公开(公告)号：US20200034366A1

公开(公告)日：2020-01-30

申请号：US16457794

申请日：2019-06-28

申请人： drchrono Inc.

发明人： Daniel Kivatinos ,  Michael Nusimow ,  Martin Borgt ,  Soham Waychal

IPC分类号： G06F16/2455 ,  G06F16/28 ,  G06N3/04 ,  G06N3/08 ,  G06N20/10 ,  G06N20/20 ,  G06K9/62 ,  G16H10/60

摘要： A machine learning system may be used to suggest clinical questions to ask during or after a patient appointment. A first encoder may encode information and a second encoder may encode second information related to the current patient appointment. An aggregate encoding may be generated using the encoded first information and encoded second information. The current patient appointment may be clustered with similar appointments based on the aggregate encoding. Outlier analysis may be performed to determine if the appointment is an outlier, and, if so, which features contribute the most to outlier status. The system may generate one or more questions to ask about the features that contribute the most to outlier status.

公开(公告)号：US11417417B2

公开(公告)日：2022-08-16

申请号：US16457803

申请日：2019-06-28

申请人： drchrono Inc.

发明人： Daniel Kivatinos ,  Michael Nusimow ,  Martin Borgt ,  Soham Waychal

IPC分类号： G16H70/60 ,  G16H50/20 ,  G16H70/20 ,  A61B5/11 ,  G16H10/20 ,  G06N3/04 ,  G06N5/02 ,  G06K9/62 ,  G06F17/16

摘要： A machine learning system may be used to predict clinical questions to ask on a clinical form. A first encoder may encode first information and a second encoder may encoder second information from a medical record of a past appointment. The first and second encoded information and additional encoded information may be used to predict a clinical question to ask by using a reinforcement learning system. The reinforcement learning system may be trained by receiving ratings of questions from users.

公开(公告)号：US11687577B2

公开(公告)日：2023-06-27

申请号：US16457794

申请日：2019-06-28

申请人： drchrono Inc.

发明人： Daniel Kivatinos ,  Michael Nusimow ,  Martin Borgt ,  Soham Waychal

IPC分类号： G06F16/24 ,  G06F16/35 ,  G06F16/2455 ,  G06F16/28 ,  G06N3/084 ,  G16H10/60 ,  G06N20/20 ,  G06N20/10 ,  G06F18/23213 ,  G06F18/2413 ,  G06N3/045

CPC分类号： G06F16/35 ,  G06F16/24556 ,  G06F16/285 ,  G06F18/23213 ,  G06F18/24147 ,  G06N3/045 ,  G06N3/084 ,  G06N20/10 ,  G06N20/20 ,  G16H10/60

摘要： A machine learning system may be used to suggest clinical questions to ask during or after a patient appointment. A first encoder may encode information and a second encoder may encode second information related to the current patient appointment. An aggregate encoding may be generated using the encoded first information and encoded second information. The current patient appointment may be clustered with similar appointments based on the aggregate encoding. Outlier analysis may be performed to determine if the appointment is an outlier, and, if so, which features contribute the most to outlier status. The system may generate one or more questions to ask about the features that contribute the most to outlier status.

公开(公告)号：US20200035343A1

公开(公告)日：2020-01-30

申请号：US16457787

申请日：2019-06-28

申请人： drchrono Inc.

发明人： Daniel Kivatinos ,  Michael Nusimow ,  Martin Borgt ,  Soham Waychal

IPC分类号： G16H20/10 ,  G16H10/60

摘要： A computer system may parse a set of medical events of a patient and determine when the patient has been taking a first medication and a second medication. The computer system may determine the duration of time in which the patient has been taking the first medication. An expected duration of time for the course of treatment may be provided. When it is determined that the actual course of treatment differed from the expected duration of treatment, then the system may flag a potential drug interaction. When enough of these flags are determined, an indication of a potential drug interaction may be stored and a prompt or notification sent to other health practitioners about the potential drug interaction.

公开(公告)号：US11410761B2

公开(公告)日：2022-08-09

申请号：US16457787

申请日：2019-06-28

申请人： drchrono Inc.

发明人： Daniel Kivatinos ,  Michael Nusimow ,  Martin Borgt ,  Soham Waychal

IPC分类号： G16H20/10 ,  G16H10/60 ,  G16H15/00

摘要： A computer system may parse a set of medical events of a patient and determine when the patient has been taking a first medication and a second medication. The computer system may determine the duration of time in which the patient has been taking the first medication. An expected duration of time for the course of treatment may be provided. When it is determined that the actual course of treatment differed from the expected duration of treatment, then the system may flag a potential drug interaction. When enough of these flags are determined, an indication of a potential drug interaction may be stored and a prompt or notification sent to other health practitioners about the potential drug interaction.

公开(公告)号：US20200035342A1

公开(公告)日：2020-01-30

申请号：US16457778

申请日：2019-06-28

申请人： drchrono Inc.

发明人： Daniel Kivatinos ,  Michael Nusimow ,  Martin Borgt ,  Soham Waychal

IPC分类号： G16H15/00 ,  G06N3/04 ,  G06N3/08

摘要： A machine learning system may be trained to assist physicians with claims by automatically adjusting the claims to make them more likely to be accepted by a payer or by outputting a predicted probability that the claim will be accepted. The machine learning system may use one or more encoders that encode codes, clinical notes, and claims into separate vector spaces, where the vector spaces relate similar entities. The encoded codes, clinical notes, and claims may be decoded by a decoder to predict codes comprising an adjusted claim. Alternatively, the decoder may output a predicted probability that the claim will be accepted for payment. The encoders and the decoder may be machine learning models that are trained using ground-truth training examples.

公开(公告)号：US20200035335A1

公开(公告)日：2020-01-30

申请号：US16457803

申请日：2019-06-28

申请人： drchrono Inc.

发明人： Daniel Kivatinos ,  Michael Nusimow ,  Martin Borgt ,  Soham Waychal

IPC分类号： G16H10/20 ,  G06N3/04 ,  G06F17/16 ,  G06K9/62 ,  G06N5/02

摘要： A machine learning system may be used to predict clinical questions to ask on a clinical form. A first encoder may encode first information and a second encoder may encoder second information from a medical record of a past appointment. The first and second encoded information and additional encoded information may be used to predict a clinical question to ask by using a reinforcement learning system. The reinforcement learning system may be trained by receiving ratings of questions from users.

公开(公告)号：US20200034707A1

公开(公告)日：2020-01-30

申请号：US16457769

申请日：2019-06-28

申请人： drchrono Inc.

发明人： Daniel Kivatinos ,  Michael Nusimow ,  Martin Borgt ,  Soham Waychal

IPC分类号： G06N3/08 ,  G06N3/04 ,  G16H40/20

摘要： A machine learning system may be trained to predict codes for a physician code schedule. The machine learning system may use one or more encoders that encode codes, code schedules, and claims into separate vector spaces, where the vector spaces relate similar entities. The encoded codes, code schedules, and claims may be decoded by a decoder to predict a code to add to the code schedule. The encoders and the decoder may be machine learning models that are trained using ground-truth training examples.