No description available.

No description available.

No description available.

No description available.

This dissertation comprises three papers introducing strategies, models, and frameworks to guide pandemic response. The first paper uses a novel mathematical model to analyze the coordination between government and humanitarian non-governmental organizations (NGOs) in response to pandemics. This is a vital form of public-private partnership between governments as the primary source for the humanitarian supplies required during a crisis and aid organizations. This coordination involves the equitable distribution of personal protective equipment, including face masks and face shields among health workers, patients, and the public in hospitals. Considering social costs such as deprivation and equity costs in the model, in addition to the other important classic cost terms, enables managers to organize the best possible response when such outbreaks happen. The second paper introduces a decision support framework designed to assist healthcare managers, and clinical informatics specialists in analyzing and selecting the most appropriate consensus algorithm for their organization's blockchain-based health platforms, with a specific focus on managing pandemic-related information. Blockchain technology holds great potential in addressing pandemics by enhancing security and transparency in various aspects of pandemic tracking and mitigation while promoting public engagements by facilitating real-time exchange of electronic health information. By improving information sharing and coordination among healthcare organizations, it offers more effective response efforts and helps reduce the spread of viruses. However, the performance of consensus algorithms, which are a crucial component of blockchain architecture, can vary, posing a challenge in selecting the appropriate algorithm. To address this, the framework incorporates two techniques: data envelopment analysis (DEA) and the ranking distribution technique. DEA enables the analysis of efficiency without relying solely on expert judgment, providing a more objective assessment. The ranking distribution technique enhances differentiation among algorithms, providing decision-makers with a robust basis for selecting the most suitable blockchain architecture and its associated properties. The third paper focuses on the challenges of disseminating guidance-related information to the public during a pandemic, specifically the role of opinion leaders as reliable sources of information. The study determines the practical characteristics of pandemic opinion leaders on public attitudes using surveys and identifies domain-sensitive pandemic opinion leaders on Twitter based on the discovered characteristics using social network analysis and text mining. The framework's results show that pandemic opinion leaders are active in eight different domains on the Twitter platform. Results also demonstrate that trust is the most influential characteristic of pandemic opinion leaders, while expertise, uniqueness, innovation, and reputation also play important roles. / Doctor of Philosophy / This dissertation presents a collection of three research papers that offer insights and practical techniques and strategies to effectively tackle the challenges posed by pandemics through enhanced information sharing, public engagement, and robust public-private partnerships. The first paper introduces a novel mathematical model that thoroughly examines the collaboration between governments and humanitarian non-governmental organizations (NGOs) during crises such as the Covid-19 pandemic. The model's primary focus is on the equitable distribution of vital supplies, including face masks and shields, to healthcare workers as well as the public. By incorporating considerations of social costs, fairness, and other critical factors, this model aids managers in organizing the most efficient response to initial impacts of outbreaks within a short-term planning horizon. Our primary objective is to ensure the prompt and equitable delivery of essential supplies to individuals in need, achieved primarily through establishing strong public-private partnerships. The second paper proposes a decision support framework for healthcare managers, IT analysts, and clinical informatics specialists to help them effectively analyze consensus algorithms, as the most important layer of blockchain architecture. The framework further helps them select the most suitable algorithm for their organization's blockchain-based health platforms, aligning with specific policies, needs, requirements, and goals in managing pandemic-related information. Blockchain technology offers potential in tracking medical supplies, identifying virus hotspots, and verifying protective equipment authenticity to manage pandemics. By enhancing information sharing and coordination among healthcare organizations, blockchain can minimize virus spread and improve overall response efforts. The proposed framework reduces reliance on expert judgment and addresses data uncertainty when selecting proper algorithms for blockchain-based information management systems in mitigating the effects of pandemics. The third paper delves into the intricate challenges associated with effectively disseminating guidance-related information to the public during a pandemic, placing particular emphasis on the pivotal role played by opinion leaders (OLs) as reliable sources. This study thoroughly examines the distinctive characteristics of pandemic OLs and their profound influence on public attitudes. By employing surveys, social network analysis, and text mining techniques on Twitter data, the research successfully identifies OLs within distinct pandemic-related domains. The study's significant findings provide insights into the dynamic role assumed by pandemic OLs on Twitter and their consequential impact on public perception and behavior across various domains. Ultimately, the dissertation findings strive to support decision-makers and public health officials in their efforts to effectively manage pandemics and protect public health. The research emphasizes facilitation of seamless, rapid, and dependable information sharing across various planning horizons.

Advancements in high-throughput technologies have led to an exponential increase in the generation of multi-modal data in computational biology. These datasets, comprising diverse biological measurements such as genomics, transcriptomics, proteomics, metabolomics, and imaging data, offer a comprehensive view of biological systems at various levels of complexity. However, integrating and analyzing such heterogeneous data present significant challenges due to differences in data modalities, scales, and noise levels. Another challenge for multi-modal analysis is the complex interaction network that the modalities share. Understanding the intricate interplay between different biological modalities is essential for unraveling the underlying mechanisms of complex biological processes, including disease pathogenesis, drug response, and cellular function. Machine learning algorithms have emerged as indispensable tools for studying multi-modal data in computational biology, enabling researchers to extract meaningful insights, identify biomarkers, and predict biological outcomes. In this dissertation, we first propose a multi-modal integration framework that takes two interconnected data modalities and their interaction network to iteratively update the modalities into new representations with better disease outcome predictive abilities. The deep learning-based model underscores the importance and performance gains achieved through the incorporation of network information into integration process. Additionally, a multi-modal framework is developed to estimate protein expression from mRNA and microRNA (miRNA) expressions, along with the mRNA-miRNA interaction network. The proposed network propagation model simulates in-vivo miRNA regulation on mRNA translation, offering a cost-effective alternative to experimental protein quantification. Analysis reveals that predicted protein expression exhibits a stronger correlation with ground truth protein expression compared to mRNA expression. Moreover, the effectiveness of integrative models is contingent upon the quality of input data modalities and the completeness of interaction networks, with missing values and network noise adversely affecting downstream tasks. To address these challenges, two multi-modal imputation models are proposed, facilitating the imputation of missing values in time series data. The first model allows the imputation of missing values in time series gene expression utilizing single nucleotide polymorphism (SNP) data for children at high risk of type 1 diabetes. The imputed gene expression allows us to predict the progression towards type 1 diabetes at birth with six years prediction horizon. Subsequently, a follow-up study introduces a generalized multi-modal imputation framework capable of imputing missing values in time series data using either another time series or cross-sectional data collected from the same set of samples. These models excel at imputation tasks, whether values are missing randomly or an entire time step in the series is absent. Additionally, leveraging the additional modality, they are able to estimate a completely missing time series without prior values. Finally, to mitigate noise in the interaction network, a link prediction framework for drug-target interaction prediction is developed. This study demonstrates exceptional performance in cold start predictions and investigates the efficacy of large language models for such predictions. Through a comprehensive review and evaluation of state-of-the-art algorithms, this dissertation aims to provide researchers with valuable insights, methodologies, and tools for harnessing the rich information embedded within multi-modal biological datasets.

This study examines the technology and appointment scheduling habits of older adults over the age of 55 through an exploratory sequential three phase mixed methods study. Phase One of this study examined features of ten existing mHealth applications through a qualitative content analysis, then a mHealth wireframe was developed from the app to replicate in addition to a redesigned version. Phase Two of the study was a thirty-four questions survey with 40 participants that inquired about their background with appointment scheduling, prior experience with technology, and demographics. After that, the mHealth applications were revised into two mHealth application prototypes. Lastly, Phase Three conducted a user test with the two mHealth prototypes through A/B testing with 15 participants. Findings from the survey showed the preferred method of scheduling an appointment among participants was primarily in-person or by phone. The user test revealed that some participants were willing to use a mHealth application to schedule an appointment if it was deemed easy to use. Recommendations for future research suggests that the iterative design process of a prototype with an underserved population would garner feedback inclusive of those older adults who are less tech savvy. The major contribution of this research was the development of the mHapps Framework which will be tested in a future study.

This dissertation presents a comprehensive exploration and implementation of attention mechanisms and transformers on several healthcare-related and assistive applications. The overarching goal is to demonstrate successful implementation of the state-of-the-art approaches and provide validated models with their superior performance to inform future research and development. In Chapter 1, attention mechanisms are harnessed for the fine-grained classification of white blood cells (WBCs), showcasing their efficacy in medical diagnostics. The proposed multi-attention framework ensures accurate WBC subtype classification by capturing discriminative features from various layers, leading to superior performance compared to other existing approaches used in previous work. More importantly, the attention-based method showed consistently better results than without attention in all three backbone architectures tested (ResNet, XceptionNet and Efficient- Net). Chapter 2 introduces a self-supervised framework leveraging vision transformers for object detection, semantic and custom algorithms for collision prediction in application to assistive technology for visually impaired. In addition, Multimodal sensory feedback system was designed and fabricated to convey environmental information and potential collisions to the user for real-time navigation and grasping assistance. Chapter 3 presents implementation of transformer-based method for operation-relevant human activity recognition (HAR) and demonstrated its performance over other deep learning model, long-short term memory (LSTM). In addition, feature engineering was used (principal component analysis) to extract most discriminatory and representative motion features from the instrumented sensors, indicating that the joint angle features are more important than body segment orientations. Further, identification of a minimal number and placement of wearable sensors for use in real-world data collections and activity recognitions, addressing the critical gap found in the respective field to enhance the practicality and utility of wearable sensors for HAR. The premise and efficacy of attention-based mechanisms and transformers was confirmed through its demonstrated performance in classification accuracy as compared to LSTM. These research outcomes from three distinct applications of attention-based mechanisms and trans- formers and demonstrated performance over existing models and methods support their utility and applicability across various biomedical and human activity research fields. By sharing the custom designed model architectures, implementation methods, and resulting classification performance has direct impact in the related field by allowing direct adoption and implementation of the developed methods.

Yes / Health services in many countries are investing in inter-organisational networks, linking patients’ records held in different organisations across a city or region. The aim of the systematic review was to establish how, why, and in what circumstances these networks improve patient safety, fail to do so, or increase safety risks, for people living at home. Design Realist synthesis, drawing on both quantitative and qualitative evidence, and including consultation with stakeholders in nominal groups and semi-structured interviews. Eligibility criteria The co-ordination of services for older people living at home, and medicine reconciliation for older patients returning home from hospital. Information sources 17 sources including Medline, Embase, CINAHL, Cochrane Library, Web of Science, ACM Digital Library and Applied Social Sciences Index and s (ASSIA). Outcomes Changes in patients’ clinical risks. Results We did not find any detailed accounts of the sequences of events that policy makers and others believe will lead from the deployment of interoperable networks to improved patient safety. We were, though, able to identify a substantial number of theory fragments, and these were used to develop programme theories. There is good evidence that there are problems with the co-ordination of services in general, and the reconciliation of medication lists in particular, and it indicates that most problems are social and organisational in nature. There is also good evidence that doctors and other professionals find interoperable networks difficult to use. There was limited high quality evidence about safety-related outcomes associated with the deployment of interoperable networks. Conclusions Empirical evidence does not currently justify claims about the beneficial effects of interoperable networks on patient safety. There appears to be a mismatch between technology-driven assumptions about the effects of networks and the socio-technical nature of co-ordination problems. Review registration: PROSPERO CRD42017073004 / NIHR Grant 16/53/03

The purpose of this study was to explore and describe staff experiences in managing data and/or information when utilising the District Health Information System (DHIS) as a support mechanism for data quality improvement, including the strengths and weaknesses of current data management processes. It was also aimed to identify key barriers and to make recommendations on how data management can be strengthened. Key informants included in this study were those based at the district office (health programme managers and information officers) and at the primary health care (PHC) facilities (facility managers, clinical nurse practitioners and data capturers). An exploratory, descriptive and generic qualitative study was conducted. Consent was requested from each participant. Data were collected through semi-structured interviews. The study findings highlighted strengths, weaknesses and key barriers as experienced by the staff. Strengths, such as having data capturers and DHIS software at most if not all facilities, were highlighted. The weaknesses and key barriers highlighted were staff shortages of both clinical and health management information staff (HMIS), shortage of resources such as computers and Internet access, poor feedback, training needs and data quality issues. Most of the weaknesses and key barriers called for further and proper implementation of the District Health Management Information Systems (DHMIS) policy, the standard operating procedures (SOP), the eHealth strategy and training of the staff, due to the reported gaps between the policy and the reality and/or practice at the facility / Health Studies / M.A. (Public Health with specialisation in Medical Informatics)