# US 12,119,104 B2 · Automated clinical workflow > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,119,104 B2 - Document ID: US12119104B2 - Status: Granted - Kind: B2 - Application number: 16/991,229 - Filed: 2020-08-12 - Published: 2021-03-04 - Granted: 2024-10-15 - Earliest claimed: 2019-08-30 - Assignees: Siemens Healthineers AG - Applicants: Siemens Healthcare GmbH - Inventors: Michael Kelm; Srikrishna Prasad - Web page: https://patentgrep.com/patent/US12119104B2 ## CPC - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G16H 40/20: for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms - G06F 9/45558: {Hypervisor-specific management and integration aspects} - G06F 16/5854: {using shape and object relationship} - G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof - G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS - G16H 30/40: for processing medical images, e.g. editing - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - G06F 2009/45583: {Memory management, e.g. access or allocation} - G06F 2009/45595: {Network integration; Enabling network access in virtual machine instances} - H04L 67/10: in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Various examples of embodiments of the invention generally relate to automating a clinical workflow, the clinical workflow including an analysis of one or more medical datasets and generation of a medical report based on the analysis. For example, machine-learning algorithms may be used for the analysis. The medical report may be generated based on one or more report templates. ## Claims ### Claim 1 A computer-implemented method, comprising: obtaining one or more medical datasets of a patient; performing a configuration of a generation of a medical report including a selection of a report template of the medical report from a report repository; selecting, using a selection algorithm, one or more algorithms from an algorithm repository including multiple candidate algorithms based on the one or more medical datasets, a user input, and the configuration of the generation of the medical report, the selecting including: providing the one or more medical datasets as an input to one or more further algorithms, triggering execution of the one or more further algorithms, at least one of the one or more further algorithms being configured to perform a landmark detection of physiological features in the one or more medical datasets, and selecting the one or more algorithms based on meta data associated with the multiple candidate algorithms and the physiological features obtained from the landmark detection by comparing the meta data and the physiological features, the comparing including a semantic reasoning based on a knowledge graph associated with one or more of: physiological features; body regions; diseases: imaging modalities; or types of medical datasets, providing the one or more medical datasets as an input to the one or more algorithms; executing the one or more algorithms using a respective dedicated container of a cloud-computing service, the one or more algorithms configured to evaluate the one or more medical datasets and the respective dedicated container of each of the one or more algorithms being instantiated upon execution of each of the one or more algorithms; generating the medical report based on an output of at least one of the one or more algorithms; transmitting the output of the one or more algorithms to a human-machine interface as a first user output; receiving feedback associated with the output of the one or more algorithms from the human-machine interface; triggering, based on the feedback, a re-execution of at least one of the one or more algorithms using the respective dedicated container of the cloud-computing service, the feedback being an input into the at least one of the at one or more algorithms; generating an updated medical report based on an updated output of the at least one of the one or more algorithms; transmitting the updated medical report to the human-machine interface as a second user output; and training the selection algorithm using recurrent training based on the user input. ### Claim 2 (depends on 1) The method of claim 1, wherein the one or more algorithms are selected during the triggering based on an output of the one or more further algorithms. ### Claim 3 (depends on 2) The method of claim 2, wherein the one or more medical datasets include a medical imaging dataset. ### Claim 4 (depends on 3) The method of claim 3, wherein the meta data is indicative of a physiological-diagnostic content description of at least one of the input and the output of the multiple candidate algorithms. ### Claim 5 (depends on 1) The method of claim 1, further comprising: providing access to the algorithm repository to enable third parties to upload new candidate algorithms along with corresponding meta-data. ### Claim 6 (depends on 1) The method of claim 1, wherein the one or more further algorithms are trained based on the user input. ### Claim 7 (depends on 1) The method of claim 1, wherein the execution of the one or more further algorithms is implemented using a pre-instantiated container of the cloud-computing service. ### Claim 8 (depends on 1) The method of claim 1, further comprising: selecting between multiple user-interaction modes for the selection of the one or more algorithms, wherein the selecting of the one or more algorithms is further based on the user input received from the human-machine interface in accordance with a selected user-interaction mode of the multiple user-interaction modes. ### Claim 9 (depends on 8) The method of claim 8, wherein the multiple user-interaction modes vary with respect to a degree of automation of the selecting of the one or more algorithms. ### Claim 10 (depends on 8) The method of claim 8, wherein the selecting between the multiple user-interaction modes is based on an accuracy feedback of previous selections of the one or more algorithms. ### Claim 11 (depends on 10) The method of claim 10, wherein the accuracy feedback is determined based on a count of re-selections of the one or more algorithms based on user inputs received from the human-machine interface. ### Claim 12 (depends on 1) The method of claim 1, wherein the selecting of the one or more algorithms comprises a pre-selection of a first set of algorithms from the algorithm repository based on the one or more medical datasets, wherein the selecting of the one or more algorithms includes a post-selection of a second set of algorithms based on the configuration of the generation of the medical report, the second set of algorithms being a subset of the first set of algorithms. ### Claim 13 (depends on 1) The method of claim 1, further comprising: transmitting the medical report to the human-machine interface; receiving user feedback associated with the medical report from the human-machine interface; and triggering, based on the user feedback received, a re-generation of the medical report. ### Claim 14 (depends on 1) The method of claim 1, wherein the feedback is associated with an output of a first algorithm of the one or more algorithms, wherein re-execution of a second algorithm of the one or more algorithms is triggered based on the feedback associated with the output of the first algorithm, the input of the second algorithm being dependent on an output of the first algorithm. ### Claim 15 (depends on 1) The method of claim 1, further comprising: obtaining a patient dataset including patient-specific information of the patient, wherein the selecting of the one or more algorithms is further based on the patient dataset. ### Claim 16 (depends on 10) The method of claim 10, wherein the accuracy feedback specifies whether the output of the one or more algorithms is satisfactory for a clinical task and a re-selection indicates that the output of the one or more algorithms is not satisfactory.