Biomedical subjects

Burke Mamlin

Publications and source records attributed to Burke Mamlin.

6 recordsLinked to original sources

PubMed2005

A call for collaboration: building an EMR for developing countries.

Millions of people are either living with or dying from HIV/AIDS; most of this living and dying is taking place in developing countries. There is an immediate need for electronic medical record systems to help scale up HIV/AIDS prevention and treatment programs, reduce critical human errors, and support the research necessary to guide future efforts. Several groups are working on this problem, but most of this work is occurring within silos. To be more effective, we must find ways to collaborate.

Developing Countries↗

PubMed2004

A simple error classification system for understanding sources of error in automatic speech recognition and human transcription.

OBJECTIVES: To (1) discover the types of errors most commonly found in clinical notes that are generated either using automatic speech recognition (ASR) or via human transcription and (2) to develop efficient rules for classifying these errors based on the categories found in (1). The purpose of classifying errors into categories is to understand the underlying processes that generate these errors, so that measures can be taken to improve these processes. METHODS: We integrated the Dragon NaturallySpeaking v4.0 speech recognition engine into the Regenstrief Medical Record System. We captured the text output of the speech engine prior to error correction by the speaker. We also acquired a set of human transcribed but uncorrected notes for comparison. We then attempted to error correct these notes based on looking at the context alone. Initially, three domain experts independently examined 104 ASR notes (containing 29,144 words) generated by a single speaker and 44 human transcribed notes (containing 14,199 words) generated by multiple speakers for errors. Collaborative group sessions were subsequently held where error categorizes were determined and rules developed and incrementally refined for systematically examining the notes and classifying errors. RESULTS: We found that the errors could be classified into nine categories: (1) announciation errors occurring due to speaker mispronounciation, (2) dictionary errors resulting from missing terms, (3) suffix errors caused by misrecognition of appropriate tenses of a word, (4) added words, (5) deleted words, (6) homonym errors resulting from substitution of a phonetically identical word, (7) spelling errors, (8) nonsense errors, words/phrases whose meaning could not be appreciated by examining just the context, and (9) critical errors, words/phrases where a reader of a note could potentially misunderstand the concept that was related by the speaker. CONCLUSIONS: A simple method is presented for examining errors in transcribed documents and classifying these errors into meaningful and useful categories. Such a classification can potentially help pinpoint sources of such errors so that measures (such as better training of the speaker and improved dictionary and language modeling) can be taken to optimize the error rates.

Automation↗

PubMed2003

Using information technology to improve the health care of older adults.

The high burden of illness and frailty common among our growing population of older adults often results in fragmentation of care across providers and health care systems, increasing the complexity and costs of caring for these patients. Information technology offers one way to meet this challenge. Scientists at the Regenstrief Institute have more than a quarter-century of experience in using medical informatics to support clinicians in the day-to-day care of older adults. Their research has progressed through several evolutionary cycles, beginning with the acquisition of relevant data and moving to studies of the most efficient and effective mechanisms that bring information to bear at the time of clinical decision making. Information technology designed with the input of the end user has the greatest promise of changing provider behavior because it balances technological challenges with the cultural context of the practice environment. One topic of active research is information technology to support transitions of care among sites and providers. These transitions place older adults at increased risk for avoidable illness, death, and health care costs. Information systems that improve communication among providers during these transitions have the potential to improve safety and reduce costs.

Aged↗

PubMed2003

Open Source software in medical informatics--why, how and what.

'Open Source' is a 20-40 year old approach to licensing and distributing software that has recently burst into public view. Against conventional wisdom this approach has been wildly successful in the general software market--probably because the openness lets programmers the world over obtain, critique, use, and build upon the source code without licensing fees. Linux, a UNIX-like operating system, is the best known success. But computer scientists at the University of California, Berkeley began the tradition of software sharing in the mid 1970s with BSD UNIX and distributed the major internet network protocols as source code without a fee. Medical informatics has its own history of Open Source distribution: Massachusetts General's COSTAR and the Veterans Administration's VISTA software have been distributed as source code at no cost for decades. Bioinformatics, our sister field, has embraced the Open Source movement and developed rich libraries of open-source software. Open Source has now gained a tiny foothold in health care (OSCAR GEHR, OpenEMed). Medical informatics researchers and funding agencies should support and nurture this movement. In a world where open-source modules were integrated into operational health care systems, informatics researchers would have real world niches into which they could engraft and test their software inventions. This could produce a burst of innovation that would help solve the many problems of the health care system. We at the Regenstrief Institute are doing our part by moving all of our development to the open-source model.

Database Management Systems↗

PubMed2002

A successful technique for removing names in pathology reports using an augmented search and replace method.

The ability to access large amounts of de-identified clinical data would facilitate epidemiologic and retrospective research. Previously described de-identification methods require knowledge of natural language processing or have not been made available to the public. We take advantage of the fact that the vast majority of proper names in pathology reports occur in pairs. In rare cases where one proper name is by itself, it is preceded or followed by an affix that identifies it as a proper name (Mrs., Dr., PhD). We created a tool based on this observation using substitution methods that was easy to implement and was largely based on publicly available data sources. We compiled a Clinical and Common Usage Word (CCUW) list as well as a fairly comprehensive proper name list. Despite the large overlap between these two lists, we were able to refine our methods to achieve accuracy similar to previous attempts at de-identification. Our method found 98.7% of 231 proper names in the narrative sections of pathology reports. Three single proper names were missed out of 1001 pathology reports (0.3%, no first name/last name pairs). It is unlikely that identification could be implied from this information. We will continue to refine our methods, specifically working to improve the quality of our CCUW and proper name lists to obtain higher levels of accuracy.

Algorithms↗

PubMedDate not supplied

The Indiana network for patient care: a working local health information infrastructure. An example of a working infrastructure collaboration that links data from five health systems and hundreds of millions of entries.

The Indiana Network for Patient Care (INPC) is a local health information infrastructure (LHII) that includes information from the five major hospital systems (fifteen separate hospitals), the county and state public health departments, and Indiana Medicaid and RxHub and that carries 660 million separate results. It provides cross-institutional access to physicians in emergency rooms and hospitals based on patient-physician proximity or on hospital credentialing. The network includes and delivers laboratory, radiology, dictation, and other documents to a majority of Indianapolis office practices. The INPC began operation seven years ago and is one of the first and best examples of an LHII.

Cooperative Behavior↗