The term ‘precision nutrition’ could suggest that current nutrition practices are ‘imprecise’. However, nutrition has been, and will always remain, a precise science, striking a balance between providing enough nutrients to meet the requirements of the animal for optimal growth, without unnecessarily inflating feed cost or nutrient excretion into the environment.
Production animal nutrition has also been a constantly evolving discipline, with regular adoption of novel concepts e.g. digestible nutrient formulation systems, net energy etc. In the past few years, improved access to sensor technologies, data science tools such as machine learning and artificial intelligence, has accelerated this evolution. Systematic data generation, advanced analytics, and interpretation, offer disruptive opportunities to better understand the nutrition and health status of the flock.
In this new paradigm of animal nutrition, veterinary health, and live production, data is the new currency. Companies that collect, monitor, map, visualize, analyze, and interpret their data will be the most competitive and sustainable. The new tools available to the poultry industry present an opportunity to be more precise.
Figure 1. Illustration of how Verax™ works, starting with data collection, data input and then interpretation and making recommendations (Source: dsm-firmenich, 2023)
Figure 1 shows how data are gathered, collected, and interpreted in the Verax™ platform. First, blood samples are taken from birds and analyzed on site. The analysis results are added to the secure Verax™ cloud database via a dedicated app. The results are benchmarked, and the significance of the analysis results are given to the producer who can then make more informed management decisions. Over time, comparisons can be made to previous seasons or flocks, helping to identify changes. Using Verax™ is especially helpful when implementing new flock management changes or nutritional changes, as the data can be used to see how the changes are affecting the physiology of the bird.
What makes Verax™ so valuable is the systematic and thorough method of data collection, notation, and storage. It is only by having such detailed notes on each sample that disruptive insights are found. The level of detail in Verax™ allows certain biomarkers to be linked with veterinary health outcomes. Any high value phenotype can be plugged into machine learning to produce algorithms for diagnostics and predictive tools.
Verax™ is accessed via a user-friendly and secure app interface on a mobile device. There are already many benefits to digitizing necropsies, but the real value comes from the thorough annotation and standardization of the data capture, allowing more in-depth insights to be drawn from the samples. The consistency of capturing several blood biomarkers and veterinary observations from every animal, house, farm and complex, allows machine learning to alert Verax™ users to potential problems before they develop.
Verax™ is part of a wider precision animal farming platform. Blood biomarkers are only one source of input, but data can be gathered from a whole range of biological matrices including saliva, digesta and excreta contents, feed and water consumption, and genetics (Figure 2).
Figure 2. Precision animal farming requires inputs from a wide range of sources (Source: dsm-firmenich, 2023)
Calcium (Ca) and phosphorus (P) are the most abundant mineral elements in the body. Most of the body’s Ca and P is stored in the skeleton which is why these minerals are so closely linked to bone health and skeletal integrity. But Ca and P are also involved in several other important pathways such as energy metabolism, blood clotting and neuromuscular function. Insufficient levels or an inadequate ratio of these minerals in the diet can cause several problems such as rickets, tibial dyschondroplasia, lameness, nerve function problems, poor appetite and body weight uniformity.
Figure 3. Typical levels of ionized calcium (mmol/l) found in the blood of broilers (Source: dsm-firmenich, 2023)
Total blood Ca is typically around 11.5-12 mg/dL, and P is usually approximately 6-7 mg/dL (Figure 5). Approximately 47-48% of blood Ca is ‘ionized‘ (metabolically active; Figure 4), whereas the remainder of blood Ca is covalently bound to plasma proteins or associated with anions such as phosphate or lactate. These concentrations do not substantially change with bird age or gender but can be disrupted by various nutrition and management factors.
Figure 4. Mean plasma calcium (mg/dL) and phosphorus (mg/dL) concentrations in the blood of broilers (Source: dsm-firmenich, 2023)
For example, ionized Ca has been observed as low as 0.6 mmol/l. Birds with levels of ionized Ca as low as this will display atypical behaviour, nervous paralysis and elevated mortality. More often, subclinical hypocalcemia or hypophosphataemia are observed, which is associated with low body weight (Figure 6) and poor flock uniformity.
Skeletal abnormalities such as bacterial chondronecrosis with osteomyelitis (BCO), enterococcus, and femoral head necrosis, are significantly more prevalent when ionized Ca levels drop below 1.1-1.2 mmol/L or when plasma total Ca concentration is below 10-10.5 mg/dL. Low plasma phosphorus, which is often associated with high plasma Ca, is also associated with skeletal abnormalities but most commonly is related to poor growth rate and body weight uniformity.
Verax™ data has shown an association between the Ca and P status of the bird and season. This may be related to blood pH or a more general disruption to the acid/base balance of birds as ambient carbon dioxide concentrations rise and fall with altered respiratory tract health and ventilation rates. Blood pH is important as this influences the proportion of Ca that is metabolically active. This interplay is one example of why more systematic analysis of multiple data streams can shed light on underlying physiological changes relevant for efficiency and welfare. Further investigation is currently being carried out to assess seasonal variations in data held in the Verax™ platform, with the possibility of making recommendations for different feeding programs in warmer or colder seasons that go beyond the traditional adjustments made by nutritionists.
Figure 5. Body weight over time in birds with high (red line) or low (blue line) levels of plasma phosphorus (Source: dsm-firmenich, 2023)
Even though Ca levels are hormonally regulated, blood Ca and P does respond to dietary inputs. Parathyroid hormone, calcitonin and vitamin D will regulate blood Ca levels to some extent, but not completely. Figure 6 shows a statistically significant association between dietary Ca and plasma Ca. This has also been shown for P (Figure 7). Interestingly, whilst dietary P has an influence on blood P, diet Ca is capable of influencing both Ca and P. Specifically, over-feeding dietary Ca has a supressing effect on blood P and vice versa. Whilst dietary Ca and P do have some influence on blood Ca and P, blood pH and acid/base balance may be more important in order to optimise blood Ca and P concentrations. For example, the proportion of total blood Ca that is metabolically active and can contribute to skeletal mineralisation is normally around 47-48% in broilers. However, this can drop by 2-4% for every 0.1 unit increase in blood pH. These interactions highlight the importance of monitoring biomarkers beyond blood Ca and P when attempting to optimise the nutrition and health status of the bird.
Figure 6. Relationship between dietary calcium and blood calcium in broilers (Source: Walk et al., 2022)
Figure 7. Relationship between dietary phosphorus and blood phosphorus in broilers (Source: Walk et al., 2022)
A common disturbance to optimal blood pH in commercial broilers high chloride intake. Chlorine based sanitizers and water treatments are not unusual, plus sources of chloride are used in the feed. These can all, inadvertently, push blood pH down which might have negative implications, not only for Ca and P, but for renal health, litter quality and growth rate. Nutritionists need to understand the balance between cations and anions, and use them as levers within the least-cost formulation strategy to produce desirable outcomes.
In 2019, a trial was conducted looking at the response time of certain blood biomarkers to a coccidiosis challenge. Potassium and carotenoids began to shift 3-7 days before any other obvious or macroscopic symptoms becoming apparent. This rapid response sparked the idea for an early warning system for coccidiosis. The hypothesis was proposed that with enough data, machine learning could be used to create a classifier model with a forecasting capacity for coccidiosis.
Verax™ uses supervised machine learning to create classifer and regressor models. There are currently many tens of thousands of data points in the database, gathered from commercial broilers with a naturally occurring prevalence of coccidiosis. To create the model, the data set was split into two sections; 60% used for training, and 40% used for validation. All the birds with coccidiosis were identified and a biomarker profile was created which predicted that phenotype. The model was then validated on the other subset of birds. Over time and with more data, especially from birds that have coccidiosis, the accuracy of the model increases and permits the identification of specific Eimeira species.
This principle was applied in practice on a farm in the US. Blood samples were taken from birds on four different farms on day 14. The blood analysis results were used to predict that two of the farms would have a coccidiosis outbreak later, and the other two would not. A second visit to the farms on day 28 confirmed the predictions.
Although the model is not 100% accurate yet, there is a very strong association with excellent statistical performance in terms of false positive and false negative rates on the forecasting ability of the model. Figure 8 shows an example of the user interface in Verax™ for tracking flocks, including coccidiosis scores, over time.
Figure 8. Verax™ user interface
27 February 2025
Get in touch with a dsm-firmenich Animal Nutrition & Health specialist or find contacts around the world to suit your needs.
At dsm-firmenich, we love to connect with you.
Follow us on any of the channels below.
We detected that you are visitng this page from United States. Therefore we are redirecting you to the localized version.
