Medicaid Reimbursement for Common Orthopaedic Trauma Procedures Is 16.0% Less Compared With Medicare With Substantial Variability Between States.

OBJECTIVES: This study seeks to evaluate the variability of Medicaid reimbursement and compare it with Medicare reimbursement using the 20 most commonly billed orthopaedic trauma Current Procedural Terminology (CPT) codes nationwide. The authors anticipate significant variability between states and hypothesize that Medicaid payment will be significantly less than Medicare payment. METHODS: The top 20 most common orthopaedic trauma surgery procedural codes were identified from a previous analysis performed by Haglin et al. The Centers for Medicare and Medicaid Services Physician Fee Schedule was used to determine reimbursement rates from Medicare, and state Medicaid fee schedules were used to determine reimbursement rates for Medicaid. State Medicaid rates were compared with their corresponding Medicare rates to determine a dollar difference. In addition, the dollar difference for each CPT code was divided by its respective physician relative value unit. This was used to acknowledge the possible variability in the complexity of orthopaedic procedures and the related physician effort. The Medicare Wage Index was used to adjust Medicaid rates based on the cost of living for the state as well. Coefficients of variation were calculated to represent overall variability in Medicaid and Medicare reimbursement rates. RESULTS: The mean reimbursement rates for Medicaid were lower for all 20 procedures compared with Medicare. On average, Medicaid reimbursed 16.0% less than Medicare and 29.6% less when adjusting for cost of living. MCD reimbursed at a higher rate than MCR for all procedures in only 9 states (Alaska, Arizona, Arkansas, Montana, Nebraska, New Jersey, New Mexico, North Dakota, and South Dakota) while 38 states reimbursed at a lower rate than MCR, on average. The coefficient of variation ranged from 0.24 to 0.34 for the Medicaid unadjusted group and from 0.35 to 0.46 for the Medicare Wage Index-adjusted group. By contrast, the Medicare group was consistent at 0.06 for all 20 procedures. The average dollar difference across the 20 CPT codes for Medicaid reimbursement compared with Medicare reimbursement ranged from -$76.89 to -$225.17, and the dollar difference per relative value unit ranged from -$5.96 to -$15.16. CONCLUSIONS: This study found a high amount of variation between state Medicaid reimbursement rates and average rates that were significantly lower than Medicare reimbursement rates for the top 20 most used orthopaedic trauma CPT codes as identified by Haglin et al. The discrepancy in reimbursement was increased when Medicaid rates were adjusted for state cost of living. LEVEL OF EVIDENCE: Prognostic, Level III. See Instructions for Authors for a complete description of levels of evidence.

Trends in Top Surgery Patient Characteristics, Wound Complications, and CPT Code Use by Plastic Surgeons: A Decade-Long Analysis.

BACKGROUND: Gender-affirming top surgery is becoming increasingly common, with greater diversity in the patients receiving top surgery. The purpose of this study was to examine national trends in patient demographics, characteristics, wound complication rates, and concurrent procedures in patients receiving gender-affirming top surgeries. METHODS: Patients with gender dysphoria who underwent breast procedures, including mastectomy, mastopexy, breast augmentation, or breast reduction by a plastic surgeon between 2013 and 2022, were identified from the American College of Surgeons National Surgical Quality Improvement Program database. These procedures were considered to be gender-affirming "top surgery." Univariate analyses were performed to examine trend changes in the patient population and types of additional procedures performed over the last decade. RESULTS: There was a 38-fold increase in the number of patients who received top surgery during the most recent years compared to the first 2 years of the decade. Significantly more individuals receiving top surgery in recent years were nonbinary ( P < 0.01). There was a significant decrease in percentage of active smokers ( P < 0.01) while there was an increase in percentage of patients with diabetes ( P = 0.03). While there was a significant increase in the number of obese patients receiving top surgery ( P < 0.01), there were no differences in postoperative wound complications between the years. Significantly more patients received additional procedures ( P < 0.01) and had about a 9-fold increase in distinct number of additional CPT codes from 2013-2014 to 2021-2022. CONCLUSIONS: Our study found that there has been (1) a significant increase in the number of top surgery patients from 2013 to 2022 overall and (2) a particular increase in patients with preoperative comorbidities, such as a higher body mass index and diabetes. Understanding current and evolving trends in patients undergoing surgical treatment for gender dysphoria can inform individualized care plans that best serve the needs of patients and optimize overall outcomes.

Inter-rater reliability of ACS-NSQIP colorectal procedure coding in Canada.

BACKGROUND: The American College of Surgeons National Surgical Quality Improvement Project (ACS-NSQIP) uses Current Procedural Terminology (CPT) codes for risk-adjusted calculations. This study evaluates the inter-rater reliability of coding colorectal resections across Canada by ACS-NSQIP surgical clinical nurse reviewers (SCNR) and its impact on risk predictions. METHODS: SCNRs in Canada were asked to code simulated operative reports. Percent agreement and free-marginal kappa correlation were calculated. The ACS-NSQIP risk calculator was utilized to illustrate its impact on risk prediction. RESULTS: Responses from 44 of 150 (29.3 â€‹%) SCNRs revealed 3 to 6 different codes chosen per case, with agreement ranging from 6.7 â€‹% to 62.3 â€‹%. Free-marginal kappa correlation ranged from moderate agreement (0.53) to high disagreement (-0.17). ACS-NSQIP risk calculator predicted large absolute differences in risk for serious complications (0.2 â€‹%-13.7 â€‹%) and mortality (0.2 â€‹%-6.3 â€‹%). CONCLUSION: This study demonstrated low inter-rater reliability in coding ACS-NSQIP colorectal procedures in Canada among SCNRs, impacting risk predictions.

Medicare payment trends compared to inflation for anesthesia services.

STUDY OBJECTIVE: Identify changes and trends in the real value of Medicare payments for anesthesia services between 2000 and 2020 and how it may affect practices. DESIGN: Retrospective analysis. SETTING: We utilized the Physician/Supplier Procedure Summary (PSPS) datasets of Medicare Part B claims to identify high volume anesthesia services in 2020 with 20 years of data. The Consumer Price Index was used as a measure of inflation to adjust prices. PATIENTS: The PSPS datasets contain summaries of all annual Medicare Part B claims and payment amounts by carrier and locality. INTERVENTIONS: Patients receiving anesthesia services. MEASUREMENTS: For each service, identified by Current Procedural Terminology (CPT) codes, we trended the average Medicare payment per procedure from 2000 to 2020 and calculated year to year changes and compound annual growth rate (CAGR). We also evaluated base and time units for each CPT code and the national Medicare anesthesia conversion factor (CF) for the same years. MAIN RESULTS: The average Medicare payment in the study sample increased 20.1% from 2000 to 2020. After adjusting for inflation, the average Medicare payment per anesthesia service decreased by 20.8% over that period. The Medicare anesthesia CF increased 24.9% in the same period, and after adjusting for inflation, the real value of the CF decreased 16.9%. Average CAGR across the 20 anesthesia services was 0.88%, compared to the average annual inflation at 2.06%. CONCLUSIONS: Average Medicare payment for common anesthesia services after adjusting for inflation have decreased from 2000 to 2020, consistent with findings in other physician specialties. Understanding these trends is important for practice viability and suggests significant financial implications for anesthesia practices and hospitals if the trend were to continue.

Understanding Provider Cost of MRI for Appendicitis in Children: A Time-Driven Activity-Based Costing Analysis.

OBJECTIVE: To use time driven activity-based costing to characterize the provider cost of rapid MRI for appendicitis compared to other MRI examinations billed with the same Current Procedural Terminology codes commonly used for MRI appendicitis examinations. METHODS: Rapid MRI appendicitis examination was compared with MRI pelvis without intravenous contrast, MRI abdomen/pelvis without intravenous contrast, and MRI abdomen/pelvis with intravenous contrast. Process maps for each examination were created through direct shadowing of patient procedures (n = 20) and feedback from relevant health care professionals. Additional data were collected from the electronic medical record for 327 MRI examinations. Practical capacity cost rates were calculated for personnel, equipment, and facilities. The cost of each step was calculated by multiplying the capacity cost rate with the mean duration of each step. Stepwise costs were summed to generate a total cost for each MRI examination. RESULTS: The mean duration and costs for MRI examination type were as follows: MRI appendicitis: 11 (range: 6-25) min, $20.03 (7.80-44.24); MRI pelvis without intravenous contrast: 55 (29-205) min, $105.99 (64.18-285.13); MRI abdomen/pelvis without intravenous contrast: 65 (26-173) min, $144.83 (61.16-196.50); MRI abdomen/pelvis with intravenous contrast: 128 (39-303) min, $236.99 (102.62-556.54). CONCLUSION: The estimated cost of providing a rapid appendicitis MRI examination is significantly less than other MRI examinations billed using Current Procedural Terminology codes typically used for appendicitis MRI. Mechanisms to appropriately bill rapid MRI examinations with limited sequences are needed to improve cost efficiency for the patient and to enable wider use of limited MRI examinations in the pediatric population.

We Are Not Speaking the Same Language: Current Procedural Terminology Coding and Provision of Care in Lymphatic Reconstruction.

INTRODUCTION: Current Procedural Terminology (CPT) codes provide a uniform language for medical billing, but specific codes have not been assigned for lymphatic reconstruction techniques. The authors hypothesized that inadequate codes would contribute to heterogeneous coding practices and reimbursement challenges, ultimately limiting surgeons' ability to treat patients. METHODS: A 22-item virtual questionnaire was offered to 959 members of the American Society of Reconstructive Microsurgeons to assess the volume of lymphatic reconstruction procedures performed, CPT codes used for each procedure, and challenges related to coding and providing care. RESULTS: The survey was completed by 66 board-certified/board-eligible plastic surgeons (6.9%), who unanimously agreed that lymphatic surgery is integral to cancer care, with 86.4% indicating that immediate lymphatic reconstruction should be offered after lymphadenectomy. Most performed lymphovenous bypass, immediate lymphatic reconstruction, liposuction, and vascularized lymph node transfer.Respondents reported that available CPT codes failed to reflect procedural scope. A wide variety of CPT codes was used to report each type of procedure. Insurance coverage problems led to 69.7% of respondents forgoing operations and 32% reducing treatment offerings. Insurance coverage and CPT codes were identified as significant barriers to care by 98.5% and 95.5% of respondents, respectively. CONCLUSIONS: Respondents unanimously agreed on the importance of lymphatic reconstruction in cancer care, and most identified inadequate CPT codes as causing billing issues, which hindered their ability to offer surgical treatment. Appropriate and specific CPT codes are necessary to ensure accuracy and consistency of reporting and ultimately to improve patient access to care.

Declining Inflation-Adjusted Medicare Physician Fees: An Unsustainable Trend in Hip Arthroscopy.

INTRODUCTION: Although hip arthroscopy continues to be one of the most used arthroscopic procedures, no focused, comprehensive evaluation of reimbursement trends has been conducted. The purpose of this study was to analyze the temporal Medicare reimbursement trends for hip arthroscopy procedures. METHODS: From 2011 to 2021, the Medicare Physician Fee Schedule Look-Up Tool was queried for Current Procedural Terminology (CPT) codes related to hip arthroscopy (29860 to 29863, 29914 to 29916). All monetary data were adjusted to 2021 US dollars. The compound annual growth rate and total percentage change were calculated. Mann-Kendall trend tests were used to evaluate the reimbursement trends. RESULTS: Based on the unadjusted values, a significant increase in physician fee was observed from 2011 to 2021 for CPT codes 29861 (removal of loose or foreign bodies; % change: 3.49, P = 0.03) and 29862 (chondroplasty, abrasion arthroplasty, labral resection; % change: 3.19, P = 0.03). The remaining CPT codes experienced no notable changes in reimbursement based on the unadjusted values. After adjusting for inflation, all seven of the hip arthroscopy CPT codes were observed to experience a notable decline in Medicare reimbursement. Hip arthroscopy with acetabuloplasty (CPT: 29915) and labral repair (CPT: 29916) exhibited the greatest reduction in reimbursement with a decrease in physician fee of 24.69% ( P < 0.001) and 24.64% ( P < 0.001), respectively, over the study period. DISCUSSION: Medicare reimbursement for all seven of the commonly used hip arthroscopy services did not keep up with inflation, demonstrating marked reductions from 2011 to 2021. Specifically, the inflation-adjusted reimbursements decreased between 19.23% and 24.69% between 2011 and 2021.

Letter re: Misidentification of Transcarotid Artery Revascularization by Current Procedural Terminology.

In this letter, we discussed the selection of patients undergoing Transcarotid Artery Revascularization (TCAR) using the Current Procedural Terminology (CPT) codes. We examined a previous study using CPT code 37215 to identify TCAR cases using the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database. As an ACS-NSQIP participating site, we have complete access to the ACS-NSQIP database, and we performed a more in-depth examination of the method. We found significant discrepancies in the method described and conclude that it is methodologically flawed to use CPT code 37215 to differentiate TCAR cases. This study not only re-evaluates the validity of the previous study but also has the potential to prevent other researchers from employing the erroneous methodology for TCAR selection using the CPT code, which is one of the most widely used standardizations of medical communication for surgical procedures. This is particularly pertinent given the recent "TCAR revolution", where significant attention has been focused on TCAR.

The Time Burden of Office Visits in Contemporary Pituitary Care, 2016 to 2019.

BACKGROUND: The concept of "time toxicity" has emerged to address the impact of time spent in the healthcare system; however, little work has examined the phenomenon in the field of otolaryngology. OBJECTIVE: To validate the use of Evaluation and Management (E/M) current procedural terminology codes as a method to assess time burden and to pilot this tool to characterize the time toxicity of office visits associated with a diagnosis of pituitary adenoma between 2016 and 2019. METHODS: A retrospective cohort study of outpatient office visits quantified differences between timestamps documenting visit length and their associated E/M code visit length. The IBM MarketScan database was queried to identify patients with a diagnosis of pituitary adenoma in 2016 and to analyze their new and return claims between 2016 and 2019. One-way ANOVA and two-sample t-tests were used to examine claim quantity, time in office, and yearly visit time. RESULTS: In the validation study, estimated visit time via E/M codes and actual visit time were statistically different (P < 0.01), with E/M codes underestimating actual time spent in 79.0% of visits. In the MarketScan analysis, in 2016, 2099 patients received a primary diagnosis of pituitary adenoma. There were 8490 additional-related claims for this cohort from 2016 to 2019. The plurality of new office visits were with endocrinologists (n = 857; 29.3%). Total time spent in office decreased yearly, from a mean of 113 min (2016) to 69 min (2019) (P < 0.001). CONCLUSIONS: E/M codes underestimate the length of outpatient visits; therefore, time toxicity experienced by pituitary patients may be greater than reported. Further studies are needed to develop additional assessment tools for time toxicity and promote increased efficiency of care for patients with pituitary adenomas.

Modifier 22 Use in Fee-for-Service Medicare.

Importance: Modifier 22 is a mechanism designed for surgeons to identify cases that are more complex than their Current Procedural Terminology code accounts for. However, empirical studies of the use and efficacy of modifier 22 are lacking. Objective: To assess the use of modifier 22 in common surgical procedures and the association of use with compensation. Design, Setting, and Participants: This was a cross-sectional analysis of the 2021 Physician/Supplier Procedure Summary Limited Data Set including all Part B carrier and durable medical equipment fee-for-service claims. Claims for 10 common surgical procedures were evaluated, including mastectomy, total hip arthroplasty, total knee arthroplasty, coronary artery bypass grafting, laparoscopic right colectomy, laparoscopic appendectomy, laparoscopic cholecystectomy, kidney transplant, laparoscopic total abdominal hysterectomy and bilateral salpingo-oophorectomy, and lumbar laminectomy. Data were analyzed from August to November 2023. Main Outcomes and Measures: Rate of modifier 22 use, rate of claim denial, mean charges, mean payment for accepted claims, and mean payment for all claims. Results: The sample included 625 316 surgical procedures performed in calendar year 2021. The proportion of modifier 22 coding for a procedure ranged from 5725 of 251 521 (2.3%) in total knee arthroplasty to 1566 of 18 459 (8.5%) in laparoscopic total abdominal hysterectomy and bilateral salpingo-oophorectomy. Submitted charges were 11.1% (95% CI, 9.1-13.2) to 22.8% (95% CI, 21.3-24.3) higher for claims with modifier 22, depending on the procedure. Among accepted claims, those with modifier 22 had increased payments ranging from 0.8% (95% CI, 0.7-1.0) to 4.8% (95% CI, 4.5-5.1). However, claims with modifier 22 were more likely to be denied (7.4% vs 4.0%; P < .001). As a result, overall mean payments were mixed, with 4 procedures having lower payments when modifier 22 was appended, 4 procedures having higher payments with modifier 22, and 2 procedures with no difference. The largest increase in mean payment for modifier 22 claims was for kidney transplant with an increased payment of $71.46 (95% CI, 55.32-87.60), which translates to a relative increase of 3.4% (95% CI, 2.9-4.6). Conclusions and Relevance: The findings in this study suggest that modifier 22 had little to no financial benefit when appended to claims for a diverse panel of surgical procedures. In the current system, surgeons have little reason to request modifier 22, and no mechanisms currently exist for surgeons to recoup payment for difficult operations.

Systematic evaluation of common natural language processing techniques to codify clinical notes.

Proper codification of medical diagnoses and procedures is essential for optimized health care management, quality improvement, research, and reimbursement tasks within large healthcare systems. Assignment of diagnostic or procedure codes is a tedious manual process, often prone to human error. Natural Language Processing (NLP) has been suggested to facilitate this manual codification process. Yet, little is known on best practices to utilize NLP for such applications. With Large Language Models (LLMs) becoming more ubiquitous in daily life, it is critical to remember, not every task requires that level of resource and effort. Here we comprehensively assessed the performance of common NLP techniques to predict current procedural terminology (CPT) from operative notes. CPT codes are commonly used to track surgical procedures and interventions and are the primary means for reimbursement. Our analysis of 100 most common musculoskeletal CPT codes suggest that traditional approaches can outperform more resource intensive approaches like BERT significantly (P-value = 4.4e-17) with average AUROC of 0.96 and accuracy of 0.97, in addition to providing interpretability which can be very helpful and even crucial in the clinical domain. We also proposed a complexity measure to quantify the complexity of a classification task and how this measure could influence the effect of dataset size on model's performance. Finally, we provide preliminary evidence that NLP can help minimize the codification error, including mislabeling due to human error.

The 22-Modifier in Total Hip and Knee Arthroplasty: A Comprehensive Analysis.

BACKGROUND: The 22-modifier requests additional compensation for increased case complexity. Unfortunately, there is little to guide physicians on the application, which may increase successful reimbursement. We sought to evaluate various factors affecting reimbursement of the 22-modifier in primary total joint arthroplasty (TJA) and report which factors contributed to successful utilization. METHODS: In this retrospective study, all cases from a single practice where the 22-modifier was added to Current Procedural Terminology codes: 27130 (total hip arthroplasty) and 27447 (total knee arthroplasty) from October 2018 to March 2022 were evaluated. Out of the 6,869 total cases performed, 816 22-modifier cases were identified (11.9%). Operative reports, demographics, insurance type, billing information, and clinical records were assessed. T-tests were used to determine statistical significance. RESULTS: Of the 816 cases, 221 (27.1%) were successfully reimbursed. Cases justified 22-modifier application with obesity, anatomic variations, or intraoperative factors. Some cases lacked justification, or operative reports were not submitted. Reimbursement was successful for 27.6% of obesity cases, 29.7% of intraoperative complications, and 35.7% of anatomic variations. There was a significantly higher likelihood of Medicare reimbursement than third-party payers or Medicaid (69.6 versus 20.5 and 6.9%) (P < .0001). Additionally, Medicare was more likely to reimburse for obesity (76.6 versus 20.0, and 5.2%), anatomic variations (77.3 versus 22.0%), and intraoperative factors (66.6 versus 21.1, and 1.7%). CONCLUSIONS: Reimbursement for 22-modifier cases in TJA is unlikely. Obesity was cited for most 22-modifier justifications, but anatomic variation justification was successfully reimbursed most often. Medicare was most likely to reimburse compared to third-party payers or Medicaid. These findings should be considered when applying a 22-modifier to TJA procedures.

Can Publicly Available Artificial Intelligence Successfully Identify Current Procedural Terminology Codes for Common Procedures in Neurosurgery?

OBJECTIVE: Coding for neurosurgical procedures is a complex process that is dynamically changing year to year, through the annual introduction and removal of codes and modifiers. The authors hoped to elucidate if publicly available artificial intelligence (AI) could offer solutions for neurosurgeons with regard to coding. METHODS: Multiple publicly available AI platforms were asked to provide Current Procedural Terminology (CPT) codes and Revenue Value Units (RVU) values for common neurosurgical procedures of the brain and spine with a given indication for the procedure. The responses of platforms were recorded and compared to the currently valid CPT codes used for the procedure and the amount of RVUs that would be gained. RESULTS: Six platforms and Google were asked for the appropriate CPT codes for 10 endovascular, spinal, and cranial procedures each. The highest performing platforms were as follows: Perplexity.AI identified 70% of endovascular, BingAI identified 55% of spinal, and ChatGPT 4.0 with Bing identified 75% of cranial CPT codes. With regard to RVUs, the top performer gained 78% of endovascular, 42% of spinal, and 70% of cranial possible RVUs. With regard to accuracy, AI platforms on average outperformed Google (45% vs. 25%, P = 0.04236). CONCLUSIONS: The ability of publicly available AIs to successfully code for neurosurgical procedures holds great promise in the future. Future development of AI should focus on improving accuracy with regard to CPT codes and providing supporting documentation for its decisions. Improvement on the existing capabilities of AI platforms can allow for increased operational efficiency and cost savings for practices.

Development and multicentre validation of the FLEX score: personalised preoperative surgical risk prediction using attention-based ICD-10 and Current Procedural Terminology set embeddings.

BACKGROUND: Preoperative knowledge of surgical risks can improve perioperative care and patient outcomes. However, assessments requiring clinician examination of patients or manual chart review can be too burdensome for routine use. METHODS: We conducted a multicentre retrospective study of 243 479 adult noncardiac surgical patients at four hospitals within the Mass General Brigham (MGB) system in the USA. We developed a machine learning method using routinely collected coding and patient characteristics data from the electronic health record which predicts 30-day mortality, 30-day readmission, discharge to long-term care, and hospital length of stay. RESULTS: Our method, the Flexible Surgical Set Embedding (FLEX) score, achieved state-of-the-art performance to identify comorbidities that significantly contribute to the risk of each adverse outcome. The contributions of comorbidities are weighted based on patient-specific context, yielding personalised risk predictions. Understanding the significant drivers of risk of adverse outcomes for each patient can inform clinicians of potential targets for intervention. CONCLUSIONS: FLEX utilises information from a wider range of medical diagnostic and procedural codes than previously possible and can adapt to different coding practices to accurately predict adverse postoperative outcomes.

Forecasting The Impact of the 2023 Current Procedural Terminology Coding Changes On Ventral Hernia Work Relative Value Units. A Cross-Sectional Study.

BACKGROUND: In January 2023, significant changes were implemented to ventral hernia repair Current Procedural Terminology codes, with new codes replacing previous codes. The new codes were assigned a 0-day global period. The impact of these changes on clinical productivity remains unclear. Our objective was to forecast the impact of Current Procedural Terminology changes on ventral hernia-related work relative value units using historical data. METHODS: Ventral hernia repairs performed between March 2021 and December 2022 on adults by a single surgeon with available 90-day follow-up were retrospectively retrieved from the Abdominal Core Health Quality Collaborative. Demographic, hernia, and operative and postoperative data were collected. The ventral hernia repairs were coded twice using the previous and new Current Procedural Terminology codes, and work relative value units were calculated using both systems. The median work relative value units per case were compared using the Wilcoxon signed-rank test. RESULTS: A total of 143 ventral hernia repairs were included. The median age was 59 years, and 50% of patients were male. Median hernia width and length were 3.5 and 5.0 cm, respectively. The most common ventral hernia types were incisional 57% and umbilical 33%. Twenty percent of hernias were recurrent, and 99% were elective repairs. 49% of the procedures were open, 30% robotic, and 21% laparoscopic. Component separation was performed in 16%. The median length of stay was 0.0, and the median number of 90-day outpatient postoperative visits was 1.0. The new Current Procedural Terminology coding system was associated with a higher median 90-day work relative value units per case (14.1) than the previous system (13.8) (P = .002). Subset analysis identified statistically higher median 90-day work relative value units per case using the new versus previous Current Procedural Terminology codes for hernias with the largest defect dimension >10 cm (23.3 vs 18.8), umbilical/epigastric/Spigelian hernias (9.2 vs 7.1), recurrent hernias (20.1 vs 17.3) and open ventral hernia repairs (9.8 vs 7.1), all P < .05. Median 90-day work relative value units per case were statistically lower using the new versus previous codes for non-recurrent (11.6 vs 13.8) and incarcerated/strangulated (14.8 vs 14.9) hernias, all P < .05. In the new coding system, postoperative care within 90-days contributed to a median of 1.3 work relative value units per case (9% of total 90-day work relative value units). CONCLUSION: We forecast that in our practice, the 2023 ventral hernia repair Current Procedural Terminology changes will result in a modest impact on clinical productivity. The impact of these changes on a particular practice depends on surgical practice patterns and ventral hernia case mix.

GRU-D-Weibull: A novel real-time individualized endpoint prediction.

BACKGROUND: In the era of healthcare digital transformation, using electronic health record (EHR) data to generate various endpoint estimates for active monitoring is highly desirable in chronic disease management. However, traditional predictive modeling strategies leveraging well-curated data sets can have limited real-world implementation potential due to various data quality issues in EHR data. METHODS: We propose a novel predictive modeling approach, GRU-D-Weibull, which models Weibull distribution leveraging gated recurrent units with decay (GRU-D), for real-time individualized endpoint prediction and population level risk management using EHR data. EXPERIMENTS: We systematically evaluated the performance and showcased the real-world implementability of the proposed approach through individual level endpoint prediction using a cohort of patients with chronic kidney disease stage 4 (CKD4). A total of 536 features including ICD/CPT codes, medications, lab tests, vital measurements, and demographics were retrieved for 6879 CKD4 patients. The performance metrics including C-index, L1-loss, Parkes' error, and predicted survival probability at time of event were compared between GRU-D-Weibull and other alternative approaches including accelerated failure time model (AFT), XGBoost based AFT (XGB(AFT)), random survival forest (RSF), and Nnet-survival. Both in-process and post-process calibrations were experimented on GRU-D-Weibull generated survival probabilities. RESULTS: GRU-D-Weibull demonstrated C-index of ~0.7 at index date, which increased to ~0.77 at 4.3 years of follow-up, comparable to that of RSF. GRU-D-Weibull achieved absolute L1-loss of ~1.1 years (sd≈0.95) at CKD4 index date, and a minimum of ~0.45 year (sd≈0.3) at 4 years of follow-up, comparing to second-ranked RSF of ~1.4 years (sd≈1.1) at index date and ~0.64 years (sd≈0.26) at 4 years. Both significantly outperform competing approaches. GRU-D-Weibull constrained predicted survival probability at time of event to smaller and more fixed range than competing models throughout follow-up. Significant correlations were observed between prediction error and missing proportions of all major categories of input features at index date (Corr ~0.1 to ~0.3), which faded away within 1 year after index date as more data became available. Through post training recalibration, we achieved a close alignment between the predicted and observed survival probabilities across multiple prediction horizons at different time points during follow-up. CONCLUSION: GRU-D-Weibull shows advantages over competing methods in handling missingness commonly encountered in EHR data and providing both probability and point estimates for diverse prediction horizons during follow-up. The experiment highlights the potential of GRU-D-Weibull as a suitable candidate for individualized endpoint risk management, utilizing real-time clinical data to generate various endpoint estimates for monitoring. Additional research is warranted to evaluate the influence of different data quality aspects on prediction performance. Furthermore, collaboration with clinicians is essential to explore the integration of this approach into clinical workflows and evaluate its effects on decision-making processes and patient outcomes.