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

Improving Diagnostics with Deep Forest Applied to Electronic Health Records

An electronic health record (EHR) is a vital high-dimensional part of medical concepts. Discovering implicit correlations in the information of this data set and the research and informative aspects can improve the treatment and management process. The challenge of concern is the data sources' limitations in finding a stable model to relate medical concepts and use these existing connections. This paper presents Patient Forest, a novel end-to-end approach for learning patient representations from tree-structured data for readmission and mortality prediction tasks. By leveraging statistical features, the proposed model is able to provide an accurate and reliable classifier for predicting readmission and mortality. Experiments on MIMIC-III and eICU datasets demonstrate Patient Forest outperforms existing machine learning models, especially when the training data are limited. Additionally, a qualitative evaluation of Patient Forest is conducted by visualising the learnt representations in 2D space using the t-SNE, which further confirms the effectiveness of the proposed model in learning EHR representations.

Development of an interactive web dashboard to facilitate the reexamination of pathology reports for instances of underbilling of CPT codes

Current Procedural Terminology Codes is a numerical coding system used to bill for medical procedures and services and crucially, represents a major reimbursement pathway. Given that pathology services represent a consequential source of hospital revenue, understanding instances where codes may have been misassigned or underbilled is critical. Several algorithms have been proposed that can identify improperly billed CPT codes in existing datasets of pathology reports. Estimation of the fiscal impacts of these reports requires a coder (i.e., billing staff) to review the original reports and manually code them again. As the re-assignment of codes using machine learning algorithms can be done quickly, the bottleneck in validating these reassignments is in this manual re-coding process, which can prove cumbersome. This work documents the development of a rapidly deployable dashboard for examination of reports that the original coder may have misbilled. Our dashboard features the following main components: (1) a bar plot to show the predicted probabilities for each CPT code, (2) an interpretation plot showing how each word in the report combines to form the overall prediction, and (3) a place for the user to input the CPT code they have chosen to assign. This dashboard utilizes the algorithms developed to accurately identify CPT codes to highlight the codes missed by the original coders. In order to demonstrate the function of this web application, we recruited pathologists to utilize it to highlight reports that had codes incorrectly assigned. We expect this application to accelerate the validation of re-assigned codes through facilitating rapid review of false-positive pathology reports. In the future, we will use this technology to review thousands of past cases in order to estimate the impact of underbilling has on departmental revenue.

Comparison of Machine-Learning Algorithms for the Prediction of Current Procedural Terminology (CPT) Codes from Pathology Reports

BACKGROUND

Pathology reports serve as an auditable trial of a patient's clinical narrative, containing text pertaining to diagnosis, prognosis, and specimen processing. Recent works have utilized natural language processing (NLP) pipelines, which include rule-based or machine-learning analytics, to uncover textual patterns that inform clinical endpoints and biomarker information. Although deep learning methods have come to the forefront of NLP, there have been limited comparisons with the performance of other machine-learning methods in extracting key insights for the prediction of medical procedure information, which is used to inform reimbursement for pathology departments. In addition, the utility of combining and ranking information from multiple report subfields as compared with exclusively using the diagnostic field for the prediction of Current Procedural Terminology (CPT) codes and signing pathologists remains unclear.

METHODS

After preprocessing pathology reports, we utilized advanced topic modeling to identify topics that characterize a cohort of 93,039 pathology reports at the Dartmouth-Hitchcock Department of Pathology and Laboratory Medicine (DPLM). We separately compared XGBoost, SVM, and BERT (Bidirectional Encoder Representation from Transformers) methodologies for the prediction of primary CPT codes (CPT 88302, 88304, 88305, 88307, 88309) as well as 38 ancillary CPT codes, using both the diagnostic text alone and text from all subfields. We performed similar analyses for characterizing text from a group of the 20 pathologists with the most pathology report sign-outs. Finally, we uncovered important report subcomponents by using model explanation techniques.

RESULTS

We identified 20 topics that pertained to diagnostic and procedural information. Operating on diagnostic text alone, BERT outperformed XGBoost for the prediction of primary CPT codes. When utilizing all report subfields, XGBoost outperformed BERT for the prediction of primary CPT codes. Utilizing additional subfields of the pathology report increased prediction accuracy across ancillary CPT codes, and performance gains for using additional report subfields were high for the XGBoost model for primary CPT codes. Misclassifications of CPT codes were between codes of a similar complexity, and misclassifications between pathologists were subspecialty related.

CONCLUSIONS

Our approach generated CPT code predictions with an accuracy that was higher than previously reported. Although diagnostic text is an important source of information, additional insights may be extracted from other report subfields. Although BERT approaches performed comparably to the XGBoost approaches, they may lend valuable information to pipelines that combine image, text, and -omics information. Future resource-saving opportunities exist to help hospitals detect mis-billing, standardize report text, and estimate productivity metrics that pertain to pathologist compensation (RVUs).

Harmonized procedure coding system for surgical procedures and analysis of surgical site infections (SSI) of five European countries

BACKGROUND

The use of routine data will be essential in future healthcare research. Therefore, harmonizing procedure codes is a first step to facilitate this approach as international research endeavour. An example for the use of routine data on a large scope is the investigation of surgical site infections (SSI). Ongoing surveillance programs evaluate the incidence of SSI on a national or regional basis in a limited number of procedures. For example, analyses by the European Centre for Disease Prevention (ECDC) nine procedures and provides a mapping table for two coding systems (ICD9, National Healthcare Safety Network [NHSN]). However, indicator procedures do not reliably depict overall SSI epidemiology. Thus, a broader analysis of all surgical procedures is desirable. The need for manual translation of country specific procedures codes, however, impedes the use of routine data for such an analysis on an international level. This project aimed to create an international surgical procedure coding systems allowing for automatic translation and categorization of procedures documented in country-specific codes.

METHODS

We included the existing surgical procedure coding systems of five European countries (France, Germany, Italy, Spain, and the United Kingdom [UK]). In an iterative process, country specific codes were grouped in ever more categories until each group represented a coherent unit based on method of surgery, interventions performed, extent and site of the surgical procedure. Next two ID specialist (arbitrated by a third in case of disagreement) independently assigned country-specific codes to the resulting categories. Finally, specialist from each surgical discipline reviewed these assignments for their respective field.

RESULTS

A total number of 153 SALT (Staphylococcus aureus Surgical Site Infection Multinational Epidemiology in Europe) codes from 10 specialties were assigned to 15,432 surgical procedures. Almost 4000 (26%) procedure codes from the SALT coding system were classified as orthopaedic and trauma surgeries, thus this medical field represents the most diverse group within the SALT coding system, followed by abdominal surgical procedures with 2390 (15%) procedure codes.

CONCLUSION

Mapping country-specific codes procedure codes onto to a limited number of coherent, internally and externally validated codes proofed feasible. The resultant SALT procedure code gives the opportunity to harmonize big data sets containing surgical procedures from international centres, and may simplify comparability of future international trial findings.

TRIAL REGISTRATION

The study was registered at clinicaltrials.gov under NCT03353532 on November 27^th, 2017.