Evaluating the Efficacy of Large Language Models in CPT Coding for Craniofacial Surgery: A Comparative Analysis.

BACKGROUND: The advent of Large Language Models (LLMs) like ChatGPT has introduced significant advancements in various surgical disciplines. These developments have led to an increased interest in the utilization of LLMs for Current Procedural Terminology (CPT) coding in surgery. With CPT coding being a complex and time-consuming process, often exacerbated by the scarcity of professional coders, there is a pressing need for innovative solutions to enhance coding efficiency and accuracy. METHODS: This observational study evaluated the effectiveness of 5 publicly available large language models-Perplexity.AI, Bard, BingAI, ChatGPT 3.5, and ChatGPT 4.0-in accurately identifying CPT codes for craniofacial procedures. A consistent query format was employed to test each model, ensuring the inclusion of detailed procedure components where necessary. The responses were classified as correct, partially correct, or incorrect based on their alignment with established CPT coding for the specified procedures. RESULTS: The results indicate that while there is no overall significant association between the type of AI model and the correctness of CPT code identification, there are notable differences in performance for simple and complex CPT codes among the models. Specifically, ChatGPT 4.0 showed higher accuracy for complex codes, whereas Perplexity.AI and Bard were more consistent with simple codes. DISCUSSION: The use of AI chatbots for CPT coding in craniofacial surgery presents a promising avenue for reducing the administrative burden and associated costs of manual coding. Despite the lower accuracy rates compared with specialized, trained algorithms, the accessibility and minimal training requirements of the AI chatbots make them attractive alternatives. The study also suggests that priming AI models with operative notes may enhance their accuracy, offering a resource-efficient strategy for improving CPT coding in clinical practice. CONCLUSIONS: This study highlights the feasibility and potential benefits of integrating LLMs into the CPT coding process for craniofacial surgery. The findings advocate for further refinement and training of AI models to improve their accuracy and practicality, suggesting a future where AI-assisted coding could become a standard component of surgical workflows, aligning with the ongoing digital transformation in health care.

Advanced Visualization in Minimally Invasive Spine Surgery: The Ergonomics, Economics, and Evolution of Camera-Based Tubes and Retractors.

BACKGROUND: Tubular spine surgery has emerged as a hallmark of minimally invasive spine (MIS) procedures. In recent years, thanks to technological advances, tubular dilators and retractors have been integrated with digital cameras to allow for ergonomic, high-definition visualization of the surgical field. OBJECTIVE: To detail the evolution, ergonomics, economics, and outcomes of camera-based tubular spine surgery, spanning the origins of MIS tubular techniques to the current use of operative microscopes and tube-mounted digital cameras (TMDCs). METHODS: This is a narrative review of studies examining the evolution of tubular spine surgery as well as its most recent advances, with a particular emphasis on advances in visualization of the surgical field. RESULTS: Despite early resistance to tubular techniques due to a steep learning curve, minimally invasive tubular approaches are being increasingly adopted by the mainstream spine surgical community, which has resulted in an expansion of both indications and procedural modalities. This can largely be attributed to the increased quality of visualization, as evidenced by improvements in microscopes as well as emerging technologies like exoscopes and TMDCs. Tubular MIS procedures have also achieved superior efficacy compared with open surgical approaches for the treatment of several spinal pathologies while allowing for improved ergonomics, which may have lasting consequences on surgeon longevity. CONCLUSIONS: Advances in visualization technologies have allowed tubular surgery to become an effective, ergonomic, and muscle-sparing alternative to open spine surgery. Further research is necessary to quantify the true costs and outcomes associated with nascent TMDC technology. CLINICAL RELEVANCE: This work elucidates developments in visualization for tubular spine surgery.

Smartphone Applications for Remote Monitoring of Patients after Transsphenoidal Pituitary Surgery: A Narrative Review of Emerging Technologies.

INTRODUCTION: Almost all postoperative assessments for pituitary patients are performed in clinical settings under the supervision of medical providers. With the emergence of telemedicine, however, there are opportunities to monitor these patients remotely. The potential for use of such technologies is inconsistently described in the brain tumor literature, especially for patients with pituitary adenomas. METHODS: In this comprehensive narrative review, we present the literature for the use of mobile applications (apps) for monitoring of postoperative symptomatology that is specific to patients undergoing pituitary surgery. Our primary research question was: "Which smartphone apps exist in the literature to monitor parameters associated with common complications of pituitary surgery?" Specifically, we search for apps in the literature which facilitate the measurement of parameters associated with adrenal insufficiency, disorders of water imbalance, and visual changes, three common complications of pituitary surgery. RESULTS: 26 apps were identified. Fourteen apps pertained to monitoring of visual changes, followed by nine apps for monitoring water and electrolyte imbalances and three apps for monitoring adrenal dysfunction. Novel technologies which were integrated into these apps included digital image-based colorimetry, sonouroflowmetry, visual contrast sensitivity, and lateral flow immunoassays, among others. CONCLUSION: Due to advancing capabilities of smartphone apps, the potential of telemedicine may extend beyond patient appointments. We show that by integrating novel advances in medical technologies from a variety of specialties, it is possible to develop smartphone-based protocols for remote monitoring of patients after pituitary surgery.

What Is the Value Proposition of Evidence-Based Guidelines? An Application of the Operative Value Index for Lumbar Fusions.

BACKGROUND: Elective lumbar fusions have received criticism for inappropriate utilization. Here, we use a novel Operative Value Index (OVI) to assess whether "indicated," evidence-based lumbar fusions are associated with increased value (outcomes per dollar spent). METHODS: This study is a retrospective analysis of a prospective observational cohort of 294 patients undergoing elective lumbar fusions at a single large academic institution. All patients were preoperatively evaluated by a panel of neurosurgeons for concordance with evidence-based medicine (EBM), determined through guidelines from the North American Spine Society. Oswestry Disability Index (ODI) scores were collected for all patients both preoperatively and at 6-months postoperatively. Time-driven activity-based costing was employed to determine both direct and indirect intraoperative costs. The OVI was defined as the percent improvement in ODI per $1000 spent intraoperatively. Generalized linear mixed model regression, adjusting for confounders, was performed to assess whether EBM-concordant surgeries were associated with higher OVI. RESULTS: Of 294 elective lumbar fusions, 92.9% (n = 273) were EBM-concordant. The average total cost of an EBM-concordant lumbar fusion was $17,932 (supplies: $13,020; personnel: $4314), compared to $20,616 (supplies: $15,467; personnel: $4758) for an EBM-discordant fusion. Average OVI was 2.27 for a concordant fusion, compared to 0.11 for a discordant fusion. Generalized linear mixed model analysis revealed that EBM-concordant cases were associated with significantly higher OVI (ß-coefficient 2.0, P < 0.001). CONCLUSIONS: EBM-concordant fusions were associated with 2% greater improvement in ODI scores from baseline for every $1000 spent intraoperatively. Systematic methods for increasing guideline adherence for lumbar fusions could therefore improve value at scale.

How Do the True Intraoperative Costs of Endoscopic Diskectomy Compare With Microdiskectomy for Lumbar Disk Herniations? A Time-Driven Activity-Based Cost Analysis.

BACKGROUND AND OBJECTIVES: Endoscopic lumbar diskectomy (ED) is a minimally invasive option for addressing lumbar disk herniations. With the introduction of value-based care systems, assessing the true cost of certain procedures is critical when creating reimbursement models and comparing procedures. Here, we compared the costs of performing a microdiskectomy (MD) and ED using time-driven activity-based costing. METHODS: Total cost for the intraoperative episode was calculated using time-driven activity-based costing methodology. Individual costs were obtained by direct observation and electronic medical records and through querying multiple departments (business operations, sterile processing, plant operations, and pharmacy). Timestamps for all involved personnel and material resources were documented. A retrospective analysis was performed on 202 patients who underwent lumbar diskectomy through either MD (n = 167) or ED (n = 35) from 2018 to 2022. Personnel cost was calculated by multiplying the cost per unit time for each personnel type by the length of time spent in the operating room. Supply cost was calculated by aggregating the cost of all individual supplies, from medications to consumables to surgical trays, used during the case. Univariate and multivariable regression analyses were performed comparing the costs between these procedures. RESULTS: The average intraoperative cost per case for ED and MD was $3915 ± $1025 and $3162 ± $954, respectively. Multivariable regression analysis revealed that ED had higher total cost (ß-coefficient: $912 ± $281, P = <.01) and supply cost (ß-coefficient: $474 ± $155, P = <.01) than MD. When accounting for surgeon as a covariate, however, total cost (P = .478) and supply cost (P = .468) differences between ED and MD were negligible. CONCLUSION: ED has shown to be a better value option in addressing lumbar disk herniations, mostly because of advantages in perioperative care. Here, we show that when correcting for surgeon-level effects, the cost between the two procedures is statistically insignificant, reaffirming the value provided by ED.

Do Busier Surgeons Have Lower Intraoperative Costs? An Analysis of Anterior Cervical Discectomy and Fusion Using Time-Driven Activity-Based Costing.

STUDY DESIGN: The present study is a single-center, retrospective cohort study of patients undergoing neurosurgical anterior cervical discectomy and fusion (ACDF). OBJECTIVE: Our objective was to use time-driven activity-based costing (TDABC) methodology to determine whether surgeons' case volume influenced the true intraoperative costs of ACDFs performed at our institution. SUMMARY OF BACKGROUND DATA: Successful participation in emerging reimbursement models, such as bundled payments, requires an understanding of true intraoperative costs, as well as the modifiable drivers of those costs. Certain surgeons may have cost profiles that are favorable for these "at-risk" reimbursement models, while other surgeons may not. METHODS: Total cost was divided into direct and indirect costs. Individual costs were obtained by direct observation, electronic medical records, and through querying multiple departments (business operations, sterile processing, plant operations, and pharmacy). Timestamps for all involved personnel and material resources were documented. All surgeons performing ACDFs at our primary and affiliated hospital sites from 2017 to 2022 were divided into four volume-based cohorts: 1-9 cases (n=10 surgeons, 38 cases), 10-29 cases (n=7 surgeons, 126 cases), 30-100 cases (n=3 surgeons, 234 cases), and > 100 cases (n=2 surgeons, 561 cases). RESULTS: The average total intraoperative cost per case was $7,116 +/- $2,945. The major cost contributors were supply cost ($4,444, 62.5%) and personnel cost ($2,417, 34.0%). A generalized linear mixed model utilizing Poisson distribution was performed with the surgeon as a random effect. Surgeons performing 1-9 total cases, 10-29 cases, and 30-100 cases had increased total cost of surgery (P < 0.001; P < 0.001; and P<0.001, respectively) compared to high-volume surgeons (> 100 cases). Among all volume cohorts, high-volume surgeons also had the lowest mean supply cost, personnel cost, and operative times, while the opposite was true for the lowest-volume surgeons (1-9 cases). CONCLUSION: It is becoming increasingly important for hospitals to identify modifiable sources of variation in cost. We demonstrate a novel use of TDABC for this purpose. LEVEL OF EVIDENCE: Level-III.

What is the Marginal Cost of Using Robot Assistance or Navigation for Transforaminal Lumbar Interbody Fusion? A Time-Driven Activity-Based Cost Analysis.

BACKGROUND AND OBJECTIVE: Our primary objective was to compare the marginal intraoperative cost of 3 different methods for pedicle screw placement as part of transforaminal lumbar interbody fusions (TLIFs). Specifically, we used time-driven activity-based costing to compare costs between robot-assisted TLIF (RA-TLIF), TLIF with intraoperative navigation (ION-TLIF), and freehand (non-navigated, nonrobotic) TLIF. METHODS: Total cost was divided into direct and indirect costs. We identified all instances of RA-TLIF (n = 20), ION-TLIF (n = 59), and freehand TLIF (n = 233) from 2020 to 2022 at our institution. Software was developed to automate the extraction of all intraoperatively used personnel and material resources from the electronic medical record. Total costs were determined through a combination of direct observation, electronic medical record extraction, and interdepartmental collaboration (business operations, sterile processing, pharmacy, and plant operation departments). Multivariable linear regression analysis was performed to compare costs between TLIF modalities, accounting for patient-specific factors as well as number of levels fused, surgeon, and hospital site. RESULTS: The average total intraoperative cost per case for the RA-TLIF, ION-TLIF, and freehand TLIF cohorts was $24 838 ± $10 748, $15 991 ± $6254, and $14 498 ± $6580, respectively. Regression analysis revealed that RA-TLIF had significantly higher intraoperative cost compared with both ION-TLIF (ß-coefficient: $7383 ± $1575, P < .001) and freehand TLIF (ß-coefficient: $8182 ± $1523, P < .001). These cost differences were primarily driven by supply cost. However, there were no significant differences in intraoperative cost between ION-TLIF and freehand TLIF ( P = .32). CONCLUSION: We demonstrate a novel use of time-driven activity-based costing methodology to compare different modalities for executing the same type of lumbar fusion procedure. RA-TLIF entails significantly higher supply cost when compared with other modalities, which explains its association with higher total intraoperative cost. The use of ION, however, does not add extra expense compared with freehand TLIF when accounting for confounders. This might have implications as surgeons and hospitals move toward bundled payments.

Does Body Mass Index Influence Intraoperative Costs and Operative Times for Anterior Cervical Discectomy and Fusion? A Time-Driven Activity-Based Costing Analysis.

OBJECTIVE: Spine surgeons are often unaware of drivers of cost variation for anterior cervical discectomy and fusion (ACDF). We used time-driven activity-based costing to assess the relationship between body mass index (BMI), total cost, and operating room (OR) times for ACDFs. METHODS: Total cost was divided into direct and indirect costs. Individual costs were obtained by direct observation, electronic medical records, and through querying multiple departments. Timestamps for all involved personnel and material resources were documented. Total intraoperative costs were estimated for all ACDFs from 2017 to 2022. All patients were categorized into distinct BMI-based cohorts. Linear regression models were performed to assess the relationship between BMI, total cost, and OR times. RESULTS: A total of 959 patients underwent ACDFs between 2017 and 2022. The average age and BMI were 58.1 ± 11.2 years and 30.2 ± 6.4 kg/m2, respectively. The average total intraoperative cost per case was $7120 ± $2963. Multivariable regression analysis revealed that BMI was not significantly associated with total cost (P = 0.36), supply cost (P = 0.39), or personnel cost (P = 0.20). Higher BMI was significantly associated with increased time spent in the OR (P = 0.018); however, it was not a significant factor for the duration of surgery itself (P = 0.755). Rather, higher BMI was significantly associated with nonoperative OR time (P < 0.001). CONCLUSIONS: Time-driven activity-based costing is a feasible and scalable methodology for understanding the true intraoperative costs of ACDF. Although higher BMI was not associated with increased total cost, it was associated with increased preparatory time in the OR.

What is the Marginal Intraoperative Cost of Using an Exoscope or Operative Microscope for Anterior Cervical Discectomy and Fusion? A Time-Driven Activity-Based Cost Analysis.

OBJECTIVE: Our primary objective was to compare the intraoperative costs of 3 different surgical visualization techniques for anterior cervical discectomy and fusion (ACDF). Specifically, we used time-driven activity-based costing (TDABC) methodology to compare costs between ACDFs performed with operative microscopes (OM-ACDF), exoscopes (EX-ACDF), and loupes (loupes-ACDF). METHODS: Total cost was divided into direct and indirect costs. Individual costs were obtained by direct observation, electronic medical records, and through querying multiple departments (business operations, sterile processing, plant operations, and pharmacy). Timestamps for all involved personnel and material resources were documented. We identified all instances of loupes-ACDF (n = 882), EX-ACDF (n = 26), and OM-ACDF (n = 52) performed at our institution. We performed multivariable linear regression analyses to compare costs between these modalities, accounting for patient-specific factors as well as number of levels fused, surgeon, and hospital site. RESULTS: The average total intraoperative costs per loupes-ACDF, EX-ACDF, and OM-ACDF cases were $7081 +/- $2,942, $7951 +/- $3,488, and $6557 +/- $954, respectively. Regression analysis revealed no difference in intraoperative cost between loupes-ACDF and EX-ACDF (P = 0.717), loupes-ACDF and OM-ACDF (0.954), or OM-ACDF and EX-ACDF (0.217). On a more granular level, however, EX-ACDF was associated with increased cost of consumables, including drapes, compared to both OM-ACDF (ß-coefficient: $369 +/- $121, P = 0.002) and loupes-ACDF (ß-coefficient: $284 +/- $86, P = 0.001). CONCLUSIONS: Although hospitals may be aware of the purchasing fees associated with microscopes and exoscopes, there is no clear documentation of how these technologies affect intraoperative cost. We demonstrate a novel use of TDABC for this purpose.

When Does Intervention End and Surgery Begin? The Role of Interventional Pain Management in the Treatment of Spine Pathology.

PURPOSE OF REVIEW: Recent advances in the field of interventional pain management (IPM) involve minimally invasive procedures such as percutaneous lumbar decompression, interspinous spacer placement, interspinous-interlaminar fusion and sacroiliac joint fusion. These developments have received pushback from surgical professional societies, who state spinal instrumentation and arthrodesis should only be performed by spine surgeons. The purpose of this review is to evaluate the validity of this claim. A literature search was conducted on Google Scholar and PubMed databases. Articles were included which examined IPM in the following contexts: credentialing and procedural privileging guidelines, fellowship training and education, and procedural outcomes compared to those of surgical specialties. Our primary research question is: "Should interventionalists be performing decompression and fusion procedures?". FINDINGS: Advanced percutaneous spine procedures are not universally incorporated into pain fellowship curriculums. Trainees attempt to compensate for these deficiencies through industry-led training, which has been criticized for lacking central regulation. There is also a paucity of studies comparing procedural outcomes between surgeons and interventionalists for complex spine procedures, including decompression and fusion. Pain fellowship curriculums have not kept pace with some of procedural advancements within the field. Interventionalists are also not trained to manage potential complications of spinal instrumentation and arthrodesis, which has been recognized as an essential requirement for procedural privileging. Decompression and fusion may therefore be outside the scope of an interventionalist's practice.