Retrained ML Model Determines Electrode Position Signals for Catheter
Summary
Anumana, Inc. filed USPTO patent application US20260108169A1 on June 30, 2025, published April 23, 2026, covering a system and method for determining electrode position signals in catheters using a retrained machine-learning model. The system uses patient-agnostic data for initial training and patient-specific data for retraining, then processes potential signals and magnetic sensor data to generate position signals for catheter electrodes. CPC classifications span cardiac mapping (A61B 5/068), position tracking (A61B 5/062), and catheter-specific markers (A61M 25/0127).
About this source
USPTO classification A61M covers devices that introduce or withdraw fluids from the body: infusion pumps, catheters, syringes, inhalers, wound drainage, dialysis equipment, and fluid-handling microfluidics. Every newly published application in A61M lands in this feed, around 205 a month. Applications publish 18 months after filing. Watch this if you compete in infusion therapy or drug delivery, file freedom-to-operate analyses for medical device startups, scout acquisition targets in cardiovascular or respiratory devices, or track hospital R&D arms that are quietly patenting clinical innovations.
What changed
Anumana, Inc. filed a patent application (US20260108169A1) covering a system and method for determining electrode position signals in cardiac catheters using a retrained machine-learning model. The system includes a catheter with multiple electrodes for collecting potential signals and a magnetic sensor for collecting magnetic data. The machine-learning model is first trained on patient-agnostic data, then retrained on patient-specific data, enabling generation of position signals for individual electrodes. The application does not itself impose compliance obligations on third parties.
For competitors in cardiac mapping, catheter navigation, or AI-assisted medical devices, this application signals Anumana's intellectual property strategy in ML-based position tracking. Companies developing similar electrode position-determination systems should conduct freedom-to-operate analyses and consider whether their own innovations warrant patent protection.
Archived snapshot
Apr 24, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
METHODS AND SYSTEMS FOR DETERMINING POSITION SIGNALS OF ELECTRODES USING A RETRAINED MACHINE-LEARNING MODEL
Application US20260108169A1 Kind: A1 Apr 23, 2026
Assignee
Anumana, Inc.
Inventors
Deepak Anand, Yogisha Heggadahalli Jayendra, Karthik K. Bharadwaj, Sughosh Indurkar, Rakesh Barve, Animesh Agarwal
Abstract
A system for determining position signals of electrodes using a retrained machine-learning model includes at least a catheter including a plurality of electrodes configured to collect a plurality of potential signals and a magnetic sensor configured to collect magnetic data, and at least a computing device including a memory. The processor receives a first training set, wherein the first training set includes patient-agnostic data; receives a second training set, wherein the second training set includes patient-specific data, trains a mapping machine-learning model using the first training set, retrains the mapping machine-learning model using the second training set, receives at least a first signal, wherein the first signal includes a potential signal of the plurality of potential signal and the magnetic data, and generates, using the retrained machine-learning model, as a function of the at least a first signal, a first position signal for an electrode of the plurality of electrodes.
CPC Classifications
A61B 5/068 A61B 5/062 A61B 5/6852 A61B 5/7267 A61B 5/367 A61B 5/7264 A61M 25/0127 A61M 2025/0166
Filing Date
2025-06-30
Application No.
19255273
Parties
Related changes
Get daily alerts for USPTO Patent Applications - Medical Devices (A61M)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - Medical Devices (A61M) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.