Non‐invasive AI model for human functional patterns recognition in IADLs

Abstract

Background Alzheimer's Disease (AD) diagnosis at early stages currently represents an important challenge for the scientific community, which is gradually accentuated due to the global perspective of population aging. Current clinical processes for the diagnosis of this disease are increasingly effective; these include invasive tests of nervous system biomarkers, which are complemented by non‐invasive tests of human cognitive and functional performance, such as the mini‐mental state examination and the analysis of Instrumental Activities of Daily Living (IADLs). Method The present work is centered around the development of technological tools for creating an automated model to support the diagnosis of early AD disease. We present a novel non‐invasive methodology for the development of an Artificial Intelligence‐based model, which analyzes human biomechanical markers of IADLs activities to recognize human functional patterns. For the development of this model, we have built a dataset of egocentric videos containing IADLs activities, organized in four classes, based on the prehensile patterns of the hands: strength and precision, and on the kinematics of the instruments: displacement and manipulation. We have characterized the dataset using mathematical methods to get information to directly emulate the relationship with Lawton and Brody's geriatric test, which is used in clinical protocols to estimate human functional capacity. This characterization relationship between biomechanical markers and human functional patterns represents a benefit for quantitative and objective assessment in support of geriatric evaluation and patient follow‐up. Result Our proposed model results in an accuracy of 73.74% in the recognition of human functional patterns related to the kinematics of the instruments, 59.84% in the analysis of the prehensile pattern of the hands, and 48.5% when the classes were recognized independently. Conclusion This allows us to establish in a quantifiable way performance region benchmarks of human functional capacity for IADLs activities, by obtaining a support model in the diagnostic evaluation of AD disease at early stages. Our proposed model allows us to establish the guideline to improve the automatic recognition of human functional patterns, of which we obtained an acceptable percentage testing instruments kinematics', followed by the hands' prehensile patterns.

Emergency department‐to‐community care transition barriers: A qualitative study of older adults

“…Lessons learned for those with cognitive impairment could apply to the broader older adult population studied within this work. Translating the prior and current work into a potential future line of investigation, the increased use of technology [42][43][44] (e.g. artificial intelligence, two-way text messaging) among older adults may pragmatically address identified barriers in this work by facilitating home review of discharge instructions, enabling access to outpatient follow-up clinical care, providing personalized physical activity guidance to overcome new limitations, and identifying assistive resources in the community for both family caregivers and older adults after an acute illness.…”

Human functional pattern recognition with focus on hand detection in egocentric vision through an artificial intelligence approach

“…These were later fed into the human functional pattern recognition process. This work was inspired by a previous work done by our group 9 , where human biomechanical markers were analyzed throughout the performance of IADL activities to recognize the human functional pattern. The methodology used in this work is as shown below:…”

Assessment of cognitive impairment using artificial intelligence from user-web-mobile interaction

“…The research and development of innovative technological systems for the management of the growing number of patients with cognitive diseases has increased in recent years 11 , integrating into these systems some of the cognitive test, data collection, and automatic data processing based on geriatric metrics using artificial intelligence (AI) methods 12,13,14 . Some of these systems focus on supporting the diagnosis and detection of the disease at an early stage, while others focus on monitoring the disease.…”