System and method for predicting health condition of a patient
US11087879B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 22, 2016 |
| Grant date | Aug 10, 2021 |
| Priority date | — |
| Expiry date | Apr 11, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG16H40/63
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
According to embodiments illustrated herein, there is provided a system for predicting a health condition of a patient. The system further includes one or more processors configured to separately cluster data points from a set of medical records associated with a first class of patients and a second class of patients. A similarity value of each of the clustered data points with respect to a pre-selected subset of data points that represents landmark points may be determined, using a parameterized similarity measure. One or more classifiers are trained using the determined similarity value of each data point. The trained one or more classifiers are adapted to learn one or more parameters of the parameterized similarity measure during the training. An occurrence of the health condition of the patient may be predicted based on the trained one or more classifiers and one or more medical records of the patient.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.