Can we trust computers to assess the cognition of stroke patients? A systematic review
Bibliographic record
Abstract
Purpose: To summarize the classification of computerized cognitive assessment (CCA) tools for assessing stroke patients, to clarify their benefits and limitations, and to reveal strategies for future studies on CCA tools. Methods: A literature review was performed using PubMed, Embase, Scopus, JAMA Network, Cochrane Library and PsycINFO databases from January 1st, 2010, to August 1st, 2022. Two authors independently screened the literature following the same criteria, evaluated the study quality, and collected data from the articles. Results: A total of 8,697 papers were acquired from the six databases. A total of 74 potentially eligible articles were selected for review. Of these, 29 articles were not relevant to this research, 3 were reviews, 2 were not written in English, and 1 was on an ongoing trial. By screening the references of the reviews, 3 additional articles were included in this study. Thus, a total of 42 articles met the criteria for the review. In terms of the CCA tools analyzed in these studies, they included five types: virtual reality (VR)-based, robot-based, telephone-based, smartphone-based, and computer-based cognitive assessments. Patients' stages of the disease ranged from the subacute phase and rehabilitation phase to the community phase. A total of 27 studies supported the effectiveness of CCA tools, while 22 out of 42 articles mentioned their benefits and 32 revealed areas for future improvement of CCA tools. Conclusions: Although the use of CCA tools for assessing the cognition of post-stroke patients is becoming popular, there are still some limitations and challenges of using such tools in stroke survivors. More evidence is thus needed to verify the value and specific role of these tools in assessing the cognitive impairment of stroke patients.
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 | 0.025 | 0.137 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.010 | 0.007 |
| Bibliometrics | 0.019 | 0.015 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.005 | 0.006 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".