Situational awareness for unsupervised administration of cognitive assessments in remote or clinical settings

JP2025532927APending Publication Date: 2025-10-03LINUS HEALTH INC
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
JP2025518394
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2022-09-28
Filing Date
2023-09-28
Publication Date
2025-10-03

AI Technical Summary

Technical Problem

Remote cognitive assessments in unsupervised settings face challenges due to environmental interference, which can distort results and lead to misdiagnosis, as participants may be distracted or their behavior is affected by their surroundings, and existing solutions fail to adequately address multiple simultaneous attention deficits and multi-modal interference.

Method used

A system utilizing multiple sensors to detect and classify environmental interference through a neural network framework that processes signals from various modalities, including accelerometers, gyroscopes, microphones, and video cameras, to infer environmental interference and suggest corrective actions.

Benefits of technology

Improves the accuracy of remote cognitive assessments by detecting and mitigating environmental interference, ensuring more reliable diagnostic outcomes by accounting for participant behavior and environmental conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025532927000001_ABST
    Figure 2025532927000001_ABST
Patent Text Reader

Abstract

According to various embodiments, solutions including methods, systems, and computer program products are provided for assessing environmental conditions surrounding an individual being assessed. In various embodiments, a method for assessing an individual is provided. A plurality of signals are received, each signal from one of a plurality of sensors. Each signal may be associated with a modality of assessment. Each of the plurality of signals may be processed in an individualized signal processing module. A plurality of features may be extracted, each from one of the processed plurality of signals. The plurality of features may be aggregated into machine learning inputs in the feature processing module. The machine learning inputs may be provided to a machine learning algorithm. An inference may be made that environmental interference is occurring based on the output of the machine learning algorithm.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • fall risk indicator measurement device

    JP7886666B1