US 12,327,630 B2
Machine learning models for automated request processing
William K. Cochran, Franklin, TN (US); Bijuna S. Pramila, Livingston, NJ (US); Han Van Vo, King of Prussia, PA (US); Hari C. Narayanan, Livingston, NJ (US); and Navin Rai, Trumbull, CT (US)
Assigned to Evicore Healthcare MSI, LLC, Bluffton, SC (US)
Filed by Evicore Healthcare MSI, LLC, Bluffton, SC (US)
Filed on Dec. 18, 2023, as Appl. No. 18/543,017.
Application 18/543,017 is a continuation of application No. 17/124,712, filed on Dec. 17, 2020, granted, now 11,848,097.
Prior Publication US 2024/0120080 A1, Apr. 11, 2024
Int. Cl. G06K 9/00 (2022.01); G06N 20/00 (2019.01); G06Q 10/10 (2023.01); G06Q 40/08 (2012.01); G06T 7/00 (2017.01); G16H 10/20 (2018.01); G16H 15/00 (2018.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01); G16H 40/20 (2018.01); G16H 50/20 (2018.01); G16H 50/70 (2018.01); A61B 5/055 (2006.01); A61B 6/03 (2006.01)
CPC G16H 40/20 (2018.01) [G06N 20/00 (2019.01); G06Q 10/10 (2013.01); G06Q 40/08 (2013.01); G06T 7/0012 (2013.01); G16H 10/20 (2018.01); G16H 15/00 (2018.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G16H 50/70 (2018.01); A61B 5/055 (2013.01); A61B 6/032 (2013.01); G06T 2207/20076 (2013.01); G06T 2207/20081 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computerized method of automatically processing a medical imaging record using a machine learning model, the computerized method comprising:
receiving a first medical imaging record from a first system, wherein the first medical imaging record is specific to a first entity;
applying a set of specified approval criteria to the first medical imaging record to determine a provisional outcome;
in response to the provisional outcome being positive, transmitting a signal indicating approval to the first system;
in response to the provisional outcome being negative:
providing data related to the first medical imaging record to a user interface; and
selectively identifying an exception to the provisional outcome in response to input received by the user interface;
in response to the exception being identified, transmitting the signal indicating approval to the first system;
in response to the exception not being identified:
generating, by a machine learning model prediction engine, a likelihood estimate that a denial of a patient imaging request will be overturned via an appeal, based on the first medical imaging record;
comparing the generated likelihood estimate to a target threshold; and
in response to the generated likelihood estimate being greater than the target threshold, transmitting the signal indicating approval to the first system;
receiving an appeal notification from the first entity at the first system; and
in response to receiving, at the first system, the appeal notification and the signal indicating approval, responding to the appeal notification according to the signal indicating approval by automatically overturning a denial of the patient imaging request.