Cognitive status assessment of older adults – test administration by conversational artificial intelligence (AI) chatbot: proof-of-concept investigation
Bibliographic record
Abstract
Background The Telephone Interview for Cognitive Status-Modified (TICS-M) is a widely utilized tool for remotely assessing cognitive function, particularly among community-dwelling older adults who are unable to attend in-person evaluations. In healthcare, AI has the potential to enhance service delivery by increasing efficiency, expanding accessibility, and reducing the cost per service. Using a conversational AI chatbot, we automated administration of TICS-M (traditionally administered by psychologists), referring to this chatbot-administered version as TICS-M-AI. The aim was to investigate proof-of-concept for chatbot automation of cognitive assessment. We report three studies evaluating psychometric properties of TICS-M-AI and an additional study on safety.Method Study1: Concurrent validity of the TICS-M-AI was assessed by administration of the TICS-M (by Psychologist) and the TICS-M-AI to the same participants (n = 100), one week apart. Study 2: Test-retest reliability was assessed by administering the TICS-M-AI twice to each participant, one week apart (n = 82) and comparing results. Study 3: Construct validity was assessed by attempted replication, using TICS-M-AI data (n = 264), of a previously published study by Lindgren et al. (2019) of item response patterns observed using data obtained by traditional clinician administered TICS-M. Study 4: Safety was assessed by comparing rates of reported assessment-related distress between TICS-M (n = 100) and TICS-M-AI (n = 264) administrationsResults TICS-M-AI concurrent validity (r = 0.81, 88% classification agreement, κ = 0.73) with the TICS-M and good test-retest reliability (r = 0.76, ICC = 0.72, 83% agreement, κ = 0.65). Using the TICS-M-AI we replicated Lindgren et al. (2019) result which used the TICS-M.Conclusions TICS-M-AI administered by an AI chatbot performed well compared to traditional TICS-M administration by a psychologist. TICS-M-AI is reliable, valid, and equally safe with added advantages of lower cost, scalability, and broader accessibility. Future research should address generalizability across diverse populations and refine AI adaptability.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.014 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".