The intersection of digital health and artificial intelligence: Clearing the cloud of uncertainty
Bibliographic record
Abstract
Digital health (DH) and artificial intelligence (AI) in healthcare are rapidly evolving but were addressed synonymously by many healthcare authorities and practitioners. A deep understanding and clarification of these concepts are fundamental and a prerequisite for developing robust frameworks and practical guidelines to ensure the safety, efficacy, and effectiveness of DH solutions and AI-embedded technologies. Categorizing DH into technologies (DHTs) and services (DHSs) enables regulatory, HTA, and reimbursement bodies to develop category-specific frameworks and guidelines for evaluating these solutions effectively. DH is the key in generating real-world data, which is increasingly important in decision-making processes. The potential benefits of DHTs in improving health outcomes and reducing health system costs can position them alongside traditional health technologies in certain medical conditions. AI, one of the potential tools for DH, can be embedded in technologies, such as medical devices or applications, to enhance functionality and performance. AI excels at handling numerical and perceptual data. In the context of numerical data, machine learning algorithms enable prediction, classification, and clustering. In managing perceptual data, AI recognizes image/video, voice, and text. In recent years, generative AI, a form of AI that generates new content by employing a combination of a wide range of learning approaches, has become prominent in research and influences the health sector. A thorough understanding of DH and AI, along with accurate terminology use, would facilitate the timely generation of regulatory and HTA-grade evidence that helps improve health outcomes and decision-making certainty.
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 | 0.022 | 0.041 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.007 | 0.006 |
| Science and technology studies | 0.006 | 0.046 |
| Scholarly communication | 0.028 | 0.058 |
| Open science | 0.003 | 0.016 |
| Research integrity | 0.011 | 0.014 |
| Insufficient payload (model declined to judge) | 0.010 | 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".