Using Object-Oriented Simulation to Assess the Impact of the Frequency and Accuracy of Mobility Scoring on the Estimation of Epidemiological Parameters for Lameness in Dairy Herds.

Mobility scoring data can be used to estimate the prevalence, incidence, and duration of lameness in dairy herds. Mobility scoring is often performed infrequently with variable sensitivity, but how this impacts the estimation of lameness parameters is largely unknown. We developed a simulation model to investigate the impact of the frequency and accuracy of mobility scoring on the estimation of lameness parameters for different herd scenarios. Herds with a varying prevalence (10, 30, or 50%) and duration (distributed around median days 18, 36, 54, 72, or 108) of lameness were simulated at daily time steps for five years. The lameness parameters investigated were prevalence, duration, new case rate, time to first lameness, and probability of remaining sound in the first year. True parameters were calculated from daily data and compared to those calculated when replicating different frequencies (weekly, two-weekly, monthly, quarterly), sensitivities (60-100%), and specificities (95-100%) of mobility scoring. Our results showed that over-estimation of incidence and under-estimation of duration can occur when the sensitivity and specificity of mobility scoring are <100%. This effect increases with more frequent scoring. Lameness prevalence was the only parameter that could be estimated with reasonable accuracy when simulating quarterly mobility scoring. These findings can help inform mobility scoring practices and the interpretation of mobility scoring data.

Quantification of the effect of in utero events on lifetime resilience in dairy cows.

Currently, the dairy industry is facing many challenges that could affect its sustainability, including climate change and public perception of the industry. As a result, interest is increasing in the concept of identifying resilient animals, those with a long productive lifespan, as well as good reproductive performance and milk yield. There is much evidence that events in utero, that is, the developmental origins of health and disease hypothesis, alter the life-course health of offspring and we hypothesized that these could alter resilience in calves, where resilience is identified using lifetime data. The aim of this study was to quantify lifetime resilience scores (LRS) using an existing scoring system, based on longevity with secondary corrections for age at first calving and calving interval, and to quantify the effects of in utero events on the LRS using 2 datasets. The first was a large dataset of cattle on 83 farms in Great Britain born from 2006 to 2015 and the second was a smaller, more granular dataset of cattle born between 2003 and 2015 in the Langhill research herd at Scotland's Rural College. Events during dam's pregnancy included health events (lameness, mastitis, use of an antibiotic or anti-inflammatory medication), the effect of heat stress as measured by temperature-humidity index, and perturbations in milk yield and quality (somatic cell count, percentage fat, percentage protein and fat:protein ratio). Daughters born to dams that experienced higher temperature-humidity indexes while they were in utero during the first and third trimesters of pregnancy had lower LRS. Daughter LRS were also lower where milk yields or median fat percentages in the first trimester were low, and when milk yields were high in the third trimester. Dam LRS was positively associated with LRS of their offspring; however, as parity of the dam increased, LRS of their calves decreased. Similarly, in the Langhill herd, dams of a higher parity produced calves with lower LRS. Additionally, dams that recorded a high maximum locomotion score in the third trimester of pregnancy were negatively associated with lower calf LRS in the Langhill herd. Our results suggest that events that occur during pregnancy have lifelong consequences for the calf's lifetime performance. However, experience of higher temperature-humidity indexes, higher dam LRS, and mothers in higher parities explained a relatively small proportion of variation in offspring LRS, which suggests that other factors play a substantial role in determining calf LRS. Although "big data" can contain a considerable amount of noise, similar findings between the 2 datasets indicate it is likely these findings are real.

Improvement of mammary gland health in 81 'sentinel herds' in England and Scotland between 2012 and 2021.

BACKGROUND: Achieving a reduction in mastitis in dairy cows is a common industry goal, but there is no recent peer-reviewed record of progress in the UK. METHODS: A convenience sample of 125 herds in England and Scotland was recruited based on the quality of records in 2016, willingness to participate and representative geographical distribution. Individual cow somatic cell counts and clinical mastitis data from 2012 to 2021 were summarised annually, and temporal changes were analysed. Eighty-one herds had sufficient data for comparison between 2012 and 2021, for one or more parameters. RESULTS: Over this period, the median incidence rate of clinical mastitis decreased from 40.0 to 21.0 cases per 100 cows per year (p < 0.001), with improvement in both lactation and dry period indicators. Lactation new infection rate calculated from individual cow somatic cell counts fell from 8.75% to 5.95% (p < 0.001), dry period new infection rate fell from 16.8% to 14.1% (p < 0.05) and proportion of cows over 200,000 cells/mL fell from 20.0% to 14.3% (p < 0.001). LIMITATIONS: Data were necessarily from herds with good records and do not provide absolute values for the industry. CONCLUSION: The findings reflect good progress over a 10-year period in a cohort of well-recorded herds and align with other national datasets.

The use of machine learning to predict somatic cell count status in dairy cows post-calving.

Udder health remains a priority for the global dairy industry to reduce pain, economic losses, and antibiotic usage. The dry period is a critical time for the prevention of new intra-mammary infections and it provides a point for curing existing intra-mammary infections. Given the wealth of udder health data commonly generated through routine milk recording and the importance of udder health to the productivity and longevity of individual cows, an opportunity exists to extract greater value from cow-level data to undertake risk-based decision-making. The aim of this research was to construct a machine learning model, using routinely collected farm data, to make probabilistic predictions at drying off for an individual cow's risk of a raised somatic cell count (hence intra-mammary infection) post-calving. Anonymized data were obtained as a large convenience sample from 108 UK dairy herds that undertook regular milk recording. The outcome measure evaluated was the presence of a raised somatic cell count in the 30 days post-calving in this observational study. Using a 56-farm training dataset, machine learning analysis was performed using the extreme gradient boosting decision tree algorithm, XGBoost. External validation was undertaken on a separate 28-farm test dataset. Statistical assessment to evaluate model performance using the external dataset returned calibration plots, a Scaled Brier Score of 0.095, and a Mean Absolute Calibration Error of 0.009. Test dataset model calibration performance indicated that the probability of a raised somatic cell count post-calving was well differentiated across probabilities to allow an end user to apply group-level risk decisions. Herd-level new intra-mammary infection rate during the dry period was a key driver of the probability that a cow had a raised SCC post-calving, highlighting the importance of optimizing environmental hygiene conditions. In conclusion, this research has determined that probabilistic classification of the risk of a raised SCC in the 30 days post-calving is achievable with a high degree of certainty, using routinely collected data. These predicted probabilities provide the opportunity for farmers to undertake risk decision-making by grouping cows based on their probabilities and optimizing management strategies for individual cows immediately after calving, according to their likelihood of intra-mammary infection.

Emerging Roles for Artificial Intelligence in Heart Failure Imaging.

Artificial intelligence (AI) applications are expanding in cardiac imaging. AI research has shown promise in workflow optimization, disease diagnosis, and integration of clinical and imaging data to predict patient outcomes. The diagnostic and prognostic paradigm of heart failure is heavily reliant on cardiac imaging. As AI becomes increasingly validated and integrated into clinical practice, AI influence on heart failure management will grow. This review discusses areas of current research and potential clinical applications in AI as applied to heart failure cardiac imaging.

Performance of tumour microenvironment deconvolution methods in breast cancer using single-cell simulated bulk mixtures.

Cells within the tumour microenvironment (TME) can impact tumour development and influence treatment response. Computational approaches have been developed to deconvolve the TME from bulk RNA-seq. Using scRNA-seq profiling from breast tumours we simulate thousands of bulk mixtures, representing tumour purities and cell lineages, to compare the performance of nine TME deconvolution methods (BayesPrism, Scaden, CIBERSORTx, MuSiC, DWLS, hspe, CPM, Bisque, and EPIC). Some methods are more robust in deconvolving mixtures with high tumour purity levels. Most methods tend to mis-predict normal epithelial for cancer epithelial as tumour purity increases, a finding that is validated in two independent datasets. The breast cancer molecular subtype influences this mis-prediction. BayesPrism and DWLS have the lowest combined numbers of false positives and false negatives, and have the best performance when deconvolving granular immune lineages. Our findings highlight the need for more single-cell characterisation of rarer cell types, and suggest that tumour cell compositions should be considered when deconvolving the TME.

A comprehensive study of skeletal muscle imaging in FHL1-related reducing body myopathy.

OBJECTIVE: FHL1-related reducing body myopathy is an ultra-rare, X-linked dominant myopathy. In this cross-sectional study, we characterize skeletal muscle ultrasound, muscle MRI, and cardiac MRI findings in FHL1-related reducing body myopathy patients. METHODS: Seventeen patients (11 male, mean age 35.4, range 12-76 years) from nine independent families with FHL1-related reducing body myopathy underwent clinical evaluation, muscle ultrasound (n = 11/17), and lower extremity muscle MRI (n = 14/17), including Dixon MRI (n = 6/17). Muscle ultrasound echogenicity was graded using a modified Heckmatt scale. T1 and STIR axial images of the lower extremity muscles were evaluated for pattern and distribution of abnormalities. Quantitative analysis of intramuscular fat fraction was performed using the Dixon MRI images. Cardiac studies included electrocardiogram (n = 15/17), echocardiogram (n = 17/17), and cardiac MRI (n = 6/17). Cardiac muscle function, T1 maps, T2-weighted black blood images, and late gadolinium enhancement patterns were analyzed. RESULTS: Muscle ultrasound showed a distinct pattern of increased echointensity in skeletal muscles with a nonuniform, multifocal, and "geographical" distribution, selectively involving the deeper fascicles of muscles such as biceps and tibialis anterior. Lower extremity muscle MRI showed relative sparing of gluteus maximus, rectus femoris, gracilis, and lateral gastrocnemius muscles and an asymmetric and multifocal, "geographical" pattern of T1 hyperintensity within affected muscles. Cardiac studies revealed mild and nonspecific abnormalities on electrocardiogram and echocardiogram with unremarkable cardiac MRI studies. INTERPRETATION: Skeletal muscle ultrasound and muscle MRI reflect the multifocal aggregate formation in muscle in FHL1-related reducing body myopathy and are practical and informative tools that can aid in diagnosis and monitoring of disease progression.

Atherosclerosis Imaging Quantitative Computed Tomography (AI-QCT) to guide referral to invasive coronary angiography in the randomized controlled CONSERVE trial.

AIMS: We compared diagnostic performance, costs, and association with major adverse cardiovascular events (MACE) of clinical coronary computed tomography angiography (CCTA) interpretation versus semiautomated approach that use artificial intelligence and machine learning for atherosclerosis imaging-quantitative computed tomography (AI-QCT) for patients being referred for nonemergent invasive coronary angiography (ICA). METHODS: CCTA data from individuals enrolled into the randomized controlled Computed Tomographic Angiography for Selective Cardiac Catheterization trial for an American College of Cardiology (ACC)/American Heart Association (AHA) guideline indication for ICA were analyzed. Site interpretation of CCTAs were compared to those analyzed by a cloud-based software (Cleerly, Inc.) that performs AI-QCT for stenosis determination, coronary vascular measurements and quantification and characterization of atherosclerotic plaque. CCTA interpretation and AI-QCT guided findings were related to MACE at 1-year follow-up. RESULTS: Seven hundred forty-seven stable patients (60 ± 12.2 years, 49% women) were included. Using AI-QCT, 9% of patients had no CAD compared with 34% for clinical CCTA interpretation. Application of AI-QCT to identify obstructive coronary stenosis at the ≥50% and ≥70% threshold would have reduced ICA by 87% and 95%, respectively. Clinical outcomes for patients without AI-QCT-identified obstructive stenosis was excellent; for 78% of patients with maximum stenosis < 50%, no cardiovascular death or acute myocardial infarction occurred. When applying an AI-QCT referral management approach to avoid ICA in patients with <50% or <70% stenosis, overall costs were reduced by 26% and 34%, respectively. CONCLUSIONS: In stable patients referred for ACC/AHA guideline-indicated nonemergent ICA, application of artificial intelligence and machine learning for AI-QCT can significantly reduce ICA rates and costs with no change in 1-year MACE.

ROAD: The Road Event Awareness Dataset for Autonomous Driving.

Humans drive in a holistic fashion which entails, in particular, understanding dynamic road events and their evolution. Injecting these capabilities in autonomous vehicles can thus take situational awareness and decision making closer to human-level performance. To this purpose, we introduce the ROad event Awareness Dataset (ROAD) for Autonomous Driving, to our knowledge the first of its kind. ROAD is designed to test an autonomous vehicle's ability to detect road events, defined as triplets composed by an active agent, the action(s) it performs and the corresponding scene locations. ROAD comprises videos originally from the Oxford RobotCar Dataset, annotated with bounding boxes showing the location in the image plane of each road event. We benchmark various detection tasks, proposing as a baseline a new incremental algorithm for online road event awareness termed 3D-RetinaNet. We also report the performance on the ROAD tasks of Slowfast and YOLOv5 detectors, as well as that of the winners of the ICCV2021 ROAD challenge, which highlight the challenges faced by situation awareness in autonomous driving. ROAD is designed to allow scholars to investigate exciting tasks such as complex (road) activity detection, future event anticipation and continual learning. The dataset is available at https://github.com/gurkirt/road-dataset; the baseline can be found at https://github.com/gurkirt/3D-RetinaNet.

Comparative performance of composite measures from two phase III clinical trials of ixekizumab in psoriatic arthritis.

BACKGROUND/OBJECTIVE: The aim of this study was to evaluate relative performance of composite measures in psoriatic arthritis and assess the impact of structural damage and functional disability on outcomes during ixekizumab treatment. METHODS: Data from SPIRIT-P1 and SPIRIT-P2 were analysed to evaluate the effect of ixekizumab on achievement of low disease activity (LDA) and remission with the minimal disease activity (MDA) and very low disease activity (VLDA) composite, Disease Activity index for Psoriatic Arthritis (DAPSA), Psoriatic Arthritis Disease Activity Score, GRAppa Composite ScorE and modified Composite Psoriatic Disease Activity Index (mCPDAI). Performance was compared by quantifying residual symptom burden and the impact of structural damage and functional disability. RESULTS: Significantly more ixekizumab-treated patients achieved treatment targets at week 24 versus placebo assessed with all composites. More patients achieved targets assessed by mCPDAI and DAPSA than other composites. Residual disease activity was similar between composites, but residual high patient-reported outcomes (PROs) and functional disability were more frequent when assessed with mCPDAI and DAPSA. Achievement of treatment targets was reduced by high baseline levels of structural damage and functional disability. CONCLUSION: Residual disease activity was similar in patients achieving treatment targets assessed with all composites, but residual high PROs and functional disability were more common when assessed with mCPDAI and DAPSA, most likely due to the absence/attenuated functional assessment in these composites. High baseline levels of structural damage and functional disability attenuated response rates with all composites, affecting MDA/VLDA most prominently; LDA may be the most appropriate target in these patients. TRIAL REGISTRATION NUMBER: NCT01695239.

Potential of ESBL-producing Escherichia coli selection in bovine feces after intramammary administration of first generation cephalosporins using in vitro experiments.

Selection and spread of Extended Spectrum Beta-Lactamase (ESBL) -producing Enterobacteriaceae within animal production systems and potential spillover to humans is a major concern. Intramammary treatment of dairy cows with first-generation cephalosporins is a common practice and potentially selects for ESBL-producing Enterobacteriaceae, although it is unknown whether this really occurs in the bovine fecal environment. We aimed to study the potential effects of intramammary application of cephapirin (CP) and cefalonium (CL) to select for ESBL-producing Escherichia coli in the intestinal content of treated dairy cows and in manure slurry, using in vitro competition experiments with ESBL and non-ESBL E. coli isolates. No selection of ESBL-producing E. coli was observed at or below concentrations of 0.8 µg/ml and 4.0 µg/ml in bovine feces for CP and CL, respectively, and at or below 8.0 µg/ml and 4.0 µg/ml, respectively, in manure slurry. We calculated that the maximum concentration of CP and CL after intramammary treatment with commercial products will not exceed 0.29 µg/ml in feces and 0.03 µg/ml in manure slurry. Therefore, the results of this study did not find evidence supporting the selection of ESBL-producing E. coli in bovine feces or in manure slurry after intramammary use of commercial CP or CL-containing products.

Quantifiable brain atrophy synthesis for benchmarking of cortical thickness estimation methods.

Cortical thickness (CTh) is routinely used to quantify grey matter atrophy as it is a significant biomarker in studying neurodegenerative and neurological conditions. Clinical studies commonly employ one of several available CTh estimation software tools to estimate CTh from brain MRI scans. In recent years, machine learning-based methods emerged as a faster alternative to the main-stream CTh estimation methods (e.g. FreeSurfer). Evaluation and comparison of CTh estimation methods often include various metrics and downstream tasks, but none fully covers the sensitivity to sub-voxel atrophy characteristic of neurodegeneration. In addition, current evaluation methods do not provide a framework for the intra-method region-wise evaluation of CTh estimation methods. Therefore, we propose a method for brain MRI synthesis capable of generating a range of sub-voxel atrophy levels (global and local) with quantifiable changes from the baseline scan. We further create a synthetic test set and evaluate four different CTh estimation methods: FreeSurfer (cross-sectional), FreeSurfer (longitudinal), DL+DiReCT and HerstonNet. DL+DiReCT showed superior sensitivity to sub-voxel atrophy over other methods in our testing framework. The obtained results indicate that our synthetic test set is suitable for benchmarking CTh estimation methods on both global and local scales as well as regional inter-and intra-method performance comparison.

Cardiovascular Imaging in Pregnancy: Valvulopathy, Hypertrophic Cardiomyopathy, and Aortopathy.

Pregnancy is associated with profound hemodynamic changes that are particularly impactful in patients with underlying cardiovascular disease. Management of pregnant women with cardiovascular disease requires careful evaluation that considers the well-being of both the woman and the developing fetus. Clinical assessment begins before pregnancy and continues throughout gestation into the post-partum period and is supplemented by cardiac imaging. This review discusses the role of imaging, specifically echocardiography, cardiac MRI, and cardiac CT, in pregnant women with valvular diseases, hypertrophic cardiomyopathy, and aortic pathology.

Identifying associations between management practices and antimicrobial resistances of sentinel bacteria recovered from bulk tank milk on dairy farms.

There is increasing emphasis on the need to reduce antimicrobial use (AMU) on dairy farms to reduce the emergence of resistant bacteria which could compromise animal health and impact human medicine. In addition to AMU, the role of farm management is an area of growing interest and represents an alternative route for possible interventions. The aim of this study was to evaluate the impact of farm management practices and AMU on resistances of sentinel bacteria in bulk milk. Dairy farms from two, geographically separate locations within the British Isles were recruited as part of two study groups. Farm management data from study group 1 (n = 125) and study group 2 (n = 16) were collected by means of a face-to-face questionnaire with farmers carried out during farm visits. For study group 2, additional data on AMU was collated from veterinary medicine sales records. Sentinel bacterial species (Enterococcus spp. and E. coli), which have been reported to be of value in antimicrobial resistance (AMR) studies, were isolated from bulk tank milk to monitor antimicrobial susceptibilities by means of minimum inhibitory concentrations (MICs). MIC data for both groups was used to generate an overall "score" for each farm. For both groups, this overall farm mean MIC was used as the outcome variable to evaluate the impact of farm management and AMU. This was achieved through use of elastic net modelling, a regularised regression method which also featured a bootstrapping procedure to produce robust models. Inference of models was based on covariate stabilities and bootstrapped P-values to identify farm management and AMU practices that have significant effects on MICs of sentinel bacteria. Practices which were found to be of importance with respect to Enterococcus spp. included management of slurry, external entry of livestock to the dairy herd, use of bedding materials and conditioners, cubicle cleaning routines and antibiotic practices, including use of ß-lactams and fluoroquinolones. Practices deemed to be of importance for E. coli MICs included cubicle and bedding management practices, teat preparation routines at milking and the milking procedure itself. We conclude that a variety of routine farm management practices are associated with MICs of sentinel bacteria in bulk milk. Amendment of these practices offers additional possible routes of intervention, alongside alterations to AMU, to mitigate the emergence and dissemination of AMR on dairy farms.

Validation and algorithmic audit of a deep learning system for the detection of proximal femoral fractures in patients in the emergency department: a diagnostic accuracy study.

BACKGROUND: Proximal femoral fractures are an important clinical and public health issue associated with substantial morbidity and early mortality. Artificial intelligence might offer improved diagnostic accuracy for these fractures, but typical approaches to testing of artificial intelligence models can underestimate the risks of artificial intelligence-based diagnostic systems. METHODS: We present a preclinical evaluation of a deep learning model intended to detect proximal femoral fractures in frontal x-ray films in emergency department patients, trained on films from the Royal Adelaide Hospital (Adelaide, SA, Australia). This evaluation included a reader study comparing the performance of the model against five radiologists (three musculoskeletal specialists and two general radiologists) on a dataset of 200 fracture cases and 200 non-fractures (also from the Royal Adelaide Hospital), an external validation study using a dataset obtained from Stanford University Medical Center, CA, USA, and an algorithmic audit to detect any unusual or unexpected model behaviour. FINDINGS: In the reader study, the area under the receiver operating characteristic curve (AUC) for the performance of the deep learning model was 0·994 (95% CI 0·988-0·999) compared with an AUC of 0·969 (0·960-0·978) for the five radiologists. This strong model performance was maintained on external validation, with an AUC of 0·980 (0·931-1·000). However, the preclinical evaluation identified barriers to safe deployment, including a substantial shift in the model operating point on external validation and an increased error rate on cases with abnormal bones (eg, Paget's disease). INTERPRETATION: The model outperformed the radiologists tested and maintained performance on external validation, but showed several unexpected limitations during further testing. Thorough preclinical evaluation of artificial intelligence models, including algorithmic auditing, can reveal unexpected and potentially harmful behaviour even in high-performance artificial intelligence systems, which can inform future clinical testing and deployment decisions. FUNDING: None.

Artificial Intelligence Advancements in the Cardiovascular Imaging of Coronary Atherosclerosis.

Coronary artery disease is a leading cause of death worldwide. There has been a myriad of advancements in the field of cardiovascular imaging to aid in diagnosis, treatment, and prevention of coronary artery disease. The application of artificial intelligence in medicine, particularly in cardiovascular medicine has erupted in the past decade. This article serves to highlight the highest yield articles within cardiovascular imaging with an emphasis on coronary CT angiography methods for % stenosis evaluation and atherosclerosis quantification for the general cardiologist. The paper finally discusses the evolving paradigm of implementation of artificial intelligence in real world practice.

The relationship between physical activity, BMI, circadian rhythm, and sleep with cognition in bipolar disorder.

BACKGROUND: Cognitive deficits affect a significant proportion of patients with bipolar disorder (BD). Problems with sustained attention have been found independent of mood state and the causes are unclear. We aimed to investigate whether physical parameters such as activity levels, sleep, and body mass index (BMI) may be contributing factors. METHODS: Forty-six patients with BD and 42 controls completed a battery of neuropsychological tests and wore a triaxial accelerometer for 21 days which collected information on physical activity, sleep, and circadian rhythm. Ex-Gaussian analyses were used to characterise reaction time distributions. We used hierarchical regression analyses to examine whether physical activity, BMI, circadian rhythm, and sleep predicted variance in the performance of cognitive tasks. RESULTS: Neither physical activity, BMI, nor circadian rhythm predicted significant variance on any of the cognitive tasks. However, the presence of a sleep abnormality significantly predicted a higher intra-individual variability of the reaction time distributions on the Attention Network Task. CONCLUSIONS: This study suggests that there is an association between sleep abnormalities and cognition in BD, with little or no relationship with physical activity, BMI, and circadian rhythm.

Ixekizumab Demonstrates Consistent Efficacy Versus Adalimumab in Biologic Disease-Modifying Anti-rheumatic Drug-Naïve Psoriatic Arthritis Patients Regardless of Psoriasis Severity: 52-Week Post Hoc Results from SPIRIT-H2H.

INTRODUCTION: Ixekizumab, a selective interleukin-17A antagonist, was compared with adalimumab in the SPIRIT-H2H study (NCT03151551) in patients with psoriatic arthritis (PsA) and concomitant psoriasis. This post hoc analysis reports outcomes to week 52 in patients from SPIRIT-H2H, stratified by baseline psoriasis severity. METHODS: SPIRIT-H2H was a 52-week, multicenter, randomized, open-label, rater-blinded, parallel-group study of biologic disease-modifying antirheumatic drug (DMARD)-naïve patients (N = 566) with PsA and active psoriasis (≥ 3% body surface area involvement). Patients were randomized to ixekizumab or adalimumab (1:1) with stratification by baseline concomitant use of conventional synthetic DMARDs and psoriasis severity (with/without moderate-to-severe psoriasis). Patients received on-label dosing according to psoriasis severity. The primary endpoint was the proportion of patients simultaneously achieving ≥ 50% improvement in American College of Rheumatology criteria (ACR50) and 100% improvement in Psoriasis Area Severity Index (PASI100) at week 24. Secondary endpoints included musculoskeletal, disease activity (defined by composite indices), skin and nail, quality of life and safety outcomes. In this post hoc analysis, primary and secondary endpoints of SPIRIT-H2H were analyzed by baseline psoriasis severity. RESULTS: A greater proportion of patients achieved the combined endpoint of ACR50 + PASI100 and PASI100 with ixekizumab compared with adalimumab at weeks 24 and 52, regardless of baseline psoriasis severity. ACR response rates were similar for ixekizumab and adalimumab across both patient subgroups. For musculoskeletal outcomes, similar efficacy was seen for ixekizumab and adalimumab, but ixekizumab showed greater responses for skin outcomes regardless of psoriasis severity. The safety profiles of ixekizumab and adalimumab were consistent between subgroups. CONCLUSIONS: Regardless of baseline psoriasis severity, ixekizumab demonstrated greater efficacy than adalimumab with respect to simultaneous achievement of ACR50 + PASI100, and showed consistent and sustained efficacy across PsA-related domains. It also demonstrated higher response rates for skin outcomes. These subgroup analyses highlight the efficacy of ixekizumab in patients with PsA irrespective of the severity of concomitant psoriasis.

Bedding system influences lying behaviour in dairy cows.

BACKGROUND: The nature and depth of bedding material have an important influence on cow lying behaviour and comfort. Increasing use of recycled manure solids (RMS) as bedding led to an investigation of the influence of this material on cow lying behaviour. METHODS: Leg mounted accelerometers were used to estimate daily lying time and number and duration of lying bouts in four groups of 40 cows. Each group spent two 2-week periods on each of four bedding systems: deep sand, deep RMS, sawdust on mattresses and RMS on mattresses. RESULTS: Total daily lying times were significantly shorter on both RMS treatments than on sawdust. Number of lying bouts per day was greater on sawdust than any other treatment, while lying bouts were 2.6 min longer on deep RMS and 9.3 min longer on sand, than on sawdust. CONCLUSIONS: Greater depth and apparent softness of bedding material does not necessarily result in longer total daily lying times. RMS may have some characteristics that reduce its attraction as a bedding material for cows. The influence of bedding system on number and duration of lying bouts and the resulting total lying time appear complex.

Deep learning in cancer diagnosis, prognosis and treatment selection.

Deep learning is a subdiscipline of artificial intelligence that uses a machine learning technique called artificial neural networks to extract patterns and make predictions from large data sets. The increasing adoption of deep learning across healthcare domains together with the availability of highly characterised cancer datasets has accelerated research into the utility of deep learning in the analysis of the complex biology of cancer. While early results are promising, this is a rapidly evolving field with new knowledge emerging in both cancer biology and deep learning. In this review, we provide an overview of emerging deep learning techniques and how they are being applied to oncology. We focus on the deep learning applications for omics data types, including genomic, methylation and transcriptomic data, as well as histopathology-based genomic inference, and provide perspectives on how the different data types can be integrated to develop decision support tools. We provide specific examples of how deep learning may be applied in cancer diagnosis, prognosis and treatment management. We also assess the current limitations and challenges for the application of deep learning in precision oncology, including the lack of phenotypically rich data and the need for more explainable deep learning models. Finally, we conclude with a discussion of how current obstacles can be overcome to enable future clinical utilisation of deep learning.