Dataset Information

Automated outcome classification of emergency department computed tomography imaging reports.

ABSTRACT: BACKGROUND:Reliably abstracting outcomes from free-text electronic health records remains a challenge. While automated classification of free text has been a popular medical informatics topic, performance validation using real-world clinical data has been limited. The two main approaches are linguistic (natural language processing [NLP]) and statistical (machine learning). The authors have developed a hybrid system for abstracting computed tomography (CT) reports for specified outcomes. OBJECTIVES:The objective was to measure performance of a hybrid NLP and machine learning system for automated outcome classification of emergency department (ED) CT imaging reports. The hypothesis was that such a system is comparable to medical personnel doing the data abstraction. METHODS:A secondary analysis was performed on a prior diagnostic imaging study on 3,710 blunt facial trauma victims. Staff radiologists dictated CT reports as free text, which were then deidentified. A trained data abstractor manually coded the reference standard outcome of acute orbital fracture, with a random subset double-coded for reliability. The data set was randomly split evenly into training and testing sets. Training patient reports were used as input to the Medical Language Extraction and Encoding (MedLEE) NLP tool to create structured output containing standardized medical terms and modifiers for certainty and temporal status. Findings were filtered for low certainty and past/future modifiers and then combined with the manual reference standard to generate decision tree classifiers using data mining tools Waikato Environment for Knowledge Analysis (WEKA) 3.7.5 and Salford Predictive Miner 6.6. Performance of decision tree classifiers was evaluated on the testing set with or without NLP processing. RESULTS:The performance of machine learning alone was comparable to prior NLP studies (sensitivity = 0.92, specificity = 0.93, precision = 0.95, recall = 0.93, f-score = 0.94), and the combined use of NLP and machine learning showed further improvement (sensitivity = 0.93, specificity = 0.97, precision = 0.97, recall = 0.96, f-score = 0.97). This performance is similar to, or better than, that of medical personnel in previous studies. CONCLUSIONS:A hybrid NLP and machine learning automated classification system shows promise in coding free-text electronic clinical data.

SUBMITTER: Yadav K

PROVIDER: S-EPMC3898888 | biostudies-literature | 2013 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated outcome classification of emergency department computed tomography imaging reports.

Yadav Kabir K Sarioglu Efsun E Smith Meaghan M Choi Hyeong-Ah HA

Academic emergency medicine : official journal of the Society for Academic Emergency Medicine 20130801 8

<h4>Background</h4>Reliably abstracting outcomes from free-text electronic health records remains a challenge. While automated classification of free text has been a popular medical informatics topic, performance validation using real-world clinical data has been limited. The two main approaches are linguistic (natural language processing [NLP]) and statistical (machine learning). The authors have developed a hybrid system for abstracting computed tomography (CT) reports for specified outcomes.< ...[more]

PMID: 24033628

Similar Datasets

Project description:Study objectiveReduced-dose computed tomography (CT) scans have been recommended for diagnosis of kidney stone but are rarely used in the emergency department (ED) setting. Test characteristics are incompletely characterized, particularly in obese patients. Our primary outcome is to determine the sensitivity and specificity of a reduced-dose CT protocol for symptomatic ureteral stones, particularly those large enough to require intervention, using a protocol stratified by patient size.MethodsThis was a prospective, blinded observational study of 201 patients at an academic medical center. Consenting subjects underwent both regular- and reduced-dose CT, stratified into a high and low body mass index (BMI) protocol based on effective abdominal diameter. Reduced-dose CT scans were interpreted by radiologists blinded to regular-dose interpretations. Follow-up for outcome and intervention was performed at 90 days.ResultsCT scans with both regular and reduced doses were conducted for 201 patients, with 63% receiving the high BMI reduced-dose protocol. Ureteral stone was identified in 102 patients (50.7%) of those receiving regular-dose CT, with a ureteral stone greater than 5 mm identified in 26 subjects (12.9%). Sensitivity of the reduced-dose CT for any ureteral stone was 90.2% (95% confidence interval [CI] 82.3% to 95.0%), with a specificity of 99.0% (95% CI 93.7% to 100.0%). For stones greater than 5 mm, sensitivity was 100% (95% CI 85.0% to 100.0%). Reduced-dose CT identified 96% of patients who required intervention for ureteral stone within 90 days. Mean reduction in size-specific dose estimate was 18.6 milligray (mGy), from 21.7 mGy (SD 9.7) to 3.4 mGy (SD 0.9).ConclusionCT with substantial dose reduction was 90.2% (95% CI 82.3% to 95.0%) sensitive and 98.9% (95% CI 85.0% to 100.0%) specific for ureteral stones in ED patients with a wide range of BMIs. Reduced-dose CT was 96.0% (95% CI 80.5% to 99.3%) sensitive for ureteral stones requiring intervention within 90 days.

Project description:OBJECTIVES:We propose a novel computational approach for the automated classification of classic versus atypical usual interstitial pneumonia (UIP). MATERIALS AND METHODS:Thirty-three patients with UIP were enrolled in this study. They were classified as classic versus atypical UIP by a consensus of 2 thoracic radiologists with more than 15 years of experience using the American Thoracic Society evidence-based guidelines for computed tomography diagnosis of UIP. Two cardiothoracic fellows with 1 year of subspecialty training provided independent readings. The system is based on regional characterization of the morphological tissue properties of lung using volumetric texture analysis of multiple-detector computed tomography images. A simple digital atlas with 36 lung subregions is used to locate texture properties, from which the responses of multidirectional Riesz wavelets are obtained. Machine learning is used to aggregate and to map the regional texture attributes to a simple score that can be used to stratify patients with UIP into classic and atypical subtypes. RESULTS:We compared the predictions on the basis of regional volumetric texture analysis with the ground truth established by expert consensus. The area under the receiver operating characteristic curve of the proposed score was estimated to be 0.81 using a leave-one-patient-out cross-validation, with high specificity for classic UIP. The performance of our automated method was found to be similar to that of the 2 fellows and to the agreement between experienced chest radiologists reported in the literature. However, the errors of our method and the fellows occurred on different cases, which suggests that combining human and computerized evaluations may be synergistic. CONCLUSIONS:Our results are encouraging and suggest that an automated system may be useful in routine clinical practice as a diagnostic aid for identifying patients with complex lung disease such as classic UIP, obviating the need for invasive surgical lung biopsy and its associated risks.

Dataset Information

Automated outcome classification of emergency department computed tomography imaging reports.

Publications

Automated outcome classification of emergency department computed tomography imaging reports.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets