Person:
Reisner, Andrew

Profile Picture

Email Address

AA Acceptance Date

Birth Date

Research Projects

Organizational Units

Job Title

Last Name

Reisner

First Name

Andrew

Name

Reisner, Andrew

Filters

2008 - 200912010 - 20171

Settings

Author's Publications: search.filters.isAuthorOfPublication.5509852a-80b0-4c01-b920-d2b01a5dbe73

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    Hypotension in ICU Patients Receiving Vasopressor Therapy
    (Nature Publishing Group UK, 2017) Yapps, Bryce; Shin, Sungtae; Bighamian, Ramin; Thorsen, Jill; Arsenault, Colleen; Quraishi, Sadeq; Hahn, Jin-Oh; Reisner, Andrew
    Vasopressor infusion (VPI) is used to treat hypotension in an ICU. We studied compliance with blood pressure (BP) goals during VPI and whether a statistical model might be efficacious for advance warning of impending hypotension, compared with a basic hypotension threshold alert. Retrospective data were obtained from a public database. Studying adult ICU patients receiving VPI at submaximal dosages, we analyzed characteristics of sustained hypotension episodes (>15 min) and then developed a logistic regression model to predict hypotension episodes using input features related to BP trends. The model was then validated with prospective data. In the retrospective dataset, 102-of-215 ICU stays experienced >1 hypotension episode (median of 2.5 episodes per day in this subgroup). When trained with 75% of retrospective dataset, testing with the remaining 25% of the dataset showed that the model and the threshold alert detected 99.6% and 100% of the episodes, respectively, with median advance forecast times (AFT) of 12 and 0 min. In a second, prospective dataset, the model detected 100% of 26 episodes with a median AFT of 22 min. In conclusion, episodes of hypotension were common during VPI in the ICU. A logistic regression model using BP temporal trend features predicted the episodes before their onset.
  • Thumbnail Image
    Publication
    Automated De-Identification of Free-Text Medical Records
    (BioMed Central, 2008) Neamatullah, Ishna; Douglass, Margaret M; Lehman, Li-wei H; Reisner, Andrew; Villarroel, Mauricio; Long, William J; Szolovits, Peter; Moody, George B; Mark, Roger Greenwood; Clifford, Gari D
    Background: Text-based patient medical records are a vital resource in medical research. In order to preserve patient confidentiality, however, the U.S. Health Insurance Portability and Accountability Act (HIPAA) requires that protected health information (PHI) be removed from medical records before they can be disseminated. Manual de-identification of large medical record databases is prohibitively expensive, time-consuming and prone to error, necessitating automatic methods for large-scale, automated de-identification. Methods: We describe an automated Perl-based de-identification software package that is generally usable on most free-text medical records, e.g., nursing notes, discharge summaries, X-ray reports, etc. The software uses lexical look-up tables, regular expressions, and simple heuristics to locate both HIPAA PHI, and an extended PHI set that includes doctors' names and years of dates. To develop the de-identification approach, we assembled a gold standard corpus of re-identified nursing notes with real PHI replaced by realistic surrogate information. This corpus consists of 2,434 nursing notes containing 334,000 words and a total of 1,779 instances of PHI taken from 163 randomly selected patient records. This gold standard corpus was used to refine the algorithm and measure its sensitivity. To test the algorithm on data not used in its development, we constructed a second test corpus of 1,836 nursing notes containing 296,400 words. The algorithm's false negative rate was evaluated using this test corpus. Results: Performance evaluation of the de-identification software on the development corpus yielded an overall recall of 0.967, precision value of 0.749, and fallout value of approximately 0.002. On the test corpus, a total of 90 instances of false negatives were found, or 27 per 100,000 word count, with an estimated recall of 0.943. Only one full date and one age over 89 were missed. No patient names were missed in either corpus. Conclusion: We have developed a pattern-matching de-identification system based on dictionary look-ups, regular expressions, and heuristics. Evaluation based on two different sets of nursing notes collected from a U.S. hospital suggests that, in terms of recall, the software out-performs a single human de-identifier (0.81) and performs at least as well as a consensus of two human de-identifiers (0.94). The system is currently tuned to de-identify PHI in nursing notes and discharge summaries but is sufficiently generalized and can be customized to handle text files of any format. Although the accuracy of the algorithm is high, it is probably insufficient to be used to publicly disseminate medical data. The open-source de-identification software and the gold standard re-identified corpus of medical records have therefore been made available to researchers via the PhysioNet website to encourage improvements in the algorithm.