Assisted screening for systematic reviews
Classifiers prioritise records for human screening; recall is measured against a fully screened sample, and the stopping rule is stated in the review protocol before screening starts.
GCRI · Labs
Machine learning is both a tool and an object of study in this lab. It assists literature screening, experimental design, image and sequence analysis and simulation, and it needs its own evaluation discipline: leakage, distribution shift and opaque failure modes are research risks to be tested, not assumed away.
Artificial intelligence and machine learning develop algorithms that learn patterns from data to classify, predict or generate outputs. They are increasingly used for hazard detection, forecasting and decision support, and are themselves a source of risk. In research and evidence, methods and modelling and innovation, machine learning can scale detection and forecasting across interconnected systems. Its own failure modes must be weighed when automated outputs inform consequential decisions. The canonical description is on the STEM Commons.
Classifiers prioritise records for human screening; recall is measured against a fully screened sample, and the stopping rule is stated in the review protocol before screening starts.
Models trained on simulations or past runs suggest which experiments to run next, using uncertainty to balance exploration and confirmation, and every suggestion is tested physically before it counts.
Segmentation and classification models are validated against expert annotation from other sites and instruments, with failure cases catalogued and shared alongside the model.
The screen a team would use to follow this method: its measures, states and decisions. Names are examples and values are illustrative.
Labs · Machine learning in laboratory · Run R-4300
| All | 0.79 | 0.04 | 7294 | Pass |
| Region A | 0.84 | 0.04 | 1004 | Review |
| Region B | 0.79 | 0.12 | 594 | Review |
| Rare class | 0.67 | 0.14 | 67 | Below bar |
Datasets and records used by artificial intelligence and machine learning on this platform, with the role each plays and the label its values carry. Sources are listed in the source register.
| Data | Rol | Label |
|---|---|---|
| Annotated benchmark datasets | Training and evaluation | REPORTED |
| Laboratory instrument outputs | Inputs to analysis models | OBSERVED |
| Simulation archives | Training surrogate models | MODELLED |
| Model and dataset cards | Intended use and known limits | DECLARED |
The model, its assumptions, its data and its uncertainty, in the form a scientist or engineer would check. Structures follow published methods. The values drawn are illustrative, not findings.
The model structure used for machine learning in laboratory science, the assumptions it makes and how each is tested.
Ri = f(Hi, Ei, Vi, Ci)hazard, exposure, vulnerability and coping capacityEAL = ∑k pk · Lkover events k with annual probability pkxt+1 = A xt + B ut + εtA carries the couplings, u the shock, ε the error| Assumption | Why it is made | How it is tested |
|---|---|---|
| Hazard and exposure are independent within an event | Keeps the loss integral tractable | Compare with a copula fit on joint records |
| Couplings are linear near the operating point | Lets shocks propagate through A | Perturb beyond the linear range and compare |
| Vulnerability curves transfer between places | Local curves are rarely available | Validate against observed losses where they exist |
Models are evaluated on held-out data that respects spatial, temporal and group structure. Robustness, calibration and fairness are tested alongside accuracy.
| Check | How it is done |
|---|---|
| Leakage audit | Splits are made by subject, site or time as the question requires, and preprocessing is fitted on training data only |
| External validation | Performance is reported on data from a different source or period |
| Calibration and robustness | Probabilities are checked for calibration, and performance under plausible perturbations is reported |
| Reporting checklist | Studies are reported against REFORMS, TRIPOD+AI or the relevant domain checklist |
Performance degrades when deployment conditions differ from training data. Models can encode biases and fail without clear warning on rare events.
Process explorer · Process
9 steps·5 stages·1 gate
Proses
The AI RMF Core has four functions, GOVERN, MAP, MEASURE and MANAGE, with GOVERN cross-cutting; the order drawn is one common reading, not a checklist.
Neutral outline of a published external standard or method, from its issuing body. Not a record of operation. Nexus does not perform, certify or approve any step shown. A gate or decision belongs to the party the source names. The actions are not necessarily an ordered set of steps. The EU AI Act is not drawn in this flow.
Artificial Intelligence and Autonomous Systems stewards artificial intelligence and machine learning for the Consortium and reviews how it is applied across platforms.
Reports is the Consortium’s quarterly publication. What you know about this subject can become evidence, a case or a correction in the next edition, credited to you and published under CC BY 4.0 where it is your own work.
Stuur nooit persoonlike data, sensitiewe infrastruktuurbesonderhede of enigiets wat u geen reg het om te deel nie. 'n Bydrae word voor gebruik beoordeel; die stuur daarvan verleen geen outeurskap of redaksionele regte nie, en borgskap koop nooit 'n bevinding nie.
Information and enquiries are open today. An enquiry receives a reference and names the next step; applications, payments, compute allocations and registrations open only when their team, terms and review capacity exist.
Maps, data and figures on this site are shown for context and general information. They are not advice, forecasts or warnings; the limits of the information are set out in the Disclaimers and Data Notices.
This site uses only strictly necessary cookies to work and to remember your privacy choices. Nothing loads from other companies, and we never sell or share your personal information.
This site uses only strictly necessary cookies to work and to remember your privacy choices. Nothing loads from other companies, and we never sell or share your personal information. We run no advertising. You can review your choices at any time through Privacy choices at the foot of every page.