IP Library Granted Patent US 12,640,263
Granted Patent B2
US 12,640,263 · App. 18/749,679 · Granted May 26, 2026

Generative artificial intelligence driven self-healing agent for medical devices

Inventors: Mathews Matson Chavarukattil (Bangalore, IN); Rama Krishna Reddy Narayana Reddy Gari (Bangalore, IN); Sridhar Madhavan (Barrington, IL); Sai Kumar Muppalla (Bangalore, IN); Manjunath Janardhan (Bangalore, IN)
Assignee: GE PRECISION HEALTHCARE LLC
G16H40/40
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,640,263
App. No.
18/749,679
Granted
May 26, 2026
Kind
B2
Abstract

A medical device includes a memory encoding processor-executable routines. The medical device also includes a processing system including one or more processors and is configured to access the memory and to execute the processor-executable routines, wherein the routines, when executed by the processing system, cause the processing system to perform actions. The actions include utilizing an autonomous self-healing agent framework, via generative artificial intelligence based reasoning, to detect an issue with the medical device, to locate an appropriate fix for the issue, and to implement the appropriate fix to resolve the issue.

Claims (31)

1 . A medical device, comprising:

a memory encoding processor-executable routines; and

a processing system comprising one or more processors and configured to access the memory and to execute the processor-executable routines, wherein the processor-executable routines, when executed by the processing system, cause the processing system to:

initiate utilization of an autonomous self-healing agent framework for healing the medical device in response to detecting an indicator of an issue from the medical device via a system bot of the medical device, wherein the autonomous self-healing agent framework comprises a tool augmented large language model;

utilize the autonomous self-healing agent framework, via generative artificial intelligence based reasoning, to:

detect the issue with the medical device;

locate an appropriate fix for the issue; and

implement the appropriate fix to resolve the issue; and

wherein the autonomous self-healing agent framework is configured to access a knowledge graph and to utilize generative artificial intelligence in reasoning through the knowledge graph to detect the issue with the medical device and to locate the appropriate fix for the issue, wherein the autonomous self-healing agent framework is configured to access tools, functions, or a combination of tools and functions provided by an equipment manufacturer of the medical device using a service application program interface, and wherein the tools and functions comprise a detection agent, a recovery agent, a monitor, or a combination thereof.

2 . The medical device of claim 1 , wherein the processor-executable routines, when executed by the processing system, further cause the processing system to initiate utilization of the autonomous self-healing agent framework for healing in response to receiving a user input, via a user bot, to initiate the utilization.

3 . The medical device of claim 1 , wherein nodes of the knowledge graph comprise service manuals for the medical device, tool descriptions, fault tree analysis, and failure modes and effects analysis.

4 . The medical device of claim 1 , wherein the autonomous self-healing agent framework is configured to access the memory when utilizing generative artificial intelligence in reasoning through the knowledge graph to detect the issue with the medical device and to locate the appropriate fix for the issue.

5 . The medical device of claim 4 , wherein the autonomous self-healing agent framework is configured to store in the memory a record of detecting the issue with the medical device and fixing the issue.

6 . The medical device of claim 1 , wherein the autonomous self-healing agent framework is configured to automatically generate a service request when the issue cannot be resolved by the autonomous self-healing agent framework.

7 . A computer-implemented method for a medical device to self-heal, comprising:

initiating, via a processing system comprising one or more processors and located on the medical device, utilization of an autonomous self-healing agent framework for healing the medical device in response to detecting an indicator of an issue from the medical device via a system bot of the medical device;

utilizing, via the processing system, the autonomous self-healing agent framework, via generative artificial intelligence based reasoning, to:

detect the issue with the medical device;

locate an appropriate fix for the issue; and

implement the appropriate fix to resolve the issue; and

wherein the autonomous self-healing agent framework accesses a knowledge graph and utilizes generative artificial intelligence in reasoning through the knowledge graph to detect the issue with the medical device and to locate the appropriate fix for the issue, wherein the autonomous self-healing agent framework accesses tools, functions, or a combination of tools and functions provided by an equipment manufacturer of the medical device using a service application program interface, and wherein the tools and functions comprise a detection agent, a recovery agent, a monitor, or a combination thereof.

8 . The computer-implemented method of claim 7 , further comprising initiating, via the processing system, utilization of the autonomous self-healing agent framework for healing in response to receiving a user input, via a user bot, to initiate the utilization.

9 . The computer-implemented method of claim 7 , further comprising utilizing, via the processing system, the autonomous self-healing agent framework to access a memory when utilizing generative artificial intelligence in reasoning through the knowledge graph to detect the issue with the medical device and to locate the appropriate fix for the issue.

10 . The computer-implemented method of claim 7 , further comprising utilizing, via the processing system, the autonomous self-healing agent framework to automatically generate a service request when the issue cannot be resolved by the autonomous self-healing agent framework.

11 . A non-transitory computer-readable medium, the computer-readable medium comprising processor-executable code that when executed by a processing system comprising one or more processors and located on a medical device, causes the processing system to:

initiate utilization of an autonomous self-healing agent framework for healing the medical device in response to detecting an indicator of an issue from the medical device via a system bot of the medical device;

utilize the autonomous self-healing agent framework stored on a medical device, via generative artificial intelligence based reasoning, to:

detect the issue with the medical device;

locate an appropriate fix for the issue; and

implement the appropriate fix to resolve the issue; and

wherein the autonomous self-healing agent framework is configured to access a knowledge graph and to utilize generative artificial intelligence in reasoning through the knowledge graph to detect the issue with the medical device and to locate the appropriate fix for the issue, wherein the autonomous self-healing agent framework is configured to access tools, functions, or a combination of tools and functions provided by an equipment manufacturer of the medical device using a service application program interface, and wherein the tools and functions comprise a detection agent, a recovery agent, a monitor, or a combination thereof.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 24, 2024
From: CHAVARUKATTIL, MATHEWS MATSON; NARAYANA REDDY GARI, RAMA KRISHNA REDDY; MADHAVAN, SRIDHAR; MUPPALLA, SAI KUMAR; JANARDHAN, MANJUNATH
To: GE PRECISION HEALTHCARE LLC
Reel/Frame 067813/0072 →
Continuity (1)
Related Publication 20250391550A1 · Dec 25, 2025
References Cited (16)
US 7055062B2 · Shah et al. · 2006 [cited by applicant]
US 8015443B2 · Adachi · 2011 [cited by applicant]
US 9375201B2 · Mercer et al. · 2016 [cited by applicant]
US 10102082B2 · Caberera et al. · 2018 [cited by applicant]
US 11221617B2 · Yu · 2022 [cited by examiner]
US 11457888B2 · Uebler · 2022 [cited by applicant]
US 11707250B2 · Campagna et al. · 2023 [cited by applicant]
US 20200209109A1 · Liang et al. · 2020 [cited by applicant]
US 20210064932A1 · Wang et al. · 2021 [cited by applicant]
US 20220103421A1 · Singh · 2022 [cited by examiner]
US 20240346256A1 · Qin · 2024 [cited by examiner]
CN 111078845A · 2020 [cited by examiner]
JP 2008149151 · 2008 [cited by applicant]
Salomone, Ivan. “Leveraging the enterprise knowledge graph for predictive maintenance.” Master's Dissertation. 2021. https://www.um.edu.mt/library/oar/handle/123456789/91915 (Year: 2021). [cited by examiner]
U.S. Appl. No. 18/628,382, filed Apr. 5, 2024, Rama Krishna Reddy Narayana Reddy Gari. [cited by applicant]
U.S. Appl. No. 18/422,591, filed Jan. 25, 2024, Sridhar Madhavan. [cited by applicant]