Semantic processing of EHR data for clinical research

There is a growing need to semantically process and integrate clinical data from different sources for clinical research. This paper presents an approach to integrate EHRs from heterogeneous resources and generate integrated data in different data formats or semantics to support various clinical research applications. The proposed approach builds semantic data virtualization layers on top of data sources, which generate data in the requested semantics or formats on demand. This approach avoids upfront dumping to and synchronizing of the data with various representations. Data from different EHR systems are first mapped to RDF data with source semantics, and then converted to representations with harmonized domain semantics where domain ontologies and terminologies are used to improve reusability. It is also possible to further convert data to application semantics and store the converted results in clinical research databases, e.g. i2b2, OMOP, to support different clinical research settings. Semantic conversions between different representations are explicitly expressed using N3 rules and executed by an N3 Reasoner (EYE), which can also generate proofs of the conversion processes. The solution presented in this paper has been applied to real-world applications that process large scale EHR data.     

Text processing in pathology. Setup and content of text data for autopsy reports

Elaboration of a text catalogue of the most important terms and findings is essential for computerized reports to be effectively introduced in pathology. Such a catalogue must be constructed so, that the majority of reports or findings, respectively, can be accommodated or generated. Structure and content of a text catalogue are illustrated with examples for autopsy reports.     

Standardizing clinical laboratory data for secondary use

Clinical databases provide a rich source of data for answering clinical research questions. However, the variables recorded in clinical data systems are often identified by local, idiosyncratic, and sometimes redundant and/or ambiguous names (or codes) rather than unique, well-organized codes from standard code systems. This reality discourages research use of such databases, because researchers must invest considerable time in cleaning up the data before they can ask their first research question. Researchers at MIT developed MIMIC-II, a nearly complete collection of clinical data about intensive care patients. Because its data are drawn from existing clinical systems, it has many of the problems described above. In collaboration with the MIT researchers, we have begun a process of cleaning up the data and mapping the variable names and codes to LOINC codes. Our first step, which we describe here, was to map all of the laboratory test observations to LOINC codes. We were able to map 87% of the unique laboratory tests that cover 94% of the total number of laboratory tests results. Of the 13% of tests that we could not map, nearly 60% were due to test names whose real meaning could not be discerned and 29% represented tests that were not yet included in the LOINC table. These results suggest that LOINC codes cover most of laboratory tests used in critical care. We have delivered this work to the MIMIC-II researchers, who have included it in their standard MIMIC-II database release so that researchers who use this database in the future will not have to do this work.     

Comprehensive graphic-based display of clinical pathology laboratory data

In this age of ever-increasing demands for and uses of patient data, technologic advancements in the form of electronic patient records permit improved data access and prompt retrieval of higher quality patient care data, with more versatility in display, facilitating the integration of information concerning patients over time and between settings of care, which is in turn more accessible for use by practitioners and provides more efficient and effective decision support in areas of patient care. The graphic display of laboratory data is central to the evolving computerized patient record and needs to be taken into careful consideration along with clinician perception and ease of data interpretation in redesigning the graphic reporting of numeric clinical pathology laboratory data. An ideal system should generate user-friendly, graphic-based comprehensive reports highlighting abnormalities with trends for diagnosis, clinical management, and risk-factor detection.     

A comparative study of mobile electronic data entry systems for clinical trials data collection

PURPOSE: To determine the speed, accuracy, ease of use, and user satisfaction of various electronic data entry platforms for use in the collection of mammography clinical trials data. METHOD AND MATERIALS: Four electronic data entry platforms were tested: standalone personal digital assistant (PDA), Tablet PC, digitizer Tablet/PDA Hybrid (DTP Hybrid), and digital pen (d-pen). Standard paper data entry was used as control. Each of five radiologist readers was assigned to enter interpretations for 20 screening mammograms using three out of the five data entry methods. Assistants recorded both start and stop data entry times of the radiologists and the number of help requests made. Data were checked for handwriting recognition accuracy for the d-pen platform using handwriting verification software. A user satisfaction survey was administered at the end of each platform reading session. RESULTS: Tablet PC and d-pen were statistically equivalent to conventional pen and paper in initial data entry speed. Average verification time for d-pen was significantly less than secondary electronic data entry of paper forms (p-value <0.001). The number of errors in handwriting recognition for d-pen was less than secondary electronic data entry of the paper forms data. Users were most satisfied with Tablet PC, d-pen, and conventional pen and paper for data entry. CONCLUSIONS: Tablet PC and d-pen are equally fast and easy-to-use data entry methods that are well tolerated by radiologist users. Handwriting recognition review and correction for the d-pen is significantly faster and more accurate than secondary manual keyboard and mouse data entry.     

Ethics and subsequent use of electronic health record data

The digital health landscape in the United States is evolving and electronic health record data hold great promise for improving health and health equity. Like many scientific and technological advances in health and medicine, there exists an exciting narrative about what we can do with the new technology, as well as reflection about what we should do with it based on what we value. Ethical reflections about the use of EHR data for research and quality improvement have considered the important issues of privacy and informed consent for subsequent use of data. Additional ethical aspects are important in the conversation, including data validity, patient obligation to participate in the learning health system, and ethics integration into training for all personnel who interact with personal health data. Attention to these ethical issues is paramount to our realizing the benefits of electronic health data.     

Data quality assessment framework to assess electronic medical record data for use in research

IntroductionThe proliferation and use of electronic medical records (EMR) in the clinical setting now provide a rich source of clinical data that can be leveraged to support research on patient outcomes, comparative effectiveness, and health systems research. Once the large volume and variety of data that robust clinical EMRs provide is aggregated, the suitability of the data for research purposes must be addressed. Therefore, the purpose of this paper is two-fold. First, we present a stepwise framework capable of guiding initial data quality assessment when matching multiple data sources regardless of context or application. Then, we demonstrate a use case of initial analysis of a longitudinal data repository of electronic health record data that illustrates the first four steps of the framework, and report results.MethodsA six-step data quality assessment framework is proposed and described that includes the following data quality assessment steps: (1) preliminary analysis, (2) documentation–longitudinal concordance, (3) breadth, (4) data element presence, (5) density, and (6) prediction. The six-step framework was applied to the Transport Data Mart—a data repository that contains over 28,000 records for patients that underwent interhospital transfer that includes EMRs from the sending hospitalization, transport, and receiving hospitalization.ResultsThere were a total of 9557 log entries of which 8139 were successfully matched to corresponding hospital encounters. 2832 were successfully mapped to both the sending and receiving hospital encounters (resulting in a 93% automatic matching rate), with 590 including air medical transport EMR data representing a complete case for testing. Results from Step 2 indicate that once records are identified and matched, there appears to be relatively limited drop-off of additional records when the criteria for matching increases, indicating the a proportion of records consistently contain nearly complete data. Measures of central tendency used in Step 3 and 4 exhibit a right skewness suggesting that a small proportion of records contain the highest number of repeated measures for the measured variables.ConclusionsThe proposed six-step data quality assessment framework is useful in establishing the metadata for a longitudinal data repository that can be replicated by other studies. There are practical issues that need to be addressed including the data quality assessments—with the most prescient being the need to establish data quality metrics for benchmarking acceptable levels of EMR data inclusiveness through testing and application.     

Image processing in pathology.

The present study is an effort to ally biopsies to well defined groups of diseases by means of automatic analysis of liver cell nuclei. The results obtained should support the morphologic differential diagnosis of liver diseases. A total of 78 liver biopsies from patients with obstructive jaundice, chronic hepatitis, acute viral hepatitis or with alcoholic liver injury were investigated. Performing automatic analysis of the microscopic pictures 95% of the equatorial sectioned liver cell nuclei are correctly recognized.     

A Fortran program for fast and compact processing of clinical radiotherapy data

A set of Fortran IV programs have been developed to enable a patient registry to operate on a minicomputer of a type frequently used for treatment planning within radiotherapy departments. The system is both comprehensive and flexible, allowing the efficient storage of clinical data in the form of coded units. The coding format used enables inexperienced operators to enter, or extract data from the system with the minimum of keyboard operations.     

The clinical pathology for the twenty-first century

At first, the ideal way of the scientific convention should be reexamined. It is approved the future direction which should do the joint with the related societies. It has been decided that it is held at a partly congruence with Japan Society of Clinical Chemistry in the next fiscal year. The Corporation Promotion Committee(chairman of prof. I. Sakurabayashi) negotiates with the Ministry of Education about the incorporation. The Society Improved Committee(chairman of prof. K. Watanabe) is discussing about a retirement system and improved select system of the councilor. And, though the more than 400 persons of clinical laboratory physicians has been registered as a certified clinical laboratory physicians, it copes in the selection committee of each university does not always taking laboratory medical doctor as a professor of the department of clinical laboratory. And, it becomes the name of the Japan Society of Clinical Pathology does not suit at present state. The Appellation Revision Subcommittee(chairman of K. Nakahara) is discussing in the ideal name of the Society. The opinion of the most part of way will concern national medical insurance. The clinical laboratory tests related groups(Japan Society of Clinical Pathology, Japanese Association of Clinical Laboratory Physicians, Japan Society of Medical technologists, Japan Registered Clinical Laboratories Association, Japan Association of Clinical Reagents Industries, Japan Council of Clinical Reagents wholesales) formed the Council on Clinical Laboratory Tests-Related Organization at present, and the demanding paper was submitted to related associations, such as Ministry of Health and Welfare, Japan Medical Association and so on.     

An administrative data merging solution for dealing with missing data in a clinical registry: adaptation from ICD-9 to ICD-10

Background  

We have previously described a method for dealing with missing data in a prospective cardiac registry initiative. The method involves merging registry data to corresponding ICD-9-CM administrative data to fill in missing data 'holes'. Here, we describe the process of translating our data merging solution to ICD-10, and then validating its performance.