Dataset Information

Development of an Electronic Algorithm to Identify in Real Time Adults Hospitalized With Suspected Community-Acquired Pneumonia.

ABSTRACT:

Background

Community-acquired pneumonia (CAP) is a major driver of hospital antibiotic use. Efficient methods to identify patients treated for CAP in real time using the electronic health record (EHR) are needed. Automated identification of these patients could facilitate systematic tracking, intervention, and feedback on CAP-specific metrics such as appropriate antibiotic choice and duration.

Methods

Using retrospective data, we identified suspected CAP cases by searching for patients who received CAP antibiotics AND had an admitting International Classification of Diseases, Tenth Revision (ICD-10) code for pneumonia OR chest imaging within 24 hours OR bacterial urinary antigen testing within 48 hours of admission (denominator query). We subsequently explored different structured and natural language processing (NLP)-derived data from the EHR to identify CAP cases. We evaluated combinations of these electronic variables through receiver operating characteristic (ROC) curves to assess which best identified CAP cases compared to cases identified by manual chart review. Exclusion criteria were age <18 years, absolute neutrophil count <500 cells/mm³, and admission to an oncology unit.

Results

Compared to the gold standard of chart review, the area under the ROC curve to detect CAP was 0.63 (95% confidence interval [CI], .55-.72; P < .01) using structured data (ie, laboratory and vital signs) and 0.83 (95% CI, .77-.90; P < .01) when NLP-derived data from radiographic reports were included. The sensitivity and specificity of the latter model were 80% and 81%, respectively.

Conclusions

Creating an electronic tool that effectively identifies CAP cases in real time is possible, but its accuracy is dependent on NLP-derived radiographic data.

SUBMITTER: Jones G

PROVIDER: S-EPMC8231365 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Community acquired pneumonia (CAP) is a high incidence disease resulting in about 260,000 hospital admissions per year in Germany, more than myocardial infarction or stroke. Worldwide, CAP is the most frequent infectious disease with high lethality ranging from 1.2 % in those 20-29 years old to over 10 % in patients older than 70 years, even in industrial nations. CAP poses numerous medical challenges, which the PROGRESS (Pneumonia Research Network on Genetic Resistance and Susceptibility for the Evolution of Severe Sepsis) network aims to tackle: Operationalization of disease severity throughout the course of disease, outcome prediction for hospitalized patients and prediction of transitions from uncomplicated CAP to severe CAP, and finally, to CAP with sepsis and organ failure as a life-threatening condition. It is a major aim of PROGRESS to understand and predict patient heterogeneity regarding outcome in the hospital and to develop novel treatment concepts.PROGRESS was designed as a clinical, observational, multi-center study of patients with CAP requiring hospitalization. More than 1600 patients selected for low burden of co-morbidities have been enrolled, aiming at a total of 3000. Course of disease, along with therapy, was closely monitored by daily assessments and long-term follow-up. Daily blood samples allow in depth molecular-genetic characterization of patients. We established a well-organized workflow for sample logistics and a comprehensive data management system to collect and manage data from more than 50 study centers in Germany and Austria. Samples are stored in a central biobank and clinical data are stored in a central data base which also integrates all data from molecular assessments.With the PROGRESS study, we established a comprehensive data base of high quality clinical and molecular data allowing investigation of pressing research questions regarding CAP. In-depth molecular characterization will contribute to the discovery of disease mechanisms and establishment of diagnostic and predictive biomarkers. A strength of PROGRESS is the focus on younger patients with low burden of co-morbidities, allowing a more direct look at host biology with less confounding. As a resulting limitation, insights from PROGRESS will require validation in representative patient cohorts to assess clinical utility.The PROGRESS study was retrospectively registered on May 24(th), 2016 with ClinicalTrials.gov: NCT02782013.