Leveraging artificial intelligence community analytics and nanopore metagenomic surveillance to monitor early enteropathogen outbreaks
Bibliographic record
Abstract
Foodborne enteric infections are a major public health and economical burden, yet their surveillance often relies on latent indicators that delay containment efforts by several days and weeks. Conversely, whole metagenome shotgun sequencing of communal wastewater allows continuous monitoring of enteric pathogens. Spikes in abundance can be observed several weeks before the first case reports emerge. In addition, AI-driven social media mining, already in use for public opinion analytics, could be repurposed for predicting outbreaks at the community level by predicting the number of people experiencing symptoms in the population given their social media activity. Here we report how AI-driven community analytics and high-throughput long-read metagenomic surveillance of communal wastewater microbiota were combined to monitor non-typhoidal salmonellosis in Quebec City, Canada, from August 2023 to February 2024. Both approaches indicated similar fluctuations over time for: (i) people experiencing salmonellosis symptoms, and (ii) Salmonella enterica relative abundance in wastewater, with predicted cases leading metagenomic peaks by a week. Moreover, both approaches detected a maximum around September 13th, 2023, 5 weeks before a Salmonella food recall for the Quebec and Ontario provinces was made by the Public Health Agency of Canada. We therefore suggest that continuous AI-driven analytics and wastewater metagenomics monitoring could become part of a nationwide surveillance pipeline from the community scale to the molecular level.
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 | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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".