Method for automatic, unsupervised classification of high-frequency oscillations in physiological recordings
US9326698B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 17, 2012 |
| Grant date | May 3, 2016 |
| Priority date | — |
| Expiry date | Mar 5, 2035 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG16H50/20
- WIPO fieldMedical technology
- WIPO sectorInstruments
Abstract
Oscillatory signals may be used to determine a region of a patient's body that is associated with a medical condition. As described herein, oscillatory signals may be detected using a high sensitivity, low specificity detector. The oscillatory signals may be representative of discrete events in a patient's body. The detected signals may be tested in the context of surrounding background activity to identify anomalous discrete physiologic events that are sufficiently different from the surrounding background activity. The anomalous discrete physiologic events having correlative morphological, time, or location characteristics may be automatically clustered and clusters of anomalous physiologic events may be determined that are indicative of at least one region of the patient's body that is associated with a medical condition.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.