# US 2022/0284999 A1 · Machine learning model for extracting diagnoses, treatments, and key dates > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2022/0284999 A1 - Document ID: US20220284999A1 - Status: Published application - Kind: A1 - Application number: 17/686,824 - Filed: 2022-03-04 - Published: 2022-09-08 - Earliest claimed: 2021-03-05 - Assignees: Flatiron Health, Inc. - Applicants: Flatiron Health, Inc. - Inventors: Alexander Rich; Barry Leybovich; Benjamin Irvine; Nisha Singh; Benjamin Birnbaum - Web page: https://patentgrep.com/patent/US20220284999A1 ## CPC - G06F 16/3344: {using natural language analysis} - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G06F 16/3346: {using probabilistic model} - G06F 16/3347: {using vector based model} - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/0499: Feedforward networks - G06N 3/09: Supervised learning - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/045: Combinations of networks - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A model-assisted system for determining a patient event date may include a processor. The processor may be programmed to access a database storing a medical record associated with a patient, the medical record comprising unstructured data; analyze the unstructured data to identify a plurality of snippets of information in the medical record associated with a patient event; determine a date associated with each of the plurality of snippets, identify a plurality of query periods associated with the patient event; and generate, for each of the query periods, a probability of whether the patient event occurred during the query period based on the plurality of snippets and the associated dates. ## Claims ### Claim 1 A model-assisted system for determining a patient event date, the system comprising: at least one processor programmed to: access a database storing a medical record associated with a patient, the medical record comprising unstructured data; analyze the unstructured data to identify a plurality of snippets of information in the medical record associated with a patient event; determine a date associated with each of the plurality of snippets; identify a plurality of query periods associated with the patient event; and generate, for each of the query periods, a probability of whether the patient event occurred during the query period based on the plurality of snippets and the associated dates. ### Claim 2 (depends on 1) The model-assisted system of claim 1, wherein the patient event comprises at least one of a diagnosis date, a treatment date, or an operation date. ### Claim 3 (depends on 1) The model-assisted system of claim 1, wherein determining the date associated with each of the plurality of snippets includes identifying a date based on metadata of a document a snippet is included in. ### Claim 4 (depends on 1) The model-assisted system of claim 1, wherein determining the date associated with each of the plurality of snippets includes identifying a date referenced in the snippet. ### Claim 5 (depends on 1) The model-assisted system of claim 1, wherein the at least one processor is further programmed to generate a plurality of snippet vectors based on the snippets. ### Claim 6 (depends on 1) The model-assisted system of claim 1, wherein identifying the plurality of query periods includes identifying a plurality of query dates and wherein the plurality of query periods include at least one period relative to each of the query dates. ### Claim 7 (depends on 6) The model-assisted system of claim 6, wherein the at least one period relative to each of the query dates includes a period encompassing the query date, a period before the query date, and a period after the query date. ### Claim 8 (depends on 6) The model-assisted system of claim 6, wherein the plurality of query dates comprise dates spaced apart by one week. ### Claim 9 (depends on 6) The model-assisted system of claim 6, wherein generating the probability includes evaluating the plurality of snippets over a plurality of time windows relative to each of the plurality of query dates. ### Claim 10 (depends on 9) The model-assisted system of claim 9, wherein evaluating the plurality of snippets over a plurality of time windows includes, for each time window of the plurality of time windows, processing snippets associated with a date falling within the time window using one or more aggregation functions. ### Claim 11 (depends on 10) The model-assisted system of claim 10, wherein the one or more aggregation functions include at least one of a sum function, a mean function, or a LogSumExp function. ### Claim 12 (depends on 10) The model-assisted system of claim 10, wherein generating the probability includes inputting a result of the plurality of functions into a feed forward network. ### Claim 13 A method for determining a patient event date, the method comprising: accessing a database storing a medical record associated with a patient, the medical record comprising unstructured data; analyzing the unstructured data to identify a plurality of snippets of information in the medical record associated with a patient event; determining a date associated with each of the plurality of snippets; identifying a plurality of query periods associated with the patient event; and generating, for each of the query periods, a probability of whether the patient event occurred during the query period based on the plurality of snippets and the associated dates. ### Claim 14 (depends on 13) The method of claim 13, wherein the patient event comprises at least one of a diagnosis date, a treatment date, or an operation date. ### Claim 15 (depends on 13) The method of claim 13, wherein identifying the plurality of query periods includes identifying a plurality of query dates and wherein the plurality of query periods include at least one period relative to each of the query dates. ### Claim 16 (depends on 15) The method of claim 15, wherein the at least one period relative to each of the query dates includes at least one period encompassing the query date, at least one period before the query date, and at least one period after the query date. ### Claim 17 (depends on 15) The method of claim 15, wherein generating the probability includes evaluating the plurality of snippets over a plurality of time windows relative to each of the plurality of query dates. ### Claim 18 (depends on 17) The method of claim 17, wherein evaluating the plurality of snippets over a plurality of time windows includes, for each of the plurality of time windows, processing the snippets associated with a date falling within the time window using a plurality of functions. ### Claim 19 (depends on 18) The method of claim 18, wherein the plurality of functions include at least one ofa sum function, a mean function, or a LogSumExp function. ### Claim 20 A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform a method for determining a patient event date, the method comprising: accessing a database storing a medical record associated with a patient, the medical record comprising unstructured data; analyzing the unstructured data to identify a plurality of snippets of information in the medical record associated with a patient event; determining a date associated with each of the plurality of snippets; identifying a plurality of query periods associated with the patient event; and generating, for each of the query periods, a probability of whether the patient event occurred during the query period based on the plurality of snippets and the associated dates.