PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 9787626

Automatic coding of diagnostic reports.

L M de Bruijn·A Hasman·J W Arends
View original source ↗Export metadata ↓

Abstract

A method is presented for assigning classification codes to pathology reports by searching similar reports from an archive collection. The key for searching is textual similarity, which estimates the true, semantic similarity. This method does not require explicit modeling, and can be applied to any language or any application domain that uses natural language reporting. A number of simulation experiments was run to assess the accuracy of the method and to indicate the role of size of the archive and the transfer of document collections across laboratories. In at least 63% of the simulation trials, the most similar archive text offered a suitable classification on organ, origin and diagnosis. In 85 to 90% of the trials, the archive's best solution was found within the first five similar reports. The results indicate that the method is suitable for its purpose: suggesting potentially correct classifications to the reporting diagnostician.

Explore related subjects

Diagnosis, Computer-AssistedHospital RecordsHumansInformation Storage and RetrievalMedical Records Systems, ComputerizedNatural Language ProcessingPathology Department, HospitalSoftwareTerminology as TopicJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

L M de Bruijn, A Hasman, J W Arends. 1998. Automatic coding of diagnostic reports.. https://pubmed.ncbi.nlm.nih.gov/9787626/

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed1999

The Pap smear, automated rescreening, and negligent nondisclosure.

A new element in the Papanicolaou smear liability crisis is the recent US Food and Drug Administration approval of 2 automated rescreening devices. Their manufacturers have undertaken aggressive advertising in medical journals and in women's magazines, generating controversy about whether this positions such devices as the new standard of care and whether failure to offer such rescreening might lead to liability alleging to tort of negligent nondisclosure, with contributing opinions from pathologists' and manufacturers' counsels. Cases are cited in prenatal diagnostics and blood banking that established liability for failing to disclose diagnostic modalities used by at most only a minority of practitioners and, therefore, have not yet achieved standard-of-care status. It is concluded that informed consent for cervicovaginal smears should include disclosure of the availability of automated rescreening to reduce negligence liability.

Diagnosis, Computer-Assisted↗
PubMed1999

Medical practice and informatics tools: a vignette.

In this article the authors recreate an improvisational vignette originally presented at the Third Annual Information Connection in Burlington, Vermont, in January 1998. The vignette illustrates various state-of-the-art decision-support systems for clinical care and their promises and problems in real-world medical practice. The characters are Dr. Alex Grant, a rural physician in solo practice; Anna Everett, a patient suffering from chronic headaches; Bob, a hospital librarian; and Sarah, Dr. Grant's nurse. The short play centers on Dr. Grant's attempt to diagnose the cause of Anna's headaches (which he and she believe to be sinus-related) and the roles information technologies--Medline searching, Anna's own Internet searches, the use of MDConsult, which provides Internet access to standard medical texts, journals, etc., and a desktop decision-support tool called Problem Knowledge Couplers--play in this process. The vignette concludes with the realization that while computer technologies can be of great help in medicine "there is still a need for a good doctor to pull it all together."

Diagnosis, Computer-Assisted↗