Dataset Information

Classification of Current Procedural Terminology Codes from Electronic Health Record Data Using Machine Learning.

ABSTRACT: BACKGROUND:Accurate anesthesiology procedure code data are essential to quality improvement, research, and reimbursement tasks within anesthesiology practices. Advanced data science techniques, including machine learning and natural language processing, offer opportunities to develop classification tools for Current Procedural Terminology codes across anesthesia procedures. METHODS:Models were created using a Train/Test dataset including 1,164,343 procedures from 16 academic and private hospitals. Five supervised machine learning models were created to classify anesthesiology Current Procedural Terminology codes, with accuracy defined as first choice classification matching the institutional-assigned code existing in the perioperative database. The two best performing models were further refined and tested on a Holdout dataset from a single institution distinct from Train/Test. A tunable confidence parameter was created to identify cases for which models were highly accurate, with the goal of at least 95% accuracy, above the reported 2018 Centers for Medicare and Medicaid Services (Baltimore, Maryland) fee-for-service accuracy. Actual submitted claim data from billing specialists were used as a reference standard. RESULTS:Support vector machine and neural network label-embedding attentive models were the best performing models, respectively, demonstrating overall accuracies of 87.9% and 84.2% (single best code), and 96.8% and 94.0% (within top three). Classification accuracy was 96.4% in 47.0% of cases using support vector machine and 94.4% in 62.2% of cases using label-embedding attentive model within the Train/Test dataset. In the Holdout dataset, respective classification accuracies were 93.1% in 58.0% of cases and 95.0% among 62.0%. The most important feature in model training was procedure text. CONCLUSIONS:Through application of machine learning and natural language processing techniques, highly accurate real-time models were created for anesthesiology Current Procedural Terminology code classification. The increased processing speed and a priori targeted accuracy of this classification approach may provide performance optimization and cost reduction for quality improvement, research, and reimbursement tasks reliant on anesthesiology procedure codes.

SUBMITTER: Burns ML

PROVIDER: S-EPMC7665375 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Classification of Current Procedural Terminology Codes from Electronic Health Record Data Using Machine Learning.

Burns Michael L ML Mathis Michael R MR Vandervest John J Tan Xinyu X Lu Bo B Colquhoun Douglas A DA Shah Nirav N Kheterpal Sachin S Saager Leif L

Anesthesiology 20200401 4

<h4>Background</h4>Accurate anesthesiology procedure code data are essential to quality improvement, research, and reimbursement tasks within anesthesiology practices. Advanced data science techniques, including machine learning and natural language processing, offer opportunities to develop classification tools for Current Procedural Terminology codes across anesthesia procedures.<h4>Methods</h4>Models were created using a Train/Test dataset including 1,164,343 procedures from 16 academic and p ...[more]

PMID: 32028374

Similar Datasets

Project description:BackgroundAdministrative costs for billing and insurance-related activities in the United States are substantial. One critical cause of the high overhead of administrative costs is medical billing errors. With advanced deep learning techniques, developing advanced models to predict hospital and professional billing codes has become feasible. These models can be used for administrative cost reduction and billing process improvements.ObjectiveIn this study, we aim to develop an automated anesthesiology current procedural terminology (CPT) prediction system that translates manually entered surgical procedure text into standard forms using neural machine translation (NMT) techniques. The standard forms are calculated using similarity scores to predict the most appropriate CPT codes. Although this system aims to enhance medical billing coding accuracy to reduce administrative costs, we compare its performance with that of previously developed machine learning algorithms.MethodsWe collected and analyzed all operative procedures performed at Michigan Medicine between January 2017 and June 2019 (2.5 years). The first 2 years of data were used to train and validate the existing models and compare the results from the NMT-based model. Data from 2019 (6-month follow-up period) were then used to measure the accuracy of the CPT code prediction. Three experimental settings were designed with different data types to evaluate the models. Experiment 1 used the surgical procedure text entered manually in the electronic health record. Experiment 2 used preprocessing of the procedure text. Experiment 3 used preprocessing of the combined procedure text and preoperative diagnoses. The NMT-based model was compared with the support vector machine (SVM) and long short-term memory (LSTM) models.ResultsThe NMT model yielded the highest top-1 accuracy in experiments 1 and 2 at 81.64% and 81.71% compared with the SVM model (81.19% and 81.27%, respectively) and the LSTM model (80.96% and 81.07%, respectively). The SVM model yielded the highest top-1 accuracy of 84.30% in experiment 3, followed by the LSTM model (83.70%) and the NMT model (82.80%). In experiment 3, the addition of preoperative diagnoses showed 3.7%, 3.2%, and 1.3% increases in the SVM, LSTM, and NMT models in top-1 accuracy over those in experiment 2, respectively. For top-3 accuracy, the SVM, LSTM, and NMT models achieved 95.64%, 95.72%, and 95.60% for experiment 1, 95.75%, 95.67%, and 95.69% for experiment 2, and 95.88%, 95.93%, and 95.06% for experiment 3, respectively.ConclusionsThis study demonstrates the feasibility of creating an automated anesthesiology CPT classification system based on NMT techniques using surgical procedure text and preoperative diagnosis. Our results show that the performance of the NMT-based CPT prediction system is equivalent to that of the SVM and LSTM prediction models. Importantly, we found that including preoperative diagnoses improved the accuracy of using the procedure text alone.

Project description:BACKGROUND:Stroke severity is an important predictor of patient outcomes and is commonly measured with the National Institutes of Health Stroke Scale (NIHSS) scores. Because these scores are often recorded as free text in physician reports, structured real-world evidence databases seldom include the severity. The aim of this study was to use machine learning models to impute NIHSS scores for all patients with newly diagnosed stroke from multi-institution electronic health record (EHR) data. METHODS:NIHSS scores available in the Optum© de-identified Integrated Claims-Clinical dataset were extracted from physician notes by applying natural language processing (NLP) methods. The cohort analyzed in the study consists of the 7149 patients with an inpatient or emergency room diagnosis of ischemic stroke, hemorrhagic stroke, or transient ischemic attack and a corresponding NLP-extracted NIHSS score. A subset of these patients (n?=?1033, 14%) were held out for independent validation of model performance and the remaining patients (n?=?6116, 86%) were used for training the model. Several machine learning models were evaluated, and parameters optimized using cross-validation on the training set. The model with optimal performance, a random forest model, was ultimately evaluated on the holdout set. RESULTS:Leveraging machine learning we identified the main factors in electronic health record data for assessing stroke severity, including death within the same month as stroke occurrence, length of hospital stay following stroke occurrence, aphagia/dysphagia diagnosis, hemiplegia diagnosis, and whether a patient was discharged to home or self-care. Comparing the imputed NIHSS scores to the NLP-extracted NIHSS scores on the holdout data set yielded an R2 (coefficient of determination) of 0.57, an R (Pearson correlation coefficient) of 0.76, and a root-mean-squared error of 4.5. CONCLUSIONS:Machine learning models built on EHR data can be used to determine proxies for stroke severity. This enables severity to be incorporated in studies of stroke patient outcomes using administrative and EHR databases.

Project description:BackgroundAccurate, pragmatic risk stratification for postoperative delirium (POD) is necessary to target preventative resources toward high-risk patients. Machine learning (ML) offers a novel approach to leveraging electronic health record (EHR) data for POD prediction. We sought to develop and internally validate a ML-derived POD risk prediction model using preoperative risk features, and to compare its performance to models developed with traditional logistic regression.MethodsThis was a retrospective analysis of preoperative EHR data from 24,885 adults undergoing a procedure requiring anesthesia care, recovering in the main post-anesthesia care unit, and staying in the hospital at least overnight between December 2016 and December 2019 at either of two hospitals in a tertiary care health system. One hundred fifteen preoperative risk features including demographics, comorbidities, nursing assessments, surgery type, and other preoperative EHR data were used to predict postoperative delirium (POD), defined as any instance of Nursing Delirium Screening Scale ≥2 or positive Confusion Assessment Method for the Intensive Care Unit within the first 7 postoperative days. Two ML models (Neural Network and XGBoost), two traditional logistic regression models ("clinician-guided" and "ML hybrid"), and a previously described delirium risk stratification tool (AWOL-S) were evaluated using the area under the receiver operating characteristic curve (AUC-ROC), sensitivity, specificity, positive likelihood ratio, and positive predictive value. Model calibration was assessed with a calibration curve. Patients with no POD assessments charted or at least 20% of input variables missing were excluded.ResultsPOD incidence was 5.3%. The AUC-ROC for Neural Net was 0.841 [95% CI 0. 816-0.863] and for XGBoost was 0.851 [95% CI 0.827-0.874], which was significantly better than the clinician-guided (AUC-ROC 0.763 [0.734-0.793], p < 0.001) and ML hybrid (AUC-ROC 0.824 [0.800-0.849], p < 0.001) regression models and AWOL-S (AUC-ROC 0.762 [95% CI 0.713-0.812], p < 0.001). Neural Net, XGBoost, and ML hybrid models demonstrated excellent calibration, while calibration of the clinician-guided and AWOL-S models was moderate; they tended to overestimate delirium risk in those already at highest risk.ConclusionUsing pragmatically collected EHR data, two ML models predicted POD in a broad perioperative population with high discrimination. Optimal application of the models would provide automated, real-time delirium risk stratification to improve perioperative management of surgical patients at risk for POD.

Project description:RationalePatients transferred from the intensive care unit to the wards who are later readmitted to the intensive care unit have increased length of stay, healthcare expenditure, and mortality compared with those who are never readmitted. Improving risk stratification for patients transferred to the wards could have important benefits for critically ill hospitalized patients.ObjectivesWe aimed to use a machine-learning technique to derive and validate an intensive care unit readmission prediction model with variables available in the electronic health record in real time and compare it to previously published algorithms.MethodsThis observational cohort study was conducted at an academic hospital in the United States with approximately 600 inpatient beds. A total of 24,885 intensive care unit transfers to the wards were included, with 14,962 transfers (60%) in the training cohort and 9,923 transfers (40%) in the internal validation cohort. Patient characteristics, nursing assessments, International Classification of Diseases, Ninth Revision codes from prior admissions, medications, intensive care unit interventions, diagnostic tests, vital signs, and laboratory results were extracted from the electronic health record and used as predictor variables in a gradient-boosted machine model. Accuracy for predicting intensive care unit readmission was compared with the Stability and Workload Index for Transfer score and Modified Early Warning Score in the internal validation cohort and also externally using the Medical Information Mart for Intensive Care database (n = 42,303 intensive care unit transfers).ResultsEleven percent (2,834) of discharges to the wards were later readmitted to the intensive care unit. The machine-learning-derived model had significantly better performance (area under the receiver operating curve, 0.76) than either the Stability and Workload Index for Transfer score (area under the receiver operating curve, 0.65), or Modified Early Warning Score (area under the receiver operating curve, 0.58; P value < 0.0001 for all comparisons). At a specificity of 95%, the derived model had a sensitivity of 28% compared with 15% for Stability and Workload Index for Transfer score and 7% for the Modified Early Warning Score. Accuracy improvements with the derived model over Modified Early Warning Score and Stability and Workload Index for Transfer were similar in the Medical Information Mart for Intensive Care-III cohort.ConclusionsA machine learning approach to predicting intensive care unit readmission was significantly more accurate than previously published algorithms in both our internal validation and the Medical Information Mart for Intensive Care-III cohort. Implementation of this approach could target patients who may benefit from additional time in the intensive care unit or more frequent monitoring after transfer to the hospital ward.

Project description:ObjectiveElectronic health records (EHR) offer medical and pharmacogenomics research unprecedented opportunities to identify and classify patients at risk. EHRs are collections of highly inter-dependent records that include biological, anatomical, physiological, and behavioral observations. They comprise a patient's clinical phenome, where each patient has thousands of date-stamped records distributed across many relational tables. Development of EHR computer-based phenotyping algorithms require time and medical insight from clinical experts, who most often can only review a small patient subset representative of the total EHR records, to identify phenotype features. In this research we evaluate whether relational machine learning (ML) using inductive logic programming (ILP) can contribute to addressing these issues as a viable approach for EHR-based phenotyping.MethodsTwo relational learning ILP approaches and three well-known WEKA (Waikato Environment for Knowledge Analysis) implementations of non-relational approaches (PART, J48, and JRIP) were used to develop models for nine phenotypes. International Classification of Diseases, Ninth Revision (ICD-9) coded EHR data were used to select training cohorts for the development of each phenotypic model. Accuracy, precision, recall, F-Measure, and Area Under the Receiver Operating Characteristic (AUROC) curve statistics were measured for each phenotypic model based on independent manually verified test cohorts. A two-sided binomial distribution test (sign test) compared the five ML approaches across phenotypes for statistical significance.ResultsWe developed an approach to automatically label training examples using ICD-9 diagnosis codes for the ML approaches being evaluated. Nine phenotypic models for each ML approach were evaluated, resulting in better overall model performance in AUROC using ILP when compared to PART (p=0.039), J48 (p=0.003) and JRIP (p=0.003).DiscussionILP has the potential to improve phenotyping by independently delivering clinically expert interpretable rules for phenotype definitions, or intuitive phenotypes to assist experts.ConclusionRelational learning using ILP offers a viable approach to EHR-driven phenotyping.

Project description:BackgroundA major problem in treating acute kidney injury (AKI) is that clinical criteria for recognition are markers of established kidney damage or impaired function; treatment before such damage manifests is desirable. Clinicians could intervene during what may be a crucial stage for preventing permanent kidney injury if patients with incipient AKI and those at high risk of developing AKI could be identified.ObjectiveIn this study, we evaluate a machine learning algorithm for early detection and prediction of AKI.DesignWe used a machine learning technique, boosted ensembles of decision trees, to train an AKI prediction tool on retrospective data taken from more than 300 000 inpatient encounters.SettingData were collected from inpatient wards at Stanford Medical Center and intensive care unit patients at Beth Israel Deaconess Medical Center.PatientsPatients older than the age of 18 whose hospital stays lasted between 5 and 1000 hours and who had at least one documented measurement of heart rate, respiratory rate, temperature, serum creatinine (SCr), and Glasgow Coma Scale (GCS).MeasurementsWe tested the algorithm's ability to detect AKI at onset and to predict AKI 12, 24, 48, and 72 hours before onset.MethodsWe tested AKI detection and prediction using the National Health Service (NHS) England AKI Algorithm as a gold standard. We additionally tested the algorithm's ability to detect AKI as defined by the Kidney Disease: Improving Global Outcomes (KDIGO) guidelines. We compared the algorithm's 3-fold cross-validation performance to the Sequential Organ Failure Assessment (SOFA) score for AKI identification in terms of area under the receiver operating characteristic (AUROC).ResultsThe algorithm demonstrated high AUROC for detecting and predicting NHS-defined AKI at all tested time points. The algorithm achieves AUROC of 0.872 (95% confidence interval [CI], 0.867-0.878) for AKI detection at time of onset. For prediction 12 hours before onset, the algorithm achieves an AUROC of 0.800 (95% CI, 0.792-0.809). For 24-hour predictions, the algorithm achieves AUROC of 0.795 (95% CI, 0.785-0.804). For 48-hour and 72-hour predictions, the algorithm achieves AUROC values of 0.761 (95% CI, 0.753-0.768) and 0.728 (95% CI, 0.719-0.737), respectively.LimitationsBecause of the retrospective nature of this study, we cannot draw any conclusions about the impact the algorithm's predictions will have on patient outcomes in a clinical setting.ConclusionsThe results of these experiments suggest that a machine learning-based AKI prediction tool may offer important prognostic capabilities for determining which patients are likely to suffer AKI, potentially allowing clinicians to intervene before kidney damage manifests.

Project description:IntroductionUnlike antibiotic and perfusion support, guidelines for sepsis source control lack high-quality evidence and are ungraded. Internally valid administrative data methods are needed to identify cases representing source control procedures to evaluate outcomes.MethodsOver five modified Delphi rounds, two independent reviewers identified Current Procedural Terminology (CPT) codes pertinent to source control. In each round, codes with perfect agreement were retained or excluded, whereas disagreements were reviewed by the panelists. Manual review of 400 patient records meeting Sepsis-3 criteria (2010-2017) clinically adjudicated which encounters included source control procedures (gold standard). The performance of consensus codes was compared with the gold standard to assess sensitivity, specificity, predictive values, and likelihood ratios.ResultsOf 5752 CPT codes, 609 consensus codes represented source control procedures. Of 400 hospitalizations for sepsis, 39 (9.8%; 95% confidence interval [CI] 7.0%-13.1%) underwent gold standard source control procedures and 29 (7.3%; 95% CI 4.9-10.3%) consensus code-defined source control procedures. Thirty consensus codes were identified (20.0% gastrointestinal/intraabdominal, 10.0% genitourinary, 13.3% hepatopancreatobiliary, 23.3% orthopedic/cranial, 23.3% soft tissue, and 10.0% intrathoracic), which had 61.5% (95% CI 44.6%-76.6%) sensitivity, 98.6% (95% CI 96.8%-99.6%) specificity, 83.2% (95% CI 66.6%-92.4%) positive, and 95.9% (95% CI 93.9%-97.2%) negative predictive values. With pretest probability at sample prevalence, an identified consensus code had a posttest probability of 83.0% (95% CI 66.0%-92.0%), whereas consensus code absence had a probability of 4.0% (95% CI 3.0-6.0) for undergoing a source control procedure.ConclusionsUsing modified Delphi methodology, we created and validated CPT codes identifying source control procedures, providing a framework for evaluation of the surgical care of patients with sepsis.

Dataset Information

Classification of Current Procedural Terminology Codes from Electronic Health Record Data Using Machine Learning.

Publications

Classification of Current Procedural Terminology Codes from Electronic Health Record Data Using Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets