Using home monitoring technology to study the effects of traumatic brain injury in older multimorbid adults

Experiences with home monitoring technology in older adults with traumatic brain injury: a qualitative study

BACKGROUND

Home monitoring systems utilising artificial intelligence hold promise for digitally enhanced healthcare in older adults. Their real-world use will depend on acceptability to the end user i.e. older adults and caregivers. We explored the experiences of adults over the age of 60 and their social and care networks with a home monitoring system installed on hospital discharge after sustaining a moderate/severe Traumatic Brain Injury (TBI), a growing public health concern.

METHODS

A qualitative descriptive approach was taken to explore experiential data from older adults and their caregivers as part of a feasibility study. Semi-structured interviews were conducted with 6 patients and 6 caregivers (N = 12) at 6-month study exit. Data were analysed using Framework analysis. Potential factors affecting acceptability and barriers and facilitators to the use of home monitoring in clinical care and research were examined.

RESULTS

Home monitoring was acceptable to older adults with TBI and their caregivers. Facilitators to the use of home monitoring were perceived need for greater support after hospital discharge, the absence of sound and video recording, and the peace of mind provided to care providers. Potential barriers to adoption were reliability, lack of confidence in technology and uncertainty at how data would be acted upon to improve safety at home.

CONCLUSIONS

Remote monitoring approaches are likely to be acceptable, especially if patients and caregivers see direct benefit to their care. We identified key barriers and facilitators to the use of home monitoring in older adults who had sustained TBI, which can inform the development of home monitoring for research and clinical use. For sustained use in this demographic the technology should be developed in conjunction with older adults and their social and care networks.

Analyzing entropy features in time-series data for pattern recognition in neurological conditions

In the field of medical diagnosis and patient monitoring, effective pattern recognition in neurological time-series data is essential. Traditional methods predominantly based on statistical or probabilistic learning and inference often struggle with multivariate, multi-source, state-varying, and noisy data while also posing privacy risks due to excessive information collection and modeling. Furthermore, these methods often overlook critical statistical information, such as the distribution of data points and inherent uncertainties. To address these challenges, we introduce an information theory-based pipeline that leverages specialized features to identify patterns in neurological time-series data while minimizing privacy risks. We incorporate various entropy methods based on the characteristics of different scenarios and entropy. For stochastic state transition applications, we incorporate Shannon's entropy, entropy rates, entropy production, and the von Neumann entropy of Markov chains. When state modeling is impractical, we select and employ approximate entropy, increment entropy, dispersion entropy, phase entropy, and slope entropy. The pipeline's effectiveness and scalability are demonstrated through pattern analysis in a dementia care dataset and also an epileptic and a myocardial infarction dataset. The results indicate that our information theory-based pipeline can achieve average performance improvements across various models on the recall rate, F1 score, and accuracy by up to 13.08 percentage points, while enhancing inference efficiency by reducing the number of model parameters by an average of 3.10 times. Thus, our approach opens a promising avenue for improved, efficient, and critical statistical information-considered pattern recognition in medical time-series data.