Developing a decision-tool to help organizations design care patterns for people with complex care facilitating integrated care: the ICARE4OLD project
Bibliographic record
Abstract
Introduction: Older adults receiving home care (HC) services or living in long-term care facilities (LTCF) often experience multimorbidity. Identifying subgroups of older people sharing the same types of chronic diseases and having similar levels of impairment can help organizations target interventions effectively. Decision-support tools can foster tailored care and integrated care for these persons, as they are based on the comprehensive assessment of all needs and capabilities a person has. The iCARE4OLD project aims at developing decision-support tools with machine learning techniques. These tools will assist physicians and caregivers to better plan healthcare trajectories for older people, using data collected with the interRAI instruments. Methods: Data from a large sample of older people receiving HC services or living in LTC homes in Canada, Italy, Finland, and New Zealand were used to run a Latent Class Analysis (LCA). This technique classified individuals according to their underlying disease patterns starting from a list of 19 chronic conditions. Results: The combined sample from all countries (N=102,000) showed a mean age of 80 years old and 65% were female. The LCA yielded a 5-class solution as the best model for all countries, for both HC and LTC, including five disease patterns. One of the models showed the following groups (1) Alzheimer/dementia; (2) psychiatric diseases; (3) cardio-pulmonary diseases ; (4) stroke/hemiplegia ; (5) other dementias. The groups of cardio-pulmonary disease pattern and the stroke/hemiplegia disease patterns showed the highest complexity, especially in Activities of Daily Living (ADLs), with 68.5% and 77.8% living with impairment. Conclusion: Our results showed that, by using a standardized assessment tool such as the interRAI, it is possible to identify homogeneous morbidity patterns in older patients receiving care in the community or long-term residential care. Prognostic machine learning algorithms are being developed and validated to better predict various health outcomes and to evaluate the modifying impact of pharmacological and non-pharmacological interventions. These algorithms will be the basis of an electronic decision support tool, which will be used by health professionals working in home care and nursing homes. This tool will show which care paths to be followed to achieve better health outcomes for older persons.
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 | 0.015 | 0.037 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
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".