No description available.

No description available.

No description available.

No description available.

No description available.

Electronic Health Record (EHR) creates a huge number of databases which are being updated dynamically. Major goal of interoperability in healthcare is to facilitate the seamless exchange of healthcare related data and an environment to supports interoperability and secure transfer of data. The health care organisations face difficulties in exchanging patient’s health care information and laboratory reports etc. due to a lack of semantic interoperability. Hence, there is a need of semantic web technologies for addressing healthcare interoperability problems by enabling various healthcare standards from various healthcare entities (doctors, clinics, hospitals etc.) to exchange data and its semantics which can be understood by both machines and humans. Thus, a framework with a similarity analyser has been proposed in the thesis that dealt with semantic interoperability. While dealing with semantic interoperability, another consideration was the use of word embedding and ontology for knowledge discovery. In medical domain, the main challenge for medical information extraction system is to find the required information by considering explicit and implicit clinical context with high degree of precision and accuracy. For semantic similarity of medical text at different levels (conceptual, sentence and document level), different methods and techniques have been widely presented, but I made sure that the semantic content of a text that is presented includes the correct meaning of words and sentences. A comparative analysis of approaches included ontology followed by word embedding or vice-versa have been applied to explore the methodology to define which approach gives better results for gaining higher semantic similarity. Selecting the Kidney Cancer dataset as a use case, I concluded that both approaches work better in different circumstances. However, the approach in which ontology is followed by word embedding to enrich data first has shown better results. Apart from enriching the EHR, extracting relevant information is also challenging. To solve this challenge, the concept of analogy has been applied to explain similarities between two different contents as analogies play a significant role in understanding new concepts. The concept of analogy helps healthcare professionals to communicate with patients effectively and help them understand their disease and treatment. So, I utilised analogies in this thesis to support the extraction of relevant information from the medical text. Since accessing EHR has been challenging, tweets text is used as an alternative for EHR as social media has appeared as a relevant data source in recent years. An algorithm has been proposed to analyse medical tweets based on analogous words. The results have been used to validate the proposed methods. Two experts from medical domain have given their views on the proposed methods in comparison with the similar method named as SemDeep. The quantitative and qualitative results have shown that the proposed analogy-based method bring diversity and are helpful in analysing the specific disease or in text classification.

Electronic health record (EHR) systems are used by medical providers to streamline the workflow and enable sharing of patient data with different providers. Beyond that primary purpose, EHR data have been used in healthcare research for exploratory and predictive analytics. EHR data are heterogeneous collections of both structured and unstructured information. In order to store data in a structured way, several ontologies have been developed to describe diagnoses and treatments. On the other hand, the unstructured clinical notes contain various more nuanced information about patients. The multidimensionality and complexity of EHR data pose many unique challenges and problems for both data mining and medical communities. In this thesis, we address several important issues and develop novel deep learning approaches in order to extract insightful knowledge from these data. Representing words as low dimensional vectors is very useful in many natural language processing tasks. This idea has been extended to medical domain where medical codes listed in medical claims are represented as vectors to facilitate exploratory analysis and predictive modeling. However, depending on a type of a medical provider, medical claims can use medical codes from different ontologies or from a combination of ontologies, which complicates learning of the representations. To be able to properly utilize such multi-source medical claim data, we propose an approach that represents medical codes from different ontologies in the same vector space. The new approach was evaluated on the code cross-reference problem, which aims at identifying similar codes across different ontologies. In our experiments, we show the proposed approach provide superior cross-referencing when compared to several existing approaches. Furthermore, considering EHR data also contain unstructured clinical notes, we also propose a method that jointly learns medical concept and word representations. The jointly learned representations of medical codes and words can be used to extract phenotypes of different diseases. Various deep learning models have recently been applied to predictive modeling of Electronic Health Records (EHR). In EHR data, each patient is represented as a sequence of temporally ordered irregularly sampled visits to health providers, where each visit is recorded as an unordered set of medical codes specifying patient's diagnosis and treatment provided during the visit. We propose a novel interpretable deep learning model, called Timeline. The main novelty of Timeline is that it has a mechanism that learns time decay factors for every medical code. We evaluated Timeline on two large-scale real world data sets. The specific task was to predict what is the primary diagnosis category for the next hospital visit given previous visits. Our results show that Timeline has higher accuracy than the state of the art deep learning models based on RNN. Clinical notes contain detailed information about health status of patients for each of their encounters with a health system. Developing effective models to automatically assign medical codes to clinical notes has been a long-standing active research area. Considering the large amount of online disease knowledge sources, which contain detailed information about signs and symptoms of different diseases, their risk factors, and epidemiology, we consider Wikipedia as an external knowledge source and propose Knowledge Source Integration (KSI), a novel end-to-end code assignment framework, which can integrate external knowledge during training of any baseline deep learning model. To evaluate KSI, we experimented with automatic assignment of ICD-9 diagnosis codes to clinical notes, aided by Wikipedia documents corresponding to the ICD-9 codes. The results show that KSI consistently improves the baseline models and that it is particularly successful in rare codes prediction. / Computer and Information Science

Rates of immune-mediated diseases (IMDs) have rapidly increased. Although the exact etiology has not yet been fully elucidated, disruptions to the microbiome has been proposed as a potential mechanism. We conducted a retrospective, longitudinal, birth cohort study utilizing electronic health records (EHR) to investigate the association between early life antibiotic exposure and the risk of developing juvenile idiopathic arthritis (JIA), pediatric psoriasis, or type 1 diabetes. Incident rate ratios (IRR) were estimated using modified Poisson regression models and adjusted for significant confounders. Children exposed to two or more antibiotics prior to 12 months of age had a 69% increased risk of developing JIA (1.69 IRR, 95% CI [1.04-2.73]), which rose to 97% when exposed prior to 6 months (1.97 IRR, 95% CI [1.11-3.49]). Children exposed to a penicillin antibiotic had a 62% increase in risk for psoriasis (1.62 IRR, 95% CI [1.06-2.49]), which rose slightly to 64% when exposure occurred between 6 and 12 months of age [(1.64 IRR, 95% CI [1.04-2.59]). We found a moderate to strong association between early antibiotic exposure and risk for JIA and psoriasis when exposure was examined by age, frequency, and type of antibiotic, but not for type 1 diabetes. Potential interactions effects between infection and antibiotics with an increased susceptibility to early life infections among children with an IMD was also observed. Overall, children exposed to antibiotics at an early age have an increased probability of developing an IMD after 12 months of age. However, alternative explanations for this association should be considered. / Public Health

This dissertation develops explainable and sparse predictive models applied to two main healthcare applications: reproductive health and oncology. Through the application of advanced machine learning techniques and survival analysis, we aim to enhance predictive accuracy and provide actionable insights in these critical areas. The thesis is structured into four distinct problems, each focusing on a particular research question. The first problem concerns the prediction of the probability of conception among couples actively trying to conceive. Using self-reported health data from a North American preconception cohort study, we analyzed factors such as sociodemographics, lifestyle, medical history, diet quality, and specific male partner characteristics. Machine learning algorithms were employed to predict the probability of conception demonstrating improved discrimination and potential clinical utility. The second problem explores the application of machine learning algorithms to electronic health record (EHR) data for identifying predictor variables associated with polycystic ovarian syndrome (PCOS) diagnosis. Employing gradient boosted trees and feed-forward multilayer perceptron classifiers, we developed a scoring system that improved the model's performance, providing a valuable tool for early detection and intervention. The third problem focuses on predicting the risk of miscarriage among female participants who conceived during the study period. Utilizing both static and survival analysis, including Cox proportional hazard models, we developed predictive models to assess miscarriage risk. The study revealed that most miscarriages were due to random genetic errors during early pregnancy, indicating that miscarriage is not easily predicted based on preconception sociodemographic and lifestyle characteristics. Finally, the fourth problem focuses on the development of predictive models for managing Chronic Myeloid Leukemia (CML) patients. We developed models to predict whether patients will achieve deep molecular response (DMR) at later treatment stages and maintaining this status up to 60 months post-treatment initiation. These models offer insights into treatment effectiveness and patient management, aiming to support clinical decision-making and improve long-term patient outcomes. By emphasizing the explainability of these models, this dissertation not only aims to provide accurate predictions but also to ensure that the results are interpretable and actionable for healthcare professionals. Overall, this thesis showcases the potential of predictive modeling to improve reproductive health and oncology-related outcomes. The development and validation of various models in these contexts underscore the value of machine learning algorithms in healthcare research, analysis of epidemiologic data, and prediction of critical health events. The findings have significant implications for enhancing patient care, informing clinical practices, and guiding healthcare policy decisions.

A new hospital in United Arab Emirates (UAE) plans to adopt health information technology (HIT) and become fully digitalized once operational. The hospital has identified a need to assess basic computer literacy of new employees prior to offering them training on various HIT applications. Lack of research in identifying an accurate assessment method for basic computer literacy among health care professionals led to this explanatory correlational research study, which compared self-assessment scores and a simulated actual computer skills test to find an appropriate tool for assessing computer literacy. The theoretical framework of the study was based on constructivist learning theory and self-efficacy theory. Two sets of data from 182 hospital employees were collected and analyzed. A t test revealed that scores of self-assessment were significantly higher than they were on the actual test, which indicated that hospital employees tend to score higher on self-assessment when compared to actual skills test. A Pearson product moment correlation revealed a statistically weak correlation between the scores, which implied that self-assessment scores were not a reliable indicator of how an individual would perform on the actual test. An actual skill test was found to be the more reliable tool to assess basic computer skills when compared to self-assessment test. The findings of the study also identified areas where employees at the local hospital lacked basic computer skills, which led to the development of the project to fill these gaps by providing training on basic computer skills prior to them getting trained on various HIT applications. The findings of the study will be useful for hospitals in UAE who are in the process of adopting HIT and for health information educators to design appropriate training curricula based on assessment of basic computer literacy.