Editorial: Methods in artificial intelligence for dementia 2024
Bibliographic record
Abstract
Editorial on the Research Topic Methods in artificial intelligence for dementiaDementia refers to a group of neurodegenerative diseases that cause a gradual decline in cognitive functions, affecting memory, thinking, decision-making, language, and motor skills.These symptoms worsen over time, impacting both patients and their caregivers (American Psychiatric Association, 2000).The main causes of dementia include Alzheimer's Disease (which accounts for about 50% of cases), cerebrovascular disease (25%), Lewy body disease (15%), and other conditions like Parkinson's and frontotemporal dementia (5%) (Burns and Iliffe, 2009).The risk of developing dementia increases with age, and as the population of older adults is projected to grow significantly by 2050, the societal impact of dementia care is expected to rise (World Health Organization, 2013).In 2015, there were about 47.5 million dementia cases worldwide, with new cases annually ranging from 10 to 15 per 1,000 people, most of which are due to Alzheimer's Disease.The average life expectancy after a dementia diagnosis is around 7 years (World Health Organization, 2015).Due to the growing global challenge, there is significant investment in preventing and detecting dementia early.Researchers are seeking costeffective and scalable methods to identify dementia in its early stages, from subtle signs like subjective memory loss to more severe forms like mild cognitive impairment and Alzheimer's dementia.This Research Topic aims to highlight the latest experimental techniques and methods of Artificial Intelligence used to investigate fundamental questions in dementia research, from risk factor and biomarker identification to genetics and dementia care.In total, five papers have been accepted on this topic and the findings are summarized below.Gregory et al. in the paper titled "Remote data collection speech analysis in people at risk for Alzheimer's disease dementia: usability and acceptability results" explored the feasibility of phone-based cognitive testing in people at risk for Alzheimer's disease.The study involved 68 participants who had baseline and 3-month follow-up measures.The first test was human-delivered, and the follow-up one was delivered using an automated phonebot.Results showed a high participant retention rate and minimal technical difficulties.The majority of the participants reported ease and comfort using the technology.It was demonstrated that phone-based cognitive assessments through these applications are not only feasible but also acceptable for midlife-to-older adults at risk for AD in the UK, which will have wider applications in remote clinical trials (Gregory et al.).
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".