Cough monitoring alerts vets two weeks earlier

A pig farmer checks up on his finisher pigs, who are monitored by microphones hanging from the ceiling. [Photos; De Snuitgeverij]

Recent trials have made it very clear what computer monitoring can achieve. An early warning system consisting of a microphone and algorithms can detect respiratory issues several days earlier than a producer or vet can. Trials all over Europe can confirm this.

Is it possible to figure out which respiratory issues are present in a pig herd only by listening to pig coughs? Impossible, some might say. Doable, others might retort. Some of these others, as early as 2012, embarked on a project to make this goal into reality – to develop a device that can capture pig sounds and take action if any alarming coughing pattern is picked up.

As you might expect, the development of such a device does not grow overnight. On the contrary, the development was already reported on by Pig Progress in the months leading up to EuroTier 2012. By that time, the prototype of the device was only launched – now, three years down the road, it has become commercially available; and more importantly, it’s been extensively tested in various pig farms all over Europe. Time to take a look what was found.

Precision Livestock Farming

Taking one step back before moving into the subject deeper, it’s developments within the range of Precision Livestock Farming (PLF) we are talking about here.

PLF is based on three guiding principles. Firstly, PLF does not aim to replace the farmer but intends to be a decision support tool. Secondly, the animal is to be considered the most crucial part in the biological production process. Lastly, three conditions are important for favourable monitoring and control:

the animal variables need to be monitored continuously;
the prediction (expectation) of the animal variable should be reliable with respect to environmental changes;
and the prediction needs to be integrated with online measurements into an analysing algorithm.

Several of these signals are easy to pick up on using existing materials – e.g. how much feed or water is consumed or what is the temperature in the farm house. Dutch-based animal technology company Fancom already developed growth monitoring using cameras a few years ago, a tool to accurately determine pig weight using cameras coupled with a computer system which interprets all data correctly using algorithms. This innovation is currently being further developed to fit in with individual pig monitoring.

Pretty much following a similar philosophy, the ‘Pig Cough Monitor’ was developed by the company Soundtalks, in cooperation with Fancom. Soundtalks is a spin-off of the Katholieke Universiteit Leuven of Leuven, Belgium and the University of Milan, Italy.

[([002_629_rb-image-2712269.jpeg]:inzetgroot)]

Close up of the Pig Cough Monitor  microphone.

Methods applied

In a recent series of trials, in the EU-PLF project, pig sounds were captured during 60 fattening rounds in 40 compartments divided over ten fattening pig farms (four compartments per farm) across Europe. The different farms had significantly different climatological conditions, housing layout, pig breeds and management styles. The farmer and local veterinarian kept track of their findings in logbooks, without access to use the respiratory distress monitor in real-time (the results were only discussed retrospectively when the fattening batches were finished). Moreover, trained animal experts performed welfare & health assessments of key indicators at discrete moments during the fattening period. The assessments were used as a reference in this paper and were the results of a ten-minute standardised manual cough count in the compartment. The hardware used to capture the sounds was a SoundTalks’ SOMO sound recording device, with microphones. The microphones were typically centred with respect to the position of the animals that were monitored (e.g. pig pen). The microphones were fixed at a height of 2 m to be close enough to animals, yet not too close for the animals to reach them. The equipment, much like similar PLF technologies, was subject to a range of robustness-related issues typical in the farm environment.

Cough monitoring

That automated cough monitoring is reliable has been known for several years. In previous tests, automated cough measurements had been established to function in the presence of a number of diseases, including swine influenza virus (SIV), Mycoplasma hyopneumoniae (M. hyo) as well as Porcine Reproductive and Respiratory Syndrome virus (PRRSv).

Making a commercially working, robust tool, which can assist producers in giving early warnings – that has become a challenge, nevertheless. As pig cough sounds differ between seasons, between race of pigs, between types and stages of diseases (co-infections) and conditions (acoustical, climatological, management etc.), the algorithms that were developed in laboratory conditions had to be modified. All case studies described in this article were caught in a respiratory distress index (RD-index), being a measure for respiratory distress, relative to the number of animals present in the compartment.

RD-values below 10 usually indicate moments with low respiratory distress, while higher RD-values indicate respiratory problems. In all the graphs, a single value of the RD-index is shown per day.

Proving whether the cough monitor actually monitors what humans expect it to do was easier said than done. Assessors at intervals walked into several pig houses all over Europe and counted coughs for ten minutes. These were then compared with what the Pig Cough Monitor would register. This article highlights two of these trials.

[([003_347_rb-image-2720218.jpeg]:inzetgroot)]

The Netherlands – Co-infection

Figure 1 shows the evolution of the respiratory distress as a function of time, measured on a farm in the Netherlands. On 18 October 2014, 79 piglets of ten weeks old entered the compartment. Necropsy (PCR-analysis of lung section) was performed on two piglets that had died before reaching the age of ten weeks. Both piglets were positive for Mycoplasma hyopneumoniae (M. hyo) and negative for influenza-A virus, PRRSv NA and PRRSv NA-HP. One piglet was further positive for PRRSv EU and weakly positive for PCV2, while the other piglet was negative for both. All animals received vaccination against PCV2, but not against PRRSv, M. hyo and influenza.
The veterinarian of the farm decided that treatment with doxycycline and sodium salicylate was necessary when the piglets entered the compartment on 18 October. This treatment was stopped after four days. It is clear that the respiratory distress index in this period is in good correlation with the observation of the veterinarian. The index starts at a high level (48), before the effect of the treatment becomes clear and the index drops to values below 10 after five days.
From 23 October onwards, the respiratory distress was rising to reach a peak level of 55 on November 10. The farmer and veterinarian, who could not consult the graph of respiratory distress in this two-direction blind test, were unaware of further respiratory problems in this period and no treatment was given to the animals. A routine diagnostic test (oral fluid multiplex PCR test) on November 12 revealed that the animals were positive for Mycoplasma hyorhinis, weakly positive for Mycoplasma hyopneumoniae and negative for e.g. Porcine Respiratory Complex, PRRSv, SIV and PCV2.

In neighbouring compartments, positive cases of influenza were found. Because high coughing levels were noticed, an eight-day treatment with doxycycline and sodium salicylate was restarted on 13 November. This type of treatment usually does not last longer than five days on this farm, but the severity of the respiratory problem forced a longer treatment period. The effect of the treatment is clearly visible, as the respiratory index drops in this period. The added value of the respiratory distress monitor is clear in this case as the rise of distress could have been noticed more than two weeks earlier. Faster treatment of the animals would have resulted in less economic loss (higher average daily gain, lower feed conversion ratio, etc.). A third increase in respiratory distress was visible around 29 November. Based on oral fluid samples from neighbouring compartments, the veterinarian believes that this increase was most probably caused by a combination of diseases, i.e., PRRSv, influenza and M. hyo. After 29 November, the respiratory distress index returned to normal values, i.e., below 10. The automatically generated respiratory distress index is in good correlation with the findings of the human assessor, as a high number of coughs were counted on three occasions. It is clear that the continuous automated measurement of respiratory distress gives a much clearer picture of the complex respiratory situation on the farm. In combination with diagnostics and the knowledge from pork producer and vet, the respiratory distress monitor proves to be a tool with added value and economic impact.

[([004_183_rb-image-2720217.jpeg]:inzetgroot)]

Spain – thermal shock

Figure 2 shows the evolution of the respiratory distress index measured on a fattening farm in Spain. Except for the beginning and the end of the fattening round, the RD-index was below scale 10 indicating no significant respiratory problems. The farmer and the veterinarian did not notice any respiratory problems during this fattening batch; hence no medical treatment was given during this round. The only medical interventions were traditional vaccinations against Aujeszky on 25 January and 16 February. The assessment on 13 March (0 coughs) further supports the idea that the respiratory status of the pigs was good during the middle of the fattening round.
The peak in respiratory distress index in the beginning of the round is very characteristic and similar peaks were measured for other batches/compartments on this farm. The peaks were a lot higher during winter times and occurred typically within the first week after placing the animals in the compartment. As the building was very open (suited to the hot climate that occurs during most of the year) and the farmer did not pre-heat the compartment prior to the arrival of the pigs, the hypothesis was that the thermal shock between the nursery and the fattening compartment makes the pigs vulnerable to different respiratory infections. However, no further data was available to support this hypothesis, although it is well known that thermal shock can have these effects. From 12 April onwards, a clear increase in the respiratory index is visible again. The farmer did not notice any respiratory problems and no actions were taken. Based on previous examples, it was assumed that there was a respiratory problem and that the economic losses could have been reduced if the farmer would have taken appropriate measures near the beginning (pre-heating) and end of the batch (treatment).

Other trials

Similar trials were carried out in farms in again the Netherlands, Hungary and France. The farm in the Netherlands had a swine influenza infection; in Hungary pleuritis and pneumonia had broken out; in France, an air washer caused respiratory problems in the finisher house. In all cases, the monitor indicated increased levels of respiratory distress. The five cases together showed all opportunities how to analyse the reliability of the continuous, automated monitoring of respiratory distress in pigs.

Conclusion: Early warnings

The trials demonstrated the tool’s potential to deliver early warnings (up to two weeks earlier) compared to a situation where producers and/or veterinarians rely on their own routine observations without the monitor. Different causes of respiratory problems (co-)infections, as well as technical problems with air washers and ventilation, have all been shown to result in an increase in automated respiratory  distress measures.

* With permission, this article has been using both text fragments as well as tables and figures from the article ‘Animal sound… talks! Real-time sound analysis for health monitoring in livestock’ by Dries Berckmans, Martijn Hemeryck, Daniel Berckmans, Erik Vranken en Toon van Waterschoot. This paper was presented at the recent International Symposium on Animal Environment & Welfare, in Chongqing, China, 23-26 Oct 2015.