Dalarna University's logo and link to the university's website

Accurate and fast extraction of step parameters from video recordings of gait allows for richer information to be obtained from clinical tests such as Timed Up and Go. Current deep-learning methods are promising, but lack in accuracy for many clinical use cases. Extracting step parameters will often depend on extracted landmarks (keypoints) on the feet. We hypothesize that such keypoints can be determined with an accuracy relevant for clinical practice from video recordings by combining an existing general-purpose pose estimation method (OpenPose) with custom convolutional neural networks (convnets) specifically trained to identify keypoints on the heel. The combined method finds keypoints on the posterior and lateral aspects of the heel of the foot in side-view and frontal-view images from which step length and step width can be determined for calibrated cameras. Six different candidate convnets were evaluated, combining three different standard architectures as networks for feature extraction (backbone), and with two different networks for predicting keypoints on the heel (head networks). Using transfer learning, the backbone networks were pre-trained on the ImageNet dataset, and the combined networks (backbone + head) were fine-tuned on data from 184 trials of older, unimpaired adults. The data was recorded at three different locations and consisted of 193 k side-view images and 110 k frontal-view images. We evaluated the six different models using the absolute distance on the floor between predicted keypoints and manually labelled keypoints. For the best-performing convnet, the median error was 0.55 cm and the 75% quartile was below 1.26 cm using data from the side-view camera. The predictions are overall accurate, but show some outliers. The results indicate potential for future clinical use by automating a key step in marker-less gait parameter extraction.

Background

Despite depression being prevalent in people with dementia, contributing to negative health outcomes and placing increased burden on individuals and family members, access to psychological interventions is limited. A potential solution is guided low-intensity behavioral activation, supported by informal caregivers and guided by healthcare professionals. However, it is necessary to adapt interventions to meet the needs and preferences of key stakeholders to enhance acceptability and relevance. Study objectives were to: (1) explore needs and preferences concerning the content and delivery model of the guided low-intensity behavioral activation intervention; and (2) adapt the intervention to ensure cultural appropriateness, relevancy, and acceptability to people with dementia and their caregivers in Sweden. 

Methods

Semi-structured interviews and focus group discussions were conducted with key stakeholders, including healthcare professionals (n = 18), community stakeholders (n = 7), people with dementia (n = 8), and informal caregivers (n = 19). A draft of the written low-intensity behavioral activation intervention and a description of the proposed intervention delivery model were provided to participants. Open-ended questions explored the perceived relevance of the intervention, alongside needs and preferences concerning content and delivery. A manifest content analysis approach was adopted. 

Results

Content analysis resulted in three categories: Content, Delivery procedures, and Illness trajectory. Results highlighted a need to consider the intervention Content via increased cultural adaptation to the Swedish context, and increasing the inclusiveness of intervention content. Delivery procedures were identified as needing to be flexible given the unpredictable nature of caring for people with dementia, with the provision of additional guidance to informal caregivers supporting the intervention. Illness trajectory was viewed as essential to consider, with the intervention regarded as suitable for those early in the dementia trajectory, alongside a need to reduce workbook text to minimize burden given dementia symptomology. 

Conclusions

The intervention and proposed delivery model were generally well received by all stakeholders. We were able to identify key adaptations to enhance cultural appropriateness, relevancy, and acceptability for a currently neglected population. Results will inform a feasibility study to explore the feasibility and acceptability of the intervention and study procedures to inform the design of a future superiority randomized controlled trial.

BACKGROUND: Dementia is a general term for several progressive neurodegenerative disorders including Alzheimer's disease. Timely and accurate detection is crucial for early intervention. Advancements in artificial intelligence present significant potential for using machine learning to aid in early detection.

OBJECTIVE: Summarize the state-of-the-art machine learning-based approaches for dementia prediction, focusing on non-invasive methods, as the burden on the patients is lower. Specifically, the analysis of gait and speech performance can offer insights into cognitive health through clinically cost-effective screening methods.

METHODS: A systematic literature review was conducted following the PRISMA protocol (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). The search was performed on three electronic databases (Scopus, Web of Science, and PubMed) to identify the relevant studies published between 2017 to 2022. A total of 40 papers were selected for review.

RESULTS: The most common machine learning methods employed were support vector machine followed by deep learning. Studies suggested the use of multimodal approaches as they can provide comprehensive and better prediction performance. Deep learning application in gait studies is still in the early stages as few studies have applied it. Moreover, including features of whole body movement contribute to better classification accuracy. Regarding speech studies, the combination of different parameters (acoustic, linguistic, cognitive testing) produced better results.

CONCLUSIONS: The review highlights the potential of machine learning, particularly non-invasive approaches, in the early prediction of dementia. The comparable prediction accuracies of manual and automatic speech analysis indicate an imminent fully automated approach for dementia detection.

The Timed Up-and-Go (TUG) test has been combined with different verbal/cognitive tasks (i.e., TUG dual task [TUGdt]) as a form of motor-cognitive testing. However, it is still unclear how different TUGdt conditions affect gait among older adults. Thirty community-dwelling older adults, with mean age of 73 years, participated in the study. Data were collected using marker-free video recordings. Gait parameters were extracted using a semiautomatic deep learning system. Comparisons of execution time and gait parameter outcomes were made under TUG and three types of TUGdt test conditions: TUGdt-naming animals, TUGdt-months backwards, and TUGdt-serial 7s. Statistical analyses were based on mean values of the gait parameters for each participant and TUG condition, including TUGdt gait cost, that is, the relative difference between TUGdt and TUG. All the investigated TUGdt conditions resulted in varying degrees of gait parameter changes. Under TUGdt conditions, participants took shorter and slower steps, with TUGdt-serial 7s causing the largest interference.

Introduction: Mental health difficulties such as anxiety and depression have negative impacts on psychological well-being and are common in people with dementia and mild cognitive impairment. However, access to psychological treatments is limited. This mixed-method systematic review will: (1) examine the effectiveness of psychological interventions to improve mental health and psychological well-being in people with dementia or mild cognitive impairment; (2) examine the effectiveness of these psychological interventions to improve mental health and psychological well-being in informal caregivers; (3) examine potential clinical and methodological moderators associated with effectiveness; (4) explore factors associated with the acceptability of psychological interventions from the perspective of key stakeholders; and (5) examine the completeness and quality of intervention reporting.

Methods and analysis: Electronic databases (ASSIA, CENTRAL, CINAHL, EMBASE, PsycINFO and MEDLINE) will be systematically searched and supplemented with expert contact, reference and citation checking, and grey literature searches. If possible, we will conduct a meta-analysis to examine the overall effectiveness of psychological interventions to improve mental health and psychological well-being in people with dementia or mild cognitive impairment and their informal caregivers; and examine potential clinical and methodological moderators associated with effectiveness. We will conduct a deductive framework synthesis, informed by the theoretical framework of acceptability, to explore factors associated with the acceptability of psychological interventions from the perspective of key stakeholders. In accordance with Joanna Briggs Institute guidance, we will adopt a convergent segregated approach to data synthesis and integration of quantitative and qualitative findings. We will examine the completeness and quality of intervention reporting according to the Template for Intervention Description and Replication checklist and guide.

Ethics and dissemination: No primary data will be collected, and therefore, ethical approval is not required. Results will be disseminated through a peer-reviewed publication, academic conferences, and plain language summaries.

Background Depression is commonly experienced by people with dementia, and associated with lower quality of life and functional decline. However, access to evidence-based psychological interventions for people with dementia and depression is limited. One potential solution is guided low-intensity behavioral activation. Following the new Medical Research Council Framework, considering factors such as potential barriers and facilitators to implementation is recommended during the development of new interventions. Aims of this study were to: (1) develop an understanding of existing healthcare and community support in the Swedish context for people with dementia and their informal caregivers; and (2) identify barriers and facilitators to intervention uptake informed by Normalization Process Theory. Methods Semi-structured interviews and focus groups were held with healthcare (n = 18) and community (n = 7) stakeholders working with people with dementia and/or informal caregivers. Interview questions were informed by Normalization Process Theory. Data was analysed utilizing a two-step deductive analysis approach using the Normalization Process Theory coding manual, with inductive categories applied to data related to the main mechanisms of the theory, but not captured by its sub-constructs. Results Twelve deductive and three inductive categories related to three Normalization Process Theory primary mechanisms (Coherence, Cognitive Participation, and Collective Action) were identified. Identified barriers to intervention uptake included: (1) additional burden for informal caregivers; (2) lack of appropriate workforce to provide guidance; (3) lack of time and financial resources; (4) people with dementia not recognising their diagnosis of dementia and/or a need for support; and (5) stigma. Identified facilitators to intervention uptake included: (1) intervention has potential to fill a large psychological treatment gap in Sweden; (2) objectives and potential benefits understood and agreed by most stakeholders; and (3) some healthcare professionals recognized their potential role in providing intervention guidance. Conclusions Several barriers and facilitators for future implementation, specific to the intervention, individuals and families, as well as professionals, were identified during intervention development. Barriers were mapped into evidence-based implementation strategies, which will be adopted to overcome identified barriers. A feasibility study further examining implementation potential, acceptability and feasibility, alongside clinical, methodological, and procedural uncertainties associated with the intervention will be conducted. 

BACKGROUND: While assessment tools can increase the detection of cognitive impairment, there is currently insufficient evidence regarding clinical outcomes based on screening for cognitive impairment in older adults.

METHODS: The study purpose was to investigate whether Timed Up and Go dual-task test (TUGdt) results, based on TUG combined with two different verbal tasks (name different animals, TUGdt-NA, and recite months in reverse order, TUGdt-MB), predicted dementia incidence over a period of five years among patients (N = 186, mean = 70.7 years; 45.7% female) diagnosed with Subjective Cognitive Impairment (SCI) and Mild Cognitive Impairment (MCI) following assessment at two memory clinics. Associations between TUG parameters and dementia incidence were examined in Cox regression models.

RESULTS: During follow-up time (median (range) 3.7 (0.1-6.1) years) 98 participants converted to dementia. Novel findings indicated that the TUGdt parameter words/time, after adjustment for age, gender, and education, can be used for the prediction of conversion to dementia in participants with SCI or MCI over a period of five years. Among the TUG-related parameters investigated, words/time showed the best predictive capacity, while time scores of TUG and TUGdt as well as TUGdt cost did not produce significant predictive results. Results further showed that the step parameter step length during TUGdt predicts conversion to dementia before adjustment for age, gender, and education. Optimal TUGdt cutoffs for predicting dementia at 2- and 4-year follow-up based on words/time were calculated. The sensitivity of the TUGdt cutoffs was high at 2-year follow-up: TUGdt-NA words/time, 0.79; TUGdt-MB words/time, 0.71; reducing respectively to 0.64 and 0.65 at 4-year follow-up.

CONCLUSIONS: TUGdt words/time parameters have potential as cost-efficient tools for conversion-to-dementia risk assessment, useful for research and clinical purposes. These parameters may be able to bridge the gap of insufficient evidence for such clinical outcomes.

TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT05893524: https://www.

CLINICALTRIALS: gov/study/NCT05893524?id=NCT05893524&rank=1 .