EAACI guidelines on environmental science in allergic diseases and asthma - Leveraging artificial intelligence and machine learning to develop a causality model in exposomics.

Allergic diseases and asthma are intrinsically linked to the environment we live in and to patterns of exposure. The integrated approach to understanding the effects of exposures on the immune system includes the ongoing collection of large-scale and complex data. This requires sophisticated methods to take full advantage of what this data can offer. Here we discuss the progress and further promise of applying artificial intelligence and machine-learning approaches to help unlock the power of complex environmental data sets toward providing causality models of exposure and intervention. We discuss a range of relevant machine-learning paradigms and models including the way such models are trained and validated together with examples of machine learning applied to allergic disease in the context of specific environmental exposures as well as attempts to tie these environmental data streams to the full representative exposome. We also discuss the promise of artificial intelligence in personalized medicine and the methodological approaches to healthcare with the final AI to improve public health.

An overview of the National COVID-19 Chest Imaging Database: data quality and cohort analysis.

BACKGROUND: The National COVID-19 Chest Imaging Database (NCCID) is a centralized database containing mainly chest X-rays and computed tomography scans from patients across the UK. The objective of the initiative is to support a better understanding of the coronavirus SARS-CoV-2 disease (COVID-19) and the development of machine learning technologies that will improve care for patients hospitalized with a severe COVID-19 infection. This article introduces the training dataset, including a snapshot analysis covering the completeness of clinical data, and availability of image data for the various use-cases (diagnosis, prognosis, longitudinal risk). An additional cohort analysis measures how well the NCCID represents the wider COVID-19-affected UK population in terms of geographic, demographic, and temporal coverage. FINDINGS: The NCCID offers high-quality DICOM images acquired across a variety of imaging machinery; multiple time points including historical images are available for a subset of patients. This volume and variety make the database well suited to development of diagnostic/prognostic models for COVID-associated respiratory conditions. Historical images and clinical data may aid long-term risk stratification, particularly as availability of comorbidity data increases through linkage to other resources. The cohort analysis revealed good alignment to general UK COVID-19 statistics for some categories, e.g., sex, whilst identifying areas for improvements to data collection methods, particularly geographic coverage. CONCLUSION: The NCCID is a growing resource that provides researchers with a large, high-quality database that can be leveraged both to support the response to the COVID-19 pandemic and as a test bed for building clinically viable medical imaging models.

Learning to see the invisible: A data-driven approach to finding the underlying patterns of abnormality in visually normal brain magnetic resonance images in patients with temporal lobe epilepsy.

OBJECTIVE: To find the covert patterns of abnormality in patients with unilateral temporal lobe epilepsy (TLE) and visually normal brain magnetic resonance images (MRI-negative), comparing them to those with visible abnormalities (MRI-positive). METHODS: We used multimodal brain MRI from patients with unilateral TLE and employed contemporary machine learning methods to predict the known laterality of seizure onset in 104 subjects (82 MRI-positive, 22 MRI-negative). A visualization approach entitled "Importance Maps" was developed to highlight image features predictive of seizure laterality in both the MRI-positive and MRI-negative cases. RESULTS: Seizure laterality could be predicted with an area under the receiver operating characteristic curve of 0.981 (95% confidence interval [CI] =0.974-0.989) in MRI-positive and 0.842 (95% CI = 0.736-0.949) in MRI-negative cases. The known image features arising from the hippocampus were the leading predictors of seizure laterality in the MRI-positive cases, whereas widespread temporal lobe abnormalities were revealed in the MRI-negative cases. SIGNIFICANCE: Covert abnormalities not discerned on visual reading were detected in MRI-negative TLE, with a spatial pattern involving the whole temporal lobe, rather than just the hippocampus. This suggests that MRI-negative TLE may be associated with subtle but widespread temporal lobe abnormalities. These abnormalities merit close inspection and postacquisition processing if there is no overt lesion.

Low frequency oscillating gradient spin-echo sequences improve sensitivity to axon diameter: An experimental study in viable nerve tissue.

Mapping axon diameters within the central and peripheral nervous system could play an important role in our understanding of nerve pathways, and help diagnose and monitor an array of neurological disorders. Numerous diffusion MRI methods have been proposed for imaging axon diameters, most of which use conventional single diffusion encoding (SDE) spin echo sequences. However, a growing number of studies show that oscillating gradient spin echo (OGSE) sequences can provide additional advantages over conventional SDE sequences. Recent theoretical results suggest that this is especially the case in realistic scenarios, such as when fibres have unknown or dispersed orientation. In the present study, we adopt the ActiveAx approach to experimentally investigate the extent of these advantages by comparing the performances of SDE and trapezoidal OGSE in viable nerve tissue. We optimise SDE and OGSE ActiveAx protocols for a rat peripheral nerve tissue and test their performance using Monte Carlo simulations and a 800 mT/m gradient strength pre-clinical imaging experiment. The imaging experiment uses excised sciatic nerve from a rat's leg placed in a MRI compatible viable isolated tissue (VIT) maintenance chamber, which keeps the tissue in a viable physiological state that preserves the structural complexity of the nerve and enables lengthy scan times. We compare model estimates to histology, which we perform on the nerve post scanning. Optimisation produces a three-shell SDE and OGSE ActiveAx protocol, with the OGSE protocol consisting of one SDE sequence and two low-frequency oscillating gradient waveform sequences. Both simulation and imaging results show that the OGSE ActiveAx estimates of the axon diameter index have a higher accuracy and a higher precision compared to those from SDE. Histology estimates of the axon diameter index in our nerve tissue samples are 4-5.8 µm and these are excellently matched with the OGSE estimates 4.2-6.5 µm, while SDE overestimates at 5.2-8 µm for the same sample. We found OGSE estimates to be more precise with on average a 0.5 µm standard deviation compared to the SDE estimates which have a 2 µm standard deviation. When testing the robustness of the estimates when the number of the diffusion gradient directions reduces, we found that both OGSE and SDE estimates are affected, however OGSE is more robust to these changes than the SDE. Overall, these results suggest, quantitatively and in in vivo conditions, that low-frequency OGSE sequences may provide improved accuracy of axon diameter mapping compared to standard SDE sequences.

Spatial variation of heart failure and air pollution in Warwickshire, UK: an investigation of small scale variation at the ward-level.

OBJECTIVES: To map using geospatial modelling techniques the morbidity and mortality caused by heart failure within Warwickshire to characterise and quantify any influence of air pollution on these risks. DESIGN: Cross-sectional. SETTING: Warwickshire, UK. PARTICIPANTS: Data from all of the 105 current Warwickshire County wards were collected on hospital admissions and deaths due to heart failure. RESULTS: In multivariate analyses, the presence of higher mono-nitrogen oxide (NOx) in a ward (3.35:1.89, 4.99), benzene (Ben) (31.9:8.36, 55.85) and index of multiple deprivation (IMD; 0.02: 0.01, 0.03), were consistently associated with a higher risk of heart failure morbidity. Particulate matter (Pm; -12.93: -20.41, -6.54) was negatively associated with the risk of heart failure morbidity. No association was found between sulfur dioxide (SO2) and heart failure morbidity. The risk of heart failure mortality was higher in wards with a higher NOx (4.30: 1.68, 7.37) and wards with more inhabitants 50+ years old (1.60: 0.47, 2.92). Pm was negatively associated (-14.69: -23.46, -6.50) with heart failure mortality. SO2, Ben and IMD scores were not associated with heart failure mortality. There was a prominent variation in heart failure morbidity and mortality risk across wards, the highest risk being in the regions around Nuneaton and Bedworth. CONCLUSIONS: This study showed distinct spatial patterns in heart failure morbidity and mortality, suggesting the potential role of environmental factors beyond individual-level risk factors. Air pollution levels should therefore be taken into account when considering the wider determinants of public health and the impact that changes in air pollution might have on the health of a population.