利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

403 条记录 (耗时 0.039 秒)

    SYSTEMS AND METHODS FOR PROVIDING SYNTHETIC DATA
    2.
    发明公开
    SYSTEMS AND METHODS FOR PROVIDING SYNTHETIC DATA 审中-公开

    公开(公告)号：US20240330404A1

    公开(公告)日：2024-10-03

    申请号：US18129502

    申请日：2023-03-31

    申请人： Optum, Inc.

    发明人： Mark Lefebvre

    IPC分类号： G06F17/18 ,  G16H10/60

    CPC分类号： G06F17/18 ,  G16H10/60

    摘要： Systems, methods, and apparatuses implementing a synthetic data generation system are provided herein. In some embodiments, an example synthetic data generation system may be configured to generate high-quality synthetic data that can be used for data analysis operations and/or generate one or more predictive outputs.

    SYSTEMS AND METHODS FOR PROVIDING ELECTRONIC AND NON-ELECTRONIC RECORDS
    3.
    发明公开
    SYSTEMS AND METHODS FOR PROVIDING ELECTRONIC AND NON-ELECTRONIC RECORDS 审中-公开

    公开(公告)号：US20240282415A1

    公开(公告)日：2024-08-22

    申请号：US18170582

    申请日：2023-02-17

    申请人： Optum, Inc.

    发明人： Marlene McIntyre ,  James Bridges ,  Jean Gibson ,  Brent O'Dell

    IPC分类号： G16H10/60 ,  G06Q40/08 ,  G16H40/20

    CPC分类号： G16H10/60 ,  G06Q40/08 ,  G16H40/20

    摘要： In an embodiment, systems and methods for retrieving medical records are provided. A request for medical records is received from a payor by a records system. The request may include a list of the medical providers and criteria. The criteria may specify whether the payor only wants electronic records or both electronic and non-electronic records. The records system compares the list of providers with a list of providers who use electronic records and determines which providers of the request use electronic records and which providers of the request do not use electronic records. For each medical provider of the request that uses electronic records, the records system may request the records from each provider using an electronic records workflow. For each medical provider of the request that does not use electronic records, the records system may request the records from each provider using a non-electronic request workflow.

    OPTIMIZED LATENT MISSING FEATURE DETECTION FOR MACHINE LEARNING MODELS
    5.
    发明公开
    OPTIMIZED LATENT MISSING FEATURE DETECTION FOR MACHINE LEARNING MODELS 审中-公开

    公开(公告)号：US20240265304A1

    公开(公告)日：2024-08-08

    申请号：US18336538

    申请日：2023-06-16

    申请人： Optum, Inc.

    发明人： Dominik Roman Christian DAHLEM ,  Eran HALPERIN ,  James ZOU ,  Kevin WU

    IPC分类号： G06N20/00

    CPC分类号： G06N20/00

    摘要： Various embodiments of the present disclosure provide techniques for optimally augmenting a training dataset for a machine learning model based on multiple model-focused predictions. The techniques may include generating a datapoint priority matrix that corresponds to a plurality of entity-feature value pairs of a training dataset for a machine learning model, generating a plurality of impact predictions and feature sensitivity predictions for the plurality of entity-feature value pairs, generating a refined datapoint priority matrix by updating the datapoint priority matrix based on the plurality of impact predictions and sensitivity predictions, and providing a datapoint collection output for the training dataset based on the refined datapoint priority matrix and a data augmentation threshold.

    SYSTEMS AND METHODS FOR PRESCRIPTION PRICE COMPARISON ACROSS PROCESSORS
    6.
    发明公开
    SYSTEMS AND METHODS FOR PRESCRIPTION PRICE COMPARISON ACROSS PROCESSORS 审中-公开

    公开(公告)号：US20240257261A1

    公开(公告)日：2024-08-01

    申请号：US18162296

    申请日：2023-01-31

    申请人： OPTUM, INC.

    发明人： Holly Calahan ,  Jason Grantham

    IPC分类号： G06Q40/08

    CPC分类号： G06Q40/08

    摘要： A pharmacy claims switch is provided that allows pharmacy claims processors to determine the lowest cost for a prescription. A pharmacy submits a claim to the switch. The claim may be for a prescription for a patient and may identify a processor associated with the patient. The switch submits the claim to a third-party intermediary who submits the claim to the identified processor. The identified processor provides a response with a price for the patient. The third-party intermediary instructs the switch to submit follower claims to alternative processors. The switch receives responses from each alternative processor that includes a price the pharmacy should charge. Based on the prices in each response, the third-party intermediary selects the processor with the lowest price, and sends a response to the switch that identifies the selected processor. The pharmacy claims switch updates the pharmacy, which may present the best price to the patient.

    BUNDLED HEALTH CARE PAYMENT ADVISOR
    7.
    发明公开
    BUNDLED HEALTH CARE PAYMENT ADVISOR 审中-公开

    公开(公告)号：US20240249362A1

    公开(公告)日：2024-07-25

    申请号：US18101249

    申请日：2023-01-25

    申请人： OPTUM, INC.

    发明人： Jimmy Nathaniel Liu ,  Jianjun Cai

    IPC分类号： G06Q40/08

    CPC分类号： G06Q40/08

    摘要： A system for managing bundled payment agreements in a health care setting is configured to obtain, from a health care provider, an electronic health care claim; compare attributes of the electronic health care claim to a repository of bundled payment agreements to determine whether: i) the electronic health care claim is associated with a bundled payment agreement between the health care provider and a payor, and ii) one or more bundling criteria are met; reject the electronic health care claim if it is determined that the electronic health care claim is associated with a bundled payment agreement and that the bundling criteria are not met; and generate a transaction log of the evaluation of the claim.

    Machine-learning-based predictive behavioral monitoring
    8.
    发明授权
    Machine-learning-based predictive behavioral monitoring 有权

    公开(公告)号：US12046372B2

    公开(公告)日：2024-07-23

    申请号：US16999133

    申请日：2020-08-21

    申请人： Optum, Inc.

    发明人： Jon Kevin Muse ,  Gregory J. Boss ,  Paul J. Godden ,  Mark Gregory Megerian

    IPC分类号： G16H50/20 ,  G16H50/30

    CPC分类号： G16H50/30 ,  G16H50/20

    摘要： Systems and methods are configured to perform machine-learning-based predictive behavioral response. In various embodiments, one or more behavioral monitoring data objects are identified and processed using a behavioral pattern prediction machine learning model to generate a behavioral pattern prediction model. The behavioral pattern prediction model is processed using a risk generation machine learning model to generate a risk model, wherein: (i) the risk generation machine learning model is generated based at least in part by one or more risk factors, and (ii) the risk model comprises a per-risk factor score for each risk factor of the one or more risk factors. The risk model is processed using an adjustment generation machine learning model to generate an adjustment model and one or more prediction-based actions are performed based on the adjustment model.

    SYSTEMS AND METHODS FOR DETERMINING EMBEDDING VECTORS FOR PROCESSING MEDICAL CLAIMS
    9.
    发明公开
    SYSTEMS AND METHODS FOR DETERMINING EMBEDDING VECTORS FOR PROCESSING MEDICAL CLAIMS 审中-公开

    公开(公告)号：US20240233031A9

    公开(公告)日：2024-07-11

    申请号：US18048515

    申请日：2022-10-21

    申请人： Optum, Inc.

    发明人： Rama Krishna SINGH ,  Ravi PANDE ,  Priyank JAIN

    IPC分类号： G06Q40/08 ,  G06Q50/22

    CPC分类号： G06Q40/08 ,  G06Q50/22

    摘要： Systems and methods are disclosed for processing medical claims to determine vector embeddings for predictive analytics and fraud detection. The method includes receiving claim data for a medical claim, the claim data comprising a plurality of medical codes. A plurality of embedding vectors is determined based on the plurality of medical codes, each embedding vector determined based on a corresponding medical code. A multi-layered matrix is determined based on the plurality of embedding vectors determined for the plurality of medical codes, wherein the multi-layered matrix is representative of the medical claim. One or more actions such as predictive analytics and fraud detection are performed based on the multi-layered matrix.