US 12,217,870 B2
Methods and systems for detecting intravascular device failure
Amit Bahl, Bloomfield Hills, MI (US); and Steven Johnson, Claremont, CA (US)
Assigned to A Little Cold Gel, LLC, Bloomfield Hills, MI (US)
Filed by A Little Cold Gel, LLC, Bloomfield Hills, MI (US)
Filed on Oct. 11, 2023, as Appl. No. 18/378,725.
Application 18/378,725 is a continuation of application No. 17/980,067, filed on Nov. 3, 2022, granted, now 11,791,049.
Claims priority of provisional application 63/274,998, filed on Nov. 3, 2021.
Prior Publication US 2024/0047067 A1, Feb. 8, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. A61M 5/168 (2006.01); A61B 8/08 (2006.01); G16H 50/20 (2018.01); A61B 90/00 (2016.01)
CPC G16H 50/20 (2018.01) [A61B 8/0841 (2013.01); A61B 8/5223 (2013.01); A61M 5/16836 (2013.01); A61B 8/0891 (2013.01); A61B 2090/378 (2016.02); A61M 2205/3375 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method for diagnosing conditions predictive of intravascular device failure, comprising:
acquiring data characterizing an area of a subject's skin surrounding an insertion site of an intravascular device;
applying a trained machine learning computer implemented method to process the acquired data, wherein the trained machine learning computer implemental method is configured to develop knowledge of training data, the training data comprising at least one of an image or measurement from a plurality of test subjects of an area underneath the test subjects' skin surrounding an insertion site of an intravascular device and an indication comprising intravascular device failure or intravascular device success paired with the image or measurement received from the test subjects; and
providing an indication to a user whether the acquired data indicates impending intravascular device failure.