The Deep Dementia Phenotyping (DEMON) Network: A global platform for innovation using data science and artificial intelligence
Bibliographic record
Abstract
Abstract Background The increasing availability of large high‐dimensional data from experimental medicine, population‐based and clinical cohorts, clinical trials, and electronic health records has the potential to transform dementia research. Our ability to make best use of this rich data will depend on utilisation of advanced machine learning and artificial intelligence (AI) techniques and collaboration across disciplinary and geographic boundaries. Method The Deep Dementia Phenotyping (DEMON) Network launched in 20191 to support the growing interest in machine learning and AI. Led by Director Prof David Llewellyn and Deputy Director Dr Janice Ranson, the leadership team additionally includes 5 Theme Leads and 14 Working Group Leads, supported by an international Steering Committee of world‐leading academics. Core funding is provided by Alzheimer’s Research UK, the Alan Turing Institute and the University of Exeter, with additional support from strategic partners including the UK Dementia Research Institute and the Alzheimer’s Society. Grand Challenges were established at a National Strategy Workshop in June 2020. Multidisciplinary Working Groups were formed to coordinate practical activities in seven key areas: Genetics and omics, experimental medicine, drug discovery and trials optimisation, biomarkers, imaging, dementia prevention, and applied models and digital health. Additional Special Interest Groups coordinate topic specific collaborations. Result Membership on 4th February 2022 comprised 1,321 individuals from 61 countries across 6 continents (see Figure). Areas of expertise include dementia research (904; 68%), data science (692; 52%), clinical practice (244; 18%), industry (162; 12%), and regulation (26; 2%). Individual membership is free, and regular knowledge transfer events are provided including a monthly seminar series, talks and workshops, training, networking, and early career development. Each Working Group meets monthly, with multiple grants, reviews, and original research articles in progress. Eight state of the science position papers are in preparation, resulting from a Symposium held in April 2021. In January 2022, 110 early career researchers participated in the Network’s flagship event ‘NEUROHACK’, a 4‐day competitive global hackathon, with pilot grants awarded to those generating the most innovative solutions. Conclusion The DEMON Network is a rapidly growing global platform for innovation that is supporting the global dementia research community to collaborate. Find out more at demondementia.com
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 | 0.017 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.010 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.013 | 0.004 |
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".