Editorial: Integration of Machine Learning and Computer Simulation in Solving Complex Physiological and Medical Questions
Bibliographic record
Abstract
BACKGROUNDThis Research Topic, "Integration of Machine Learning and Computer Simulation in Solving Complex Physiological and Medical Questions", brings together two powerful computational approaches to investigate complex disease processes: the use of high-fidelity, mechanism-based simulation models (MSMs), and the training of artificial neural networks (ANNs) via machine learning (ML) and artificial intelligence (AI).These two approaches represent distinct aspects of the scientific process: ML/AI involves correlation identification/hypothesis generation whereas MSMs provide an in silico means for hypothesis testing and conceptual model verification, with capabilities that can complement and address each other's limitations.High-fidelity MSMs can contain very large numbers of parameters, which poses challenges to effective parameterization and/or parameter space exploration, and can present prohibitive computational costs in terms of executing simulation experiments.Alternatively, ML/AI approaches are notoriously data-hungry (a considerable issue when dealing with biological data sets that are generally orders of magnitude more sparse compared to other ML applications), are highly limited in terms of testing inferred causal relationships, and are often "black boxes" in terms of interpreting why the ANNs do what they do.This Research Topic brings together work that integrates MSM and ML in a complementary fashion.We have organized these papers in the following general classes of investigation. APPLICATIONS OF INTEGRATED ML AND MSM IN PERSONALIZED MEDICINEThe ostensible goal of the practice of medicine is to treat sick individuals with the right drug and the right time, and be able to have such a treatment regimen for every sick patient.MSMs can serve as "digital twins" of individual patients and provide a means of virtually forecasting their future disease
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 | 0.008 | 0.026 |
| Meta-epidemiology (narrow) | 0.005 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.003 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.004 | 0.004 |
| Scholarly communication | 0.008 | 0.006 |
| Open science | 0.005 | 0.002 |
| Research integrity | 0.017 | 0.023 |
| Insufficient payload (model declined to judge) | 0.014 | 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".