Health effects of holistic housing renovation in a disadvantaged neighbourhood in the Netherlands: a qualitative exploration among residents and professionals.

BACKGROUND: Holistic housing renovations combine physical housing improvements with social and socioeconomic interventions (e.g. referral to social services, debt counselling, involvement in decision-making, promoting social cohesion). In a deprived neighbourhood in Utrecht, the Netherlands, this paper examined residents' and professionals' experiences, ideas, and perceptions regarding holistic housing renovation, its health effects, and underlying mechanisms explaining those effects. METHODS: Semi-structured in-depth interviews were conducted with 21 social housing residents exposed to holistic housing renovation, and 12 professionals involved in either the physical renovation or social interventions implemented. Residents were interviewed in various renovation stages (before, during, after renovation). Transcripts were deductively and inductively coded using qualitative software. RESULTS: Residents experienced and professionals acknowledged renovation stress caused by nuisance from construction work (noise, dust), having to move stuff around, and temporary moving; lack of information and control; and perceived violation of privacy. Involvement in design choices was appreciated, and mental health improvement was expected on the long term due to improved housing quality and visual amenity benefits. Social contact between residents increased as the renovation became topic for small talk. Few comments were made regarding physical health effects. The interviews revealed a certain amount of distrust in and dissatisfaction with the housing corporation, construction company, and other authorities. CONCLUSIONS: Renovation stress, aggravated by lack of information and poor accessibility of housing corporation and construction company, negatively affects mental health and sense of control. Potential stress relievers are practical help with packing and moving furniture, and increased predictability by good and targeted communication. Social interventions can best be offered after renovation, when residents live in their renovated apartment and the nuisance and stress from the renovation is behind them. Social partners can use the period leading up to the renovation to show their faces, offer practical help to reduce renovation stress, and increase residents' trust in their organization and authorities in general. This might also contribute to residents' willingness to accept help with problems in the social domain after renovation.

Cow key point detection in indoor housing conditions with a deep learning model.

Lameness in dairy cattle is a costly and highly prevalent problem that affects all aspects of sustainable dairy production, including animal welfare. Automation of gait assessment would allow monitoring of locomotion in which the cows' walking patterns can be evaluated frequently and with limited labor. With the right interpretation algorithms, this could result in more timely detection of locomotion problems. This in turn would facilitate timely intervention and early treatment, which is crucial to reduce the effect of abnormal behavior and pain on animal welfare. Gait features of dairy cows can potentially be derived from key points that locate crucial anatomical points on a cow's body. The aim of this study is 2-fold: (1) to demonstrate automation of the detection of dairy cows' key points in a practical indoor setting with natural occlusions from gates and races, and (2) to propose the necessary steps to postprocess these key points to make them suitable for subsequent gait feature calculations. Both the automated detection of key points as well as the postprocessing of them are crucial prerequisites for camera-based automated locomotion monitoring in a real farm environment. Side-view video footage of 34 Holstein-Friesian dairy cows, captured when exiting the milking parlor, were used for model development. From these videos, 758 samples of 2 successive frames were extracted. A previously developed deep learning model called T-LEAP was trained to detect 17 key points on cows in our indoor farm environment with natural occlusions. To this end, the dataset of 758 samples was randomly split into a train (n = 22 cows; no. of samples = 388), validation (n = 7 cows; no. of samples = 108), and test dataset (n = 15 cows; no. of samples = 262). The performance of T-LEAP to automatically assign key points in our indoor situation was assessed using the average percentage of correctly detected key points using a threshold of 0.2 of the head length (PCKh0.2). The model's performance on the test set achieved a good result with PCKh0.2: 89% on all 17 key points together. Detecting key points on the back (n = 3 key points) of the cow had the poorest performance PCKh0.2: 59%. In addition to the indoor performance of the model, a more detailed study of the detection performance was conducted to formulate postprocessing steps necessary to use these key points for gait feature calculations and subsequent automated locomotion monitoring. This detailed study included the evaluation of the detection performance in multiple directions. This study revealed that the performance of the key points on a cows' back were the poorest in the horizontal direction. Based on this more in-depth study, we recommend the implementation of the outlined postprocessing techniques to address the following issues: (1) correcting camera distortion, (2) rectifying erroneous key point detection, and (3) establishing the necessary procedures for translating hoof key points into gait features.

Rapid turnover of sensor data to genetic evaluation for dairy cows in the cloud.

More and more sensor and automation data are available that enable animal breeders to define novel traits. However, sensor and automation data are often frequently measured differently (e.g., milk yield and different milk components are continuously measured during each milking). These differences are challenging animal breeders to define traits and use the most appropriate analytical models for genetic evaluation and breeding values. Traditionally, the process from raw data to breeding value estimations involves several steps: data curation, trait definition, variance component estimation, genetic evaluation, and validation of the estimated breeding values (EBV). All these steps often take many iterations and several research projects to optimize the final genetic evaluations. To make this entire process-from raw data to validated EBV-more efficient, we combined all these steps in a cloud environment that allows for faster processing and a faster data distribution time. We used real data (including 1,782,373,113 daily milk-yield records of 1,120,550 dairy cows) and a real trait (a resilience trait based on the deviations from expected milk yields) to demonstrate the functioning of this cloud environment. The daily milk-yield records were incorporated into our cloud solution, in which we have set up central binary large object storage. Subsequent steps were all performed in the cloud. The data set was preprocessed in approximately 6 h to obtain the resilience indicator for 352,871 cows in the first 3 lactations. Estimation of genetic parameters (heritabilities and genetic correlations) was performed by splitting the data into 5 subsets in ASReml, and prediction of subsequent EBV was performed on the entire data set using MiXBLUP. Together with the validation of breeding values, this process encompassed 16.5 h. By combining the different steps from preprocessing sensor data to genetic evaluation of new traits in one cloud environment, we generated EBV and validation plots in approximately 1 working day. Moreover, our setup is a flexible design and can be adapted easily to test new, longitudinal sensor-driven traits and compare the performance of these new traits to previous ones.

Between-herd variation in resilience and relations to herd performance.

Resilient cows are minimally affected in their functioning by infections and other disturbances, and recover quickly. Herd management is expected to have an effect on disturbances and the resilience of cows, and this effect was investigated in this study. Two resilience indicators were first recorded on individual cows. The effect of herd-year on these resilience indicators was then estimated and corrected for genetic and year-season effects. The 2 resilience indicators were the variance and the lag-1 autocorrelation of daily milk yield deviations from an expected lactation curve. Low variance and autocorrelation indicate that a cow does not fluctuate much around her expected milk yield and is, thus, subject to few disturbances, or little affected by disturbances (resilient). The herd-year estimates of the resilience indicators were estimated for 9,917 herd-year classes based on records of 227,655 primiparous cows from 2,644 herds. The herd-year estimates of the resilience indicators were then related to herd performance variables. Large differences in the herd-year estimates of the 2 resilience indicators (variance and autocorrelation) were observed between herd-years, indicating an effect of management on these traits. Furthermore, herd-year classes with a high variance tended to have a high proportion of cows with a rumen acidosis indication (r = 0.31), high SCS (r = 0.19), low fat content (r = -0.18), long calving interval (r = 0.14), low survival to second lactation (r = -0.13), large herd size (r = 0.12), low lactose content (r = -0.12), and high production (r = 0.10). These correlations support that herds with high variance are not resilient. The correlation between the variance and the proportion of cows with a rumen acidosis indication suggests that feed management may have an important effect on the variance. Herd-year classes with a high autocorrelation tended to have a high proportion of cows with a ketosis indication (r = 0.14) and a high production (r = 0.13), but a low somatic cell score (r = -0.17) and a low proportion of cows with a rumen acidosis indication (r = -0.12). These correlations suggest that high autocorrelation at herd level indicates either good or poor resilience, and is thus a poor resilience indicator. However, the combination of a high variance and a high autocorrelation is expected to indicate many fluctuations with slow recovery. In conclusion, herd management, in particular feed management, seems to affect herd resilience.

Invited review: Toward a common language in data-driven mastitis detection research.

Sensor technologies for mastitis detection have resulted in the collection and availability of a large amount of data. As a result, scientific publications reporting mastitis detection research have become less driven by approaches based on biological assumptions and more by data-driven modeling. Most of these approaches try to predict mastitis events from (combinations of) raw sensor data to which a wide variety of methods are applied originating from machine learning and classical statistical approaches. However, an even wider variety in terminologies is used by researchers for methods that are similar in nature. This makes it difficult for readers from other disciplines to understand the specific methods that are used and how these differ from each other. The aim of this paper was to provide a framework (filtering, transformation, and classification) for describing the different methods applied in sensor data-based clinical mastitis detection research and use this framework to review and categorize the approaches and underlying methods described in the scientific literature on mastitis detection. We identified 40 scientific publications between 1992 and 2020 that applied methods to detect clinical mastitis from sensor data. Based on these publications, we developed and used the framework and categorized these scientific publications into the 2 data processing techniques of filtering and transformation. These data processing techniques make raw data more amendable to be used for the third step in our framework, that of classification, which is used to distinguish between healthy and nonhealthy (mastitis) cows. Most publications (n = 34) used filtering or transformation, or a combination of these 2, for data processing before classification, whereas the remaining publications (n = 6) classified the observations directly from raw data. Concerning classification, applying a simple threshold was the most used method (n = 19 publications). Our work identified that within approaches several different methods and terminologies for similar methods were used. Not all publications provided a clear description of the method used, and therefore it seemed that different methods were used between publications, whereas in fact just a different terminology was used, or the other way around. This paper is intended to serve as a reference for people from various research disciplines who need to collaborate and communicate efficiently about the topic of sensor-based mastitis detection and the methods used in this context. The framework used in this paper can support future research to correctly classify approaches and methods, which can improve the understanding of scientific publication. We encourage future research on sensor-based animal disease detection, including that of mastitis detection, to use a more coherent terminology for methods, and clearly state which technique (e.g., filtering) and approach (e.g., moving average) are used. This paper, therefore, can serve as a starting point and further stimulates the interdisciplinary cooperation in sensor-based mastitis research.

Predicting survival in dairy cattle by combining genomic breeding values and phenotypic information.

Advances in technology and improved data collection have increased the availability of genomic estimated breeding values (gEBV) and phenotypic information on dairy farms. This information could be used for the prediction of complex traits such as survival, which can in turn be used in replacement heifer management. In this study, we investigated which gEBV and phenotypic variables are of use in the prediction of survival. Survival was defined as survival to second lactation, plus 2 wk, a binary trait. A data set was obtained of 6,847 heifers that were all genotyped at birth. Each heifer had 50 gEBV and up to 62 phenotypic variables that became gradually available over time. Stepwise variable selection on 70% of the data was used to create multiple regression models to predict survival with data available at 5 decision moments: distinct points in the life of a heifer at which new phenotypic information becomes available. The remaining 30% of the data were kept apart to investigate predictive performance of the models on independent data. A combination of gEBV and phenotypic variables always resulted in the model with the highest Akaike information criterion value. The gEBV selected were longevity, feet and leg score, exterior score, udder score, and udder health score. Phenotypic variables on fertility, age at first calving, and milk quantity were important once available. It was impossible to predict individual survival accurately, but the mean predicted probability of survival of the surviving heifers was always higher than the mean predicted probability of the nonsurviving group (difference ranged from 0.014 to 0.028). The model obtained 2.0 to 3.0% more surviving heifers when the highest scoring 50% of heifers were selected compared with randomly selected heifers. Combining phenotypic information and gEBV always resulted in the highest scoring models for the prediction of survival, and especially improved early predictive performance. By selecting the heifers with the highest predicted probability of survival, increased survival could be realized at the population level in practice.

The effects of small-scale physical and social environmental interventions on walking behaviour among Dutch older adults living in deprived neighbourhoods: results from the quasi-experimental NEW.ROADS study.

PURPOSE: Improving the physical and social conditions of residential neighbourhoods may increase walking, especially among older people. Evidence on the effects of physical and social environmental interventions, and particularly the combination of both, on walking behaviour is scarce. We evaluated the effects of a small-scale physical environmental intervention (designated walking route), a social environmental intervention (neighbourhood walking group) and the combination of both on walking behaviour of older adults living in deprived neighbourhoods. METHODS: Survey data of 644 older adults residing in four deprived neighbourhoods of Rotterdam, the Netherlands, were used to compare changes in walking behaviour over time (weekly minutes spent recreational walking, utilitarian walking and total walking) of those exposed to 1) a designated walking route (physical condition), 2) walking groups (social condition), 3) walking routes and walking groups (combined condition), and 4) no intervention (control condition). Measurements took place at baseline (T0), and 3 months (T1) and 9 months (T2) after the intervention. Data were analysed on a multiple imputed dataset, using multi-level negative binomial regression models, adjusting for clustering of observations within individuals. All models were adjusted for demographic covariates. RESULTS: Total time spent walking per week increased between T0 and T1 for all conditions. The Incidence Rate Ratio (IRR) for the physical condition was 1.46 (95% CI:1.06;2.05) and for the social intervention 1.52 (95%CI:1.07;2.16). At T2, these differences remained significant for the physical condition, but not for the social condition and the combined condition. These findings were mirrored for utilitarian walking. No evidence was found for an effect on recreational walking. CONCLUSION: Implementing small scale, feasible, interventions in a residential neighbourhood may increase total and utilitarian walking behaviour among older adults.

Comparing regression, naive Bayes, and random forest methods in the prediction of individual survival to second lactation in Holstein cattle.

In this study, we compared multiple logistic regression, a linear method, to naive Bayes and random forest, 2 nonlinear machine-learning methods. We used all 3 methods to predict individual survival to second lactation in dairy heifers. The data set used for prediction contained 6,847 heifers born between January 2012 and June 2013, and had known survival outcomes. Each animal had 50 genomic estimated breeding values available at birth and up to 65 phenotypic variables that accumulated over time. Survival was predicted at 5 moments in life: at birth, at 18 mo, at first calving, at 6 wk after first calving, and at 200 d after first calving. The data sets were randomly split into 70% training and 30% testing sets to evaluate model performance for 20-fold validation. The methods were compared for accuracy, sensitivity, specificity, area under the curve (AUC) value, contrasts between groups for the prediction outcomes, and increase in surviving animals in a practical scenario. At birth and 18 mo, all methods had overlapping performance; no method significantly outperformed the other. At first calving, 6 wk after first calving, and 200 d after first calving, random forest and naive Bayes had overlapping performance, and both machine-learning methods outperformed multiple logistic regression. Overall, naive Bayes has the highest average AUC at all decision points up to 200 d after first calving. Random forest had the highest AUC at 200 d after first calving. All methods obtained similar increases in survival in the practical scenario. Despite this, the methods appeared to predict the survival of individual heifers differently. All methods improved over time, but the changes in mean model outcomes for surviving and non-surviving animals differed by method. Furthermore, the correlations of individual predictions between methods ranged from r = 0.417 to r = 0.700; the lowest correlations were at first calving for all methods. In short, all 3 methods were able to predict survival at a population level, because all methods improved survival in a practical scenario. However, depending on the method used, predictions for individual animals were quite different between methods.

Hour-by-hour physical activity patterns of adults aged 45-65 years: a cross-sectional study.

Background: Limited information exists on hour-by-hour physical activity (PA) patterns among adults aged 45-65 years. Therefore, this study aimed to distinguish typical hour-by-hour PA patterns, and examined which individuals typically adopt certain PA patterns. Methods: Accelerometers measured light and moderate-vigorous PA. GIS-data provided proportions of land use within an 800 and 1600 m buffer around participant's homes. Latent class analyses were performed to distinguish PA patterns and groups of individuals with similar PA patterns. Results: Four PA patterns were identified: a morning light PA pattern, a mid-day moderate-vigorous PA pattern, an overall inactive pattern and an overall active pattern. Groups of individuals with similar PA patterns differed in ethnicity, dog ownership, and the proportion of roads, sports terrain, larger green and blue space within their residential areas. Conclusions: Four typical hour-by-hour PA patterns, and three groups of individuals with similar patterns were distinguished. It is this combination that can substantially contribute to the development of more tailored policies and interventions. PA patterns were only to a limited extent associated with personal and residential characteristics, suggesting that other factors such as work time regimes, family life and leisure may also have considerable impact on the distribution of PA throughout the day.

Physical and social environmental changes to promote walking among Dutch older adults in deprived neighbourhoods: the NEW.ROADS study.

BACKGROUND: Physical activity is important for healthy ageing, and daily walking is seen as a feasible way to be active at older ages. Yet, many older persons, particularly in lower socioeconomic groups and residing in deprived neighbourhoods, are insufficiently active. Creating a physical and social neighbourhood environment that is more supportive for walking has the potential to improve walking behaviour. Current evidence of the impact of changes to the physical and/or social environmental on walking behaviour is scarce. The aim of the NEW.ROADS study is to design, implement and evaluate changes to the physical and social environment for the purpose of increasing walking behaviour among older residents of deprived neighbourhoods. METHODS: Physical and social environmental interventions were developed by matching scientific evidence on environmental determinants of walking, with input from the target population and stakeholders, and ongoing neighbourhood activities. Specifically, a neighbourhood walking route was designed and marked, and neighbourhood walking groups were organised. These environmental interventions were evaluated in a four-armed experimental study. In addition, the design of the study to evaluate the effect of these environmental changes on walking behaviour is described. DISCUSSION: Designing and implementing environmental interventions is a complex endeavour, challenged by limited available theory and evidence. Input from the target population and professional stakeholders is essential, but may also put constraints on the evaluation. TRIAL REGISTRATION: NTR3800 (registered 9/1/2013).

Field validation of protocols developed to evaluate in-line mastitis detection systems.

This paper reports on a field validation of previously developed protocols for evaluating the performance of in-line mastitis-detection systems. The protocols outlined 2 requirements of these systems: (1) to detect cows with clinical mastitis (CM) promptly and accurately to enable timely and appropriate treatment and (2) to identify cows with high somatic cell count (SCC) to manage bulk milk SCC levels. Gold standard measures, evaluation tests, performance measures, and performance targets were proposed. The current study validated the protocols on commercial dairy farms with automated in-line mastitis-detection systems using both electrical conductivity (EC) and SCC sensor systems that both monitor at whole-udder level. The protocol for requirement 1 was applied on 3 commercial farms. For requirement 2, the protocol was applied on 6 farms; 3 of them had low bulk milk SCC (128×10(3) cells/mL) and were the same farms as used for field evaluation of requirement 1. Three farms with high bulk milk SCC (270×10(3) cells/mL) were additionally enrolled. The field evaluation methodology and results were presented at a workshop including representation from 7 international suppliers of in-line mastitis-detection systems. Feedback was sought on the acceptance of standardized performance evaluation protocols and recommended refinements to the protocols. Although the methodology for requirement 1 was relatively labor intensive and required organizational skills over an extended period, no major issues were encountered during the field validation of both protocols. The validation, thus, proved the protocols to be practical. Also, no changes to the data collection process were recommended by the technology supplier representatives. However, 4 recommendations were made to refine the protocols: inclusion of an additional analysis that ignores small (low-density) clot observations in the definition of CM, extension of the time window from 4 to 5 milkings for timely alerts for CM, setting a maximum number of 10 milkings for the time window to detect a CM episode, and presentation of sensitivity for a larger range of false alerts per 1,000 milkings replacing minimum performance targets. The recommended refinements are discussed with suggested changes to the original protocols. The information presented is intended to inform further debate toward achieving international agreement on standard protocols to evaluate performance of in-line mastitis-detection systems.

Devices used by automated milking systems are similarly accurate in estimating milk yield and in collecting a representative milk sample compared with devices used by farms with conventional milk recording.

Information on accuracy of milk-sampling devices used on farms with automated milking systems (AMS) is essential for development of milk recording protocols. The hypotheses of this study were (1) devices used by AMS units are similarly accurate in estimating milk yield and in collecting representative milk samples compared with devices used by certified milk recording providers on farms with conventional milking systems (CMS) and (2) devices used on both AMS and CMS comply with accuracy criteria described by the New Zealand Standard and by the International Committee of Animal Recording (ICAR). Milk recording data from 5 AMS farms were collected during 13 milk recording test days between December 2011 and February 2013. Milk yield was estimated by ICAR-approved milk meters on AMS units. Milk samples were collected over a 48-h period and submitted to an off-site certified laboratory for milk composition analysis. Data were also collected manually from 5 to 10 cows per AMS unit; a complete milking of a cow was weighed to serve as gold standard for milk yield, and 3 milk samples per cow milking were collected and analyzed in the laboratory to serve as gold standards for milk composition. A similar procedure was used during 6 milk recording occasions with devices used during conventional milk recording at a CMS research farm. Farm type, breed, season, and region did not appear to affect accuracy of devices used on AMS units. Milk meters used by AMS units complied with ICAR limits in 12.5 and 25% of the milk recording test days for test bucket weights between 2 and 10kg and for test bucket weights >10kg, respectively. These percentages were 52 and 42%, respectively, for devices used on CMS. Analyzing all samples as one milk recording test day, 1.4% fell outside the 20% difference band for AMS compared with 1.1% of the milk samples for CMS. Devices used by AMS complied with ICAR in 73% of the milk recording test days for fat percentage, compared with 42% of the milk recording test days by devices used at the CMS farm. When analyzing all milk samples as one milk recording test day, 3.5% of the milk samples fell outside the 99% ICAR limit for AMS compared with 17.2% of the milk samples for CMS. Applying the ICAR standards for fat percentage to crude protein percentage and SCC, devices used on AMS were accurate in estimating crude protein percentage but not in estimating SCC. Thus, devices on AMS units did not comply with national nor ICAR standards with regard to milk yield and fat percentage. However, devices used on AMS were similarly or more accurate compared with devices used during conventional milk recording. It is proposed that devices used on AMS units, when calibrated regularly and when set up according to the manufacturer's instruction, have similar or improved accuracy compared with CMS devices. Because the New Zealand industry accepts data from devices currently used by certified providers for milk recording on CMS farms, results imply that the AMS devices should also be permitted to be used for milk recording.

Development of protocols to evaluate in-line mastitis-detection systems.

This paper proposes and discusses a methodology to evaluate the performance of automated mastitis-detection systems with respect to their practical value on farm. The protocols are based on 3 on-farm requirements: (1) to detect cows with clinical mastitis promptly and accurately to enable timely and appropriate treatment, (2) to identify cows with high somatic cell count to manage bulk milk SCC levels, and (3) to report the mastitis infection status of cows at the end of lactation to support decisions on individual cow dry-cow therapy. Separate protocols for each requirement are proposed and discussed, including gold standards, evaluation tests, performance indicators, and performance targets. Aspects that require further research or clarification are identified. Actual field data are used as examples. Further debate is invited, the aim being to achieve international agreement on how to evaluate and report performance of different mastitis-detection technologies. Better performance information will allow farmers to compare different mastitis-detection systems sensibly and fairly before investing. Also, the use of evaluation protocols should help technology providers to refine current, or develop new, automated mastitis-detection systems. Such developments are likely to accelerate adoption of these systems, potentially leading to improved animal health, milk quality, and labor productivity.

Applying additive logistic regression to data derived from sensors monitoring behavioral and physiological characteristics of dairy cows to detect lameness.

The hypothesis was that sensors currently available on farm that monitor behavioral and physiological characteristics have potential for the detection of lameness in dairy cows. This was tested by applying additive logistic regression to variables derived from sensor data. Data were collected between November 2010 and June 2012 on 5 commercial pasture-based dairy farms. Sensor data from weigh scales (liveweight), pedometers (activity), and milk meters (milking order, unadjusted and adjusted milk yield in the first 2 min of milking, total milk yield, and milking duration) were collected at every milking from 4,904 cows. Lameness events were recorded by farmers who were trained in detecting lameness before the study commenced. A total of 318 lameness events affecting 292 cows were available for statistical analyses. For each lameness event, the lame cow's sensor data for a time period of 14 d before observation date were randomly matched by farm and date to 10 healthy cows (i.e., cows that were not lame and had no other health event recorded for the matched time period). Sensor data relating to the 14-d time periods were used for developing univariable (using one source of sensor data) and multivariable (using multiple sources of sensor data) models. Model development involved the use of additive logistic regression by applying the LogitBoost algorithm with a regression tree as base learner. The model's output was a probability estimate for lameness, given the sensor data collected during the 14-d time period. Models were validated using leave-one-farm-out cross-validation and, as a result of this validation, each cow in the data set (318 lame and 3,180 nonlame cows) received a probability estimate for lameness. Based on the area under the curve (AUC), results indicated that univariable models had low predictive potential, with the highest AUC values found for liveweight (AUC=0.66), activity (AUC=0.60), and milking order (AUC=0.65). Combining these 3 sensors improved AUC to 0.74. Detection performance of this combined model varied between farms but it consistently and significantly outperformed univariable models across farms at a fixed specificity of 80%. Still, detection performance was not high enough to be implemented in practice on large, pasture-based dairy farms. Future research may improve performance by developing variables based on sensor data of liveweight, activity, and milking order, but that better describe changes in sensor data patterns when cows go lame.

Understanding the mechanisms linking holistic housing renovations to health and well-being of adults in disadvantaged neighbourhoods: A realist review.

Holistic housing renovations combine physical housing improvements with social and socioeconomic interventions (e.g. referral to social services, debt counselling, involvement in decision-making, promoting social cohesion). This realist review aimed at understanding underlying mechanisms linking holistic housing renovations to health and well-being of adults in disadvantaged neighbourhoods. Following systematic and iterative searching, and relevance and quality appraisals, 18 scientific articles and reports were analysed. We identified three pathways via which physical housing improvements affect health, four pathways via which social and socioeconomic interventions affect health, and two pathways via which both reinforce each other in their health effects. Our findings are theoretically novel, relevant for those conducting holistic housing renovations, and point towards gaps in the literature.

Field evaluation of 2 collar-mounted activity meters for detecting cows in estrus on a large pasture-grazed dairy farm.

This study tested the hypothesis that a commercially available system for detecting estrus based on cow activity would perform similarly to that of typical, visual assessment of mounting indicators placed on the tail head of the cow. The hypothesis was applied to a large, pasture-grazed, seasonal-calving dairy herd, and the technology was tested as a stand-alone system. One of 2 types of commercially available collar-mounted activity meters was fitted to 635 cows, and the activity data collected during the 37-d artificial breeding period were analyzed. The first collar-mounted activity meter monitored activity only (AO collars), whereas the second meter measured activity and rumination characteristics (AR collars). Only activity data were used in the current study. Activity-based estrus alerts were initially identified using the default activity threshold value recommended by the manufacturer, but a range of activity threshold values was then analyzed to determine their effect on estrus detection performance. Milk progesterone data and insemination records were used to identify gold standard positive (n = 835) and negative (n = 22,660) estrus dates, to which activity alerts were compared. Visual assessment of mounting indicators resulted in a manual detection performance of 91.3% sensitivity (SN), 99.8% specificity (SP), and 94.5% positive predictive value (PPV). The AR collars achieved 76.9, 99.4, and 82.4% for SN, SP, and PPV, whereas the AO collars achieved 62.4, 99.3, and 76.6% for SN, SP, and PPV, respectively. The observed performance of the activity systems may be underestimated due to test design and applied assumptions, including determining the date of estrus. Lowering the activity threshold from the default value improved sensitivity but the number of false positive alerts was considered to become unmanageable from a practical perspective as sensitivity reached peak values. Time window analysis, receiver operating characteristic curves, and curves of SN and PPV were found to be useful in the analysis and interpretation of results. They generate relevant performance data that allow for meaningful comparisons between similar studies. Although the 2 activity systems tested did not perform to the high level of manual estrus detection found in this study, the potential exists for these systems to be a valuable tool on farms with lower estrus detection performance or for farmers managing larger herds.

Positron range-free and multi-isotope tomography of positron emitters.

Despite improvements in small animal PET instruments, many tracers cannot be imaged at sufficiently high resolutions due to positron range, while multi-tracer PET is hampered by the fact that all annihilation photons have equal energies. Here we realize multi-isotope and sub-mm resolution PET of isotopes with several mm positron range by utilizing prompt gamma photons that are commonly neglected. A PET-SPECT-CT scanner (VECTor/CT, MILabs, The Netherlands) equipped with a high-energy cluster-pinhole collimator was used to image 124I and a mix of 124I and 18F in phantoms and mice. In addition to positrons (mean range 3.4 mm) 124I emits large amounts of 603 keV prompt gammas that-aided by excellent energy discrimination of NaI-were selected to reconstruct 124I images that are unaffected by positron range. Photons detected in the 511 keV window were used to reconstruct 18F images. Images were reconstructed iteratively using an energy dependent matrix for each isotope. Correction of 18F images for contamination with 124I annihilation photons was performed by Monte Carlo based range modelling and scaling of the 124I prompt gamma image before subtracting it from the 18F image. Additionally, prompt gamma imaging was tested for 89Zr that emits very high-energy prompts (909 keV). In Derenzo resolution phantoms 0.75 mm rods were clearly discernable for 124I, 89Zr and for simultaneously acquired 124I and 18F imaging. Image quantification in phantoms with reservoirs filled with both 124I and 18F showed excellent separation of isotopes and high quantitative accuracy. Mouse imaging showed uptake of 124I in tiny thyroid parts and simultaneously injected 18F-NaF in bone structures. The ability to obtain PET images at sub-mm resolution both for isotopes with several mm positron range and for multi-isotope PET adds to many other unique capabilities of VECTor's clustered pinhole imaging, including simultaneous sub-mm PET-SPECT and theranostic high energy SPECT.

Detection of clinical mastitis with sensor data from automatic milking systems is improved by using decision-tree induction.

The objective was to develop and validate a clinical mastitis (CM) detection model by means of decision-tree induction. For farmers milking with an automatic milking system (AMS), it is desirable that the detection model has a high level of sensitivity (Se), especially for more severe cases of CM, at a very high specificity (Sp). In addition, an alert for CM should be generated preferably at the quarter milking (QM) at which the CM infection is visible for the first time. Data were collected from 9 Dutch dairy herds milking automatically during a 2.5-yr period. Data included sensor data (electrical conductivity, color, and yield) at the QM level and visual observations of quarters with CM recorded by the farmers. Visual observations of quarters with CM were combined with sensor data of the most recent automatic milking recorded for that same quarter, within a 24-h time window before the visual assessment time. Sensor data of 3.5 million QM were collected, of which 348 QM were combined with a CM observation. Data were divided into a training set, including two-thirds of all data, and a test set. Cows in the training set were not included in the test set and vice versa. A decision-tree model was trained using only clear examples of healthy (n=24,717) or diseased (n=243) QM. The model was tested on 105 QM with CM and a random sample of 50,000 QM without CM. While keeping the Se at a level comparable to that of models currently used by AMS, the decision-tree model was able to decrease the number of false-positive alerts by more than 50%. At an Sp of 99%, 40% of the CM cases were detected. Sixty-four percent of the severe CM cases were detected and only 12.5% of the CM that were scored as watery milk. The Se increased considerably from 40% to 66.7% when the time window increased from less than 24h before the CM observation, to a time window from 24h before to 24h after the CM observation. Even at very wide time windows, however, it was impossible to reach an Se of 100%. This indicates the inability to detect all CM cases based on sensor data alone. Sensitivity levels varied largely when the decision tree was validated per herd. This trend was confirmed when decision trees were trained using data from 8 herds and tested on data from the ninth herd. This indicates that when using the decision tree as a generic CM detection model in practice, some herds will continue having difficulties in detecting CM using mastitis alert lists, whereas others will perform well.

Storing, combining and analysing turkey experimental data in the Big Data era.

With the increasing availability of large amounts of data in the livestock domain, we face the challenge to store, combine and analyse these data efficiently. With this study, we explored the use of a data lake for storing and analysing data to improve scalability and interoperability. Data originated from a 2-day animal experiment in which the gait score of approximately 200 turkeys was determined through visual inspection by an expert. Additionally, inertial measurement units (IMUs), a 3D-video camera and a force plate (FP) were installed to explore the effectiveness of these sensors in automating the visual gait scoring. We deployed a data lake using the IMU and FP data of a single day of that animal experiment. This encompasses data from 84 turkeys for which we preprocessed by performing an 'extract, transform and load' (ETL-) procedure. To test scalability of the ETL-procedure, we simulated increasing volumes of the available data from this animal experiment and computed the 'wall time' (elapsed real time) for converting FP data into comma-separated files and storing these files. With a simulated data set of 30 000 turkeys, the wall time reduced from 1 h to less than 15 min, when 12 cores were used compared to 1 core. This demonstrated the ETL-procedure to be scalable. Subsequently, a machine learning (ML) pipeline was developed to test the potential of a data lake to automatically distinguish between two classses, that is, very bad gait scores v. other scores. In conclusion, we have set up a dedicated customized data lake, loaded data and developed a prediction model via the creation of an ML pipeline. A data lake appears to be a useful tool to face the challenge of storing, combining and analysing increasing volumes of data of varying nature in an effective manner.

Pathogen effects on milk yield and composition in chronic subclinical mastitis in dairy cows.

This study aimed to evaluate the effects of chronic subclinical mastitis (CSM) on milk production and component yields in dairy cows. A total of six herds located in the Midwest area of São Paulo State, Brazil were selected. Herds were visited once every 2 weeks to measure milk yield and to collect milk samples from lactating Holstein cows. Milk samples were collected at two stages (1 and 2), and each stage comprised three milk samplings. In stage 1, a total of 117 of 647 cows were diagnosed with CSM based on at least two of three repeated somatic cell counts (SCC) > 2000,000 cells/mL and positive bacterial milk culture results (BC). Cows with CSM were selected for the second stage. In stage 2, selected cows had quarter sampling aseptically collected for BC analyses prior to milking, and quarter milk yield was measured. Milk components (total protein, fat, lactose, and total solids) were measured using mid-infrared spectroscopy. Mammary quarters were considered healthy if all three repeated SCC results were ≤ 200,000 cells/mL and no bacterial growth was detected on BC. All quarters with positive bacterial growth were classified as having (non-chronic) subclinical mastitis when only one of three SCC results were > 200,000 cells/mL, and CSM when at least two of three SCC results were > 200,000 cells/mL. The effects of CSM by type of pathogen on milk and components yield were assessed using a linear mixed model. Mammary quarters with CSM caused by major pathogens had milk loss of 1.1 kg/quarter milking in comparison to healthy quarters. Milk losses were 0.8 and 1.3 kg/quarter milking when CSM was caused by Staphylococcus aureus or environmental streptococci, respectively. In addition, healthy quarters produced more milk components than quarters with CSM caused by major pathogens. Minor pathogens causing CSM (non-aureus staphylococci and Corynebacterium spp.) had no effect on milk yield. Quarters with CSM had lower milk and component yields when compared with healthy quarters. Milk losses varied according to the type of pathogen and were higher when associated with major pathogens such as S. aureus and environmental streptococci compared with healthy quarters.