Browsing by Author "Samore, Matthew H."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Automatic de-identification of textual documents in the electronic health record: a review of recent research
    (BMC, 2010-08-02) Meystre, Stephane M.; Friedlin, F. Jeffrey; South, Brett R.; Shen, Shuying; Samore, Matthew H.; BioHealth Informatics, School of Informatics and Computing
    Background In the United States, the Health Insurance Portability and Accountability Act (HIPAA) protects the confidentiality of patient data and requires the informed consent of the patient and approval of the Internal Review Board to use data for research purposes, but these requirements can be waived if data is de-identified. For clinical data to be considered de-identified, the HIPAA "Safe Harbor" technique requires 18 data elements (called PHI: Protected Health Information) to be removed. The de-identification of narrative text documents is often realized manually, and requires significant resources. Well aware of these issues, several authors have investigated automated de-identification of narrative text documents from the electronic health record, and a review of recent research in this domain is presented here. Methods This review focuses on recently published research (after 1995), and includes relevant publications from bibliographic queries in PubMed, conference proceedings, the ACM Digital Library, and interesting publications referenced in already included papers. Results The literature search returned more than 200 publications. The majority focused only on structured data de-identification instead of narrative text, on image de-identification, or described manual de-identification, and were therefore excluded. Finally, 18 publications describing automated text de-identification were selected for detailed analysis of the architecture and methods used, the types of PHI detected and removed, the external resources used, and the types of clinical documents targeted. All text de-identification systems aimed to identify and remove person names, and many included other types of PHI. Most systems used only one or two specific clinical document types, and were mostly based on two different groups of methodologies: pattern matching and machine learning. Many systems combined both approaches for different types of PHI, but the majority relied only on pattern matching, rules, and dictionaries.Conclusions In general, methods based on dictionaries performed better with PHI that is rarely mentioned in clinical text, but are more difficult to generalize. Methods based on machine learning tend to perform better, especially with PHI that is not mentioned in the dictionaries used. Finally, the issues of anonymization, sufficient performance, and "over-scrubbing" are discussed in this publication.
  • Thumbnail Image
    Item
    A systematic review of the epidemiology of carbapenem-resistant Enterobacteriaceae in the United States
    (BMC, 2018-04-24) Livorsi, Daniel J.; Chorazy, Margaret L.; Schweizer, Marin L.; Balkenende, Erin C.; Blevins, Amy E.; Nair, Rajeshwari; Samore, Matthew H.; Nelson, Richard E.; Khader, Karim; Perencevich, Eli N.; Ruth Lilly Medical Library, School of Medicine
    Background: Carbapenem-resistant Enterobacteriaceae (CRE) pose an urgent public health threat in the United States. An important step in planning and monitoring a national response to CRE is understanding its epidemiology and associated outcomes. We conducted a systematic literature review of studies that investigated incidence and outcomes of CRE infection in the US. Methods: We performed searches in MEDLINE via Ovid, CDSR, DARE, CENTRAL, NHS EED, Scopus, and Web of Science for articles published from 1/1/2000 to 2/1/2016 about the incidence and outcomes of CRE at US sites. Results: Five studies evaluated incidence, but many used differing definitions for cases. Across the entire US population, the reported incidence of CRE was 0.3-2.93 infections per 100,000 person-years. Infection rates were highest in long-term acute-care (LTAC) hospitals. There was insufficient data to assess trends in infection rates over time. Four studies evaluated outcomes. Mortality was higher in CRE patients in some but not all studies. Conclusion: While the incidence of CRE infections in the United States remains low on a national level, the incidence is highest in LTACs. Studies assessing outcomes in CRE-infected patients are limited in number, small in size, and have reached conflicting results. Future research should measure a variety of clinical outcomes and adequately adjust for confounders to better assess the full burden of CRE.