Detroit Interventional Pain Assessment Scale: A Pain Score and Method for Measuring and Evaluating Post-Operative Pain Management-A Prospective Study.

Background and Objectives: Orthopedic surgeons commonly prescribe opioids, surpassing all medical specialties. Our objective was to develop a pain management scale that captures medication use, patient-reported pain scores, and helps orthopedic surgeons evaluate their post-operative prescribing practice. Materials and Methods: An IRB-approved prospective study followed 502 post-operative orthopedic surgery patients over a six-month period. All patients were surveyed in an orthopedic clinic at a Level 1 US Trauma Center, during a routine follow-up. Patient pain satisfaction was assessed using the validated Interventional Pain Assessment (IPA) scale, which uses three categories: 0 (no pain), 1 (tolerable pain), and 2 (intolerable pain). Daily narcotic use was translated to morphine milligram equivalents (MMEs) using the Michigan Automated Prescription System (MAPS) narcotics registry. When patient pain satisfaction and narcotic usage were combined, this scale was called the Detroit Interventional Pain Assessment (DIPA) scale. Results: The five classes based on common prescription and usage of narcotics in this cohort include the following: A (no pain medication), B (over-the-counter medication), C (occasional use of short-acting narcotics 1-30 MMEs), D (consistent/regular use of short-acting narcotics 31-79 MMEs), and E (long-duration or stronger short-acting narcotics 80+ MMEs). Patients were most satisfied with their pain management at six weeks (80.5%) and three months (75.65%), and least satisfied at two weeks (62.5%) and six months (60.9%). Additional information displayed on the DIPA graph revealed there was a significant decrease in the percentage of patients on narcotics at two weeks (65.2%) to six months (32.6%) at p < 0.001. Conclusions: The DIPA pain scale shows the relationship between patient pain perception and opioid prescription/usage, while also tracking prescriber tendencies. Providers were able to visualize their post-operative pain management progression at each designated clinic visit with corresponding alphabetical daily MME categories. In this study, results suggest that surgeons were not effective at managing the pain of patients at two weeks post-operative, which is attributed to an inadequate number of pain pills prescribed upon discharge. Overall, the DIPA graph signaled that better pain management interventions are necessitated in periods with lower efficiency scores.

Predicting Factors for Blood Transfusion in Primary Total Knee Arthroplasty Using a Machine Learning Method.

INTRODUCTION: Acute blood loss anemia requiring allogeneic blood transfusion is still a postoperative complication of total knee arthroplasty (TKA). This study aimed to use machine learning models for the prediction of blood transfusion after primary TKA and to identify contributing factors. METHODS: A total of 2,093 patients who underwent primary TKA at our institution were evaluated using data extracted from the hospital quality improvement database to identify patient demographics and surgical variables that may be associated with blood transfusion. A multilayer perceptron neural network (MPNN) machine learning algorithm was used to predict risk factors for blood transfusion and factors associated with increased length of stay. Statistical analyses including bivariate correlate analysis, Chi-Square test, and Student t-test were performed for demographic analysis and to determine the correlation between blood transfusion and other variables. RESULTS: The results demonstrated important factors associated with transfusion rates, including preoperative hemoglobin level, preoperative creatinine level, length of surgery, simultaneous bilateral surgeries, tranexamic acid usage, American Society of Anesthesiologists Physical Status score, preoperative albumin level, ethanol usage, preoperative anticoagulation medications, age, and TKA type (conventional versus robotic-assisted). Patients who underwent a blood transfusion had a markedly greater length of stay than those who did not. The MPNN machine learning model achieved excellent performance across discrimination (AUC = 0.894). DISCUSSION: The MPNN machine learning model showed its power as a statistical analysis tool to predict the ranking of factors for blood transfusion. Traditional statistics are unable to differentiate importance or predict in the same manner as a machine learning model. CONCLUSION: This study demonstrated that MPNN for the prediction of patient-specific blood transfusion rates after TKA represented a novel application of machine learning with the potential to improve preoperative planning for treatment outcomes.

Computer Vision and Machine Learning-Based Gait Pattern Recognition for Flat Fall Prediction.

BACKGROUND: Gait recognition has been applied in the prediction of the probability of elderly flat ground fall, functional evaluation during rehabilitation, and the training of patients with lower extremity motor dysfunction. Gait distinguishing between seemingly similar kinematic patterns associated with different pathological entities is a challenge for the clinician. How to realize automatic identification and judgment of abnormal gait is a significant challenge in clinical practice. The long-term goal of our study is to develop a gait recognition computer vision system using artificial intelligence (AI) and machine learning (ML) computing. This study aims to find an optimal ML algorithm using computer vision techniques and measure variables from lower limbs to classify gait patterns in healthy people. The purpose of this study is to determine the feasibility of computer vision and machine learning (ML) computing in discriminating different gait patterns associated with flat-ground falls. METHODS: We used the Kinect® Motion system to capture the spatiotemporal gait data from seven healthy subjects in three walking trials, including normal gait, pelvic-obliquity-gait, and knee-hyperextension-gait walking. Four different classification methods including convolutional neural network (CNN), support vector machine (SVM), K-nearest neighbors (KNN), and long short-term memory (LSTM) neural networks were used to automatically classify three gait patterns. Overall, 750 sets of data were collected, and the dataset was divided into 80% for algorithm training and 20% for evaluation. RESULTS: The SVM and KNN had a higher accuracy than CNN and LSTM. The SVM (94.9 ± 3.36%) had the highest accuracy in the classification of gait patterns, followed by KNN (94.0 ± 4.22%). The accuracy of CNN was 87.6 ± 7.50% and that of LSTM 83.6 ± 5.35%. CONCLUSIONS: This study revealed that the proposed AI machine learning (ML) techniques can be used to design gait biometric systems and machine vision for gait pattern recognition. Potentially, this method can be used to remotely evaluate elderly patients and help clinicians make decisions regarding disposition, follow-up, and treatment.

The Impact of COVID-19 on the Orthopaedic Surgery Residency Experience.

INTRODUCTION: The rapid spread of the COVID-19 virus led to dramatic changes in graduate medical education and surgical practice. The purpose of this study was to evaluate the effects of the COVID-19 pandemic on Orthopaedic Surgery residency education in the United States. METHODS: A survey sent to all residents of the 201 ACGME-accredited Orthopaedic Surgery programs in the United States. RESULTS: A total of 309 Orthopaedic surgery residents responded to our survey. A subset of 283 (91.6%) residents surveyed reported decreased Orthopaedic-related clinical duty hours due to the COVID-19 pandemic, and 300/309 (97.1%) reported a decrease in surgical case volume. 298 (96.4%) residents reported that their program had scheduled activities or made changes to supplement their education, most common being virtual and video conferences 296/309 (95.5%), required practice questions 132/309 (42.7%), required reading or pre-recorded lectures 122/309 (39.5%), in-person small group meetings or lectures 24/309 (7.77%), and surgical simulation activities 17/309 (5.50%). Almost half (152/309 (48.9%)) of respondents reported their overall resident education was somewhat or much worse due to the impact of COVID-19. Over a quarter (81 (26.2%)) of residents reported their well-being was negatively impacted by residency-related changes due to COVID-19. CONCLUSIONS: Based on these results, the COVID-19 pandemic has brought about significant changes to the training experience of Orthopaedic surgery residents in the United States. Although the majority of residents in this sample had favorable opinions of the educational changes their programs have instituted in light of the pandemic, clinical duty hours and case volume were reported to have substantially decreased, with a large portion of residents viewing their overall resident education as worsened and reporting negative impacts on their overall well-being.

The Joint Utilization Management Program-Implementation of a Bundle Payment Model and Comparison Between Year 1 and 2 Results.

BACKGROUND: Health care spending is projected to increase throughout the next decade alongside the number of total joint arthroplasties (TJAs) performed. Such growth places significant financial burden on the economic system. To address these concerns, Bundled Payments for Care Improvement (BPCI) is becoming a favorable reimbursement model. The aim of this study is to present the outcomes with BPCI model focused on the post-acute care (PAC) phase and compare the outcomes between years 1 and 2 of implementation. METHODS: The Joint Utilization Management Program (JUMP) was implemented in January 2014. Inclusion criteria were Medicare patients undergoing primary unilateral in-patient TJA procedures, outpatient procedures that resulted in an in-hospital admission, and trauma episodes that required TJA. Scorecards monitoring surgeons' performance and tracking length of stay (LOS) in the PAC setting were established. The data generated from these scorecards guided percentage sum-allocation from the total gain-shared sum among the participating providers. RESULTS: A total of 683 JUMP patients were assessed over two years. PAC utilization decreased between 2014 and 2015. The average LOS was longer in year 1 than year 2 (4.50 vs 3.19 days). In-patient rehabilitation (IPR) decreased from 6.45% to 3.22%, with a decrease in IPR average LOS of 1.47 days. The rate of 30-day readmission was lower for JUMP patients in 2015 than 2014 (8.77% vs 10.56%), with day of readmission being earlier (11.91 days vs 13.71 days) in 2014. CONCLUSION: Under the BPCI program, our experience with the JUMP model demonstrates higher efficiency of care in the PAC setting through reduced LOS, IPR admission rates, and 30-day readmission rate.

Incidence, Causes, and Timing of 30-Day Readmission Following Total Knee Arthroplasty.

BACKGROUND: It is important to study the incidence and causes of readmissions in order to understand why they occur and how to reduce them. This study looks at a national sample of patients following total knee arthroplasty (TKA) to identify incidences, trends, causes, and timing of 30-day readmissions. METHODS: Patients undergoing primary TKA from 2012 to 2016 in the American College of Surgeons National Surgical Quality Improvement Program database were identified (n = 197,192). Patients with fractures (n = 177), nonelective surgery (n = 2234), bilateral TKA (n = 5483), and cases with unknown readmission status (n = 1047) were excluded, leaving a total of 188,251 cases. Linear regression analysis was used to determine trends over time. RESULTS: The incidence of overall 30-day readmission following primary TKA from 2012 to 2016 was 3.19% (6014/188,251), with significant decreases in readmission rates during this time (ß = -0.001, P < .001). The top 5 causes of readmission included superficial surgical site infection (SSI; 9.7%), non-SSI infection (9.5%), cardiovascular complications (CV; 9.3%), gastrointestinal complications (8.8%), and venous thromboembolisms (8.8%). The most common cause of readmission during postoperative week 1 was CV complications (12.2%), week 2 was superficial SSI (11.6%), week 3 was deep SSI (11.4%), and week 4 was deep SSI (12.4%). CONCLUSION: Overall, 30-day readmissions following TKA were found to significantly decline from 2012 to 2016. The most common causes of overall readmission included superficial SSI, non-SSI infection, CV complications, gastrointestinal complications, and venous thromboembolisms. However, the most common causes of readmission changed from week to week postoperatively. This data may help institutions develop policies to prevent unplanned readmissions following TKA.

Clostridium difficile Colitis Following Revision Total Knee Arthroplasty: Incidence and Risk Factors.

BACKGROUND: Clostridium difficile-associated diarrhea (CDAD) is associated with adverse events and financial liability. As institutions continue to adopt CDAD rates as a quality control metric, it is important to identify patients at risk before surgery, including revision total knee arthroplasty (rTKA). This study was conducted to (1) determine the incidence of CDAD within 30 days of rTKA and (2) identify perioperative risk factors for CDAD following rTKA. METHODS: The American College of Surgeons National Surgical Quality Improvement Program was queried to identify 6023 rTKA procedures from 2015-2016. Preoperative and perioperative variables, including patient demographics, lab values, comorbidities, operative time, procedure type, presence of postoperative infections, and rates of CDAD were collected. Chi-square and Fisher's exact tests were used to detect differences between categorical variables, and t-tests were used to compare continuous variables. A stepwise logistic regression model was used to identify the risk factors for CDAD. RESULTS: The rate of CDAD within 30 days of rTKA was found to be 0.4% (24/6024). The CDAD rate following aseptic revision was 0.2% (12/4893), while the incidence of CDAD after septic revision was 1.1% (12/1130). Preoperative functional dependence (odds ratio [OR] = 5.14; P = .002), septic revision (OR = 2.77; P = .026), and cancer (OR = 14.26; P = .016) were statistically significant independent risk factors for CDAD after rTKA. CONCLUSION: The incidence of CDAD after rTKA is approximately 0.4% in the United States. Independent risk factors for CDAD include septic revision, preoperative functional dependence, and cancer. Prevention of CDAD in these higher risk patients must be considered before surgery and antibiotic selection for other infections should be managed judiciously.

Preoperative Functional Status Predicts Increased Morbidity Following Total Knee Arthroplasty.

INTRODUCTION: Dependent functional status (DEP) has been associated with higher postoperative adverse events and mortality compared to patients with independent functional status (IND). However, the association between preoperative functional status and perioperative outcomes after primary TKA has not been well reported. Therefore, the purpose of this study was to evaluate this association. Specifically, we asked: 1) does preoperative functional status impact perioperative outcomes following primary TKA, and 2) is DEP functional status prior to primary TKA an independent risk factor for 30-day complications?

Dependent Functional Status is a Risk Factor for Perioperative and Postoperative Complications After Total Hip Arthroplasty.

BACKGROUND: As the population ages, the need for total hip arthroplasty (THA) will increase. However, this will be associated with an increase in comorbidities and a decrease in the ability to independently perform activities of daily living (ADLs). This study was designed to evaluate the impact preoperative functional status has on short-term outcomes after THA. METHODS: Primary THAs performed from 2012 to 2016 were identified in the National Surgical Quality Improvement Program database. Final analysis included 115,590 cases. Patients who could perform all ADLs were classified as independent functional status (n = 113,436), and patients requiring assistance with ADLs were classified as dependent functional status (n = 2154). Univariate analysis was used to compare perioperative outcomes and 30-day complication rates. Multivariate regression was then applied to determine if preoperative dependent functional status was an independent risk factor for adverse outcomes. RESULTS: Functionally dependent patients were more likely to experience operative times >120 minutes (odds ratio [OR] = 1.39; P < .001), hospital stays >10 days (OR = 2.96; P < .001), and nonhome discharge (OR = 2.53; P < .001). Dependent functional status was also an independent risk factor for mortality (OR = 3.00; P = .001), reoperation (OR = 1.39; P = .015), readmission (OR = 1.75; P < .001), superficial surgical site infection (OR = 1.96; P = .002), wound dehiscence (OR = 2.72; P = .034), pneumonia (OR = 2.16; P = .001), reintubation (OR = 2.31; P = .007), prolonged ventilator use (OR = 3.01; P = .009), renal failure necessitating dialysis (OR = 3.94; P = .002), urinary tract infection (OR = 1.78; P = .001), blood transfusion (OR = 1.75; P < .001), and sepsis (OR = 2.38; P = .001). CONCLUSIONS: Functionally dependent patients undergoing THA are at higher risk of mortality, adverse perioperative outcomes, and complications. These data may aid for patient counseling and risk stratification.