The prevalence of the EMR in biomedical research is growing, the EMR being regarded as a source of contextually rich, longitudinal data for computation and statistical/trend analysis. However, models trained with data abstracted from the EMR often (1) do not capture all features needed to accurately predict the patient's future state and to ground clinical decisions; and (2) are not normalized to a standardized timeline. This dissertation demonstrates the advantages of instance-specific predictive models and event-based frameworks for normalizing population and patient-specific data, by evaluating a modified Lazy Bayes' Rule algorithm adapted to structured and unstructured longitudinal clinical datasets. The results of the evaluations indicate the superior performance of the instance-specific model over its global equivalents, in the context of staging clinical data via event-based change.

Consumer wearable devices and smartphones are ubiquitous and generate valuable health-related data that remain under explored. These data have the potential to enhance our understanding of depression by bridging gaps left by traditional methods that often rely on retrospective self-reports. By leveraging machine learning, we identified relationships between specific passively measured behaviors and retrospective self-reports related to depression severity, reward functioning, and sleep quality. Focusing on sleep quality, our findings indicate that self-reported and physiologically measured sleep quality assess different constructs and offer distinct insights into depression. Anomaly detection (AD) methods were examined and aimed at identifying correlations between deviations from typical behavior, as recorded by mobile health (mHealth) devices, and changes in depression severity and symptoms. Although no significant relationship was found, the AD methods effectively detected multivariate anomalies, indicating potential applications beyond depression. Additionally, real-time data from wearable devices proved effective in detecting momentary reward functioning and affect, with models performing above random chance and performance varying across demographic and clinical groups. This dissertation highlights the importance of nuanced approaches in using consumer device-generated data to passively detect depression symptomology.

Knowledge about the biology, etiology, staging, and treatment of a disease can be found in a growing and disparate set of sources, including observational clinical data, scientific literature, and clinical guidelines. However, effectively utilizing these sources to support clinical decision making remains a challenge. One of the challenges stems from the need to integrate knowledge from multiple sources that have heterogeneous representation, while locating and appraising evidence relevant to an individual patient can also be an issue. The objective of this dissertation is the formulation of an intermediate representation that logically consolidates and standardizes knowledge fragments across these sources, along with the definition of operators on this representation that generate, in a principled manner, the needed elements to facilitate answering clinical queries to support evidence-based medicine (EBM). The contributions of this work are: (1) a standardized representation, called Phenomenon-Centric Data Model Plus (PCDM+), which adopts the probabilistic entity-relationship model and captures and structures information about a disease drawn from scientific literature and patient records, emphasizing population-level observations and evidence; and (2) a set of operators that retrieve and infer information about individual patients from the PCDM+ to inform clinical queries. This work is demonstrated and evaluated in the domain of intracranial aneurysm.

Chest CT is the most common modality in thoracic imaging, especially for diagnosis of diffuse lung disease and lung cancer screening. When mining image data from PACS or clinical trials or processing large volumes of data without curation, the relevant scans must be identified among irrelevant or redundant data. Only images acquired with appropriate technical factors, patient positioning, and physiological conditions may be applicable to a particular image processing or machine learning task. Following identification of appropriate images for processing, accurate lung and lobar segmentation is a pre-requisite for the subsequent quantitative image analysis, e.g. air trapping measurement, emphysema scoring, fibrosis scoring, nodule detection, etc. Fully automated segmentation on a diverse spectrum of pathological lungs is still a challenge in clinical practice. Both the labeling and segmentation steps currently require significant manual intervention by image analysts and are prohibitive for large scale processing of big data. The goal of this dissertation is to fully automate the labeling and segmentation tasks in chest CT with high accuracy.

In this dissertation, an image based high throughput labeling pipeline using deep learning was proposed, it aimed to identify anatomical coverage, scan direction, scan posture, lung coverage completeness, contrast usage and breath-hold types. They were posed as different classification problems and some of them required further segmentation and identification of anatomical landmarks. Images of different view planes were used depending on the specific classification problem. All of our models achieved an accuracy > 99% on their respective test sets across different tasks using a research database from multi-center clinical trials. Based on the comprehensive labels from deep learning models, an optimal image series at each time point for a given patient was selected prior to lung and lobar segmentation.

Two fully convolutional networks were proposed to sequentially achieve accurate lung and lobar segmentation. Firstly, a 2D ResNet-101 based network was used for lung segmentation and 575 chest CT scans from multi-center clinical trials were used with radiologist approved lung segmentation. Secondly, a 3D DenseNet based network is applied to segment the 5 lobes and a total of 1280 different CT scans were used with radiologist approved lobar segmentation as ground truth. The dataset included various pathological lung diseases and stratified sampling was used to form the training and test sets with a ratio of 4:1 to ensure a balanced number and type of abnormality were present. Using 5-fold cross validation a mean Dice coefficient of 0.988 � 0.012 and Average Surface Distance of 0.562 � 0.49 mm were achieved by the proposed 2D CNN on lung segmentation. The 3D DenseNet on lobar segmentation achieved a Dice score of 0.959 � 0.087 and an Average surface distance of 0.873 � 0.61mm.

Advances in next-generation sequencing coupled with comparative analyses have hadtremendous implication for oncology. Differentially expressed genomic features have revealed molecular pathways, oncogenic drivers, and resistance patterns targeted by drug development leading to significant decreases in cancer mortality. The introduction of high throughput multiomics, including transcriptomics, epigenomics, and proteomics, promised to scale translational innovation. Increasing feature complexity, however, cannot be comparatively resolved, and many efforts in this space have failed due to inconclusive or conflicting results. Computational systems biology and functional genomics have proposed dynamic integration of multiple molecular pathway models for data harmonization, yet the requirement for complete information has biased discovery. Similarly, the incorporation of probabilistic approaches that constrain features may obscure incremental biologic effects. This problem is exemplified by the several dozen cancer genomic biomarkers and models from peer-reviewed high impact publications that do not meet statistical significance when applied beyond their training and validation datasets.

This dissertation seeks to employ a scientifically rigorous process of evaluation using iterativemodeling to benchmark multiomic comparisons. First, this research develops a framework for characterizing multimodal data based on structural and functional information. Second, this research benchmarks similarity metrics using varied data structures, offering techniques to reveal key biologic differences using probabilistic modeling (hierarchical clustering). This framework is then applied to neoepitope prediction incorporating human leukocyte antigen-B supertypes and used to resolve previously inconclusive and conflicting results, including the difference in survival based on B44 supertype in patients with non-small cell lung cancer (NSCLC) and melanoma treated with immune checkpoint blockade (ICB).

Ultimately, this dissertation advances our understanding of the interaction between featureselection and power in multiomic analyses and offers recommendations to enhance the reliability of these investigations.

Low-dose computed tomography (CT) screening has been widely used to detect and diagnose early stage lung cancer. Clinical trials have shown that low-dose CT reduced lung cancer mortality by 20% relative to plain chest radiography; however, challenges exist in current low-dose CT screening programs including high over-diagnosis rates, high cost and increased radiation exposure. This dissertation attempts to overcome these challenges by developing machine and deep learning models for automated lung cancer diagnosis and disease progression estimation. A novel lung segmentation approach was first developed using a bidirectional chain code method and machine learning framework. This method is designed to include the lung nodules attached to lung wall while minimizing over-segmentation error. Second, a hybrid ensemble convolutional neural network has been developed to classify lung nodule vs. non-nodule objects. The ensemble model combines the VGG, residual and densely connected module designs to improve the model classification robustness for external datasets collected with different acquisition parameters. Third, a hierarchical semantic convolutional neural network (HSCNN) has been described to classify lung nodule malignancy. Semantic characteristic features, predicted in parallel with the malignancy for each nodule, enable the interpretation of the model and improvement of malignancy prediction. Finally, a Bayesian framework combined with a continuous-time Markov model was developed to estimate the multi-state disease progression of lung cancer. The resulting model estimates individual lung cancer state transition information, providing the basis for personalized screening recommendations. Extensive experiments and results have proved the effectiveness of these methods paving the way to optimize and improve the effectiveness of existing low-dose CT screening programs.

Shifts in the consumer health landscape including the active participation of consumers within their care, the myriad of health information sources available to them, and the emphasis on preventive care, require patients to have improved information access and health literacy skills. Designers of eHealth tools must consider how best to meet the information needs of patients given that prior research has indicated that needs vary, making it unlikely that there is a homogeneous approach that will meet all needs. In spite of this, iterative design and inclusion of consumer feedback in the design process remain underutilized. This dissertation addressed this gap by creating a protocol for the design of a patient-centered information visualization for a specific population of interest, implemented here with lung cancer screening patients. Building upon past efforts in eHealth design and usability testing, the design centered on a method to produce a conceptual information model, which consisted of a five-step process that documented patient information needs and identified content and methods to address those needs. The model integrated information from various health education sources and provided dynamic personalized displays of the educational information alongside an individual’s radiology report. For this work, this model was displayed via a patient portal visualization, and evaluated by patients to determine whether patients reported the visualization as usable and whether using the visualization improved health literacy. These results were compared to a survey of general health consumers’ information preferences and health literacy. Initial results confirm that health literacy and information preferences varied by demographics (including education and the number of times prior an individual had used a patient portal) and suggest that patients find the integration of educational information alongside their reports, in contrast to the reports alone, as easier to use. The results of this study can be used as guidelines to further additional design of eHealth tools.

A tenet of precision medicine is the ability to predict a clinical response or outcome for a given individual. The creation of predictive disease models as a part of this evidence-based process has increased in recent years as electronic medical data and machine learning techniques have grown in popularity. A number of methods are available for testing internal validity when developing models. However, the performance of developed disease models must also be tested in external populations. This practice of external validation, or transportability, can help determine the extent to which information in a predictive model can be applied generally across population samples. Model performance can suffer when applied in external settings because populations have inherent differences or data was collected with different practices. A number of impediments, particularly in reporting, continue to hinder the widespread application of transportability methods. This dissertation addresses these concerns using a methodology for improving the classification of models and evaluating a proposed technique for partially adjusting problematic models. A set of simulations are proposed, taking advantage of a minimal set of published values to extend reported findings through bootstrap analysis. Interpretations derived from this method are able to guide the assignment and selection of models by transport levels. Causal transportability analysis, a previously proposed transportability theory in graphical models, is also evaluated for use in partial adjustment scenarios. The resulting process allows for evaluation of model transportability with minimal information and for assessing model adjustments. These investigations serve as useful tools for future transportability analysis. In addition, the results of this work introduce new items that can be added to reporting guidelines and support current trends to establish improved validation frameworks.