Dataset Information

Automated identification of pneumonia in chest radiograph reports in critically ill patients.

ABSTRACT: Prior studies demonstrate the suitability of natural language processing (NLP) for identifying pneumonia in chest radiograph (CXR) reports, however, few evaluate this approach in intensive care unit (ICU) patients.From a total of 194,615 ICU reports, we empirically developed a lexicon to categorize pneumonia-relevant terms and uncertainty profiles. We encoded lexicon items into unique queries within an NLP software application and designed an algorithm to assign automated interpretations ('positive', 'possible', or 'negative') based on each report's query profile. We evaluated algorithm performance in a sample of 2,466 CXR reports interpreted by physician consensus and in two ICU patient subgroups including those admitted for pneumonia and for rheumatologic/endocrine diagnoses.Most reports were deemed 'negative' (51.8%) by physician consensus. Many were 'possible' (41.7%); only 6.5% were 'positive' for pneumonia. The lexicon included 105 terms and uncertainty profiles that were encoded into 31 NLP queries. Queries identified 534,322 'hits' in the full sample, with 2.7 ± 2.6 'hits' per report. An algorithm, comprised of twenty rules and probability steps, assigned interpretations to reports based on query profiles. In the validation set, the algorithm had 92.7% sensitivity, 91.1% specificity, 93.3% positive predictive value, and 90.3% negative predictive value for differentiating 'negative' from 'positive'/'possible' reports. In the ICU subgroups, the algorithm also demonstrated good performance, misclassifying few reports (5.8%).Many CXR reports in ICU patients demonstrate frank uncertainty regarding a pneumonia diagnosis. This electronic tool demonstrates promise for assigning automated interpretations to CXR reports by leveraging both terms and uncertainty profiles.

SUBMITTER: Liu V

PROVIDER: S-EPMC3765332 | biostudies-literature | 2013 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated identification of pneumonia in chest radiograph reports in critically ill patients.

Liu Vincent V Clark Mark P MP Mendoza Mark M Saket Ramin R Gardner Marla N MN Turk Benjamin J BJ Escobar Gabriel J GJ

BMC medical informatics and decision making 20130815

<h4>Background</h4>Prior studies demonstrate the suitability of natural language processing (NLP) for identifying pneumonia in chest radiograph (CXR) reports, however, few evaluate this approach in intensive care unit (ICU) patients.<h4>Methods</h4>From a total of 194,615 ICU reports, we empirically developed a lexicon to categorize pneumonia-relevant terms and uncertainty profiles. We encoded lexicon items into unique queries within an NLP software application and designed an algorithm to assig ...[more]

PMID: 23947340

Similar Datasets

Project description:Micronutrient deficiencies can develop in critically ill patients, arising from factors such as decreased intake, increased losses, drug interactions, and hypermetabolism. These deficiencies may compromise important immune functions, with potential implications for patient outcomes. Alternatively, micronutrient blood levels may become low due to inflammation-driven redistribution rather than consumption. This explorative pilot study investigates blood micronutrient concentrations during the first three weeks of ICU stay in critically ill COVID-19 patients and evaluates the impact of additional micronutrient administration. Moreover, associations between inflammation, disease severity, and micronutrient status were explored. We measured weekly concentrations of vitamins A, B6, D, and E; iron; zinc; copper; selenium; and CRP as a marker of inflammation state and the SOFA score indicating disease severity in 20 critically ill COVID-19 patients during three weeks of ICU stay. Half of the patients received additional (intravenous) micronutrient administration. Data were analyzed with linear mixed models and Pearson's correlation coefficient. High deficiency rates of vitamins A, B6, and D; zinc; and selenium (50-100%) were found at ICU admission, along with low iron status. After three weeks, vitamins B6 and D deficiencies persisted, and iron status remained low. Plasma levels of vitamins A and E, zinc, and selenium improved. No significant differences in micronutrient levels were found between patient groups. Negative correlations were identified between the CRP level and levels of vitamins A and E, iron, transferrin, zinc, and selenium. SOFA scores negatively correlated with vitamin D and selenium levels. Our findings reveal high micronutrient deficiency rates at ICU admission. Additional micronutrient administration did not enhance levels or expedite their increase. Spontaneous increases in vitamins A and E, zinc, and selenium levels were associated with inflammation resolution, suggesting that observed low levels may be attributed, at least in part, to redistribution rather than true deficiencies.

Dataset Information

Automated identification of pneumonia in chest radiograph reports in critically ill patients.

Publications

Automated identification of pneumonia in chest radiograph reports in critically ill patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets