Try a new search

Format these results:

Searched for:

person:iorior01

Total Results:

215


Assessing Ability for ChatGPT to Answer Total Knee Arthroplasty-Related Questions

Magruder, Matthew L; Rodriguez, Ariel; Wong, Che Hang Jason; Erez, Orry; Piuzzi, Nicolas S; Scuderi, Gil R; Slover, James; Oh, Jason H; Schwarzkopf, Ran; Chen, Antonia F; Iorio, Richard; Goodman, Stuart B; Mont, Michael A
INTRODUCTION/BACKGROUND:Artificial intelligence (AI) in the field of orthopaedics has been a topic of increasing interest and opportunity in recent years. Its applications are widespread both for physicians and patients, including use in clinical decision-making, in the operating room, and in research. In this study, we aimed to assess the quality of ChatGPT answers when asked questions related to total knee arthroplasty (TKA). METHODS:ChatGPT prompts were created by turning 15 of the American Academy of Orthopaedic Surgeons (AAOS) Clinical Practice Guidelines into questions. An online survey was created, which included screenshots of each prompt and answers to the 15 questions. Surgeons were asked to grade ChatGPT answers from 1 to 5 based on their characteristics: 1) Relevance; 2) Accuracy; 3) Clarity; 4) Completeness; 5) Evidence-based; and 6) Consistency. There were eleven Adult Joint Reconstruction fellowship-trained surgeons who completed the survey. Questions were subclassified based on the subject of the prompt: 1) risk factors, 2) implant/Intraoperative, and 3) pain/functional outcomes. The average and standard deviation for all answers, as well as for each subgroup, were calculated. Inter-rater reliability (IRR) was also calculated. RESULTS:All answer characteristics were graded as being above average (i.e., a score > 3). Relevance demonstrated the highest scores (4.43±0.77) by surgeons surveyed, and consistency demonstrated the lowest scores (3.54±1.10). ChatGPT prompts in the Risk Factors group demonstrated the best responses, while those in the Pain/Functional Outcome group demonstrated the lowest. The overall IRR was found to be 0.33 (poor reliability), with the highest IRR for relevance (0.43) and the lowest for evidence-based (0.28). CONCLUSION/CONCLUSIONS:ChatGPT can answer questions regarding well-established clinical guidelines in TKA with above-average accuracy but demonstrates variable reliability. This investigation is the first step in understanding large language model (LLM) AIs like ChatGPT and how well they perform in the field of arthroplasty.
PMID: 38364879
ISSN: 1532-8406
CID: 5636052

A Digital Platform for the Self-Management of Knee Arthritis: MyArthritisRx.com

Iorio, Richard; Biadasz, Nicholas; Giunta, Nancy; Chen, Antonia F; Einhorn, Thomas A; Karia, Raj
MyArthritisRx.com (MARx) is an online digital platform with resources to effectively manage osteoarthritis and directs patients to the appropriate information and tools to manage their disease. The key to self-management is a self-evaluation and staging program powered by an algorithm based on 150,000 arthritis patients. Outcome data (PROMs), comorbidities, demographics, and personalized characteristics are used to provide a personalized self-evaluation and staging assessment which characterizes disease severity and risk of progression. The initial 6-week program was completed by 100 pilot patients with 92% reporting some improvement. MARx offers evidence of efficacy with promise of cost savings and improved arthritis care.
PMID: 36402505
ISSN: 1558-1373
CID: 5371822

Low-Dose Aspirin is Safe and Effective for Venous Thromboembolism Prevention in Patients Undergoing Revision Total Knee Arthroplasty: A Retrospective Cohort Study

Tang, Alex; Zak, Stephen G; Waren, Daniel; Iorio, Richard; Slover, James D; Bosco, Joseph A; Schwarzkopf, Ran
Venous thromboembolism (VTE) events are rare, but serious complications of total joint replacement affect patients and health care systems due to the morbidity, mortality, and associated cost of its complications. There is currently no established universal standard of care for prophylaxis against VTE in patients undergoing revision total knee arthroplasty (rTKA). The aim of this study was to determine whether a protocol of 81-mg aspirin (ASA) bis in die (BID) is safe and/or sufficient in preventing VTE in patients undergoing rTKAs versus 325-mg ASA BID. In 2017, our institution adopted a new protocol for VTE prophylaxis for arthroplasty patients. Patients initially received 325-mg ASA BID for 1 month and then changed to a lower dose of 81-mg BID. A retrospective review from 2011 to 2019 was conducted identifying 1,438 consecutive rTKA patients and 90-day postoperative outcomes including VTE, gastrointestinal, and wound bleeding complications, acute periprosthetic joint infection, and mortality. In the 74 months prior to protocol implementation, 1,003 rTKAs were performed and nine VTE cases were diagnosed (0.90%). After 26 months of the protocol change, 435 rTKAs were performed with one VTE case identified (0.23%). There was no significant difference in rates or odds in postoperative pulmonary embolism (PE; p = 0.27), DVT (p = 0.35), and total VTE rates (p = 0.16) among patients using either protocol. There were also no differences in bleeding complications (p = 0.15) or infection rate (p = 0.36). No mortalities were observed. In the conclusion, 81-mg ASA BID is noninferior to 325-mg ASA BID in maintaining low rates of VTE and may be safe for use in patients undergoing rTKA.
PMID: 32898907
ISSN: 1938-2480
CID: 4588992

The 2021 Centers for Medicare and Medicaid Services Fee Schedule's Impact on Adult Reconstruction Surgeon Productivity and Reimbursement

Skeehan, Christopher D; Ortiz, Dionisio; Sicat, Chelsea Sue; Iorio, Richard; Slover, James; Bosco, Joseph A
BACKGROUND:On December 20, 2020, the Centers for Medicare and Medicaid Services (CMS) finalized its proposed rule: CMS-1734-P. This 2021 Final Rule significantly changed Medicare total joint arthroplasty (TJA) reimbursement. The precise impact on surgeon productivity and reimbursement is unknown. In the present study, we sought to model the potential impact of these changes for multiple unique practice configurations. METHODS:A mathematical model was applied to CMS data to determine the impact of CMS-1734-F on multiple, theoretical TJA practice configurations. Variables tested were the annual percentage of revision vs primary arthroplasty cases performed and the annual percentage of operative vs office-based productivity. The model defined baseline annual surgeon productivity as the 2018 Medical Group Management Association hip and knee arthroplasty surgeon median productivity of 10,568 work relative value units (wRVUs). RESULTS:All modeled simulations demonstrated a year-to-year increase in wRVUs independent of practice configuration. However, simulations that demonstrated less than a 3.35% increase in wRVUs from year-to-year saw a decrease in reimbursement. Those simulations with higher wRVU increases tended to have a higher percentage of revision vs primary arthroplasty cases and/or had annual productivity that was derived to a greater extent from office encounters than surgical cases. CONCLUSION/CONCLUSIONS:The impact of CMS-1734-F will vary based on 3 factors: (1) the relative contribution of a surgeon's operative TJA practice compared with their office-based practice to their annual wRVUs; (2) the relative percentage of revision TJAs vs the percentage of primary TJAs performed; and (3) the relative percentage of primary TJA compared to non-arthroplasty surgeries as a component of overall operative practice. The decreased reimbursement will be disproportionately felt by arthroplasty surgeons who perform relatively fewer revision TJA procedures and whose office-based productivity makes up a smaller overall percentage of their annual workload.
PMID: 34247872
ISSN: 1532-8406
CID: 4938142

Improving Arthroplasty Efficiency and Quality Through Concentrating Service Volume by Complexity: Surviving the Medicare Policy Changes

Iorio, Richard; Peavy, Patrick R; Keyes, David W; Dempsey, Susan M; McCready, David O; Kang, James D
We have an academic medical center (AMC), an associated community-based hospital (CBH) and several ambulatory care centers which are being prepared to provide same day discharge (SDD) total joint arthroplasty (TJA) and unicompartmental knee arthroplasty (UKA). The near-capacity AMC cared for medically and technically complicated TJA patients. The CBH wanted to increase volume, improve margins, and become a center of excellence with an efficient hospital outpatient department and SDD TJA experience.
PMID: 33931281
ISSN: 1532-8406
CID: 4865732

Aseptic Loosening of Porous Metaphyseal Sleeves and Tantalum Cones in Revision Total Knee Arthroplasty: A Systematic Review

Roach, Ryan P; Clair, Andrew J; Behery, Omar A; Thakkar, Savyasachi C; Iorio, Richard; Deshmukh, Ajit J
Bone loss often complicates revision total knee arthroplasty (TKA). Management of metaphyseal defects varies, with no clearly superior technique. Two commonly utilized options for metaphyseal defect management include porous-coated metaphyseal sleeves and tantalum cones. A systematic review was conducted according to the international Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We combined search terms "Total knee arthroplasty" AND/OR "Sleeve," "Cone" as either keywords or medical subject heading (MeSH) terms in multiple databases according to PRISMA recommendations. All retrieved articles were reviewed and assessed using defined inclusion and exclusion criteria. A total of 27 studies (12 sleeves and 15 cones) of revision TKAs were included. In the 12 studies on sleeve implantation in revision TKAs, 1,617 sleeves were implanted in 1,133 revision TKAs in 1,025 patients. The overall rate of reoperation was 110/1,133 (9.7%) and the total rate of aseptic loosening per sleeve was 13/1,617 (0.8%). In the 15 studies on tantalum cone implantation in revision TKAs, 701 cones were implanted into 620 revision TKAs in 612 patients. The overall rate of reoperation was 116/620 (18.7%), and the overall rate of aseptic loosening per cone was 12/701 (1.7%). Rates of aseptic loosening of the two implants were found to be similar, while the rate of reoperation was nearly double in revision TKAs utilizing tantalum cones. Variability in the selected studies and the likely multifactorial nature of failure do not allow for any definitive conclusions to be made. This review elucidates the necessity for additional literature examining revision TKA implants.
PMID: 32074656
ISSN: 1938-2480
CID: 4312372

Artificial Intelligence to Identify Arthroplasty Implants From Radiographs of the Hip

Karnuta, Jaret M; Haeberle, Heather S; Luu, Bryan C; Roth, Alexander L; Molloy, Robert M; Nystrom, Lukas M; Piuzzi, Nicolas S; Schaffer, Jonathan L; Chen, Antonia F; Iorio, Richard; Krebs, Viktor E; Ramkumar, Prem N
BACKGROUND:The surgical management of complications surrounding patients who have undergone hip arthroplasty necessitates accurate identification of the femoral implant manufacturer and model. Failure to do so risks delays in care, increased morbidity, and further economic burden. Because few arthroplasty experts can confidently classify implants using plain radiographs, automated image processing using deep learning for implant identification may offer an opportunity to improve the value of care rendered. METHODS:We trained, validated, and externally tested a deep-learning system to classify total hip arthroplasty and hip resurfacing arthroplasty femoral implants as one of 18 different manufacturer models from 1972 retrospectively collected anterior-posterior (AP) plain radiographs from 4 sites in one quaternary referral health system. From these radiographs, 1559 were used for training, 207 for validation, and 206 for external testing. Performance was evaluated by calculating the area under the receiver-operating characteristic curve, sensitivity, specificity, and accuracy, as compared with a reference standard of implant model from operative reports with implant serial numbers. RESULTS:The training and validation data sets from 1715 patients and 1766 AP radiographs included 18 different femoral components across four leading implant manufacturers and 10 fellowship-trained arthroplasty surgeons. After 1000 training epochs by the deep-learning system, the system discriminated 18 implant models with an area under the receiver-operating characteristic curve of 0.999, accuracy of 99.6%, sensitivity of 94.3%, and specificity of 99.8% in the external-testing data set of 206 AP radiographs. CONCLUSIONS:A deep-learning system using AP plain radiographs accurately differentiated among 18 hip arthroplasty models from four industry leading manufacturers.
PMID: 33281020
ISSN: 1532-8406
CID: 4898862

Patient Engagement Technologies in Orthopaedics: What They Are, What They Offer, and Impact

Kavolus, Joseph J; Moverman, Michael A; Karas, Vasili; Iorio, Richard
The modern era is an increasingly digital and connected world. Most of the Americans now use a smartphone irrespective of age or income level. As smartphone technologies become ubiquitous, there is tremendous interest and growth in mobile health applications. One segment of these new technologies are the so-called patient engagement platforms. These technologies present a host of features that may improve care. This article provides an introduction to this growing technology sector, offers insight into what they may offer patients and surgeons, and discusses how to evaluate various platforms.
PMID: 33826580
ISSN: 1940-5480
CID: 4839302

Investigation of Foot Sensor Insoles for Measuring Functional Outcome After Total Knee Replacement

Chu, Lauren M; Walker, Peter S; Iorio, Richard; Zuckerman, Joseph D; Slover, James D; Lajam, Claudette M; Schwarzkopf, Ran
BACKGROUND:To measure functional outcome, patient reported outcome measures (PROMs) are most often used but biomechanical tests can provide valuable supplementary data. The objective of this study was to investigate instrumented insoles for measuring ground-to-foot forces during basic activities. METHODS:Three groups were evaluated: normal controls, preoperative, and postoperative total knees. The Knee Society Scoring System (KSS) Short Form was used, and with foot pressure sensor insoles, a timed-up-and-go (TUG) test and a sit-to-stand (STS) test was used. RESULTS:Comparing preoperative to postoperative and control groups, there were significant differences in most parameters. There were no significant differences between controls and postoperative knees. Of the 33 correlation coefficients between three PROM parameters and six biomechanical parameters for the three groups, only five coefficients were greater than 0.5. CONCLUSIONS:The biomechanical data was substantially independent of the PROM data and provided additional functional evaluation. The most useful parameters were the left-right force ratios during sit-to stand (STS) and the timed-up-and-go (TUG) time.
PMID: 34081888
ISSN: 2328-5273
CID: 4891892

Artificial Intelligence to Identify Arthroplasty Implants From Radiographs of the Knee

Karnuta, Jaret M; Luu, Bryan C; Roth, Alexander L; Haeberle, Heather S; Chen, Antonia F; Iorio, Richard; Schaffer, Jonathan L; Mont, Michael A; Patterson, Brendan M; Krebs, Viktor E; Ramkumar, Prem N
BACKGROUND:Revisions and reoperations for patients who have undergone total knee arthroplasty (TKA), unicompartmental knee arthroplasty (UKA), and distal femoral replacement (DFR) necessitates accurate identification of implant manufacturer and model. Failure risks delays in care, increased morbidity, and further financial burden. Deep learning permits automated image processing to mitigate the challenges behind expeditious, cost-effective preoperative planning. Our aim was to investigate whether a deep-learning algorithm could accurately identify the manufacturer and model of arthroplasty implants about the knee from plain radiographs. METHODS:We trained, validated, and externally tested a deep-learning algorithm to classify knee arthroplasty implants from one of 9 different implant models from retrospectively collected anterior-posterior (AP) plain radiographs from four sites in one quaternary referral health system. The performance was evaluated by calculating the area under the receiver-operating characteristic curve (AUC), sensitivity, specificity, and accuracy when compared with a reference standard of implant model from operative reports. RESULTS:The training and validation data sets were comprised of 682 radiographs across 424 patients and included a wide range of TKAs from the four leading implant manufacturers. After 1000 training epochs by the deep-learning algorithm, the model discriminated nine implant models with an AUC of 0.99, accuracy 99%, sensitivity of 95%, and specificity of 99% in the external-testing data set of 74 radiographs. CONCLUSIONS:A deep learning algorithm using plain radiographs differentiated between 9 unique knee arthroplasty implants from four manufacturers with near-perfect accuracy. The iterative capability of the algorithm allows for scalable expansion of implant discriminations and represents an opportunity in delivering cost-effective care for revision arthroplasty.
PMID: 33160805
ISSN: 1532-8406
CID: 4785942