AI system
- System
-
SoundTalks (24/7 AI sound-based cough monitor with respiratory health status score)
- Model
-
Not assessed
- Release
-
Not assessed
- Application developer
-
SoundTalks NV, Leuven, Belgium
- Role
-
Not assessed
- Configuration
-
Not assessed
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Two SoundTalks monitors in a 600-pig nursery airspace. Parallel oral fluid and bioaerosol qPCR sampling. Circulating swine influenza A virus producing coughing.
- Human oversight
-
Not assessed
- Relation to AI
-
The AI produced a respiratory health score that tracked swine influenza A loads measured by qPCR. Alerts were hidden from investigators, so the study measures association rather than any alert that changed what happened. Funding and three co-authors came from Boehringer Ingelheim Vetmedica. The paper states the funders were not involved in collection, analysis or interpretation.
- AI contribution
-
The AI produced a respiratory health score that tracked swine influenza A loads measured by qPCR. Alerts were hidden from investigators, so the study measures association rather than any alert that changed what happened. Funding and three co-authors came from Boehringer Ingelheim Vetmedica. The paper states the funders were not involved in collection, analysis or interpretation.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
LMU Munich blinded study in a German nursery: swine influenza A loads in oral fluids and bioaerosols were associated with falls in the AI's respiratory health score; no intervention outcome.
- Category
-
Improved Knowledge Discovery
- Status
-
Not assessed
- Beneficiary groups
-
Organizations. People.
- Beneficiaries
-
Not assessed
- Reach
-
Not assessed
- Distribution and access
-
Not assessed
- Duration
-
Not assessed
- Expected?
-
Yes
- Costs and harms
-
Not assessed
Measurement
- Studies
-
Not assessed
- Study design
-
Not assessed
- Measurement
-
Not assessed
- Setting and sample
-
Not assessed
- Measures
-
Not assessed
- Comparison
-
human-conducted clinical coughing scores on the same pigs
- Results
-
Reference: twenty human clinical coughing scores per batch, with a coughing index of at most 0.4% (batch 1) and a maximum of 1.26% (batch 2). Result: a 24/7 AI respiratory health score that fell as the human-scored coughing rose (Spearman's rho −0.478 and −0.468).
- Additional value from AI
-
Not assessed
- Limitations
-
Not assessed
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Not assessed
- Amount
-
Not assessed
- Currency and prices
-
Not assessed
- Period and unit
-
Not assessed
- Realization
-
Not assessed
- Recipients and payers
-
Not assessed
- Gross or net
-
Not assessed
- Included costs
-
Not assessed
- Comparison
-
Not assessed
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer: SoundTalks NV, Leuven, Belgium. Operator: Clinic for Swine,
LMU Munich, on a commercial piglet-producing farm in Germany. - Jurisdictions
-
Developer:
Belgium. Operator: 
Germany. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Monitors able to separate pig coughs from barn noise. Pathogen loads high enough to depress the score.
- Replication attempts
-
1 follow-up entries. Benefit recurred: 1.
- Later findings
-
Not assessed
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0197-source-0001–0002
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Operator, Independent
- Original evidence
-
Not assessed
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
Organizations. People.
- Depth
-
Not assessed
- Reasons
-
Organizations: Monitors were blinded, so no alert was acted on; the study documents associations, not a changed treatment or production outcome. People: No outcome for the farmer or animals is reported.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
Independently studied
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Livestock health. Swine respiratory disease monitoring.
- Purpose
-
Continuously count pig coughs, separate them from barn noise and compute a daily respiratory health status. Yellow and red alerts give an early warning of respiratory disease.
- Dates
-
Date basis unassessed: 2024 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: 41f3fd2686ba…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
4 revisions. Latest: 21 October 2026.
Sources
-
Peer-reviewed study Deployer
Eddicks M, Feicht F, Beckjunker J, Genzow M, Alonso C, Reese S, Ritzmann M, Stadler J. Monitoring of Respiratory Disease Patterns in a Multimicrobially Infected Pig Population Using Artificial Intelligence and Aggregate Samples. Viruses 16(10):1575 (2024). doi:10.3390/v16101575
High swIAV-RNA loads in OFs and AS were significantly associated with a decrease in respiratory health, expressed by a respiratory health score calculated by the AI
-
Peer-reviewed study Independent author
Yoon CE, Cho DH, Park HL, Song JY, Park S, Lee SW, Go YY, Choi IS, Song CS, Lee JB, Park SY, Kang YL. AI-Based Respiratory Monitoring-Guided Evaluation of Rottlerin Therapy for PRRS in Grower-Finisher Pig Farms. Viruses 18(1):72 (2026). doi:10.3390/v18010072
Respiratory Health Status (ReHS) and a derived Clinical Cough Index (CCI = 100 - ReHS) were continuously recorded with SoundTalks®