Jeff Gilchrist

Integration of new technology in a legacy system for collecting medical data - challenges and lessons learned

Integrating new technology into a legacy medical system can be very challenging. Completely new systems cannot always be built due to the high cost of medical equipment, thus integrating some new technology into an existing system may be required. This paper looks at the issues and challenges surrounding the integration of new components into a legacy system for collecting medical data. We discuss how the issues were solved, the lessons learned, and how future upgrades can be made more easily.

Parallel Lossless Data Compression Based on the Burrows-Wheeler Transform

In this paper, we present parallel algorithms for lossless data compression based on the Burrows-Wheeler transform (BWT) block-sorting technique. We investigate the performance of using data parallelism and task parallelism for both multi-threaded and message-passing programming. The output produced by the parallel algorithms is fully compatible with their sequential counterparts. To balance the workload among processors we develop a task scheduling strategy. An extensive set of experiments is performed with a shared memory NUMA system using up to 120 processors and on a distributed memory cluster using up to 100 processors. Our experimental results show that significant speedup can be achieved with both data parallel and task parallel methodologies. These algorithms will greatly reduce the amount of time it takes to compress large amounts of data while the compressed data remains in a form that users without access to multiple processor systems can still use.

Performance evaluation of various storage formats for Clinical Data Repositories

The performance of three different Entity-Attribute-Value (EAV) storage formats for Clinical Data Repositories (CDRs) is compared with regards to querying millions of data points from clinical sources to assess the amount of storage space the data use, the speed with which the data can be obtained, and the complexity of the queries required to retrieve the data. Performance results are presented that show that the hybrid EAV approach provides a nice balance of the simple and multi-data type formats.

Performance Evaluation of Various Storage Formats for Clinical Data Repositories

The performance of three different Entity-Attribute-Value (EAV) storage formats for Clinical Data Repositories (CDRs) is compared with regards to querying millions of data points from clinical sources to assess the amount of storage space the data use, the speed with which the data can be obtained, and the complexity of the queries required to retrieve the data. Performance results are presented that show that the hybrid EAV approach provides a nice balance of the simple and multi-data type formats.

Parallel lossless data compression using the Burrows-Wheeler Transform

In this paper, we present parallel algorithms for lossless data compression based on the Burrows-Wheeler Transform (BWT) block-sorting technique. We investigate the performance of using data parallelism and task parallelism for both multi-threaded and message-passing programming. The output produced by the parallel algorithms is fully compatible with their sequential counterparts. To balance the workload among processors we develop a task scheduling strategy. An extensive set of experiments is performed with a shared memory NUMA system using up to 120 processors and on a distributed memory cluster using up to 100 processors. Our experimental results show that significant speedup can be achieved with both data parallel and task parallel methodologies. These algorithms will greatly reduce the amount of time it takes to compress large amounts of data while the compressed data remains in a form that users without access to multiple processor systems can still use.

A Decision-Support System for Expecting Mothers and Obstetricians

This work describes the method used and results achieved in the classification of perinatal outcomes that includes estimating the risk of preterm birth, and a number of outcomes for infants in the neonatal intensive care unit (NICU). A second aspect is knowledge translation in the form of a decision-support tool; being developed for obstetricians and pregnant women to deal with decisions regarding high risk pregnancies.

Usefulness analysis of a Clinical Data Repository design

The perceived usefulness of a Clinical Data Repository (CDR) prototype in a hospital setting was assessed by clinicians to determine whether they would find it helpful for their clinical and research work. The CDR automatically collects and stores clinical data in real time from patient monitoring devices, clinical information systems, laboratory systems, and the Health Records Department in a de-identified, easily extractable format for secondary uses. A secure online survey was distributed to physicians, research institute investigators, and research institute coordinators at the Childrens Hospital of Eastern Ontario (CHEO) through email. According to the survey responses, participants felt the CDR was a useful tool, showed interest in it, and thought it would be important to have for future work. To illustrate how the CDR could be used in a clinical setting we have provided a sample clinical application; a tool for engaging physicians and parents in discussion about the clinical progress and prognosis of infants in the Neonatal Intensive Care Unit (NICU).

Discrimination of Inconsistencies in Medical Data

Missing and erroneous values in patient cases can significantly impact the ability to perform biomedical research for identifying risk factors and causes of clinical events and disease progression. We present a framework that classifies the inconsistencies in a database to automatically process the data for research purposes. The goal is to improve the quality of medical databases by identifying the reason that data are missing, and automatically processing outliers and typographical errors to retain more information from a database. This framework presents an alternative to deleting cases with outliers and typographical errors, while also imputing relevant values into cases with missing data based on the reason that the data is missing, the source of the data, and the data type.

Developing an Automated Clinical Trending Tool for the Neonatal Intensive Care Unit (NICU)

The purpose of this work was to develop a clinical trending tool which tracks patient vital signs and generates alerts for deviations from a defined baseline. This work analyzes four types of patients: a stable patient, a patient who left the Neonatal Intensive Care Unit for an extended period, and two patients who experienced a clinical deterioration. By displaying visual tools which are more intuitive and user friendly for physicians and alerting for short term vital sign deviations of these different patients, we aim to identify trends which may precede clinical deterioration in patients.

Integration of outcome estimations with a clinical decision support system: Application in the neonatal intensive care unit (NICU)

Our previous research led to the development of mortality risk estimations for infants in the neonatal intensive care unit (NICU) using quality archived databases. A decision support system was created with a clinician module containing relevant patient information and a variety of outcome estimations; the PPADS (Physician-Parent Decision Support) tool also contains a module for parents with the aim to help them make joint decisions with physicians on the direction of care for their infant. New work developed the ANN-Builder which uses an open-source artificial neural network library that would enable handling real-time data streaming and automate the process of providing risk estimations of mortality. Additionally, the patient data and risk estimations were successfully integrated into the PPADS tool. The mortality estimations surpass the clinical expectations. The next and final step will be to replace missing values in the data and add alarms for major changes in the risk estimations provided by the system.