Digital representations of past, current, and future health using vectors
US10978189B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 30, 2018 |
| Grant date | Apr 13, 2021 |
| Priority date | — |
| Expiry date | Nov 29, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2219/004
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A computing entity accesses instances of medical information corresponding to a population of patients and generates a plurality of medical sentences corresponding to the population by, for each patient of the population, generating one medical sentence corresponding to the patient and a timestamp associated with each instance such that the one medical sentence comprises one or more medical codes in a chronological order. The computing entity generates a vector dictionary comprising a plurality of multi-dimensional vectors based on a vector generation model trained using machine learning and the plurality of medical sentences with each multi-dimensional vector corresponding to a medical code. The computing entity generates a digital representation of a first patient of the population using an anagram model and the vector dictionary, determines a health state of the first patient based on the digital representation, and provides an output indicating the health state of the first patient.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.