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

Current Applications of Artificial Intelligence in Billing Practices and Clinical Plastic Surgery

Integration of artificial intelligence (AI), specifically with natural language processing and machine learning, holds tremendous potential to enhance both clinical practices and administrative workflows within plastic surgery. AI has been applied to various aspects of patient care in plastic surgery, including postoperative free flap monitoring, evaluating preoperative risk assessments, and analyzing clinical documentation. Previous studies have demonstrated the ability to interpret current procedural terminology codes from clinical documentation using natural language processing. Various automated medical billing companies have used AI to improve the revenue management cycle at hospitals nationwide. Additionally, AI has been piloted by insurance companies to streamline the prior authorization process. AI implementation holds potential to enhance billing practices and maximize healthcare revenue for practicing physicians.

Impact of Social Vulnerability on Cardiac Arrest Mortality in the United States, 2016 to 2020

BACKGROUND

Cardiac arrest is 1 of the leading causes of morbidity and mortality, with an estimated 340 000 out-of-hospital and 292 000 in-hospital cardiac arrest events per year in the United States. Survival rates are lower in certain racial and socioeconomic groups.

METHODS AND RESULTS

We performed a county-level cross-sectional longitudinal study using the Centers for Disease Control and Prevention's Wide-Ranging Online Data for Epidemiologic Research multiple causes of death data set between 2016 and 2020 among individuals of all ages whose death was attributed to cardiac arrest. The Social Vulnerability Index is a composite measure that includes socioeconomic vulnerability, household composition, disability, individuals from racial and ethnic minority groups status and language, and housing and transportation domains. We examined the impact of social determinants on cardiac arrest mortality stratified by age, race, ethnicity, and sex in the United States. All age-adjusted mortality rate (cardiac arrest AAMRs) are reported as per 100 000. Overall cardiac arrest AAMR during the study period was 95.6. The cardiac arrest AAMR was higher for men compared with women (119.6 versus 89.9) and for the Black population compared with the White population (150.4 versus 92.3). The cardiac arrest AAMR increased from 64.8 in counties in quintile 1 of Social Vulnerability Index to 141 in quintile 5, with an average increase of 13% (95% CI, 9.8%-16.9%) in AAMR per quintile increase.

CONCLUSIONS

Mortality from cardiac arrest varies widely, with a >2-fold difference between the counties with the highest and lowest social vulnerability, highlighting the differential burden of cardiac arrest deaths throughout the United States based on social determinants of health.

You Cannot Function in "Overwhelm": Helping Primary Care Navigate the Slow End of the Pandemic

GOAL

This study was developed to explicate underlying organizational factors contributing to the deterioration of primary care clinicians' mental health during the COVID-19 pandemic.

METHODS

Using data from the Larry A. Green Center for the Advancement of Primary Health Care for the Public Good's national survey of primary care clinicians from March 2020 to March 2022, a multidisciplinary team analyzed more than 11,150 open-ended comments. Phase 1 of the analysis happened in real-time as surveys were returned, using deductive and inductive coding. Phase 2 used grounded theory to identify emergent themes. Qualitative findings were triangulated with the survey's quantitative data.

PRINCIPAL FINDINGS

The clinicians shifted from feelings of anxiety and uncertainty at the start of the pandemic to isolation, lack of fulfillment, moral injury, and plans to leave the profession. The frequency with which they spoke of depression, burnout, and moral injury was striking. The contributors to this distress included crushing workloads, worsening staff shortages, and insufficient reimbursement. Consequences, both felt and anticipated, included fatigue and demoralization from the inability to manage escalating workloads. Survey findings identified responses that could alleviate the mental health crisis, namely: (1) measuring and customizing workloads based on work capacity; (2) quantifying resources needed to return to sufficient staffing levels; (3) promoting state and federal support for sustainable practice infrastructures with less administrative burden; and (4) creating patient visits of different lengths to rebuild relationships and trust and facilitate more accurate diagnoses.

PRACTICAL APPLICATIONS

Attention to clinicians' mental health should be rapidly directed to on-demand, confidential mental health support so they can receive the care they need and not worry about any stigma or loss of license for accepting that help. Interventions that address work-life balance, workload, and resources can improve care, support retention of the critically important primary care workforce, and attract more trainees to primary care careers.

The Cost of Ambulatory Breast Reduction: Hospital Reimbursement Versus Surgeon Payments

Introduction: Reduction mammoplasty (RM) is one of the most common operations performed in plastic surgery. While US national surgical expenditures have risen in recent years, studies have reported decreasing reimbursement rates for plastic surgeons. The purpose of this study is to characterize the trends in charges and payments for a common plastic surgery operation, ambulatory RM, for facilities and physicians. Methods: A Medicare patient records database was used to capture hospital, surgeon, and anesthesiologist charges and payments for ambulatory RM from 2005 to 2014. Values were adjusted for inflation. A ratio of hospital to surgeon charges and payments were calculated: charge multiplier (CM) and payment multiplier (PM), respectively. Charges, payments, Charlson comorbidity index, CM, and PM values were analyzed for trends. Results: This study included 1001 patients. During the study period, the facility charge for RM per patient increased from $8477 to $11,102 (31% increase; p < .0005), and the surgeon charge increased from $7088 to $7199 (2% increase; p = .0009). Facility payments increased from $3661 to $3930 (7% increase; p < .0005), and surgeon payments decreased from $1178 to $1002 (15% decrease; p < .0005). CM increased from 1.2 to 1.54, and PM increased from 3.11 to 3.92. Conclusions: Charges and payments to facilities for ambulatory RM increased disproportionately to that of surgeons, likely due in part to rising administrative costs in health care delivery. This may disincentivize plastic surgeons from offering RM at hospital-based surgical centers, limiting patient access to this operation.

Administration's Share of Personnel in Veterans Health Administration and Private Sector Care

Importance

Health care administrative overhead is greater in the US than some other nations but has not been assessed in the Veterans Health Administration (VHA).

Objective

To compare administrative staffing patterns in the VHA and private (non-VHA) sectors.

Design, Setting, and Participants

This cross-sectional study was conducted using US employment data from 2019, prior to pandemic-related disruptions in health care staffing, and was carried out between January 14 and August 10, 2023. A nationally representative sample of federal and nonfederal personnel in hospitals and ambulatory care settings from the American Community Survey (ACS), all employees reported in VHA personnel records, and personnel in health insurance carriers and brokers tabulated by the Bureau of Labor Statistics (BLS) were analyzed.

Exposure

VHA vs private sector health care employment, including 397 occupations grouped into 18 categories.

Main Outcome and Measure

The proportion of staff working in administrative occupations.

Results

Among 3 239 553 persons surveyed in the ACS, 122 315 individuals (weighted population, 12 501 185 individuals) were civilians working in hospitals or ambulatory care; of the weighted population, 12 156 988 individuals (mean age, 42.6 years [95% CI, 42.5-42.7 years]; 76.2% [95% CI, 75.9%-76.5%] females) were private sector personnel and 344 197 individuals (mean age, 46.2 years [95% CI, 45.7-46.7 years]; 63.8% [95% CI, 61.8%-65.8%] females) were federal employees. In clinical settings, administrative occupations accounted for 23.4% (95% CI, 23.1%-23.8%) of private sector vs 19.8% (95% CI, 18.1%-21.4%) of VHA personnel. After including 1 000 800 employees at private sector health insurers and brokers and 13 956 VHA Central Office personnel with administrative occupations, administration accounted for 3 851 374 of 13 157 788 private sector employees (29.3%) vs 77 500 of 343 721 VHA employees (22.5%). Physicians represented approximately 7% of personnel in the VHA (7.2% [95% CI, 6.1%-8.2%]) and private sector (6.5% [95% CI, 6.3%-6.7%]), while the VHA deployed more registered nurses (23.7% [95% CI, 21.6%-25.8%] vs 21.2% [95% CI, 20.9%-21.5%]) and social service personnel (6.3% [95% CI, 5.4%-7.1%] vs 4.9% [95% CI, 4.7%-5.0%]) than the private sector.

Conclusions and Relevance

In this study, administrative occupations accounted for a smaller share of personnel in the VHA compared with private sector care, a difference possibly attributable to the VHA's simpler financing system. These findings suggest that if staffing patterns in the private sector mirrored those of the VHA, nearly 900 000 fewer administrative staff might be needed.

Artificially Intelligent Billing in Spine Surgery: An Analysis of a Large Language Model

STUDY DESIGN

Retrospective cohort study.

OBJECTIVES

This study assessed the effectiveness of a popular large language model, ChatGPT-4, in predicting Current Procedural Terminology (CPT) codes from surgical operative notes. By employing a combination of prompt engineering, natural language processing (NLP), and machine learning techniques on standard operative notes, the study sought to enhance billing efficiency, optimize revenue collection, and reduce coding errors.

METHODS

The model was given 3 different types of prompts for 50 surgical operative notes from 2 spine surgeons. The first trial was simply asking the model to generate CPT codes for a given OP note. The second trial included 3 OP notes and associated CPT codes to, and the third trial included a list of every possible CPT code in the dataset to prime the model. CPT codes generated by the model were compared to those generated by the billing department. Model evaluation was performed in the form of calculating the area under the ROC (AUROC), and area under precision-recall curves (AUPRC).

RESULTS

The trial that involved priming ChatGPT with a list of every possible CPT code performed the best, with an AUROC of .87 and an AUPRC of .67, and an AUROC of .81 and AUPRC of .76 when examining only the most common CPT codes.

CONCLUSIONS

ChatGPT-4 can aid in automating CPT billing from orthopedic surgery operative notes, driving down healthcare expenditures and enhancing billing code precision as the model evolves and fine-tuning becomes available.

AI Alone Will Not Reduce the Administrative Burden of Health Care

This Viewpoint considers AI’s limits in solving the medical billing quagmire and argues that standardizing health insurance claim forms and simplifying billing must occur before AI can shoulder the load.

Postpandemic Evaluation of the Eco-Efficiency of Personal Protective Equipment Against COVID-19 in Emergency Departments: Proposal for a Mixed Methods Study

BACKGROUND

The COVID-19 pandemic has had a profound impact on emergency department (ED) care in Canada and around the world. To prevent transmission of COVID-19, personal protective equipment (PPE) was required for all ED care providers in contact with suspected cases. With mass vaccination and improvements in several infection prevention components, our hypothesis is that the risks of transmission of COVID-19 will be significantly reduced and that current PPE use will have economic and ecological consequences that exceed its anticipated benefits. Evidence is needed to evaluate PPE use so that recommendations can ensure the clinical, economic, and environmental efficiency (ie, eco-efficiency) of its use.

OBJECTIVE

To support the development of recommendations for the eco-efficient use of PPE, our research objectives are to (1) estimate the clinical effectiveness (reduced transmission, hospitalizations, mortality, and work absenteeism) of PPE against COVID-19 for health care workers; (2) estimate the financial cost of using PPE in the ED for the management of suspected or confirmed COVID-19 patients; and (3) estimate the ecological footprint of PPE use against COVID-19 in the ED.

METHODS

We will conduct a mixed method study to evaluate the eco-efficiency of PPE use in the 5 EDs of the CHU de Québec-Université Laval (Québec, Canada). To achieve our goals, the project will include four phases: systematic review of the literature to assess the clinical effectiveness of PPE (objective 1; phase 1); cost estimation of PPE use in the ED using a time-driven activity-based costing method (objective 2; phase 2); ecological footprint estimation of PPE use using a life cycle assessment approach (objective 3; phase 3); and cost-consequence analysis and focus groups (integration of objectives 1 to 3; phase 4).

RESULTS

The first 3 phases have started. The results of these phases will be available in 2023. Phase 4 will begin in 2023 and results will be available in 2024.

CONCLUSIONS

While the benefits of PPE use are likely to diminish as health care workers' immunity increases, it is important to assess its economic and ecological impacts to develop recommendations to guide its eco-efficient use.

TRIAL REGISTRATION

PROSPERO CRD42022302598; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=302598.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/50682.

The Cost Shifting Economics of United States Emergency Department Professional Services (2016-2019)

STUDY OBJECTIVE

We estimate the economics of US emergency department (ED) professional services, which is increasingly under strain given the longstanding effect of unreimbursed care, and falling Medicare and commercial payments.

METHODS

We used data from the Nationwide Emergency Department Sample (NEDS), Medicare, Medicaid, Health Care Cost Institute, and surveys to estimate national ED clinician revenue and costs from 2016 to 2019. We compare annual revenue and cost for each payor and calculate foregone revenue, the amount clinicians may have collected had uninsured patients had either Medicaid or commercial insurance.

RESULTS

In 576.5 million ED visits (2016 to 2019), 12% were uninsured, 24% were Medicare-insured, 32% Medicaid-insured, 28% were commercially insured, and 4% had another insurance source. Annual ED clinician revenue averaged $23.5 billion versus costs of $22.5 billion. In 2019, ED visits covered by commercial insurance generated $14.3 billion in revenues and cost $6.5 billion. Medicare visits generated $5.3 billion and cost $5.7 billion; Medicaid visits generated $3.3 billion and cost $7 billion. Uninsured ED visits generated $0.5 billion and cost $2.9 billion. The average annual foregone revenue for ED clinicians to treat the uninsured was $2.7 billion.

CONCLUSION

Large cost-shifting from commercial insurance cross-subsidizes ED professional services for other patients. This includes the Medicaid-insured, Medicare-insured, and uninsured, all of whom incur ED professional service costs that substantially exceed their revenue. Foregone revenue for treating the uninsured relative to what may have been collected if patients had health insurance is substantial.

Active steps to reduce administrative spending associated with financial transactions in US health care

US health care administrative spending is approximately $1 trillion annually. A major operational area is the financial transactions ecosystem, which has approximately $200 billion in spending annually. Efficient financial transactions ecosystems from other industries and countries exhibit 2 features: immediate payment assurance and high use of automation throughout the process. The current system has an average transaction cost of $12 to $19 per claim across private payers and providers for more than 9 billion claims per year; each claim on average takes 4 to 6 weeks to process and pay. For simple claims, the transaction cost is $7 to $10 across private payers and providers; for complex claims, $35 to $40. Prior authorization on approximately 5000 codes has an average cost of $40 to $50 per submission for private payers and $20 to $30 for providers. Interventions aligned with a more efficient financial transactions ecosystem could reduce spending by $40 billion to $60 billion; approximately half is at the organizational level (scaling interventions being implemented by leading private payers and providers) and half at the industry level (adopting a centralized automated claims clearinghouse, standardizing medical policies for a subset of prior authorizations, and standardizing physician licensure for a national provider directory).

Impact of social vulnerability on cardiac arrest mortality in the United States, 2016-2020

Importance

Cardiac arrest is one of the leading causes of morbidity and mortality, with an estimated 340,000 out-of-hospital and 292,000 in-hospital cardiac arrest events per year in the U.S. Survival rates are lower in certain racial and socioeconomic groups.

Objective

To examine the impact of social determinants on cardiac arrest mortality among adults stratified by age, race, and sex in the U.S.

Design

A county-level cross-sectional longitudinal study using death data between 2016 and 2020 from the Centers for Disease Control and Prevention's (CDC) Wide-Ranging Online Data for Epidemiologic Research (WONDER) database.

Setting

Using the multiple causes of death dataset from the CDC's WONDER database, cardiac arrests were identified using the International Classification of Diseases (ICD), tenth revision, clinical modification codes.

Participants

Individuals aged 15 years or more whose death was attributed to cardiac arrest.

Exposures

Social vulnerability index (SVI), reported by the CDC, is a composite measure that includes socioeconomic vulnerability, household composition, disability, minority status and language, and housing and transportation domains.

Main outcomes and measures

Cardiac arrest mortality per 100,000 adults.

Results

Overall age-adjusted cardiac arrest mortality (AAMR) during the study period was 95.6 per 100,000 persons. The AAMR was higher for men as compared with women (119.6 vs. 89.9 per 100,000) and for Black, as compared with White, adults (150.4 vs. 92.3 per 100,000). The AAMR increased from 64.8 per 100,000 persons in counties in Quintile 1 (Q1) of SVI to 141 per 100,000 persons in Quintile 5, with an average increase of 13% (95% CI: 9.8-16.9) in AAMR per quintile increase.

Conclusion and relevance

Mortality from cardiac arrest varies widely, with a more than 2-fold difference between the counties with the highest and lowest social vulnerability, highlighting the differential burden of cardiac arrest deaths throughout the U.S. based on social determinants of health.

Beyond demonstrations: implementing a primary care hybrid payment model in Medicare

The National Academies of Sciences, Engineering, and Medicine's (NASEM's) 2021 report on primary care called for a hybrid payment approach-a mix of fee-for-service and population-based payment-with performance accountability to strike the proper balance for desired practice transformation and to support primary care's important and expanding role. The NASEM report also proposed substantial increases to primary care payment and reforms to the Medicare Physician Fee Schedule. This paper addresses pragmatic ways to implement these recommendations, describing and proposing solutions to the main implementation challenges. The urgent need for primary care payment reform calls for adopting a hybrid model within the Medicare fee schedule rather than engaging in another round of demonstrations, despite legal and practical obstacles to adoption. The paper explores reasons for adopting a roughly 50:50 blend of fee-for-service and population-based payment and addresses other design features, presenting reasons why spending accountability should rely on utilization measures under primary care control rather than performance on total cost of care, and proposes a fresh approach to quality, emphasizing that quality measures should be parsimonious, focused on important outcomes with demonstrated quality improvement.

Towards Medical Billing Automation: NLP for Outpatient Clinician Note Classification

Objectives

Our primary objective was to develop a natural language processing approach that accurately predicts outpatient Evaluation and Management (E/M) level of service (LoS) codes using clinicians' notes from a health system electronic health record. A secondary objective was to investigate the impact of clinic note de-identification on document classification performance.

Methods

We used retrospective outpatient office clinic notes from four medical and surgical specialties. Classification models were fine-tuned on the clinic notes datasets and stratified by subspecialty. The success criteria for the classification tasks were the classification accuracy and F1-scores on internal test data. For the secondary objective, the dataset was de-identified using Named Entity Recognition (NER) to remove protected health information (PHI), and models were retrained.

Results

The models demonstrated similar predictive performance across different specialties, except for internal medicine, which had the lowest classification accuracy across all model architectures. The models trained on the entire note corpus achieved an E/M LoS CPT code classification accuracy of 74.8% (CI 95: 74.1-75.6). However, the de-identified note corpus showed a markedly lower classification accuracy of 48.2% (CI 95: 47.7-48.6) compared to the model trained on the identified notes.

Conclusion

The study demonstrates the potential of NLP-based document classifiers to accurately predict E/M LoS CPT codes using clinical notes from various medical and procedural specialties. The models' performance suggests that the classification task's complexity merits further investigation. The de-identification experiment demonstrated that de-identification may negatively impact classifier performance. Further research is needed to validate the performance of our NLP classifiers in different healthcare settings and patient populations and to investigate the potential implications of de-identification on model performance.

The Volume and Cost of Quality Metric Reporting

Importance

US hospitals report data on many health care quality metrics to government and independent health care rating organizations, but the annual cost to acute care hospitals of measuring and reporting quality metric data, independent of resources spent on quality interventions, is not well known.

Objective

To evaluate externally reported inpatient quality metrics for adult patients and estimate the cost of data collection and reporting, independent of quality-improvement efforts.

Design, Setting, and Participants

Retrospective time-driven activity-based costing study at the Johns Hopkins Hospital (Baltimore, Maryland) with hospital personnel involved in quality metric reporting processes interviewed between January 1, 2019, and June 30, 2019, about quality reporting activities in the 2018 calendar year.

Main Outcomes and Measures

Outcomes included the number of metrics, annual person-hours per metric type, and annual personnel cost per metric type.

Results

A total of 162 unique metrics were identified, of which 96 (59.3%) were claims-based, 107 (66.0%) were outcome metrics, and 101 (62.3%) were related to patient safety. Preparing and reporting data for these metrics required an estimated 108 478 person-hours, with an estimated personnel cost of $5 038 218.28 (2022 USD) plus an additional $602 730.66 in vendor fees. Claims-based (96 metrics; $37 553.58 per metric per year) and chart-abstracted (26 metrics; $33 871.30 per metric per year) metrics used the most resources per metric, while electronic metrics consumed far less (4 metrics; $1901.58 per metric per year).

Conclusions and Relevance

Significant resources are expended exclusively for quality reporting, and some methods of quality assessment are far more expensive than others. Claims-based metrics were unexpectedly found to be the most resource intensive of all metric types. Policy makers should consider reducing the number of metrics and shifting to electronic metrics, when possible, to optimize resources spent in the overall pursuit of higher quality.

Development of billing post competency evaluation index system for nurses in China: a Delphi study

AIM

This study developed a set of competency evaluation indicators for billing nurses in China.

BACKGROUND

In clinical practice, nurses often take up billing responsibilities that are accompanied by certain risks. However, the competency evaluation index system for billing nurses has not been established in China.

METHODS

This study consisted of two main phases of research design: the first phase included a literature review and semi-structured interviews. Individual semi-structured interviews were conducted with 12 nurses in billing departments and 15 nurse managers in related departments. Concepts distilled from the literature review were linked to the results of the semi-structured interviews; this phase produced the first draft of indicators for assessing the professional competence of nurses in billing departments. In the second phase, two rounds of correspondence were conducted with 20 Chinese nursing experts using the Delphi method to test and evaluate the content of the index. The consensus was defined in advance as a mean score of 4.0 or above, with at least 75% agreement among participants. In this way, the final indicator framework was determined.

RESULTS

Using the iceberg model as a theoretical foundation, the literature review identified four main dimensions and associated themes. The semi-structured interviews confirmed all of the themes from the literature review while generating new themes, both of which were incorporated into the first draft of the index. Then two rounds of the Delphi survey were conducted. The positive coefficients of experts in the two rounds were 100% and 95%, respectively, while the authority coefficients were 0.963 and 0.961, respectively. The coefficients of variation were 0.00-0.33 and 0.05-0.24, respectively. The competency evaluation index system for billing nurses consisted of 4 first-level indicators, 16 s-level indicators, and 53 third-level indicators.

CONCLUSION

The competency evaluation index system for billing nurses, which was developed on the basis of the iceberg model, was scientific and applicable.

IMPLICATIONS FOR NURSING MANAGEMENT

The competency assessment index system for billing nurses may provide an effective practical framework for nursing administration to evaluate, train, and assess the competency of billing nurses.

Falling ill raises the health insurer's administration bill

In many countries, governments use payment systems to compensate health insurers more for enrollees with higher expected costs. However, little empirical research has examined whether these payment systems should also include health insurers' administrative costs. We provide two sources of evidence that health insurers with a more morbid population have higher administrative costs. First, we show at the customer level a causal relationship between individual morbidity and individual administrative contacts with the insurer, using the weekly evolution of the number of individual customer contacts (calls, emails, in-person visits etc.) of a large Swiss health insurer. Using a difference-in-differences design, we find that the onset of a chronic illness causes on average a persistent increase of about 40% in individuals' contacts with the health insurer. Second, we provide evidence that this relationship also holds for total administrative costs at the insurer level. We study twenty years of Swiss health insurance market data and find a positive elasticity of around 1, indicating that, all else equal, an insurer with a more morbid population, equal to 1% more health care spending, faces about 1% higher administrative costs.

Can a Novel Natural Language Processing Model and Artificial Intelligence Automatically Generate Billing Codes From Spine Surgical Operative Notes?

STUDY DESIGN

Retrospective cohort.

OBJECTIVE

Billing and coding-related administrative tasks are a major source of healthcare expenditure in the United States. We aim to show that a second-iteration Natural Language Processing (NLP) machine learning algorithm, XLNet, can automate the generation of CPT codes from operative notes in ACDF, PCDF, and CDA procedures.

METHODS

We collected 922 operative notes from patients who underwent ACDF, PCDF, or CDA from 2015 to 2020 and included CPT codes generated by the billing code department. We trained XLNet, a generalized autoregressive pretraining method, on this dataset and tested its performance by calculating AUROC and AUPRC.

RESULTS

The performance of the model approached human accuracy. Trial 1 (ACDF) achieved an AUROC of .82 (range: .48-.93), an AUPRC of .81 (range: .45-.97), and class-by-class accuracy of 77% (range: 34%-91%); trial 2 (PCDF) achieved an AUROC of .83 (.44-.94), an AUPRC of .70 (.45-.96), and class-by-class accuracy of 71% (42%-93%); trial 3 (ACDF and CDA) achieved an AUROC of .95 (.68-.99), an AUPRC of .91 (.56-.98), and class-by-class accuracy of 87% (63%-99%); trial 4 (ACDF, PCDF, CDA) achieved an AUROC of .95 (.76-.99), an AUPRC of .84 (.49-.99), and class-by-class accuracy of 88% (70%-99%).

CONCLUSIONS

We show that the XLNet model can be successfully applied to orthopedic surgeon's operative notes to generate CPT billing codes. As NLP models as a whole continue to improve, billing can be greatly augmented with artificial intelligence assisted generation of CPT billing codes which will help minimize error and promote standardization in the process.

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.

A Medical and Moral Imperative: Testimony for the U.S. Senate Budget Committee "Medicare for All" Hearing

On May 12, 2022, Senator Bernie Sanders held a hearing in the U.S. Senate Budget Committee on Medicare for All legislation. These were the first such hearings in the U.S. Senate. In testimony presented to the Budget Committee, I argued that the achievement of Medicare for All was a medical and moral imperative. I explored the problem of uninsurance, noting that 30 million Americans remain uninsured at a cost of more than 30,000 deaths annually. I contended that improving the quality of coverage was equally crucial, describing how some 41 million Americans remain underinsured at a grave cost to their health and financial wellbeing. Finally, I examined the economics of Medicare for All reform, and showed how the reduction of the enormous administrative waste in American healthcare could save hundreds of billions of dollars a year. Medicare for All, I concluded, is the one health reform that could expand and improve coverage for all while simultaneously controlling costs.

Physician perceptions of drug utilization management: Results of a national survey

The use of drug utilization management techniques such as formulary exclusions, prior authorizations, and step edits has risen sharply during the last decade, contributing to the growing burden on physicians and patients. Limited quantitative data exist, however, on physician perceptions of drug utilization management. A national survey was conducted between February 9 and March 30, 2021, targeting office-based physicians working in the United States to assess their perceptions on drug utilization management in their practice. Of the 742 physicians that participated in the study, over 80% reported deciding against prescribing certain treatments in anticipation of drug utilization management at least sometimes (>50% of the time). Despite utilization management having an impact on prescribing decisions, about half of physicians said that the utilization management policies they encounter rarely or never (0–25% of the time) align with clinical evidence.

How Emerging Telehealth Models Challenge Policymaking

Policy Points Current telehealth policy discussions are focused on synchronous video and audio telehealth visits delivered by traditional providers and have neglected the growing number of alternative telehealth offerings. These alternative telehealth offerings range from simply supporting traditional brick-and-mortar providers to telehealth-only companies that directly compete with them. We describe policy challenges across this range of alternative telehealth offerings in terms of using the appropriate payment model, determining the payment amount, and ensuring the quality of care.

Economic Analysis of Infectious Disease Consultation for Staphylococcus aureus Bacteremia Among Hospitalized Patients

IMPORTANCE

Staphylococcus aureus bacteremia is associated with a significant burden of mortality, morbidity, and health care costs. Infectious disease consultation may be associated with reduced mortality and bacteremia recurrence rates.

OBJECTIVE

To evaluate the cost-effectiveness of infectious disease consultation for Staphylococcus aureus bacteremia.

DESIGN, SETTING, AND PARTICIPANTS

In this economic evaluation, a decision-analytic model was constructed comparing infectious disease consult with no consult. The population was adult hospital inpatients with Staphylococcus aureus bacteremia diagnosed with at least 1 positive blood culture. Cost-effectiveness was calculated as deaths averted and incremental cost-effectiveness ratios. Uncertainty was addressed by plotting cost-effectiveness planes and acceptability curves for various willingness-to-pay thresholds. Costs and outcomes were calculated for a time horizon of 6 months. The analysis was performed from a societal perspective and included studies that had been published by January 2022.

INTERVENTIONS

Patients received or did not receive formal bedside consultation after positive blood cultures for Staphylococcus aureus bacteremia.

MAIN OUTCOMES AND MEASURES

The main outcomes were incremental difference in effectiveness (survival probabilities), incremental difference in cost (US dollars) and incremental cost-effectiveness ratios (US dollars/deaths averted).

RESULTS

This model included 1708 patients who received consultation and 1273 patients who did not. In the base-case analysis, the cost associated with the infectious disease consult strategy was $54 137.4 and the associated probability of survival was 0.77. For the no consult strategy, the cost was $57 051.2, and the probability of survival was 0.72. The incremental difference in cost between strategies was $2913.8, and the incremental difference in effectiveness was 0.05. Overall, consultation was associated with estimated savings of $55 613.4/death averted (incremental cost-effectiveness ratio, -$55613.4/death averted). In the probabilistic analysis, at a willingness-to-pay threshold of $50 000, infectious disease consult was cost-effective compared with no consult in 54% of 10 000 simulations. In cost-effectiveness acceptability curves, the consult strategy was cost-effective in 58% to 73%) of simulations compared with no consult for a willingness-to-pay threshold ranging from $0 to $150 000.

CONCLUSIONS AND RELEVANCE

These findings suggest that infectious disease consultation may be a cost-effective strategy for management of Staphylococcus aureus bacteremia and that it is associated with health care cost-savings.

The Physician and Administrator-Reported Cost of Drug Utilization Management to Physician Practices: A Cross-Sectional Survey

BACKGROUND

The use of drug utilization management techniques such as formulary exclusions, prior authorizations, and step edits has risen sharply during the last decade, contributing to growing administrative costs for physician practices. However, limited data exist on the extent of these administrative costs, with previous studies relying on data from over a decade ago.

OBJECTIVE

The aim of this study was to assess physician and practice administrator experiences with drug utilization management.

METHODS

A national survey was conducted between 9 February and 30 March 2021, targeting 925 physicians and administrators working at medical practices in the US. Time spent by physicians and their staff on tasks related to drug utilization management for prescription medications was collected and used to calculate the dollar value of that time.

RESULTS

We estimated that physicians spent a median of 4.0 h per week on drug utilization management, while nurses spent 15.0 h and other staff spent between 3.6 and 10.0 h on drug utilization management per physician per week. This time was associated with a calculated median dollar value of $75,927 per physician per year. Extrapolating this estimate to a national scale suggests that time spent annually by physician practices on drug utilization management could be valued at more than $43 billion.

CONCLUSIONS

Drug utilization management results in significant time spent by US physician practices, which in turn, results in meaningful costs to these practices. As the prevalence of drug utilization management continues to grow, the impact on physician practices will remain an important topic.

The Underuse of Medicare's Prevention and Coordination Codes in Primary Care : A Cross-Sectional and Modeling Study

BACKGROUND

Efforts to better support primary care include the addition of primary care-focused billing codes to the Medicare Physician Fee Schedule (MPFS).

OBJECTIVE

To examine potential and actual use by primary care physicians (PCPs) of the prevention and coordination codes that have been added to the MPFS.

DESIGN

Cross-sectional and modeling study.

SETTING

Nationally representative claims and survey data.

PARTICIPANTS

Medicare patients.

MEASUREMENTS

Frequency of use and estimated Medicare revenue involving 34 billing codes representing prevention and coordination services for which PCPs could but do not necessarily bill.

RESULTS

Eligibility among Medicare patients for each service ranged from 8.8% to 100%. Among eligible patients, the median use of billing codes was 2.3%, even though PCPs provided code-appropriate services to more patients, for example, to 5.0% to 60.6% of patients eligible for prevention services. If a PCP provided and billed all prevention and coordination services to half of all eligible patients, the PCP could add to the practice's annual revenue $124 435 (interquartile range [IQR], $30 654 to $226 813) for prevention services and $86 082 (IQR, $18 011 to $154 152) for coordination services.

LIMITATION

Service provision based on survey questions may not reflect all billing requirements; revenues do not incorporate the compliance, billing, and opportunity costs that may be incurred when using these codes.

CONCLUSION

Primary care physicians forego considerable amounts of revenue because they infrequently use billing codes for prevention and coordination services despite having eligible patients and providing code-appropriate services to some of those patients. Therefore, creating additional billing codes for distinct activities in the MPFS may not be an effective strategy for supporting primary care.

PRIMARY FUNDING SOURCE

National Institute on Aging.

Billing And Insurance-Related Administrative Costs: A Cross-National Analysis

Billing and insurance-related costs are a significant source of wasteful health care spending in Organization for Economic Cooperation and Development nations, but these administrative burdens vary across national systems. We executed a microlevel accounting of these costs in different national settings at six provider locations in five nations (Australia, Canada, Germany, the Netherlands, and Singapore) that supplements our prior study measuring the costs in the US. We found that billing and insurance-related costs for inpatient bills range from a low of $6 in Canada to a high of $215 in the US for an inpatient surgical bill (purchasing power parity adjusted). We created a taxonomy of billing and insurance-related activities (eligibility, coding, submission, and rework) that was applied to data from the six sites and allows cross-national comparisons. Higher costs in the US and Australia are attributed to high coding costs. Much of the savings achieved in some nations is attributable to assigning tasks to people in lower-skill job categories, although most of the savings are due to more efficient billing and insurance-related processes. Some nations also reduce these costs by offering financial counseling to patients before treatment. Our microlevel approach can identify specific cost drivers and reveal national billing features that reduce coding costs. It illustrates a valuable pathway for future research in understanding and mitigating administrative costs in health care.

Adaptation of time‐driven activity‐based costing to the evaluation of the efficiency of ambulatory care provided in the emergency department

Objectives

The aim of this study was: (1) to adapt the time‐driven activity‐based costing (TDABC) method to emergency department (ED) ambulatory care; (2) to estimate the cost of care associated with frequently encountered ambulatory conditions; and (3) to compare costs calculated using estimated time and objectively measured time.

Methods

TDABC was applied to a retrospective cohort of patients with upper respiratory tract infections, urinary tract infections, unspecified abdominal pain, lower back pain and limb lacerations who visited an ED in Québec City (Canada) during fiscal year 2015–2016. The calculated cost of care was the product of the time required to complete each care procedure and the cost per minute of each human resource or equipment involved. Costing based on durations estimated by care professionals were compared to those based on objective measurements in the field.

Results

Overall, 220 care episodes were included and 3080 time measurements of 75 different processes were collected. Differences between costs calculated using estimated and measured times were statistically significant for all conditions except lower back pain and ranged from $4.30 to $55.20 (US) per episode. Differences were larger for conditions requiring more advanced procedures, such as imaging or the attention of ED professionals.

Conclusions

The greater the use of advanced procedures or the involvement of ED professionals in the care, the greater is the discrepancy between estimated‐time‐based and measured‐time‐based costing. TDABC should be applied using objective measurement of the time per procedure.

Single-payer Health Care: Financial Implications for a Physician

When considering proposed reforms of the U.S. health care system, some physicians dismiss the single-payer model (Medicare for All or state-based universal health care proposals) out of concern that their reimbursement and thus their income would be reduced. This study is an effort to quantitate that concern in the case of state-based plans and, in so doing, to suggest a template for evaluating the financial consequences for physicians of single-payer health care reform in general. To put the data into concrete, practical terms, I envision a hypothetical primary care physician's practice and develop its plausible financial components in the present multi-payer system and in five proposed state-based, single-payer systems. The calculations reveal that in all five single-payer plans evaluated, the hypothetical physician's Total Net Income (take-home pay) would exceed that in the current multi-payer system. Whether these results apply to actual practices or not, they suggest that, when considering the financial impact of single-payer reform on their practices, physicians should consider all the financial consequences of such reform, not just the proposed reimbursement level. More quantitative analyses of these important financial variables in different practice settings must be pursued.

Association between state-level malpractice environment and clinician electronic health record (EHR) time

OBJECTIVE

Clinicians spend significant time working in the electronic health record (EHR). The US is an outlier in EHR time, suggesting that EHR-related work may be driven in part by the legal environment and threat of malpractice. To assess this, we evaluate the association between state-level malpractice climate and clinician time spent in the EHR.

MATERIALS AND METHODS

We use EHR metadata from 351 ambulatory care health systems in the United States using Epic from January-August 2019 combined with state-level data on malpractice incidence and payouts. We used descriptive statistics to measure variation in clinician EHR time, including total EHR time, documentation time per day, and after-hours EHR time per day. Multi-variable regression evaluated the association between clinicians in high malpractice states and EHR use.

RESULTS

We found no association between location in a state in the top-quartile of malpractice payouts and time spent in the EHR per day, time spent in the EHR outside of scheduled hours, or time spent documenting per day, except for a subgroup of the clinicians in the highest malpractice specialties, where there was a small increase in EHR time per day (B = 6.08 min, P < 0.001) and time spent documenting notes (B = 2.77 min, P < 0.001).

DISCUSSION

State-level differences in malpractice incidence are unlikely to be a significant driver of EHR work for most clinicians.

CONCLUSION

Policymakers seeking to address EHR documentation burden should examine burden driven by other socio-technical demands on clinician time, such as billing or quality measurement.

Effects of Fragmentation and the Case for Greater Cohesion in Neurologic Care Delivery

GOALS

To define fragmentation in neurologic care delivery, explain the positive and negative drivers in neurologic practice that contribute to fragmentation, illustrate situations that increase fragmentation risk, emphasize the costs and impact on both patients and providers, and propose solutions that allow for more cohesive care.

WORK GROUP

The Transforming Leaders Program (TLP) class of 2020 was tasked by American Academy of Neurology (AAN) leadership to identify the leading trends in inpatient and outpatient neurology and to predict their effects on future neurologic practice.

METHODS

Research material included AAN databases, PubMed searches, discussion with topic experts, and AAN leadership.

RESULTS

Trends in care delivery are driven by changes in the work force, shifts in health care delivery, care costs, changes in evidence-based care, and patient factors. These trends can contribute to care fragmentation. Potential solutions to these problems are proposed based on care models developed in oncology and medicine.

LIMITATIONS

This article shares our opinions as there is a lack of evidence-based guidelines for optimal neurologic care delivery.

Facial Feminization Surgery under Insurance: The University of California Los Angeles Experience

Despite improved insurance coverage for gender confirmation surgeries in the United States, coverage for facial feminization surgery (FFS) continues to be difficult. Here, we describe our institutional experience on navigation, time, and costs of the FFS insurance authorization process.

Prospects of Integrating Gig Economy in the Saudi Arabian Health-care System from the Perspectives of Health-care Decision-makers and Practitioners

Background

Gig economy is an approach in the labor market which is characterized by the prevalence of short-term contracts or freelance work in contrast to permanent jobs. The gig workers are independent workers or temporary contract workers who enter into formal/informal agreements with on-demand companies to provide their services. Rather than employing full-time/permanent employees companies may utilize gig workers as per the demand and work burden, which can minimize the costs incurred in managing permanent employees. However, there is a lack of research on using gig economy in health care, its prospects and the issues involved.

Purpose

The purpose of this study is to identify and evaluate various prospects in integrating gig economy with the Saudi health-care system.

Methods

An online survey questionnaire instrument including 22 prospects under three categories including organizational competitiveness, resource management, and sustainable development was used for collecting data from 712 health-care decision-makers and practitioners in Saudi Arabia. Findings were analyzed using the statistical means and standard deviations for each item in the questionnaire for analyzing the role of each factor in depth, and t-tests were used for comparing the responses between the groups.

Results

T-tests revealed no significant differences among the experts and health-care workers in relation to organizational competitiveness and resource management; however, significant differences in opinions were identified in relation to sustainable development. Individual factors including motivation for Saudization program (mean=4.5, SD=1.15) and creating employment opportunities in rural areas (mean=4.5, SD=1.08), growth in economy (mean=4.4, SD=1.43), increased opportunities for women and disabled (mean=4.4, SD=1.28), and growth in employment (mean=4.3, SD=1.68) were the major prospects identified in relation to the use of gig economy in the Saudi Arabian health-care system.

Conclusion

Gig economy may offer a wide range of benefits in health care, especially sustainable development, effective resource management, and organizational competitiveness.

Patient administrative burden in the US health care system

OBJECTIVE

To assess the prevalence of patient administrative tasks and whether they are associated with delayed and/or foregone care.

DATA SOURCE

March 2019 Health Reform Monitoring Survey.

STUDY DESIGN

We assess the prevalence of five common patient administrative tasks-scheduling, obtaining information, prior authorizations, resolving billing issues, and resolving premium problems-and associated administrative burden, defined as delayed and/or foregone care. Using multivariate logistic models, we examined the association of demographic characteristics with odds of doing tasks and experiencing burdens. Our outcome variables were five common types of administrative tasks as well as composite measures of any task, any delayed care, any foregone care, and any burden (combined delayed/foregone), respectively.

DATA COLLECTION

We developed and administered survey questions to a nationally representative sample of insured, nonelderly adults (n = 4155).

PRINCIPAL FINDINGS

The survey completion rate was 62%. Seventy-three percent of respondents reported performing at least one administrative task in the past year. About one in three task-doers, or 24.4% of respondents overall, reported delayed or foregone care due to an administrative task: Adjusted for demographics, disability status had the strongest association with administrative tasks (adjusted odds ratio [OR] 2.91, p < 0.001) and burden (adjusted OR 1.66, p < 0.001). Being a woman was associated with doing administrative tasks (adjusted OR 2.19, p < 0.001). Being a college graduate was associated with performing an administrative task (adjusted OR 2.79, p < 0.001), while higher income was associated with fewer subsequent burdens (adjusted OR 0.55, p < 0.01).

CONCLUSIONS

Patients frequently do administrative tasks that can create burdens resulting in delayed/foregone care. The prevalence of delayed/foregone care due to administrative tasks is comparable to similar estimates of cost-related barriers to care. Demographic disparities in burden warrant further attention. Enhancing measurement of patient administrative work and associated burdens may identify opportunities for assessing quality, value, and patient experience.

Electronic health records and clinician burnout: A story of three eras

OBJECTIVE

The study sought to provide physicians, informaticians, and institutional policymakers with an introductory tutorial about the history of medical documentation, sources of clinician burnout, and opportunities to improve electronic health records (EHRs). We now have unprecedented opportunities in health care, with the promise of new cures, improved equity, greater sensitivity to social and behavioral determinants of health, and data-driven precision medicine all on the horizon. EHRs have succeeded in making many aspects of care safer and more reliable. Unfortunately, current limitations in EHR usability and problems with clinician burnout distract from these successes. A complex interplay of technology, policy, and healthcare delivery has contributed to our current frustrations with EHRs. Fortunately, there are opportunities to improve the EHR and health system. A stronger emphasis on improving the clinician's experience through close collaboration by informaticians, clinicians, and vendors can combine with specific policy changes to address the causes of burnout.

TARGET AUDIENCE

This tutorial is intended for clinicians, informaticians, policymakers, and regulators, who are essential participants in discussions focused on improving clinician burnout. Learners in biomedicine, regardless of clinical discipline, also may benefit from this primer and review.

SCOPE

We include (1) an overview of medical documentation from a historical perspective; (2) a summary of the forces converging over the past 20 years to develop and disseminate the modern EHR; and (3) future opportunities to improve EHR structure, function, user base, and time required to collect and extract information.

US Physicians' Perspective on the Sudden Shift to Telehealth: Survey Study

Background

Given the sudden shift to telemedicine during the early COVID-19 pandemic, we conducted a survey of practicing physicians’ experience with telehealth during the prepandemic and early pandemic periods. Our survey estimates that most patient visits in the United States during the early COVID-19 pandemic period were conducted via telehealth. Given this magnitude and the potential benefits and challenges of telehealth for the US health care system, in this paper, we obtain, summarize, and analyze telehealth views and experiences of US-based practicing-physicians.

Objective

The aim of this study was to examine the extent of shift toward telehealth training and care provision during the early pandemic from the US-based practicing physicians’ perspective. We also sought to determine the short- and long-term implications of this shift on the quality, access, and mode of US health care delivery.

Methods

We conducted a purposive, snowball-sampled survey of US practicing-physicians. A total of 148 physician completed the survey. Data were collected from July 17, 2020, through September 4, 2020.

Results

Sample training intensity scaled 21-fold during the early pandemic period, and patient-care visits conducted via telehealth increased, on average, from 13.1% directly before the pandemic to 59.7% during the early pandemic period. Surveyed physician respondents reported that telehealth patient visits and face-to-face patient visits are comparable in quality. The difference was not statistically significant based on a nonparametric sign test (P=.11). Moreover, physicians feel that telehealth care should continue to play a larger role (44.9% of total visits) in postpandemic health care in the United States. Our survey findings suggest a high market concentration in telehealth software, which is a market structural characteristic that may have implications on the cost and access of telehealth. The results varied markedly by physician employer type.

Conclusions

During the shift toward telehealth, there has been a considerable discovery among physicians regarding US telehealth physicians. Physicians are now better prepared to undertake telehealth care from a training perspective. They are favorable toward a permanently expanded telehealth role, with potential for enhanced health care access, and the realization of enhanced access may depend on market structural characteristics of telehealth software platforms.

Determining variable costs in the acute urolithiasis cycle of care through time-driven activity-based costing

OBJECTIVE

To characterize full cycle of care costs for managing an acute ureteral stone using time-driven activity-based costing.

METHODS

We defined all phases of care for patients presenting with an acute ureteral stone and built an overarching process map. Maps for sub-processes were constructed through interviews with providers and direct observation of clinical spaces. This facilitated calculation of cost per minute for all aspects of care delivery, which were multiplied by associated process times. These were added to consumable costs to determine cost for each specific step and later aggregated to determine total cost for each sub-process. We compared costs of eight common clinical pathways for acute stone management, defining total cycle of care cost as the sum of all sub-processes that comprised each pathway.

RESULTS

Cost per sub-process included $920 for emergency department (ED) care, $1665 for operative stent placement, $2368 for percutaneous nephrostomy tube placement, $106 for urology clinic consultation, $238 for preoperative center visit, $4057 for ureteroscopy with laser lithotripsy (URS), $2923 for extracorporeal shock wave lithotripsy, $169 for clinic stent removal, $197 for abdominal x-ray, and $166 for ultrasound. The lowest cost pathway ($1388) was for medical expulsive therapy, whereas the most expensive pathway ($8002) entailed a repeat ED visit prompting temporizing stent placement and interval URS.

CONCLUSION

We found a high degree of cost variation between care pathways common to management of acute ureteral stone episodes. Reliable cost accounting data and an understanding of variability in clinical pathway costs can inform value-based care redesign as payors move away from pure fee-for-service reimbursement.

Reducing administrative costs in US health care: Assessing single payer and its alternatives

OBJECTIVE

Excess administrative costs in the US health care system are routinely referenced as a justification for comprehensive reform. While there is agreement that these costs are too high, there is little understanding of what generates administrative costs and what policy options might mitigate them.

DATA SOURCES

Literature review and national utilization and expenditure data.

STUDY DESIGN

We developed a simulation model of physician billing and insurance-related (BIR) costs to estimate how certain policy reforms would generate savings. Our model is based on structural elements of the payment process in the United States and considers each provider's number of health plan contracts, the number of features in each health plan, the clinical and nonclinical processes required to submit a bill for payment, and the compliance costs associated with medical billing.

DATA EXTRACTION

For several types of visits, we estimated fixed and variable costs of the billing process. We used the model to estimate the BIR costs at a national level under a variety of policy scenarios, including variations of a single payer "Medicare-for-All" model that extends fee-for-service Medicare to the entire population and policy efforts to reduce administrative costs in a multi-payer model. We conducted sensitivity analyses of a wide variety of model parameters.

PRINCIPAL FINDINGS

Our model estimates that national BIR costs are reduced between 33% and 53% in Medicare-for-All style single-payer models and between 27% and 63% in various multi-payer models. Under a wide range of assumptions and sensitivity analyses, standardizing contracts generates larger savings with less variance than savings from single-payer strategies.

CONCLUSION

Although moving toward a single-payer system will reduce BIR costs, certain reforms to payer-provider contracts could generate at least as many administrative cost savings without radically reforming the entire health system. BIR costs can be meaningfully reduced without abandoning a multi-payer system.

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.

An evaluation of healthcare utilization and clinical charges in children and adults with cystic fibrosis

BACKGROUND

Prior studies have estimated healthcare costs for cystic fibrosis (CF) of $8000-$131,000, but do not account for impacts of CF modulator therapy. This study aims to assess utilization patterns and cost of CF care in a center in the United States.

METHODS

Care utilization patterns and costs at a large pediatric-adult CF center were examined from November 2017 to November 2018. Subjects were stratified by age and cost (excluding pharmacy costs) were calculated based on hospital-derived utilization charges.

RESULTS

A total of 166 patients were reviewed with mean clinical charges of $28,755. Lower lung function ($23,032 normal lung function, $62,293 moderate reduction, $186,786 severe reduction; p = .05), hospitalizations ($85,452 yes, $6362 no; p = .0001), Pseudomonas positive culture ($48,660 positive, $22,013 negative, p = .0001), and CF-related diabetes ($161,892 CFRD, $22,153 no CFRD; p = .001) were associated with increased charges. Patients utilizing Ivacaftor had lower charges compared to lumacaftor-ivacaftor ($6633 vs. $33,039; p = .05) and tezacaftor-ivacaftor ($6633 vs. $64,434; p = .002).

CONCLUSION

Our study characterized utilization and care charges among a CF cohort. Lower lung function, hospitalizations, and CFRD were associated with increased charges.

Time and Financial Costs for Physician Practices to Participate in the Medicare Merit-based Incentive Payment System: A Qualitative Study

Importance

The Merit-based Incentive Payment System (MIPS) is a major Medicare value-based purchasing program, influencing payment for more than 1 million clinicians annually. There is a growing concern that MIPS increases administrative burden, and little is known about what it costs physician practices to participate in the program.

Objective

To examine the costs for independent physician practices to participate in MIPS in 2019.

Design Setting and Participants

This qualitative study identified and interviewed leaders of physician practices participating in the US Centers for Medicare & Medicaid Services (CMS) MIPS program, including those in MIPS alternative payment models. Time required and financial costs were calculated from responses to in-depth, semistructured interviews conducted from December 12, 2019, to June 23, 2020. Physician practices were categorized by size (small, 1-9 physicians; medium, 10-25; and large, ≥50), specialty (primary care, general surgery, or multispecialty), and US census region. Participants were asked about 2019 costs related to clinician and staff time, information technology, and external vendors. Time was converted to financial costs using the Medical Group Management Association's Provider Compensation and the Management and Staff Compensation databases.

Main Outcomes and Measures

Annual time spent by staff on MIPS-related activities and mean per-physician costs to physician practices in 2019.

Results

Leaders of 30 physician practices (9 [30.0%] small primary care, 6 [20.0%] small general surgery, 4 [13.3%] medium primary care, 4 [13.3%] medium general surgery, and 7 [23.3%] large multispecialty) represented all US census regions, and 14 of the 30 (46.7%) practices participated in a MIPS alternative payment model in 2019. The mean per-physician cost to practices of participating in MIPS was $12 811 (interquartile range [IQR], $2861-$17 715). Physicians, clinical staff, and administrative staff together spent 201.7 (IQR, 50.9-295.2) hours annually per physician on MIPS-related activities. Medical assistants and nursing staff together spent a mean of 99.2 (IQR, 0-163.3) hours per physician each year; frontline physicians spent 53.6 (IQR, 0.6-55.8) hours; executive administrators spent 28.6 (IQR, 3.1-26.7) hours; other clinicians and staff spent a combined 20.3 (IQR, 0-36.8) hours. Physician time accounted for the greatest proportion of overall MIPS-related costs (54%; $6909; IQR, $94-$9905).

Conclusions and Relevance

In this qualitative study, physician practice leaders reported significant time and financial costs of participating in the MIPS program. Attention to reducing the burden of MIPS may be warranted.

Process mapping in healthcare: a systematic review

INTRODUCTION

Process mapping (PM) supports better understanding of complex systems and adaptation of improvement interventions to their local context. However, there is little research on its use in healthcare. This study (i) proposes a conceptual framework outlining quality criteria to guide the effective implementation, evaluation and reporting of PM in healthcare; (ii) reviews published PM cases to identify context and quality of PM application, and the reported benefits of using PM in healthcare.

METHODS

We developed the conceptual framework by reviewing methodological guidance on PM and empirical literature on its use in healthcare improvement interventions. We conducted a systematic review of empirical literature using PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology. Inclusion criteria were: full text empirical study; describing the process through which PM has been applied in a healthcare setting; published in English. Databases searched are: Medline, Embase, HMIC-Health Management Information Consortium, CINAHL-Cumulative Index to Nursing and Allied Health Literature, Scopus. Two independent reviewers extracted and analysed data. Each manuscript underwent line by line coding. The conceptual framework was used to evaluate adherence of empirical studies to the identified PM quality criteria. Context in which PM is used and benefits of using PM were coded using an inductive thematic analysis approach.

RESULTS

The framework outlines quality criteria for each PM phase: (i) preparation, planning and process identification, (ii) data and information gathering, (iii) process map generation, (iv) analysis, (v) taking it forward. PM is used in a variety of settings and approaches to improvement. None of the reviewed studies (N = 105) met all ten quality criteria; 7% were compliant with 8/10 or 9/10 criteria. 45% of studies reported that PM was generated through multi-professional meetings and 15% reported patient involvement. Studies highlighted the value of PM in navigating the complexity characterising healthcare improvement interventions.

CONCLUSION

The full potential of PM is inhibited by variance in reporting and poor adherence to underpinning principles. Greater rigour in the application of the method is required. We encourage the use and further development of the proposed framework to support training, application and reporting of PM.

TRIAL REGISTRATION

Prospero ID: CRD42017082140.

Variation In Telemedicine Use And Outpatient Care During The COVID-19 Pandemic In The United States

Coronavirus disease 2019 (COVID-19) spurred a rapid rise in telemedicine, but it is unclear how use has varied by clinical and patient factors during the pandemic. We examined the variation in total outpatient visits and telemedicine use across patient demographics, specialties, and conditions in a database of 16.7 million commercially insured and Medicare Advantage enrollees from January to June 2020. During the pandemic, 30.1 percent of all visits were provided via telemedicine, and the weekly number of visits increased twenty-three-fold compared with the prepandemic period. Telemedicine use was lower in communities with higher rates of poverty (31.9 percent versus 27.9 percent for the lowest and highest quartiles of poverty rate, respectively). Across specialties, the use of any telemedicine during the pandemic ranged from 68 percent of endocrinologists to 9 percent of ophthalmologists. Across common conditions, the percentage of visits provided during the pandemic via telemedicine ranged from 53 percent for depression to 3 percent for glaucoma. Higher rates of telemedicine use for common conditions were associated with smaller decreases in total weekly visits during the pandemic.

Assessment of Electronic Health Record Use Between US and Non-US Health Systems

Importance

Understanding how the electronic health record (EHR) system changes clinician work, productivity, and well-being is critical. Little is known regarding global variation in patterns of use.

Objective

To provide insights into which EHR activities clinicians spend their time doing, the EHR tools they use, the system messages they receive, and the amount of time they spend using the EHR after hours.

Design, Setting, and Participants

This cross-sectional study analyzed the deidentified metadata of ambulatory care health systems in the US, Canada, Northern Europe, Western Europe, the Middle East, and Oceania from January 1, 2019, to August 31, 2019. All of these organizations used the EHR software from Epic Systems and represented most of Epic Systems's ambulatory customer base. The sample included all clinicians with scheduled patient appointments, such as physicians and advanced practice practitioners.

Exposures

Clinician EHR use was tracked by deidentified and aggregated metadata across a variety of clinical activities.

Main Outcomes and Measures

Descriptive statistics for clinician EHR use included time spent on clinical activities, note documentation (as measured by the percentage of characters in the note generated by automated or manual data entry source), messages received, and time spent after hours.

Results

A total of 371 health systems were included in the sample, of which 348 (93.8%) were located in the US and 23 (6.2%) were located in other countries. US clinicians spent more time per day actively using the EHR compared with non-US clinicians (mean time, 90.2 minutes vs 59.1 minutes; P < .001). In addition, US clinicians vs non-US clinicians spent significantly more time performing 4 clinical activities: notes (40.7 minutes vs 30.7 minutes; P < .001), orders (19.5 minutes vs 8.75 minutes; P < .001), in-basket messages (12.5 minutes vs 4.80 minutes; P < .001), and clinical review (17.6 minutes vs 14.8 minutes; P = .01). Clinicians in the US composed more automated note text than their non-US counterparts (77.5% vs 60.8% of note text; P < .001) and received statistically significantly more messages per day (33.8 vs 12.8; P < .001). Furthermore, US clinicians used the EHR for a longer time after hours, logging in 26.5 minutes per day vs 19.5 minutes per day for non-US clinicians (P = .01). The median US clinician spent as much time actively using the EHR per day (90.1 minutes) as a non-US clinician in the 99th percentile of active EHR use time per day (90.7 minutes) in the sample. These results persisted after controlling for organizational characteristics, including structure, type, size, and daily patient volume.

Conclusions and Relevance

This study found that US clinicians compared with their non-US counterparts spent substantially more time actively using the EHR for a wide range of clinical activities or tasks. This finding suggests that US clinicians have a greater EHR burden that may be associated with nontechnical factors, which policy makers and health system leaders should consider when addressing clinician wellness.

Pricing Universal Health Care: How Much Would The Use Of Medical Care Rise?

The return of a Democratic administration to the White House, coupled with coronavirus disease 2019 (COVID-19) pandemic-induced contractions of job-based insurance, may reignite debate over public coverage expansion and its costs. Decades of research demonstrate that uninsured people and people with copays and deductibles use less care than people with first-dollar coverage. Hence, most economic analyses of Medicare for All proposals and other coverage expansions project increased utilization and associated costs. We review the utilization surges that such analyses have predicted and contrast them with the more modest utilization increments observed after past coverage expansions in the US and other affluent nations. The discrepancy between predicted and observed utilization changes suggests that analysts underestimate the role of supply-side constraints-for example, the finite number of physicians and hospital beds. Our review of the utilization effects of past coverage expansions suggests that a first-dollar universal coverage expansion would increase ambulatory visits by 7-10 percent and hospital use by 0-3 percent. Modest administrative savings could offset the costs of such increases.

Trends in Pediatric Primary Care Visits During the Coronavirus Disease of 2019 Pandemic

OBJECTIVE

Months after the declaration of the coronavirus disease of 2019 (COVID-19) national emergency, visits among children remained suppressed for unclear reasons, which we sought to understand by examining child visit rates.

METHODS

Using de-identified claims data for children <18 years old from OptumLabs® Data Warehouse, a large commercial claims database, we compared monthly primary care visit and vaccination rates from January-October 2020 to January-October 2018 and 2019. Visit rates were analyzed by visit reason and by the month after (eg, month +1) the COVID-19 public health emergency declaration using a series of child-level Poisson regression models.

RESULTS

There were 3.4, 3.4, and 3.1 million children in 2018, 2019, and 2020 cohorts, respectively. Compared to the same months in prior years, primary care visits in 2020 were 60% lower in month +1 (incidence rate ratio [IRR] 0.40, 99% confidence interval [CI] 0.40-0.40) and 17% lower in month +7 (IRR 0.83, 99% CI 0.83-0.83). Preventive visit rates were 53% lower in month +1 (IRR 0.47, 99% CI 0.47-0.47), but 8% higher than prior years in month +7 (IRR 1.08, 99% CI 1.08-1.08). Monthly rates of vaccine administration followed a similar pattern. Problem-focused visits remained 31% lower in month +7 (IRR 0.69, 99% CI 0.68-0.69), with notably fewer infection-related visits (acute respiratory tract infections IRR 0.37, 99% CI 0.36-0.37; gastroenteritis IRR 0.20, 99% CI 0.20-0.20).

CONCLUSION

Seven months after the COVID-19 emergency declaration, receipt of pediatric care remained suppressed due to fewer problem-focused visits, with notably fewer infection-related visits. By October 2020, rates of preventive visits and vaccination exceeded rates in prior years.