There is a marked trend of using information technologies to improve healthcare. Among all the health IT, electronic health record (EHR) systems hold great promises as they modernize the paradigm and practice of care provision. However, empirical studies in the literature found mixed evidence on whether EHRs improve quality of care. I posit two explanations for the mixed evidence. First, most prior studies failed to account for system use and only focused on EHR purchase or adoption. Second, most existing EHR systems provide inadequate clinical decision support and hence, fail to reveal the full potential of digital health. In this dissertation I address two broad research questions: a) Does meaningful use of EHRs improve quality of care? and b) How do we advance clinical decision making through innovative computational techniques of healthcare analytics? To these ends, the dissertation comprises four essays. The first essay examines whether meaningful use of EHRs improve quality of care through a natural experiment. I found that meaningful use significantly improve quality of care, and this effect is greater in historically disadvantaged hospitals such as small, non-teaching, or rural hospitals. These empirical findings present salient practical and policy implications about the role of health IT. On the other hand, in the other three essays I work with real-world EHR data sets and propose healthcare analytics frameworks and methods to better utilize clinical text (Essay II), integrate clinical guidelines and EHR data for risk prediction (Essay III), and develop a principled approach for multifaceted risk profiling (Essay IV). Models, frameworks, and design principles proposed in these essays advance not only health IT research, but also more broadly contribute to business analytics, design science, and predictive modeling research.

Context. Foreign Accent Syndrome is a rare neurological disorder, where among other symptoms of the patient’s emotional speech is affected. As FAS is one of the mildest speech disorders, there has not been much research done on the cost-effective biomarkers which reflect recovery of competences speech. Objectives. In this pilot study, we implement the Emotional Temperature biomarker and check its validity for assessing the FAS. We compare the results of implemented biomarker with another biomarker based on the global distances for FAS and identify the better one. Methods. To reach the objective, the emotional speech data of two patients at different phases of the treatment are considered. After preprocessing, experiments are performed on various window sizes and the observed correctly classified instances in automatic recognition are used to calculate Emotional temperature. Further, we use the better biomarker for tracking the recovery in the patient’s speech. Results. The Emotional temperature of the patient is calculated and compared with the ground truth and with that of the other biomarker. The Emotional temperature is calculated to track the emergence of compensatory skills in speech. Conclusions. A biomarker based on the frame-view of speech signal has been implemented. The implementation has used the state of art feature set and thus is an unproved version of the classical Emotional Temperature. The biomarker has been used to automatically assess the recovery of two patients diagnosed with FAS. The biomarker has been compared against the global view biomarker and has advantages over it. It also has been compared to human evaluations and captures the same dynamics.

The U.S. health care system is considered costly and highly inefficient, devoting substantial resources to the treatment of acute conditions in a hospital setting rather than focusing on prevention and keeping patients out of the hospital. The potential for cost savings is large; in the U.S. more than $30 billion are spent each year on hospitalizations deemed preventable, 31% of which is attributed to heart diseases and 20% to diabetes. Motivated by this, our work focuses on developing centralized and distributed learning methods to predict future heart- or diabetes- related hospitalizations based on patient Electronic Health Records (EHRs). We explore a variety of supervised classification methods and we present a novel likelihood ratio based method (K-LRT) that predicts hospitalizations and offers interpretability by identifying the K most significant features that lead to a positive prediction for each patient. Next, assuming that the positive class consists of multiple clusters (hospitalized patients due to different reasons), while the negative class is drawn from a single cluster (non-hospitalized patients healthy in every aspect), we present an alternating optimization approach, which jointly discovers the clusters in the positive class and optimizes the classifiers that separate each positive cluster from the negative samples. We establish the convergence of the method and characterize its VC dimension. Last, we develop a decentralized cluster Primal-Dual Splitting (cPDS) method for large-scale problems, that is computationally efficient and privacy-aware. Such a distributed learning scheme is relevant for multi-institutional collaborations or peer-to-peer applications, allowing the agents to collaborate, while keeping every participant's data private. cPDS is proved to have an improved convergence rate compared to existing centralized and decentralized methods. We test all methods on real EHR data from the Boston Medical Center and compare results in terms of prediction accuracy and interpretability.

Submitted by Renata Galdino Rocha e Silva (renatagrs@hotmail.com) on 2016-11-09T18:51:03Z No. of bitstreams: 1 Dissertação - Final- Renata Galdino v22 09112016.pdf: 5061207 bytes, checksum: 4dd6980b0cbefdfd51254bc5f6025d67 (MD5) / Approved for entry into archive by GILSON ROCHA MIRANDA (gilson.miranda@fgv.br) on 2016-11-22T17:46:11Z (GMT) No. of bitstreams: 1 Dissertação - Final- Renata Galdino v22 09112016.pdf: 5061207 bytes, checksum: 4dd6980b0cbefdfd51254bc5f6025d67 (MD5) / Made available in DSpace on 2016-12-07T11:31:50Z (GMT). No. of bitstreams: 1 Dissertação - Final- Renata Galdino v22 09112016.pdf: 5061207 bytes, checksum: 4dd6980b0cbefdfd51254bc5f6025d67 (MD5) Previous issue date: 2016-05-31 / Healthcare sector analyses have proven that a small portion of individuals with chronic conditions consume the majority of the resources needed for the treatment of these conditions. Therefore, to achieve the industry’s primary objectives of providing healthcare, reducing costs and improving the patients’ overall wellness, the Brazilian healthcare system should employ proactive models of intervention regarding patients who are very likely to become high-cost. Approaches focusing on specific populations and data quality allow decision makers to have a clear comprehension of the needs presented by each specific group - groups are established as per industry practice - and to plan actions oriented toward cost reduction and improved quality of the services provided. This study aims to assess a risk modelling strategy for predicting which specific types of patients are likely to become high-cost individuals in the Brazilian healthcare system. Such modeling is comprised by Health Analytics Strategies that characterize the global insurance industry and seeks to identify potentially high-cost patients by using data mining techniques, historical data and predictive analysis. / Análises do setor de saúde têm confirmado que uma pequena parcela de indivíduos com condições crônicas consome a maior parte dos recursos destinados ao tratamento destas doenças. Neste sentido, para alcançar os objetivos básicos do setor de melhorar a qualidade, reduzir os custos e melhorar a experiência do paciente, o sistema de saúde deve focar-se em modelos orientados à atuação proativa com foco em intervenção nos pacientes que possuem maior risco de migração para o grupo de alto custo. Abordagens focadas em populações específicas e com informações íntegras permitem que os tomadores de decisão entendam as necessidades de acordo com cada grupo avaliado e planejem ações direcionadas, de forma a reduzir custos e melhorar a qualidade dos serviços prestados. Desta forma, este trabalho visa efetuar um estudo sobre estratégia de modelagem de riscos para predição de pacientes de alto custo no sistema de saúde brasileiro. Tal modelagem faz parte da estratégia de Health Analytics dos principais grupos seguradores globais e busca, mediante uso de técnicas de mineração de dados e análises preditivas, a identificação de pacientes de alto custo para o ano seguinte com base no histórico de informações.

Healthcare analytics has traditionally relied upon linear and logistic regression models to address clinical research questions mostly because they produce highly interpretable results [1, 2]. These results contain valuable statistics such as p-values, coefficients, and odds ratios that provide healthcare professionals with knowledge about the significance of each covariate and exposure for predicting the outcome of interest [1]. Thus, they are often favored over new deep learning models that are generally more accurate but less interpretable and scalable. However, the statistical power of linear and logistic regression is contingent upon satisfying modeling assumptions, which usually requires altering or transforming the data, thereby hindering interpretability. Thus, generalized additive models are useful for overcoming this limitation while still preserving interpretability and accuracy. The major research question in this work involves investigating whether particular sedative agents (fentanyl, propofol, versed, ativan, and precedex) are associated with different discharge dispositions for patients with acute traumatic brain injury (TBI). To address this, we compare the effectiveness of various models (traditional linear regression (LR), generalized additive models (GAMs), and deep learning) in providing guidance for sedative choice. We evaluated the performance of each model using metrics for accuracy, interpretability, scalability, and generalizability. Our results show that the new deep learning models were the most accurate while the traditional LR and GAM models maintained better interpretability and scalability. The GAMs provided enhanced interpretability through pairwise interaction heat maps and generalized well to other domains and class distributions since they do not require satisfying the modeling assumptions used in LR. By evaluating the model results, we found that versed was associated with better discharge dispositions while ativan was associated with worse discharge dispositions. We also identified other significant covariates including age, the Northeast region, the Acute Physiology and Chronic Health Evaluation (APACHE) score, Glasgow Coma Scale (GCS), and ethanol level. The versatility of versed may account for its association with better discharge dispositions while ativan may have negative effects when used to facilitate intubation. Additionally, most of the significant covariates pertain to the clinical state of the patient (APACHE, GCS, etc.) whereas most non-significant covariates were demographic (gender, ethnicity, etc.). Though we found that deep learning slightly improved over LR and generalized additive models after fine-tuning the hyperparameters, the deep learning results were less interpretable and therefore not ideal for making the aforementioned clinical insights. However deep learning may be preferable in cases with greater complexity and more data, particularly in situations where interpretability is not as critical. Further research is necessary to validate our findings, investigate alternative modeling approaches, and examine other outcomes and exposures of interest. / Master of Science / Patients with Traumatic Brain Injury (TBI) often require sedative agents to facilitate intubation and prevent further brain injury by reducing anxiety and decreasing level of consciousness. It is important for clinicians to choose the sedative that is most conducive to optimizing patient outcomes. Hence, the purpose of our research is to provide guidance to aid this decision. Additionally, we compare different modeling approaches to provide insights into their relative strengths and weaknesses. To achieve this goal, we investigated whether the exposure of particular sedatives (fentanyl, propofol, versed, ativan, and precedex) was associated with different hospital discharge locations for patients with TBI. From best to worst, these discharge locations are home, rehabilitation, nursing home, remains hospitalized, and death. Our results show that versed was associated with better discharge locations and ativan was associated with worse discharge locations. The fact that versed is often used for alternative purposes may account for its association with better discharge locations. Further research is necessary to further investigate this and the possible negative effects of using ativan to facilitate intubation. We also found that other variables that influence discharge disposition are age, the Northeast region, and other variables pertaining to the clinical state of the patient (severity of illness metrics, etc.). By comparing the different modeling approaches, we found that the new deep learning methods were difficult to interpret but provided a slight improvement in performance after optimization. Traditional methods such as linear regression allowed us to interpret the model output and make the aforementioned clinical insights. However, generalized additive models (GAMs) are often more practical because they can better accommodate other class distributions and domains.