Literature DB >> 32028374

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

Michael L Burns1, Michael R Mathis, John Vandervest, Xinyu Tan, Bo Lu, Douglas A Colquhoun, Nirav Shah, Sachin Kheterpal, Leif Saager.   

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.

Entities:  

Mesh:

Year:  2020        PMID: 32028374      PMCID: PMC7665375          DOI: 10.1097/ALN.0000000000003150

Source DB:  PubMed          Journal:  Anesthesiology        ISSN: 0003-3022            Impact factor:   7.892


  22 in total

Review 1.  Perioperative effectiveness research using large databases.

Authors:  Robert E Freundlich; Sachin Kheterpal
Journal:  Best Pract Res Clin Anaesthesiol       Date:  2011-12

2.  Automated documentation error detection and notification improves anesthesia billing performance.

Authors:  Stephen F Spring; Warren S Sandberg; Shaji Anupama; John L Walsh; William D Driscoll; Douglas E Raines
Journal:  Anesthesiology       Date:  2007-01       Impact factor: 7.892

3.  Long short-term memory.

Authors:  S Hochreiter; J Schmidhuber
Journal:  Neural Comput       Date:  1997-11-15       Impact factor: 2.026

4.  Changes in Primary Care Access Between 2012 and 2016 for New Patients With Medicaid and Private Coverage.

Authors:  Daniel Polsky; Molly Candon; Brendan Saloner; Douglas Wissoker; Katherine Hempstead; Genevieve M Kenney; Karin Rhodes
Journal:  JAMA Intern Med       Date:  2017-04-01       Impact factor: 21.873

5.  Artificial Intelligence and Machine Learning in Anesthesiology.

Authors:  Christopher W Connor
Journal:  Anesthesiology       Date:  2019-12       Impact factor: 7.892

6.  Defining the Intrinsic Cardiac Risks of Operations to Improve Preoperative Cardiac Risk Assessments.

Authors:  Jason B Liu; Yaoming Liu; Mark E Cohen; Clifford Y Ko; Bobbie J Sweitzer
Journal:  Anesthesiology       Date:  2018-02       Impact factor: 7.892

7.  Administrative Costs Associated With Physician Billing and Insurance-Related Activities at an Academic Health Care System.

Authors:  Phillip Tseng; Robert S Kaplan; Barak D Richman; Mahek A Shah; Kevin A Schulman
Journal:  JAMA       Date:  2018-02-20       Impact factor: 56.272

8.  Risk of Epidural Hematoma after Neuraxial Techniques in Thrombocytopenic Parturients: A Report from the Multicenter Perioperative Outcomes Group.

Authors:  Linden O Lee; Brian T Bateman; Sachin Kheterpal; Thomas T Klumpner; Michelle Housey; Michael F Aziz; Karen W Hand; Mark MacEachern; Christopher G Goodier; Jeffrey Bernstein; Melissa E Bauer
Journal:  Anesthesiology       Date:  2017-06       Impact factor: 7.892

9.  Machine learning-based classification of diffuse large B-cell lymphoma patients by eight gene expression profiles.

Authors:  Shuangtao Zhao; Xiaoli Dong; Wenzhi Shen; Zhen Ye; Rong Xiang
Journal:  Cancer Med       Date:  2016-02-11       Impact factor: 4.452

10.  Guidelines for Developing and Reporting Machine Learning Predictive Models in Biomedical Research: A Multidisciplinary View.

Authors:  Wei Luo; Dinh Phung; Truyen Tran; Sunil Gupta; Santu Rana; Chandan Karmakar; Alistair Shilton; John Yearwood; Nevenka Dimitrova; Tu Bao Ho; Svetha Venkatesh; Michael Berk
Journal:  J Med Internet Res       Date:  2016-12-16       Impact factor: 5.428

View more
  2 in total

1.  Procedure Code Utilization for Vascular Access Device Placement in the Inpatient Setting: A Retrospective Analysis.

Authors:  Erica DeBoer; Kimberly Alsbrooks
Journal:  Perspect Health Inf Manag       Date:  2022-07-01

2.  Neural Machine Translation-Based Automated Current Procedural Terminology Classification System Using Procedure Text: Development and Validation Study.

Authors:  Hyeon Joo; Michael Burns; Sai Saradha Kalidaikurichi Lakshmanan; Yaokun Hu; V G Vinod Vydiswaran
Journal:  JMIR Form Res       Date:  2021-05-26
  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.