Each year approximately five million people are treated in the nation's intensive care units making intensive care one of the most expensive components of the U.S. healthcare system. Of these patients, 400,000-500,000 will die annually giving the ICU the distinction of having the highest rate of mortality and complications in the hospital setting. Studies have demonstrated that one in ten patients who die each day in ICUs might survive if intensivists were present to manage clinical care and direct treatment plans (Randolph & Pronovost, 2002; Dimick, Pronovost, Heitmiller & Lipsett, 2001; Pronovost et al., 2002). The utilization of supplemental remote telemedicine has been investigated as a means of compensating for the limited resource of intensivists (Breslow et al., 2004; Rosenfeld et al., 2000). One specific use of this technology, the electronic intensive care unit or eICU®, has previously demonstrated the potential to improve physiological and economic outcomes in ICU patients through the use of integrated decision-support and patient data systems. The present study focuses on the eICU® as a 21st century technology capable of improving the quality of patient care and identifies those factors most likely to impact the success of this clinical intervention. This research utilizes a non-experimental pre-and post-intervention study design and examines patient data collected on all admissions to five ICUs managed by two regional tertiary care hospitals during a 36-month time period. Each ICU is equipped with eICU® software systems that allow intensivist surveillance of patients from a remote facility. The data is analyzed using both structural equation modeling and decision tree regression modeling to statistically evaluate the effects of patient, hospital and unit characteristics on proximal and distal outcomes in ICU patients. As the development of clinical complications subsequently affects patient length of stay, cost of stay, and mortality, it becomes increasingly imperative to seek interventions capable of reducing the risk of unfavorable patient outcomes. This study closely examines one such intervention, the eICU®.

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.