Protocol of the pilot study to test and evaluate the iCARE tool: a machine learning-based e-platform tool to make health prognoses and support decision-making for the care of older persons with complex chronic conditions
Bibliographic record
Abstract
INTRODUCTION: The provision of optimal care for older adults with complex chronic conditions (CCCs) poses significant challenges due to the interplay of multiple medical, pharmacological, functional and psychosocial factors. To address these challenges, the I-CARE4OLD project, funded by the EU-Horizon 2020 programme, developed an advanced clinical decision support tool-the iCARE tool-leveraging large longitudinal data from millions of home care and nursing home recipients across eight countries. The tool uses machine learning techniques applied to data from interRAI assessments, enriched with registry data, to predict health trajectories and evaluate pharmacological and non-pharmacological interventions. This study aims to pilot the iCARE tool and assess its feasibility, usability and impact on clinical decision-making among healthcare professionals. METHODS AND ANALYSIS: A minimum of 20 participants from each of the seven countries (Italy, Belgium, the Netherlands, Poland, Finland, Czechia and the USA) participated in the study. Participants were general practitioners, geriatricians and other medical specialists, nurses, physiotherapists and other healthcare providers involved in the care of older adults with CCC. The study design involved pre-surveys and post-surveys, tool testing with hypothetical patient cases and evaluations of predictions and treatment recommendations. Two pilot modalities-decision loop and non-decision loop-were implemented to assess the effect of the iCARE tool on clinical decisions. Descriptive statistics and bivariate and multivariate analysis will be conducted. All notes and text field data will be translated into English, and a thematic analysis will be performed. The pilot testing started in September 2024, and data collection ended in January 2025. At the time this protocol was submitted for publication, data collection was complete but data analysis had not yet begun. ETHICS AND DISSEMINATION: Ethical approvals were granted in each participating country before the start of the pilot. All participants gave informed consent to participate in the study. The results of the study will be published in peer-reviewed journals and disseminated during national and international scientific and professional conferences and meetings. Stakeholders will also be informed via the project website and social media, and through targeted methods such as webinars, factsheets and (feedback) workshops. The I-CARE4OLD consortium will strive to publish as much as possible open access, including analytical scripts. Databases will not become publicly available, but the data sets used and/or analysed as part of the project can be made available on reasonable request and with the permission of the I-CARE4OLD consortium.
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 | 0.030 | 0.031 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.043 | 0.012 |
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".