There is intense interest in adopting computer-aided diagnosis (CAD) systems, particularly those developed based on deep learning algorithms, for applications in a number of medical specialties. However, success of these CAD systems relies heavily on large annotated datasets; otherwise, deep learning often results in algorithms that perform poorly and lack generalizability. Therefore, this dissertation seeks to address this critical problem: How to develop efficient and effective deep learning algorithms for medical applications where large annotated datasets are unavailable. In doing so, we have outlined three specific aims: (1) acquiring necessary annotations efficiently from human experts; (2) utilizing existing annotations effectively from advanced architecture; and (3) extracting generic knowledge directly from unannotated images. Our extensive experiments indicate that, with a small part of the dataset annotated, the developed deep learning methods can match, or even outperform those that require annotating the entire dataset. The last part of this dissertation presents the importance and application of imaging in healthcare, elaborating on how the developed techniques can impact several key facets of the CAD system for detecting pulmonary embolism. Further research is necessary to determine the feasibility of applying these advanced deep learning technologies in clinical practice, particularly when annotation is limited. Progress in this area has the potential to enable deep learning algorithms to generalize to real clinical data and eventually allow CAD systems to be employed in clinical medicine at the point of care.

Critical care environments are complex in nature. Fluctuating team dynamics and the plethora of technology and equipment create unforeseen demands on clinicians. Such environments become chaotic very quickly due to the chronic exposure to unpredictable clusters of events. In order to cope with this complexity, clinicians tend to develop ad-hoc adaptations to function in an effective manner. It is these adaptations or "deviations" from expected behaviors that provide insight into the processes that shape the overall behavior of the complex system. The research described in this manuscript examines the cognitive basis of clinicians' adaptive mechanisms and presents a methodology for studying the same. Examining interactions in complex systems is difficult due to the disassociation between the nature of the environment and the tools available to analyze underlying processes. In this work, the use of a mixed methodology framework to study trauma critical care, a complex environment, is presented. The hybrid framework supplements existing methods of data collection (qualitative observations) with quantitative methods (use of electronic tags) to capture activities in the complex system. Quantitative models of activities (using Hidden Markov Modeling) and theoretical models of deviations were developed to support this mixed methodology framework. The quantitative activity models developed were tested with a set of fifteen simulated activities that represent workflow in trauma care. A mean recognition rate of 87.5% was obtained in automatically recognizing activities. Theoretical models, on the other hand, were developed using field observations of 30 trauma cases. The analysis of the classification schema (with substantial inter-rater reliability) and 161 deviations identified shows that expertise and role played by the clinician in the trauma team influences the nature of deviations made (p<0.01). The results shows that while expert clinicians deviate to innovate, deviations of novices often result in errors. Experts' flexibility and adaptiveness allow their deviations to generate innovative ideas, in particular when dynamic adjustments are required in complex situations. The findings suggest that while adherence to protocols and standards is important for novice practitioners to reduce medical errors and ensure patient safety, there is strong need for training novices in coping with complex situations as well.

In the current millennium, extensive use of computers and the internet caused an exponential increase in information. Few research areas are as important as information extraction, which primarily involves extracting concepts and the relations between them from free text. Limitations in the size of training data, lack of lexicons and lack of relationship patterns are major factors for poor performance in information extraction. This is because the training data cannot possibly contain all concepts and their synonyms; and it contains only limited examples of relationship patterns between concepts. Creating training data, lexicons and relationship patterns is expensive, especially in the biomedical domain (including clinical notes) because of the depth of domain knowledge required of the curators. Dictionary-based approaches for concept extraction in this domain are not sufficient to effectively overcome the complexities that arise because of the descriptive nature of human languages. For example, there is a relatively higher amount of abbreviations (not all of them present in lexicons) compared to everyday English text. Sometimes abbreviations are modifiers of an adjective (e.g. CD4-negative) rather than nouns (and hence, not usually considered named entities). There are many chemical names with numbers, commas, hyphens and parentheses (e.g. t(3;3)(q21;q26)), which will be separated by most tokenizers. In addition, partial words are used in place of full words (e.g. up- and downregulate); and some of the words used are highly specialized for the domain. Clinical notes contain peculiar drug names, anatomical nomenclature, other specialized names and phrases that are not standard in everyday English or in published articles (e.g. "l shoulder inj"). State of the art concept extraction systems use machine learning algorithms to overcome some of these challenges. However, they need a large annotated corpus for every concept class that needs to be extracted. A novel natural language processing approach to minimize this limitation in concept extraction is proposed here using distributional semantics. Distributional semantics is an emerging field arising from the notion that the meaning or semantics of a piece of text (discourse) depends on the distribution of the elements of that discourse in relation to its surroundings. Distributional information from large unlabeled data is used to automatically create lexicons for the concepts to be tagged, clusters of contextually similar words, and thesauri of distributionally similar words. These automatically generated lexical resources are shown here to be more useful than manually created lexicons for extracting concepts from both literature and narratives. Further, machine learning features based on distributional semantics are shown to improve the accuracy of BANNER, and could be used in other machine learning systems such as cTakes to improve their performance. In addition, in order to simplify the sentence patterns and facilitate association extraction, a new algorithm using a "shotgun" approach is proposed. The goal of sentence simplification has traditionally been to reduce the grammatical complexity of sentences while retaining the relevant information content and meaning to enable better readability for humans and enhanced processing by parsers. Sentence simplification is shown here to improve the performance of association extraction systems for both biomedical literature and clinical notes. It helps improve the accuracy of protein-protein interaction extraction from the literature and also improves relationship extraction from clinical notes (such as between medical problems, tests and treatments). Overall, the two main contributions of this work include the application of sentence simplification to association extraction as described above, and the use of distributional semantics for concept extraction. The proposed work on concept extraction amalgamates for the first time two diverse research areas -distributional semantics and information extraction. This approach renders all the advantages offered in other semi-supervised machine learning systems, and, unlike other proposed semi-supervised approaches, it can be used on top of different basic frameworks and algorithms.