US 12,419,585 B2
Patient data management systems and conversational interaction methods
Yuxiang Zhong, Arcadia, CA (US); Pratik Agrawal, Porter Ranch, CA (US); Huzefa F. Neemuchwala, Simi Valley, CA (US); Sinu Bessy Abraham, Gallatin, TN (US); Boyi Jiang, Northridge, CA (US); Michael P. Stone, Long Beach, CA (US); Kevin E. Velado, Northridge, CA (US); Chantal M. McMahon, Los Angeles, CA (US); Siddharth Arunachalam, Northridge, CA (US); and Anupam Phukan, La Crescenta, CA (US)
Assigned to MEDTRONIC MINIMED, INC., Northridge, CA (US)
Filed by MEDTRONIC MINIMED, INC., Northridge, CA (US)
Filed on May 10, 2021, as Appl. No. 17/316,571.
Application 17/316,571 is a continuation of application No. 15/933,266, filed on Mar. 22, 2018, granted, now 11,000,236.
Claims priority of provisional application 62/534,051, filed on Jul. 18, 2017.
Claims priority of provisional application 62/476,493, filed on Mar. 24, 2017.
Claims priority of provisional application 62/476,517, filed on Mar. 24, 2017.
Claims priority of provisional application 62/476,451, filed on Mar. 24, 2017.
Claims priority of provisional application 62/476,456, filed on Mar. 24, 2017.
Claims priority of provisional application 62/476,506, filed on Mar. 24, 2017.
Claims priority of provisional application 62/476,444, filed on Mar. 24, 2017.
Claims priority of provisional application 62/476,468, filed on Mar. 24, 2017.
Prior Publication US 2021/0259641 A1, Aug. 26, 2021
Int. Cl. A61B 5/00 (2006.01); A61B 5/11 (2006.01); A61B 5/145 (2006.01); A61M 5/142 (2006.01); A61M 5/172 (2006.01); G06F 16/22 (2019.01); G06F 16/28 (2019.01); G06F 16/3329 (2025.01); G16H 10/60 (2018.01); G16H 20/10 (2018.01); G16H 20/17 (2018.01); G16H 20/30 (2018.01); G16H 20/60 (2018.01); G16H 20/70 (2018.01); G16H 40/63 (2018.01); G16H 50/20 (2018.01); G16H 50/30 (2018.01); G16H 50/50 (2018.01); G16H 50/70 (2018.01)
CPC A61B 5/7275 (2013.01) [A61B 5/0004 (2013.01); A61B 5/1112 (2013.01); A61B 5/14532 (2013.01); A61B 5/4833 (2013.01); A61B 5/4839 (2013.01); A61B 5/486 (2013.01); A61B 5/7264 (2013.01); A61B 5/7405 (2013.01); A61B 5/742 (2013.01); A61B 5/7455 (2013.01); A61B 5/746 (2013.01); A61B 5/749 (2013.01); A61M 5/142 (2013.01); A61M 5/14212 (2013.01); A61M 5/172 (2013.01); A61M 5/1723 (2013.01); G06F 16/2264 (2019.01); G06F 16/288 (2019.01); G06F 16/3329 (2019.01); G16H 10/60 (2018.01); G16H 20/10 (2018.01); G16H 20/17 (2018.01); G16H 20/30 (2018.01); G16H 20/60 (2018.01); G16H 20/70 (2018.01); G16H 40/63 (2018.01); G16H 50/20 (2018.01); G16H 50/30 (2018.01); G16H 50/50 (2018.01); G16H 50/70 (2018.01); A61B 5/1118 (2013.01); A61B 5/4848 (2013.01); A61B 5/4866 (2013.01); A61B 2560/0252 (2013.01); A61B 2560/0257 (2013.01); A61B 2562/029 (2013.01); A61M 2205/3303 (2013.01); A61M 2205/3584 (2013.01); A61M 2205/3592 (2013.01); A61M 2205/50 (2013.01); A61M 2205/502 (2013.01); A61M 2205/505 (2013.01); A61M 2205/80 (2013.01); A61M 2230/201 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of querying a database, the method comprising:
receiving, by a computing device coupled to the database, an input query pertaining to a prospective therapy modification for a patient, the input query comprising a conversational input from a client device, wherein:
the prospective therapy modification comprises a modification to a therapy regimen being taken by the patient, the therapy regimen including therapy delivered using a medical device,
the database comprises a plurality of logical layers that contain different subsets of data pertaining to a group of patients,
each logical layer has a corresponding graph structure with nodes representing containers or logical groupings of data in the logical layer, and
the graph structures indicate causal or logical relationships between nodes through edges connecting related nodes;
obtaining data pertaining to a physiological condition of the patient, wherein the data pertaining to the physiological condition of the patient comprises measurement data from a sensor;
determining, by the computing device, an intent of the input query by applying natural language processing to the conversational input;
identifying, by the computing device, a logical layer for searching based at least in part on the intent of the input query;
identifying, by the computing device, a subset of similar patients based on edges connecting a node associated with the patient to nodes associated with the subset of similar patients;
generating, by the computing device, a query statement for searching the identified logical layer to obtain historical data pertaining to the prospective therapy modification as applied to the subset of similar patients, based at least in part on the input query;
querying the identified logical layer of the database using the query statement to obtain the historical data, wherein querying the identified logical layer comprises traversing a graph structure of the identified logical layer in accordance with the query statement, through one or more paths containing nodes associated with the historical data;
determining, by the computing device based on the historical data, information on a current operational context of the medical device, and a current measurement from the sensor, a therapy recommendation that, when incorporated into the therapy regimen, is most likely to yield a better outcome with respect to the physiological condition of the patient, wherein the therapy recommendation comprises a recommendation regarding the therapy delivered using the medical device;
providing, by the computing device to the client device, the therapy recommendation in response to the conversational input; and
applying, by the computing device, the therapy recommendation through controlling the medical device to deliver a therapeutic dose of medication, wherein controlling the medical device comprises:
automatically generating a dosage command for the medical device, or
generating a dosage command based on user input in accordance with the therapy recommendation.