Billing by residents and attending physicians in family medicine: the effects of the provider, patient, and visit factors

Impact of Primary Care Exception Expansion on Family Medicine Resident Billing During the COVID-19 Pandemic

BACKGROUND AND OBJECTIVES

The Medicare Primary Care Exception (PCE) permits indirect supervision of residents performing lower-complexity visits in primary care settings. During the COVID-19 pandemic, Medicare expanded the PCE to all patient visits regardless of complexity. This study investigates how PCE expansion changed resident billing practices at a family medicine residency during calendar year 2020. We hypothesized that residents not constrained by the PCE would bill more high-level visits.

METHODS

We queried billing codes from attendings' and residents' established evaluation and management visits associated with the University of Washington Family Medicine Residency (UWFMR) from January to December 2020. We used χ2 tests to compare resident and attending physicians' use of low/moderate and high-level codes by quarter.

RESULTS

Resident high-complexity code use increased after PCE expansion in Q4 (odds ratio [OR] 3.50 [2.34-5.23]) compared to Q1. No change was observed among attending physicians (OR 1.05 [0.86-1.28]). Resident and attending billing patterns became more similar following PCE expansion.

CONCLUSIONS

With the PCE expansion, senior family medicine resident physicians at UWFMR used higher-complexity billing codes at a rate approximating that of attending physicians. The findings of this study have implications regarding the financial well-being and sustainability of primary care residency training and raise a relevant policy question about whether the PCE expansion should persist. More research is needed to determine whether these findings were replicated in other primary care residency practices, the impact on resident education, and the impact on patient outcomes.

Resident and Family Physician Perspectives on Billing: An Exploratory Study

INTRODUCTION

Within revenue cycle management, billing is an important activity for physicians with financial implications across remuneration models. We assessed the self-reported billing confidence of residents and attending physicians practicing at an academic family health team in a single payer setting.

METHODS

All residents and attending physicians working or who had worked at the team were invited to complete a 20-question electronic survey on their exposure to billing education and their self-reported confidence with various billing activities.

RESULTS

Twenty-five percent (n=40) of eligible physicians completed the survey. There were statistically significant differences between attending and resident physicians' billing experience (median 117.5 vs. 7.5 months). Analysis of free text comments revealed the positive impact of early billing exposure and opportunities for longitudinal feedback.

CONCLUSION

Despite the small sample size, findings suggest that early exposure of family medicine residents to billing with standardized training contributes to a more positive experience during residency.

Validation and Improvement of a Convolutional Neural Network to Predict the Involved Pathology in a Head and Neck Surgery Cohort

The selection of patients for the constitution of a cohort is a major issue for clinical research (prospective studies and retrospective studies in real life). Our objective was to validate in real life conditions the use of a Deep Learning process based on a neural network, for the classification of patients according to the pathology involved in a head and neck surgery department. 24,434 Electronic Health Records (EHR) from the first visit between 2000 and 2020 were extracted. More than 6000 EHR were manually classified in ten groups of interest according to the reason for consultation with a clinical relevance. A convolutional neural network (TensorFlow, previously reported by Hsu et al.) was then used to predict the group of patients based on their pathology, using two levels of classification based on clinically relevant criteria. On the first and second level of classification, macro-average performances were: 0.95, 0.83, 0.85, 0.97, 0.84 and 0.93, 0.76, 0.83, 0.96, 0.79 for accuracy, recall, precision, specificity and F1-score versus accuracy, recall and precision of 0.580, 580 and 0.582 for Hsu et al., respectively. We validated this model to predict the pathology involved and to constitute clinically relevant cohorts in a tertiary hospital. This model did not require a preprocessing stage, was used in French and showed equivalent or better performances than other already published techniques.

A systematic review of outpatient billing practices

Objectives:

Healthcare coding and billing are an important aspect of practice management that directly impacts the financial stability of a health care practice. To financially sustain or grow a medical practice, it is imperative that resident and faculty physicians have knowledge and skills for accurate billing in every patient encounter.

Methods:

A systematic review was conducted to identify recently published studies that report on improvements in medical coding and billing accuracy, clinical documentation, and reimbursement rate. A search of three databases yielded a total of 5754 records. After screening, 41 records were sought for retrieval and a total of 18 records were obtained for review.

Results:

Following a thorough review of literature, the most common reasons for inaccurate or inappropriate billing were a lack of formal education within residency curriculum, inadequate clinical documentation supporting level of billing, and lack of a feedback system aimed to correct billing errors.

Conclusion:

A formal education curriculum implemented in training could enhance knowledge and application of accurate billing and coding and further benefit practice longevity. The purpose of this systematic review is to apply knowledge gained to the development and implementation of a quality improvement study intended to improve accuracy of coding and billing within an academic pediatric outpatient center.

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

BACKGROUND

Administrative 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.

OBJECTIVE

In 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.

METHODS

We 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.

RESULTS

The 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.

CONCLUSIONS

This 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.

Research and Reporting Considerations for Observational Studies Using Electronic Health Record Data

Electronic health records (EHRs) are an increasingly important source of real-world health care data for observational research. Analyses of data collected for purposes other than research require careful consideration of data quality as well as the general research and reporting principles relevant to observational studies. The core principles for observational research in general also apply to observational research using EHR data, and these are well addressed in prior literature and guidelines. This article provides additional recommendations for EHR-based research. Considerations unique to EHR-based studies include assessment of the accuracy of computer-executable cohort definitions that can incorporate unstructured data from clinical notes and management of data challenges, such as irregular sampling, missingness, and variation across time and place. Principled application of existing research and reporting guidelines alongside these additional considerations will improve the quality of EHR-based observational studies.