Search PubMed⌕ Search

Biomedical subjects

Burke W Mamlin

Publications and source records attributed to Burke W Mamlin.

5 recordsLinked to original sources

Implementing electronic medical record systems in developing countries.

The developing world faces a series of health crises including HIV/AIDS and tuberculosis that threaten the lives of millions of people. Lack of infrastructure and trained, experienced staff are considered important barriers to scaling up treatment for these diseases. In this paper we explain why information systems are important in many healthcare projects in the developing world. We discuss pilot projects demonstrating that such systems are possible and can expand to manage hundreds of thousands of patients. We also pass on the most important practical lessons in design and implementation from our experience in doing this work. Finally, we discuss the importance of collaboration between projects in the development of electronic medical record systems rather than reinventing systems in isolation, and the use of open standards and open source software.

Computer Security↗

Installing and implementing a computer-based patient record system in sub-Saharan Africa: the Mosoriot Medical Record System.

The authors implemented an electronic medical record system in a rural Kenyan health center. Visit data are recorded on a paper encounter form, eliminating duplicate documentation in multiple clinic logbooks. Data are entered into an MS-Access database supported by redundant power systems. The system was initiated in February 2001, and 10,000 visit records were entered for 6,190 patients in six months. The authors present a summary of the clinics visited, diagnoses made, drugs prescribed, and tests performed. After system implementation, patient visits were 22% shorter. They spent 58% less time with providers (p < 0.001) and 38% less time waiting (p = 0.06). Clinic personnel spent 50% less time interacting with patients, two thirds less time interacting with each other, and more time in personal activities. This simple electronic medical record system has bridged the "digital divide." Financial and technical sustainability by Kenyans will be key to its future use and development.

Delivery of Health Care↗

Automated extraction and normalization of findings from cancer-related free-text radiology reports.

UNLABELLED: We describe the performance of a particular natural language processing system that uses knowledge vectors to extract findings from radiology reports. LifeCode (A-Life Medical, Inc.) has been successfully coding reports for billing purposes for several years. In this study, we describe the use of LifeCode to code all findings within a set of 500 cancer-related radiology reports against a test set in which all findings were manually tagged. The system was trained with 1400 reports prior to running the test set. RESULTS: LifeCode had a recall of 84.5% and precision of 95.7% in the coding of cancer-related radiology report findings. CONCLUSION: Despite the use of a modest sized training set and minimal training iterations, when applied to cancer-related reports the system achieved recall and precision measures comparable to other reputable natural language processors in this domain.

Expert Systems↗

Open-source toolkit for simple XML annotation.

Use of Extensible Markup Language (XML) is increasingly prevalent among medical informatics projects. Many of these projects involve, at some point, the interaction between a researcher and specialized XML documents for the purpose of annotating the XML data. We offer a simple toolkit to assist these researchers. Our solution is a simple, yet fully functional, annotation system that can easily be adapted to the needs of the researcher. All of the materials for this toolkit are freely available.

Algorithms↗