As computer printouts replace handwritten and typewritten information in a Medical Records department, it becomes more advantageous for the Registered Records Administrator (RRA) to learn how to interact with a computer terminal. Computer applications in the Medical Records field increase the availability and accessibility of patient information. The Medical Records System discussed in this paper has been adapted by the Medical Records department of the College of Health Sciences of the University of Central Florida as a tool for demonstrating the relationship between the computer and the successful management of medical records. This system will provide hands on experience to all medical records students. It has the capability of adding, deleting or changing the medical records of patients on the Master Patient Index and the Patient Master File. Statistics are calculated and reports are generated monthly or on request for areas of particular interest, such as Payment Source, Discharge Analysis, and Utilization Review. These reports help analyze the effectiveness of specific treatment and the flow rate of patients. As improvements become necessary, the system will be modified to reflect any new requirements in the medical records field.

Thesis. 1978. M.S.--Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. / MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING. / Includes bibliographical references. / M.S.

With the increasing adoption of health information technology and the growth in the resulting electronic repositories of clinical data, the secondary use of electronic health record data has become one of the most promising approaches to enabling and speeding clinical research. Unfortunately, electronic health record data are known to suffer from significant data quality problems. Awareness of the problem of electronic health record data quality is growing, but methods for measuring data quality remain ad hoc. Clinical researchers must handle this complicated problem without systematic or validated methods. The lack of appropriate or trustworthy electronic health record data quality assessment methodology limits the validity of research performed with electronic health record data. This dissertation documents the development of a data quality assessment framework and guideline for clinical researchers engaged in the secondary use of electronic health record data for retrospective research. Through a systematic literature review and interviews with key stakeholders, we identified core constructs of data quality, as well as priorities for future approaches to electronic health record data quality assessment. We used a data-driven approach to demonstrate that data quality is task-dependent, indicating that appropriate data quality measures must be selected, applied, and interpreted within the context of a specific study. On the basis of these results, we developed and evaluated a dynamic guideline for data quality measures in order to help researchers choose data quality measures and methods appropriately within the context of reusing electronic health record data for research.

Molecular imaging of the human body is beginning to revolutionize drug development, drug delivery targeting, prognostics and diagnostics, and patient screening for clinical trials. The primary clinical tool of molecular imaging is Positron Emission Tomography (PET), which uses radioactively tagged probes (radioligands) for the in vivo quantification of blood flow, metabolism, protein distribution, gene expression and drug target occupancy. While many radioligands are used in human research, only a few have been adopted for clinical use. A major obstacle to translating these tools from bench-to-bedside is that PET images acquired using complex radioligands can not be properly interpreted or quantified without arterial blood sampling during the scan. Arterial blood sampling is an invasive, risky, costly, time consuming and uncomfortable procedure that deters subjects' participation and requires highly specialized medical staff presence and laboratories to run blood analysis. Many approaches have been developed over the years to reduce the number of blood samples for certain classes of radioligands, yet the ultimate goal of zero blood samples has remained illusive. In this dissertation we break this proverbial blood barrier and present for the first time a non-invasive PET quantification framework. To accomplish this, we introduce novel image processing, modeling, and tomographic reconstruction tools. First, we developed dedicated pharmacokinetic modeling, machine learning and optimization framework based on the fusion of Electronic Health Records (EHR) data with dynamic PET brain imaging information. EHR data is used to infer individualized metabolism and clearance rates of the radioligand from the body. This is combined with simultaneous estimation on multiple distinct regions of the PET image. A substantial part of this effort involved curating, and then mining, an extensive database of PET, EHR and arterial blood sampling data. Second, we outline a new tomographic reconstruction and resolution modeling approach that takes into account the scanner point spread function in order to improve the resolution of existing PET data-sets. This technique allows visualization and quantification of structures smaller than previously possible. Recovery of signal from blood vessels and integration with the non-invasive framework is demonstrated. We also show general applicability of this technique for visualization and signal recovery from the raphe, a sub-resolution cluster of nuclei in the brain that were previously not detectible with standard techniques. Our framework can be generalizable to all classes of radioligands, independent of their kinetics and distribution within body. Work presented in this thesis will allow the PET scientific and clinical community to advance towards the ultimate goal of making PET cost-effective and to enable new clinical use cases.

Inappropriate use of medications (IUM) is a global problem that can lead to unnecessary harm to the patients and unnecessary costs across the health care system. Identifying and reducing IUM has been a long-lasting challenge and currently, no systematic and automated solution exists to address it. IUM can be manually identified by experts using medication appropriateness criteria (MAC). In this research I first conducted a review of approaches used to identify IUM and reduce IUM. Next, I developed a conceptual model for representing the MAC, and then developed a tool and a workflow for translating the MAC into structured form. Because indications are an important component of the MAC, I conducted a critical appraisal of existing knowledge sources that can be used to that end, namely the medication-indication knowledge-bases. Finally, I demonstrated how these structured MAC can be used to identify patients who are potentially subject to IUM and evaluated the accuracy of this approach. This research identifies the knowledge gaps and technological challenges in identifying and reducing IUM and addresses some of these gaps through the creation of a representation for MAC, a repository of structured MAC, and a set of tools that can assist in evaluating the impact of interventions aimed to reduce IUM or assess its downstream effects. This research also discusses the limitations of existing methods for executing computable decision support rules and proposes solutions needed to enhance these methods so they can support implementation of the MAC.

The increasing adoption of electronic health records (EHRs) has led to an unprecedented amount of patient health information stored in an electronic format. The ability to comb through this information is imperative, both for patient care and computational modeling. Creating a system to minimize unnecessary EHR data, automatically distill longitudinal patient information, and highlight salient parts of a patient’s record is currently an unmet need. However, summarization of EHR data is not a trivial task, as there exist many challenges with reasoning over this data. EHR data elements are most often obtained at irregular intervals as patients are more likely to receive medical care when they are ill, than when they are healthy. The presence of narrative documentation adds another layer of complexity as the notes are riddled with over-sampled text, often caused by the frequent copy-and-pasting during the documentation process. This dissertation synthesizes a set of challenges for automated EHR summarization identified in the literature and presents an array of methods for dealing with some of these challenges. We used hybrid data-driven and knowledge-based approaches to examine abundant redundancy in clinical narrative text, a data-driven approach to identify and mitigate biases in laboratory testing patterns with implications for using clinical data for research, and a probabilistic modeling approach to automatically summarize patient records and learn computational models of disease with heterogeneous data types. The dissertation also demonstrates two applications of the developed methods to important clinical questions: the questions of laboratory test overutilization and cohort selection from EHR data.

The electronic health record (EHR) is an invaluable resource for medical knowledge discovery. EHR data interrogation requires significant medical and technical knowledge. To access EHR data, medical researchers often rely on query analysts to translate their EHR information needs into EHR database queries. The conversation between the medical researcher and the query analyst is an information needs negotiation; I have named this process biomedical query mediation (BQM). There exists no BQM standard to guide medical researchers and query analysts to effectively bridge the communication gap between these medical and technical experts. The current practice of BQM likely varies among query analysts. This variation may contribute to the delivery of EHR data sets with varying degrees of accuracy. For example, a query analyst may return an EHR dataset that misrepresents the medical researcher’s information need or another query analyst may return a different EHR dataset to the medical researcher for the same information need. The process used to formulate the medical researcher’s information need and translate that need into an executable EHR database query may have severe downstream consequences affecting the reliability and quality of EHR datasets for medical research. This dissertation contributes early understandings of the BQM process and thereby improves the transparency and highlights the complexity of BQM by completing five studies: 1) survey the literature from other information intensive scientific disciplines to identify knowledge and methods potentially useful for BQM, 2) perform a review of existing tools and forms for assisting researchers in BQM, 3) perform a content analysis of the BQM process, 4) conduct a cognitive task analysis to detail a generalized workflow, and 5) develop an enriched concept schema to capture comprehensive EHR data needs. This dissertation employs extensive qualitative methods using grounded theory, expert interviews, and cognitive task analysis to produce a deep understanding of BQM. Additionally, I contribute a promising concept class schema to represent medical researchers’ EHR data needs to help standardize the BQM process.

Communication is a critical aspect of clinical work. In 2010, the Joint Commission (JC) found that gaps in communication were among leading factors contributing to medical errors. Healthcare processes, such as patient discharge, depend on interdisciplinary communication to be successful. Electronic health records (EHRs) have the potential to facilitate communication and information sharing between interdisciplinary care team members; however, challenges remain in designing tools for team-based care and questions remain in understanding how EHRs impact interdisciplinary team communication. This dissertation focuses on understanding how EHRs can be designed to support communication and information sharing within interdisciplinary patient care teams. The first aim of the dissertation investigated how EHRs impact interdisciplinary clinical teams’ communication, shared mental models, and information sharing activities. The results showed that implementing new EHR tools appeared to have little impact on communication and shared mental models, but new information sharing activities mediated by EHR developed. These changes and lack thereof suggest that new EHR tools will be specifically needed to facilitate interdisciplinary team information sharing activities. The second aim of the dissertation investigates the information sharing activities and information needs of interdisciplinary team members during patient discharge. The results showed that the information clinicians sought out during discharge depended on the roles that person played as well as the progress of the discharge process. Future EHR tools should be aware of how patient care teams are progressing through the patient discharge process in order to provide information contextualized to their current tasks. In conclusion, interdisciplinary team communication and information sharing remain poorly supported by current EHRs and new tools designed specifically for interdisciplinary teams should provide information based on the completion of team activities.

In population health, the study of unobserved, or latent, heterogeneity in longitudinal data may help inform public health interventions. Growth mixture modeling is a flexible tool for modeling latent heterogeneity in longitudinal data. However, the application of growth mixture models to certain data types, namely, complex survey data and electronic health records, is underdeveloped. For valid statistical inferences in complex survey data, features of the sample design must be incorporated into statistical analysis. In electronic health records, the application of growth mixture modeling is challenged by high levels of missing values. In this dissertation, I have three goals: First, I propose a Bayesian growth mixture model for complex survey data in which I directly incorporate features of the complex sample design. Second, I extend a Bayesian growth mixture model of multiple longitudinal health outcomes collected in electronic health records to a shared parameter model that can account for dierent missing data assumptions. Third, I develop open-source software packages in R for each method that can be used for model tting, selection, and checking.

Background: Cancer treatment and management require complicated clinical decision making to provide the highest quality of care for an individual patient. This is facilitated in part with ever-increasing availability of medications and treatments but hindered due to barriers such as access to care, cost of medications, clinician knowledge, and patient preferences or clinical factors. Although guidelines for cancer treatment and many symptoms have been developed to inform clinical practice, implementation of these guidelines into practice is often delayed or does not occur. Informatics-based approaches, such as clinical decision support, may be an effective tool to improve guideline implementation by delivering patient-specific and evidence-based knowledge to the clinician at the point of care to allow shared decision making with a patient and their family. The large amount of data in the electronic health record can be utilized to develop, evaluate, and implement automated approaches; however, the quality of the data must first be examined and evaluated. Methods: This dissertation addresses gaps the literature about clinical decision making for cancer care delivery. Specifically, following an introduction and review of the literature for relevant topics to this dissertation, the researcher presents three studies. In Study One, the researcher explores the use of clinical decision support in cancer therapeutic decision making by conducting a systematic review of the literature. In Study Two, the researcher conducts a quantitative study to describe the rate of guideline concordant care provided for prevention of acute chemotherapy-induced nausea and vomiting (CINV) and to identify predictors of receiving guideline concordant care. In Study Three, the researcher conducts a mixed-methods study to evaluate the completeness, concordance, and heterogeneity of clinician documentation of CINV. The final chapter of this dissertation is comprised of key findings of each study, the strengths and limitations, clinical and research implications, and future research. Results: In Study One, the systematic review, the researcher identified ten studies that prospectively studied clinical decision support systems or tools in a cancer setting to guide therapeutic decision making. There was variability in these studies, including study design, outcomes measured, and results. There was a trend toward benefit, both in process and patient-specific outcomes. Importantly, few studies were integrated into the electronic health record. In Study Two, of 180 patients age 26 years or less, 36% received guideline concordant care as defined by pediatric or adult guidelines, as appropriate. Factors associated with receiving guideline concordant care included receiving a cisplatin-based regimen, being treated in adult oncology compared to pediatric oncology, and solid tumor diagnosis. In Study Three, of the 127 patient records reviewed for the documentation of chemotherapy-induced nausea and vomiting, 75% had prescriber assessment documented and 58% had nursing assessment documented. Of those who had documented assessments by both prescriber and nurse, 72% were in agreement of the presence/absence of chemotherapy-induced nausea and vomiting. After mapping the concept through the United Medical Language System and developing a post-coordinated expression to identify chemotherapy-induced nausea and vomiting in the text, 85% of prescriber documentation and 100% of nurse documentation could be correctly categorized as present/absent. Further descriptors of the symptoms, such as severity or temporality, however, were infrequently reported. Conclusion: In summary, this dissertation provides new knowledge about decision making in cancer care delivery. Specifically, in Study One the researcher describes that clinical decision support, one potential implementation strategy to improve guideline concordant care, is understudied or under published but a promising potential intervention. In Study Two, I identified factors that were associated with receipt of guideline concordant care for CINV, and these should be further explored to develop interventions. Finally, in Study Three, I report on the limitations of the data quality of CINV documentation in the electronic health record. Future work should focus on validating these results on a multi-institutional level.