US 12,008,613 B2
Method of optimizing patient-related outcomes
Shahram Shawn Dastmalchi, San Ramon, CA (US); Vishnuvyas Sethumadhavan, Mountain View, CA (US); Mary Ellen Campana, San Mateo, CA (US); Robert Derward Rogers, Pleasanton, CA (US); and Imran N. Chaudhri, Potomac, MD (US)
Assigned to APIXIO, INC., San Mateo, CA (US)
Filed by Apixio, LLC, San Mateo, CA (US)
Filed on Jun. 29, 2023, as Appl. No. 18/344,704.
Application 18/344,704 is a continuation of application No. 17/522,649, filed on Nov. 9, 2021, granted, now 11,694,239.
Application 17/522,649 is a continuation of application No. 13/801,947, filed on Mar. 13, 2013, granted, now 11,195,213, issued on Dec. 7, 2021.
Application 13/801,947 is a continuation in part of application No. 13/223,228, filed on Aug. 31, 2011, granted, now 10,176,541, issued on Jan. 8, 2019.
Claims priority of provisional application 61/639,805, filed on Apr. 27, 2012.
Claims priority of provisional application 61/379,228, filed on Sep. 1, 2010.
Prior Publication US 2023/0377006 A1, Nov. 23, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/0283 (2023.01); G06Q 40/08 (2012.01); G16H 10/20 (2018.01); G16H 10/60 (2018.01); G16H 50/70 (2018.01)
CPC G06Q 30/0283 (2013.01) [G06Q 40/08 (2013.01); G16H 10/20 (2018.01); G16H 10/60 (2018.01); G16H 50/70 (2018.01)] 17 Claims
OG exemplary drawing
 
1. A Medical Information Navigation Engine (“MINE”) including at least one hardware processor configured to:
convert medical information formatted in various formats into a format to facilitate search speed for data queried from the medical information, the medical information associated with a plurality of patients;
generate, using the converted medical information, a plurality of patient state timelines, wherein a subset of the plurality of patient state timelines includes at least one state of interest;
generate a plurality of impact measures for each of the plurality of patient state timelines, wherein each impact measure is a cost of services provided at a given time to transition from one state to another;
generate a probability distribution of future impacts by summing all impact measures after the at least one state of interest occurs for each of the subset of the plurality of patient state timelines;
generate a suggestion model by analyzing the probability distribution of future impacts; and
apply the suggestion model to one patient state timeline to generate recommendations for the corresponding patient.