends on 1) The method of claim 1, wherein the prediction information is in a form of at least one of; a sensitivity value and a specificity value; and a ROC curve. ### Claim 3 (depends on 1) The method of claim 1, wherein the at least one prevalence value is determined at least partially based upon a basic value for a group of people defined by patient properties, taking into account available examination results and the prediction information assigned to an already concluded examination procedure. ### Claim 4 (depends on 3) The method of claim 3, wherein at least one of the basic value and the at least one prevalence value for at least one of a respective group of people and the prediction information for an examination procedure is determined at least partially in dependence on patient data for further patients acquired in the first database belonging to the respective group of people or subjected to the examination procedure for which a ground truth with respect to the diagnosis to be made is known or derivable. ### Claim 5 (depends on 1) The method of claim 1, wherein an item of evaluation information for at least one future examination procedure is automatically generated when each at least one prevalence value exceeds a threshold value. ### Claim 6 (depends on 1) The method of claim 1, wherein the at least one item of evaluation information determined includes at least one of at least one positive predictive value and at least one negative predictive value. ### Claim 7 (depends on 1) The method of claim 1, wherein the at least one item of evaluation information determined includes at least one recommended examination procedure. ### Claim 8 (depends on 7) The method of claim 7, wherein the at least one item of evaluation information determined includes a series of examination procedures in an optimization method including at least one examination procedure, wherein the optimization is performed with respect to at least one of a reliability of a positive diagnosis, a reliability of a negative diagnosis, cost-effectiveness, and time required for the examination procedures, and wherein at least one boundary condition directed at minimal reliability is used. ### Claim 9 (depends on 1) The method of claim 1, wherein, for the determining of the at least one item of evaluation information, the at least one future examination procedure is at least one of calculated and simulated in a mathematical probability model. ### Claim 10 (depends on 1) The method of claim 1, wherein the at least one item of evaluation information includes a list of examination procedures for which the at least one prevalence value exceeds a limit value describing their reliability. ### Claim 11 (depends on 1) The method of claim 1, wherein, during the determination of the at least one item of evaluation information, at least one item of availability information with respect to the at least one future examination procedure is taken into account. ### Claim 12 (depends on 1) The method of claim 1, wherein, in a future examination procedure to be performed via medical examination technology, an examination protocol matched to the group of people is determined as the at least one item of evaluation information and is at least one of sent to an examination device, implemented, and at least displayed on the examination device. ### Claim 13 A support system, comprising: a first database storing electronic health records for a plurality of patients, each of the stored electronic health records including patient data with at least one of at least one property of one of the plurality of patients and at least one examination result from at least one already concluded examination procedure on the respective one of the plurality of patients; a second database storing prediction information describing at least one of sensitivity and specificity for each respective at least one examination procedure with respect to a diagnosis to be made; a classification unit to assign a patient to a group of people in dependence on at least one part of the patient data for the patient and a diagnosis to be made; a prevalence-determining unit to determine a prevalence value relative to the diagnosis to be made for the patient in dependence on at least one of the group of people and the patient data; an evaluation-information-determining unit to determine evaluation information based on at least one future examination procedure performable with respect to the diagnosis to be made, taking into account the prevalence value for the diagnosis to be made and the patient and the prediction information for the at least one examination procedure; and an output unit to output the evaluation information determined. ### Claim 14 (depends on 1) A non-transitory computer readable memory, storing a computer program configured to carry out the method of claim 1 when executed on a computing apparatus. ### Claim 15 (depends on 1) A non-transitory electronically readable data carrier, storing a computer program configured to carry out the method of claim 1 when executed on a computing apparatus. ### Claim 16 (depends on 2) The method of claim 2, wherein the at least one prevalence value is determined at least partially based upon a basic value for a group of people defined by patient properties, taking into account available examination results and the prediction information assigned to an already concluded examination procedure. ### Claim 17 (depends on 5) The method of claim 5, wherein the at least one item of evaluation information automatically generated is specific for the diagnosis to be made. ### Claim 18 (depends on 6) The method of claim 6, wherein the at least one negative predictive value is for a user selected examination procedure. ### Claim 19 (depends on 7) The method of claim 7, wherein the at least one recommended examination procedure includes a series of recommended examination procedures. ### Claim 20 (depends on 11) The method of claim 11, wherein the at least one future examination procedure is retrieved from an information system. ### Claim 21 (depends on 1) The method of claim 1, wherein at least one of a basic value and the at least one prevalence value for at least one of a respective group of people and the prediction information for an examination procedure is determined at least partially in dependence on patient data for further patients acquired in the first database belonging to the respective group of people or subjected to the examination procedure for which a ground truth with respect to the diagnosis to be made is known or derivable.