MedISys: A Multilingual Media Monitoring Tool for Medical Intelligence and Early Warning
Bibliographic record
Abstract
Most Western countries have an institution with the task of detecting and monitoring potential threats to Public Health (PH) in their countries, i.e. chemical, biological, radiological and nuclear (CBRN) threats, which can be natural (diseases), deliberate (terrorism) or accidental. One of the daily duties of these PH bodies includes monitoring the local, national and international media for reports on disease outbreaks, on the disappearance or the release of dangerous substances, etc. This typically involves identifying and analysing relevant news articles in up to half a million news reports per day in various languages. \nIn order to facilitate this task, the European Commission¿s Joint Research Centre (JRC) in collaboration with the EC¿s Directorate General for Health and Consumer Protection (DG SANCO) has developed the fully-automatic Medical Intelligence System MedISys, which takes away many of the routine tasks of this process and detects early warning signals that can be used as a starting point for the daily media review. MedISys gathers news reports in 42 languages from about 1,500 web portals and twenty commercial news providers, filters documents of potential interest to PH officials, categorises them, monitors trends and alerts users of an unexpected increase of articles in any of the fine-grained categories, separately for each country of the world. MedISys allows to customise the view of reports to specific languages, subjects and news sources. It furthermore allows moderators to select, group and disseminate the information to further user groups, via email, SMS, web pages and PDF reports. \nA challenge faced by all PH organisations is the fact that a lot of relevant information is only available in foreign languages and that employing experts in all the languages is expensive and difficult. By aggregating the information found in many different news articles in all the available languages, MedISys can automatically issue warnings to users (through graphs, email alerts, etc.) as soon as relevant information appears in any of the languages covered, and often before the information is published in the user¿s own language. \nMedISys is actively used by international organisations such as EC¿s DG SANCO, the European Centre for Disease Prevention and Control ECDC and the World Health Organisation WHO, by many PH bodies inside the European Union (e.g. the French Institut de Veille Sanitaire and the Spanish Instituto de Salud Carlos III), as well as by various bodies outside the EU (e.g. the US-American CDC and the Canadian Global Public Health Intelligence Network GPHIN). A public web site with restricted functionality, available at http://medusa.jrc.it/, is visited by an average of 1,000 distinct users per day.\nThe speaker will give an overview of the challenges faced by Public Health bodies, describe the main functionality of MedISys including the features that distinguish it from other media monitoring systems, and talk about the ongoing collaboration in the G8¿s Global Health Security Action Group GHSAG with the purpose of further increasing the usefulness of the system.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.024 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".