<p dir="ltr">Efficient management of plant diseases and their spread within fields requires a system capable of early and accurate disease identification and its severity estimation. Many plant diseases have distinct visual symptoms, which can be used to correctly identify, classify, and manage them. Recent technological advancements have led to increased adoption of deep neural networks (DNN) for developing deep learning (DL)-based computer vision systems. An accurate disease identification and severity estimation system using a DL-based computer vision framework is critical for efficiently managing corn diseases under field conditions and further restricting the spread of disease. Image processing and machine learning methods for disease identification and classification have been employed in the last two decades using high-cost sensors that need frequent calibration. Researchers have used low-cost red, green, and blue (RGB) sensors to mostly identify single diseases affecting crops, whereas, in real-world applications, a single leaf can be affected by multiple diseases. This research identifies gaps in knowledge of DL applications to field crops by reviewing 70 research articles published between 1983 and 2022. It creates a much-needed disease database for corn grown under field conditions by adding custom-acquired image data to other publicly available image repositories. The image data was used to train and evaluate the performance of commonly used DL-based image classification models for differentiating single diseases on individual corn leaves under field conditions. However, many disease lesions of different shapes and sizes can simultaneously develop on infected leaves. The performance of DL-based image classification and object detection models was evaluated to accurately identify multiple simultaneous diseases with varying symptoms. Disease identification under field conditions is necessary to implement an effective disease management system. However, recent work has demonstrated poor generalization accuracies of DL models trained on lab-acquired imagery for identifying diseases in the field. Therefore, after achieving promising results for disease identification, DL generalization performance was assessed and improved using different dataset combinations with varying backgrounds. A novel neural network architecture using a hierarchical structure was also proposed, which resulted in improved generalization performance. Additionally, disease severity must be estimated to implement an effective management response. DL models were evaluated to estimate the severity of multiple corn diseases under field conditions using aerial and ground-based platforms to identify specific lesions from above and below the canopy. A progressive web application was designed to empower end users with disease recognition capabilities. Overall, this research reports findings of the performance of deep learning image processing, object detection, and segmentation models for identifying single/multiple diseases on field corn and the development of tools that can potentially be a component of production-ready disease diagnosis systems for implementing effective management practices.</p>

Background: Financial constraints challenge evidence of the effectiveness of dermatological inpatient management. Objective: To evaluate the effectiveness of hospitalization in atopic dermatitis and psoriasis regarding initial and sustained benefits. Methods: Prospective study on adults with psoriasis vulgaris (n = 22) and atopic dermatitis (n = 14). At admission, discharge, and 3 months after discharge, validated outcomes of objective and subjective disease severity were assessed by trained investigators. Results: Hospitalization resulted in substantial benefit in quality of life and clinical disease severity. Looking at mean scores, the observed benefit appeared stable until 3-month follow-up. The analysis of individual patient data revealed significant changes in disease severity between discharge and 3-month follow-up with some patients relapsing, others further improving. Reasons for hospitalization and treatment performed were not related to sustained benefit. Conclusions: In psoriasis vulgaris and atopic dermatitis, hospitalization effectively improved quality of life and clinical disease severity. Further research should focus on prognostic factors for sustained improvement. / Dieser Beitrag ist mit Zustimmung des Rechteinhabers aufgrund einer (DFG-geförderten) Allianz- bzw. Nationallizenz frei zugänglich.

Background: Financial constraints challenge evidence of the effectiveness of dermatological inpatient management. Objective: To evaluate the effectiveness of hospitalization in atopic dermatitis and psoriasis regarding initial and sustained benefits. Methods: Prospective study on adults with psoriasis vulgaris (n = 22) and atopic dermatitis (n = 14). At admission, discharge, and 3 months after discharge, validated outcomes of objective and subjective disease severity were assessed by trained investigators. Results: Hospitalization resulted in substantial benefit in quality of life and clinical disease severity. Looking at mean scores, the observed benefit appeared stable until 3-month follow-up. The analysis of individual patient data revealed significant changes in disease severity between discharge and 3-month follow-up with some patients relapsing, others further improving. Reasons for hospitalization and treatment performed were not related to sustained benefit. Conclusions: In psoriasis vulgaris and atopic dermatitis, hospitalization effectively improved quality of life and clinical disease severity. Further research should focus on prognostic factors for sustained improvement. / Dieser Beitrag ist mit Zustimmung des Rechteinhabers aufgrund einer (DFG-geförderten) Allianz- bzw. Nationallizenz frei zugänglich.

<p>Hyperspectral reflectance data are utilised in many applications, where measured data are processed and converted into physical, chemical and/or biological properties of the target objects and/or processes being studied. It has been proven that crop reflectance data can be used to detect, characterise and quantify disease severity and plant density.</p><p>In this thesis, various methods were proposed and used for detection, characterisation and quantification of disease severity and plant density utilising data acquired by hand-held spectrometers. Following this direction, hyperspectral images provide both spatial and spectral information opening for more efficient analysis.</p><p>Hence, in this thesis, various surface water quality parameters of inland waters have been monitored using hyperspectral images acquired by airborne systems. After processing the images to obtain ground reflectance data, the analysis was performed using similar methods to those of the previous case. Hence, these methods may also find application in future satellite based hyperspectral imaging systems.</p><p>However, the large size of these images raises the need for efficient data reduction. Self organising and learning neural networks, that can follow and preserve the topology of the data, have been shown to be efficient for data reduction. More advanced variants of these neural networks, referred to as the weighted neural networks (WNN), were proposed in this thesis, such as the weighted incremental neural network (WINN), which can be used for efficient reduction, mapping and clustering of large high-dimensional data sets, such as hyperspectral images.</p><p>Finally, the analysis can be reversed to generate spectra from simpler measurements using multiple colour-filter mosaics, as suggested in the thesis. The acquired instantaneous single image, including the mosaic effects, is demosaicked to generate a multi-band image that can finally be transformed into a hyperspectral image.</p>

Hyperspectral reflectance data are utilised in many applications, where measured data are processed and converted into physical, chemical and/or biological properties of the target objects and/or processes being studied. It has been proven that crop reflectance data can be used to detect, characterise and quantify disease severity and plant density. In this thesis, various methods were proposed and used for detection, characterisation and quantification of disease severity and plant density utilising data acquired by hand-held spectrometers. Following this direction, hyperspectral images provide both spatial and spectral information opening for more efficient analysis. Hence, in this thesis, various surface water quality parameters of inland waters have been monitored using hyperspectral images acquired by airborne systems. After processing the images to obtain ground reflectance data, the analysis was performed using similar methods to those of the previous case. Hence, these methods may also find application in future satellite based hyperspectral imaging systems. However, the large size of these images raises the need for efficient data reduction. Self organising and learning neural networks, that can follow and preserve the topology of the data, have been shown to be efficient for data reduction. More advanced variants of these neural networks, referred to as the weighted neural networks (WNN), were proposed in this thesis, such as the weighted incremental neural network (WINN), which can be used for efficient reduction, mapping and clustering of large high-dimensional data sets, such as hyperspectral images. Finally, the analysis can be reversed to generate spectra from simpler measurements using multiple colour-filter mosaics, as suggested in the thesis. The acquired instantaneous single image, including the mosaic effects, is demosaicked to generate a multi-band image that can finally be transformed into a hyperspectral image.

Introduction: Epidemiological studies have indicated that 5-38% of influenza like illnesses (ILI) develop into severe disease due to, among others, factors such as; underlying chronic diseases, age, pregnancy, and viral mutations. There are suggestions that dual or multiple virus infections may affect disease severity. This study investigated the association between co-infection between influenza A viruses and other respiratory viruses and disease severity. Methodology: Datum for samples from North West England tested between January 2007 and June 2012 was analysed for patterns of co-infection between influenza A viruses and ten respiratory viruses. Risk of hospitalization to a general ward ICU or death in single versus mixed infections was assessed using multiple logistic regression models. Results: One or more viruses were identified in 37.8% (11,715/30,975) of samples, of which 10.4% (1,214) were mixed infections and 89.6% (10,501) were single infections. Among patients with influenza A(H1N1)pdm09, co-infections occurred in 4.7% (137⁄2,879) vs. 6.5% (59⁄902) in those with seasonal influenza A virus infection. In general, patients with mixed respiratory virus infections had a higher risk of admission to a general ward (OR: 1.43, 95% CI: 1.2 – 1.7, p = <0.0001) than those with a single infection. Co-infection between seasonal influenza A viruses and influenza B virus was associated with a significant increase in the risk of admission to ICU/ death (OR: 22.0, 95% CI: 2.21 – 219.8 p = 0.008). RSV/seasonal influenza A viruses co-infection also associated with increased risk but this was not statistically significant. For the pandemic influenza A(H1N1)pdm09 virus, RSV and AdV co-infection increased risk of hospitalization to a general ward, whereas Flu B increased risk of admission to ICU/ death, but none of these were statistically significant. Considering only single infections, RSV and hPIV1-3 increased risk of admission to a general ward (OR: 1.49, 95% CI: 1.28 – 1.73, p = <0.0001 and OR: 1.34, 95% CI: 1.003 – 1.8, p = 0.05) and admission to ICU/ death (OR: 1.5, 95% CI: 1.20 – 2.0, p = <0.0001 and OR: 1.60, 95% CI: 1.02 – 2.40, p = 0.04). Conclusion: Co-infection is a significant predictor of disease outcome; there is insufficient public health data on this subject as not all samples sent for investigation of respiratory virus infection are tested for all respiratory viruses. Integration of testing for respiratory viruses’ co-infections into routine clinical practice and R&D on integrated drugs and vaccines for influenza A&B, RSV, and AdV, and development of multi-target diagnostic tests is encouraged.

<p><strong>Background</strong>: Human rhinovirus/enterovirus (HRV/ENT) infections are commonly identified in children with acute respiratory infections (ARIs), but data on their clinical severity remains limited. We compared the clinical severity of HRV/ENT to respiratory syncytial virus (RSV), influenza A/B (FLU) and other common respiratory virus in children.</p> <p><strong>Methods</strong>: Retrospective study of children with ARIs and confirmed single positive viral infections on mid-turbinate swabs by molecular assays. Outcome measures included hospital admission and, for inpatients, a composite end-point consisting of intensive care admission, hospitalization greater than 5 days, oxygen requirements or death.</p> <p><strong>Results</strong>: A total of 116 HRV/ENT, 102 RSV, 99 FLU and 64 other common respiratory viruses were identified. Children with single HRV/ENT infections presented with significantly higher rates of underlying immunosuppressive conditions compared to those with RSV (37.9% vs 13.6%; p</p> <p><strong>Conclusions</strong>: Children with HRV/ENT had a more severe clinical course than those with RSV and FLUA/B infections and often had significant comorbidities. These findings emphasize the importance of considering HRV/ENT infection in children presenting with severe acute respiratory tract infections.</p> / Master of Science (MSc)

Managed care plans purport to improve the health of their members with chronic diseases. How has the growing adoption of Medicare Advantage (MA), the managed care program for Medicare beneficiaries, affected the progression of chronic disease? The literature is rich with articles focusing on managed care organizations' impacts on quality of care, access, patient satisfaction, and costs. However, few studies have analyzed these impacts with respect to market penetration of Medicare managed care. The objective of this research has been to analyze the relationships between the market penetration of MA plans and the progression of chronic diseases among Medicare beneficiaries. The Chronic Disease Severity Index scale (CDSI) was constructed to represent beneficiaries' overall chronic disease states for survey or claims-based data, when more direct clinical measures of disease progression are not available. Using the CDSI on the MEPS survey dataset from AHRQ, we sought to assess the impacts of MA market penetration and other covariates on the overall chronic disease state of Medicare beneficiaries from 2004 through 2008. Though the model explains much of the variation in CDSI change, the author expected the multilevel model would show that MA penetration explains a significant level of variation in CDSI change. However, this hypothesis was not substantiated, and the findings suggest that unmeasured factors may be contributing to additional unexplained heterogeneity. Policymakers should explore opportunities to refine the current MA program. The MA program costs the federal government more than the Traditional Fee-for-Service Medicare program, and there is no definitive evidence that outcomes differ. Within both programs, there is opportunity to experiment with different models of payment, healthcare service delivery and care coordination. The Patient Protection and Affordable Care Act (ACA) contains provisions for innovative demonstration projects in delivery and payment. The effectiveness of these ACA initiatives must be monitored, both for impacts on health outcomes and for economic effects. This research can inform future approaches to outcomes assessment using the CDSI, and multilevel modeling methodologies similar to those employed here. Firms offering MA health plans would be prudent to proactively demonstrate their value to beneficiaries and taxpayers. They should explore means of better monitoring and reporting the longitudinal outcomes of their enrolled beneficiaries. Demonstrating that they can bring value in terms of improved health outcomes will help insure their long-term survival, both in the marketplace and in the political arena. / Graduation date: 2012