A method for extracting electronic patient record data from practice management software systems used in veterinary practice

Abstract

BackgroundData extracted from electronic patient records (EPRs) within practice management software systems are increasingly used in veterinary research. The use of real patient data gives the potential to generate research that can readily be applied to clinical practice. The use of veterinary EPRs for research in the United Kingdom is hindered by the number of different Practice Management System (PMS) providers used by practices, as obtaining and combining data from different systems electronically can be problematic. The use of extensible mark up language (XML) to extract clinical data for research would potentially resolve the compatibility issues between systems. The aim of this study was to establish and validate a method for the extraction of small animal patient records from a veterinary PMS that could potentially be used across multiple systems. An XML schema was designed to extract clinical information from EPRs. The schema was tested and validated in a test system, and was then tested in a real small animal practice where data was extracted for 16 weeks. A 10 % sample of the extracted records was then compared to paper copies provided by the practice.ResultsAll 21 fields encoded by the XML schema, from all of the records in the test system, were extracted with 100 % accuracy. Over the 18 week data collection period 4946 records, from 1279 patients, were extracted from the small animal practice. The 10 % printed records checked and compared with the XML extracted records demonstrated all required data was present. No unrequired, sensitive information e.g. costs or services/products or personal client information was extracted.ConclusionsThis is the first time a method for data extraction from EPRs in veterinary practice using an XML schema has been reported in the United Kingdom. This is an efficient and accurate way of extracting data which could be applied to all PMSs nationally and internationally.Electronic supplementary materialThe online version of this article (doi:10.1186/s12917-016-0861-y) contains supplementary material, which is available to authorized users.

A Transdisciplinary Approach Supporting the Implementation of a Big Data Project in Livestock Production: An Example From the Swiss Pig Production Industry

“…Text mining tools have been reported for extracting clinical data from electronic patient records created using veterinary practice management software. However, these reports are only for companions animals (9, 32, 33). Companion animal data are consistently recorded at the individual animal level.…”

Veterinary informatics: forging the future between veterinary medicine, human medicine, and One Health initiatives—a joint paper by the Association for Veterinary Informatics (AVI) and the CTSA One Health Alliance (COHA)

“…Most studies focus on single-system or hospital analysis, establishing a gold-standard within a single institution. 27 , 108 , 109 Newer, “noisy” labeling techniques may be able to help provide training data for machine learning algorithms for specific clinical tasks, and this is an area of possible significant impact. 110 Examining the extent to which the few labeled data that exist can be used to build algorithms to help with prediction task from other domains (private practice, specialty practice) will be important to help advance the field without the massive number of medical coders who work in human healthcare.…”

“…Standardization of veterinary medical records have been isolated to individual private organizations that require specific techniques for extraction, but there have been few attempts to integrate structured terminology in veterinary clinical practice. 27 In human medicine, many medical records are encoded either during practice or as a post-processing technique once the record is complete. 28–31 This is often due to common drivers such as effective insurance billing and documented medical information retrieval, which veterinary medicine currently lacks.…”

Man’s best friend in life and death: scientific perspectives and challenges of dog brain banking

“…2), which may develop various pathologies during the screening period (ideally the whole lifespan). Veterinary databases could represent a highly valuable source of medical data as most veterinary clinics utilize practice management software [117].…”