Deep learning-based predictions of older adults' adherence to cognitive training to support training efficacy

Abstract

As the population ages, the number of older adults experiencing mild cognitive impairment (MCI), Alzheimer's disease, and other forms of dementia will increase dramatically over the next few decades. Unfortunately, cognitive changes associated with these conditions threaten independence and quality of life. To address this, researchers have developed promising cognitive training interventions to help prevent or reverse cognitive decline and cognitive impairment. However, the promise of these interventions will not be realized unless older adults regularly engage with them over the long term, and like many health behaviors, adherence to cognitive training interventions can often be poor. To maximize training benefits, it would be useful to be able to predict when adherence lapses for each individual, so that support systems can be personalized to bolster adherence and intervention engagement at optimal time points. The current research uses data from a technology-based cognitive intervention study to recognize patterns in participants' adherence levels and predict their future adherence to the training program. We leveraged the feature learning capabilities of deep neural networks to predict patterns of adherence for a given participant, based on their past behavior. A separate, personalized model was trained for each participant to capture individualistic features of adherence. We posed the adherence prediction as a binary classification problem and exploited multivariate time series analysis using an adaptive window size for model training. Further, data augmentation techniques were used to overcome the challenge of limited training data and enhance the size of the dataset. To the best of our knowledge, this is the first research effort to use advanced machine learning techniques to predict older adults' daily adherence to cognitive training programs. Experimental evaluations corroborated the promise and potential of deep learning models for adherence prediction, which furnished highest mean F-scores of 75.5, 75.5, and 74.6% for the Convolution Neural Network (CNN), Long Short-Term Memory (LSTM) network, and CNN-LSTM models respectively.

Predicting Older Adults’ Continued Computer Use After Initial Adoption

“…Future studies could also adopt qualitative and mixed methods design to gain insights directly from the users as to why they are engaging or disengaging with a technology. Finally, machine learning is another promising approach that showed the potential to help with understanding determinants and early signs of adherence failure and disengagement in technology-based activities (e.g., He et al, 2022 ; Singh et al, 2022 ). Future research could use machine learning models to supplement current understandings and existing theories.…”

Implication of analysisof machine learning models for predicting the risk of cardiovascular disease by considering lifestyle factors and featuresselection

“…Furthermore, the VOSviewer analysis highlighted a trend in 22.41% of the studies, emphasizing the use of intelligent services for predicting cardiovascular diagnoses. [23] The paper delves into the multifaceted realm of disease classification and risk assessment, particularly focusing on cardiovascular disease (CVD) through the lens of machine learning (ML) algorithms and IoT / Kuey, 30 (5), et al Dr. Padma Mishra technologies. It undertakes a thorough exploration of probability distributions, employing the Kullback-Leibler divergence and other information theory measures to unravel the intricacies of feature selection and classifier model performance.…”

A comprehensive review of machine learning algorithms and their application in geriatric medicine: present and future

“…RNN with LSTM algorithms using time-series data has provided important benefits in diagnosis and disease management for older patient population in numerous different healthcare domains. Applications include gait analysis [ 64 ], discriminating hand-movements [ 65 ], adherence to technology-based cognitive training [ 66 ], differentiation between stroke and healthy individuals using data on unhindered activities of daily living collected using wearables [ 67 ], sleep-stage classification from photoplethysmography [ 68 ], improving the prediction of Alzheimer’s disease using medical domain knowledge [ 69 ], predicting Alzheimer's disease progression [ 70 ], detecting vertebral fractures on CT scans [ 71 ], and determining life-expectancy [ 51 ], an important patient-reported outcome measure for the older population [ 51 ]. In another study, a CNN combined with a LSTM RNN was used to extract spatial and temporal information, respectively, and achieve a 100% accuracy in detection of fallers ( n = 327/327) and 99.73% ( n = 1114/117) accuracy in detection of non-fallers [ 72 ].…”