Development of a Machine Learning Model to Predict the Use of Surgery in Patients With Rheumatoid Arthritis.

OBJECTIVE: One in five patients with rheumatoid arthritis (RA) rely on surgery to restore joint function. However, variable response to disease-modifying antirheumatic drugs (DMARDs) complicates surgical planning, and it is difficult to predict which patients may ultimately require surgery. We used machine learning to develop predictive models for the likelihood of undergoing an operation related to RA and which type of operation patients who require surgery undergo. METHODS: We used electronic health record data to train two extreme gradient boosting machine learning models. The first model predicted patients' probabilities of undergoing surgery ≥5 years after their initial clinic visit. The second model predicted whether patients who underwent surgery would undergo a major joint replacement versus a less intensive procedure. Predictors included demographics, comorbidities, and medication data. The primary outcome was model discrimination, measured by area under the receiver operating characteristic curve (AUC). RESULTS: We identified 5,481 patients, of whom 278 (5.1%) underwent surgery. There was no significant difference in the frequency of DMARD or steroid prescriptions between patients who did and did not have surgery, though nonsteroidal anti-inflammatory drug prescriptions were more common among patients who did have surgery (P = 0.03). The model predicting use of surgery had an AUC of 0.90 ± 0.02. The model predicting type of surgery had an AUC of 0.58 ± 0.10. CONCLUSIONS: Predictive models using clinical data have the potential to facilitate identification of patients who may undergo rheumatoid-related surgery, but not what type of procedure they will need. Integrating similar models into practice has the potential to improve surgical planning.

Predicting persistent opioid use after hand surgery: a machine learning approach.

BACKGROUND: The aim of this study was to evaluate the use of machine learning to predict persistent opioid use after hand surgery. METHODS: We trained two algorithms to predict persistent opioid use, first using a general surgery dataset and then using a hand surgery dataset, resulting in four trained models. Next, we tested each model's performance using hand surgery data. Participants included adult surgery patients enrolled in a cohort study at an academic center from 2015-2018. The first algorithm (Michigan Genomics Initiative model) was designed to accommodate patient-reported data and patients with or without prior opioid use. The second algorithm (claims model) was designed for insurance claims data from patients who were opioid-naïve only. The main outcome was model discrimination, measured by area under the receiver operating curve (AUC). RESULTS: Of 889 hand surgery patients, 49% were opioid-naïve and 21% developed persistent opioid use. Most patients underwent soft tissue procedures (55%) or fracture repair (20%). The MGI model had AUCs of 0.84 when trained only on hand surgery data, and 0.85 when trained on the full cohort of surgery patients. The claims model had AUCs of 0.69 when trained only on hand surgery data, and 0.52 when trained on the opioid-naïve cohort of surgery patients. CONCLUSION: Opioid use is common after hand surgery. Machine learning has the potential to facilitate identification of patients who are at risk for prolonged opioid use, which can promote early interventions to prevent addiction.

Are Observational Studies on Distal Radius Fracture Treatment Robust? An E-value Approach to Analysis.

BACKGROUND: Reported complication frequencies after distal radius fracture (DRF) treatment vary widely in the literature and are based mostly on observational evidence. Whether that evidence is sufficiently robust to use in practice is controversial. The E-value is an innovative sensitivity analysis that quantitates the robustness of observational evidence against unmeasured confounders, whereby a greater E-value usually implies more robust evidence and vice versa; with DRF complications, this approach can help guide readers to a more confident interpretation of the available evidence. QUESTIONS/PURPOSES: In this study, we sought (1) to compare the complication frequencies among different DRF treatment modalities, and (2) to evaluate the robustness of these observational studies using the E-value as an index for unmeasured confounding. METHODS: We searched PubMed, Embase, and SCOPUS for observational studies on the management of DRFs that were published from January 2001 to July 2021 with the last database search performed on July 31, 2021. All articles that compared different DRF treatment modalities with reported complication frequencies were included to accurately capture the quality of the observational studies in research about DRF. Risk ratios (RRs) of the overall complication and major complication risks were calculated for each subgroup comparison: volar plating versus dorsal plating, casting, external fixation, and percutaneous K-wire fixation. The RRs and their corresponding lower limits of the 95% confidence intervals (CIs) were used to derive the E-values. E-values can have a minimum possible value of 1, which signifies that the treatment-outcome association is not strong and can readily be overturned by unmeasured confounders. By contrast, a large E-value means that the observed treatment-outcome association is robust against unmeasured confounders. We averaged RRs and E-values for the effect estimates and lower limits of CIs across studies in each treatment comparison group. We identified 36 comparative observational studies that met the inclusion criteria. Seven studies compared volar with dorsal plating techniques. Volar plating was also compared with casting (eight studies), external fixation (15 studies), and percutaneous K-wire fixation (six studies). RESULTS: Total and major complication risks did not differ among different DRF treatments. The mean RRs for total and major complications were 1.2 (95% CI 0.4 to 3.9; p = 0.74) and 1.8 (95% CI 0.4 to 11.4; p = 0.52) for the volar versus dorsal plating group; 1.2 (95% CI 0.3 to 11.2; p = 0.87) and 1.5 (95% CI 0.3 to 14.9; p = 0.74) for the volar plating versus casting group; 0.6 (95% CI 0.2 to 2.2; p = 0.33) and 0.8 (95% CI 0.2 to 6.7; p = 0.86) for the volar plating versus external fixation group; and 0.6 (95% CI 0.2 to 2.6; p = 0.47) and 0.7 (95% CI 0.2 to 4.0; p = 0.67) for the volar plating versus K-wire fixation group. The mean E-values for total and major complication frequencies for the between-group comparison ranged from 3.1 to 5.8; these were relatively large in the context of a known complication risk factor, such as high-energy impact (RR 3.2), suggesting a reasonable level of robustness against unmeasured confounding. However, the E-values for lower limits of CIs remained close to 1, which indicates the observed complication frequencies in these studies were likely to have been influenced by unmeasured confounders. CONCLUSION: Complication frequencies did not differ among different DRF treatment modalities, but the observed complication frequencies from most comparative observational studies were less robust against potential unmeasured confounders. The E-value method, or another type of sensitivity analysis, should be implemented in observational hand surgery research at the individual-study level to facilitate assessment of robustness against potential unmeasured confounders. LEVEL OF EVIDENCE: Level III, therapeutic study.

Utilization, Complications, and Costs of Inpatient versus Outpatient Total Elbow Arthroplasty.

BACKGROUND: Although total hip and knee arthroplasty have largely moved to the outpatient setting, total elbow arthroplasty (TEA) remains a predominantly inpatient procedure. Currently, evidence on the safety and potential cost savings of outpatient TEA is limited. Therefore, we aimed to compare the costs and complications associated with performing TEA in the inpatient versus outpatient setting. METHODS: We identified patients who received elective TEA using the Truven Health MarketScan database. Outcomes of interest were 90-day complication rate, readmission rate, and procedure costs in the inpatient and outpatient settings. We used propensity score matching and logistic regression analysis to assess how patient comorbidities and surgical setting influenced complications and readmission rates. The median cost per patient was compared using the Mann-Whitney U test. RESULTS: We identified 307 outpatient and 414 inpatient TEA procedures over a 9-year period. Elixhauser comorbidity scores were higher for the inpatient cohort. The incidence of surgical complications was significantly higher in the inpatient than the outpatient cohort (27% vs 9%). The odds of 90-day readmissions were similar in the 2 groups (37% vs 25%). In terms of cost, the median inpatient TEA was more expensive than outpatient TEA ($26 817 vs $18 412). However, the median cost for occupational therapy within 90 days of surgery was higher for outpatient TEA patients ($687 vs $571). CONCLUSIONS: The results of this study demonstrate that surgeons can consider a transition toward outpatient TEA for patients without significant comorbidities, as this will substantially reduce health care costs.

Factors Influencing Preferences for Plastic Surgery Conferences: A Conjoint Analysis.

The increase in virtual conferences during the COVID-19 pandemic provided unexpected advantages such as increased accessibility, while also creating concern about the effectiveness of online networking and career development. Given that a variety of conference attributes are impacted by changes in conference format, we sought to investigate how plastic surgeons prioritize key aspects of conference conduct. Methods: We sent a survey based on conjoint analysis, a statistical method for evaluating consumer preferences, to active members of the American Society of Plastic Surgeons. Respondents were asked to choose between pairs of conference options, each with unique attributes. Their answers were used to calculate feature importance values and utility coefficients for the conference attributes. Subgroup analyses were conducted based on demographic factors. Results: A total of 263 respondents completed the survey. Respondents were mostly White (181 individuals [68.8%]) and men (186 [70.7%]). Nearly half (122 [46.4%]) had been practicing 20 or more years. Conference attributes with the highest feature importance values (SDs) were cost of attendance (30.4% [14.2%]) and conference format (28.8% [14.2%]). Equity initiatives (14.5% [10.1%]), reimbursement for cost (11.1% [5.7%]), and opportunities for networking (9.5% [6.0%]) had intermediate feature importance values. Environmental impact had the lowest feature importance (5.7% [3.8%]). Conclusions: Surgeons' conference preferences depend highly on format and the presence of equity initiatives, both of which can be incorporated or modified in future conferences to ensure inclusive and successful events. Meanwhile, environmental impact is less important to surgeons, suggesting a pressing need to bring sustainability issues to their attention.

Application of the E-Value to Assess Bias in Observational Research in Plastic Surgery.

BACKGROUND: The E-value is a statistical measure that is used to quantify the degree of unmeasured confounding that is necessary to undermine the treatment-outcome associations established in observational studies. Despite the substantial amount of observational research that informs evidence-based practice in plastic surgery, sensitivity analyses based on the E-value have not been conducted in the field. METHODS: The authors performed a systematic search of the literature to identify meta-analyses of observational studies in plastic surgery. The authors calculated E-values for various treatment-outcome associations based on the risk, odds, or hazard ratios in each study, to assess unmeasured confounding effects that may influence the validity of the conclusions. The authors then analyzed the distribution of E-values from pooled versus individual studies. RESULTS: The authors identified 45 meta-analyses that met the inclusion criteria, with each containing an average of three pooled assessments of observational data. The E-value of the pooled effect estimates ranged from 1.11 to 19.49, with an average value of 3.82. As for the individual effect estimates from each primary study within the meta-analyses, the E-values ranged from 1.00 to 321.50, with an average value of 8.74. CONCLUSIONS: The authors determined that E-values vary substantially across the literature and that unmeasured confounding may be present in a high number of observational studies. Although extant statistical techniques will continue to be necessary to control for measured confounding, the E-value is a novel concept that can facilitate more robust sensitivity analyses in plastic surgery research.

Task-Specific Patient Preferences for Shared Decision-Making in Hand Surgery.

BACKGROUND: Shared decision-making for surgery can increase patient engagement, satisfaction, and clinical outcomes. However, the level of involvement that patients desire at each step of the decision-making process is unknown. METHODS: The authors surveyed patients at an academic hand surgery clinic to examine the preferred role in decision-making using validated questionnaires (i.e., Control Preference Scale, Problem-Solving Decision-Making Scale, and General Self-Efficacy Scale). The Control Preference Scale assesses general treatment preferences, whereas the Problem-Solving Decision-Making Scale distinguishes between problem-solving tasks (e.g., making diagnoses, calculating risks/benefits) and decision-making tasks. Patients' self-beliefs and perceived ability to handle difficult situations were assessed with the General Self-Efficacy Scale. The authors used linear regression models and ordinal logistic regression to examine the relationship between self-efficacy and patients' preferred role in treatment decision-making. RESULTS: Patients overall preferred an equal share of decision-making responsibility with the surgeon (mean Control Preference Scale score, 3.3 ± 0.7). Specifically, for problem-solving tasks, however, 81 percent of patients wanted to "hand over" the responsibility and 19 percent preferred shared decision-making. In contrast, for decision-making tasks, 54 percent of patients preferred shared decision-making. Each point increase in General Self-Efficacy Scale score correlated with 12 percent greater odds of preferring to retain the responsibility (OR, 1.12; 95 percent CI, 1.05 to 1.21; p = 0.001). However, self-efficacy did not show a significant effect for problem-solving tasks. CONCLUSIONS: The authors found that patients prefer surgeons to provide expert knowledge for problem-solving tasks but desire equal share of responsibility in decision-making tasks. The authors' findings support the current shift away from the paternalistic model of surgical decision-making, and provide an effective strategy to tailor shared decision-making to align care delivery with patient preferences.

Evaluation of Factors Relevant to Pain Control Among Patients After Surgical Treatment.

Importance: Opioids are often prescribed after elective surgical treatment despite the potential for misuse. Although various pain control regimens exist, patient preferences for acute postoperative pain management are unknown. Objective: To describe patient-reported key attributes of postoperative pain management. Design, Setting, and Participants: This decision analytical model used responses from a survey based on conjoint analysis to investigate the value patients placed on different aspects of postoperative pain management. Participants were patients aged 18 years or older who underwent elective hand surgical procedures between July 1, 2018, and July 23, 2019, at a single academic center. The survey was completed on a web-based platform and took place between November 2019 and January 2020. Data were analyzed from May through July 2021. Exposures: Participants were presented with a series of discrete-choice tasks and asked to select between 2 postoperative medication options that changed from question to question and had varying characteristics. Main Outcomes and Measures: Attribute importance scores and part-worth utility values for the queried aspects of pain control were calculated. Results: Of 710 individuals invited, 321 (45.2%) completed the survey; there were 212 (66.0%) women and 108 (33.6%) men, and the most common age category was 60 to 69 years (102 participants [31.8%]). Most patients reported previous opioid use (282 individuals [87.9%]). Factors in the decision-making process with the highest attribute importance scores (SDs) were risk of addiction (26.3% [13.0%]) and amount of pain relief (25.6% [14.6%]). Adverse effects 13.9% (7.2%), functional independence 11.8% (7.3%), and level of trust in the prescriber 11.4% (5.8%) had intermediate attribute importance scores (SDs). Cost 7.9% (4.4%) and stigma 3.1% (1.3%) had the lowest attribute importance scores (SDs) in patient decisions. Conclusions and Relevance: These findings suggest that multimodal pain control regimens that are associated with optimized pain relief and minimized risk of addiction are preferable to treat acute postoperative pain. The results suggest that identifying procedures for which patients prioritize minimizing risk of addiction over pain relief and incorporating patient preferences into decision-making may be associated with decreased postoperative opioid prescribing.

Variability in the Use of Disposable Surgical Supplies: A Surgeon Survey and Life Cycle Analysis.

PURPOSE: A substantial amount of waste is generated during surgery, yet few studies have investigated this problem. Therefore, we conducted a multicenter survey to investigate how the variation in the use of disposable supplies contributes to the environmental and financial burdens of health care. METHODS: We created a questionnaire to identify differences in supply use and practice characteristics among hand surgeons who participated in the Wrist and Radius Injury Surgical Trial. We determined the average cumulative cost of 10 key surgical items based on the responses. Subsequently, we estimated the kilograms of carbon dioxide emitted during the life cycle of supplies, from raw material extraction to production and disposal, using economic input-output life cycle analysis. RESULTS: Thirty-five surgeons from 19 institutions responded to the survey (65% response rate). Based on the difference in costs between surgeons who used the fewest and the most supplies, we determined that expenditures and carbon dioxide emissions could decrease by $22.47 and 10.9 kg per procedure, respectively, with leaner use of 10 key items. Furthermore, assuming that surgeon variation in supply use is present in other surgical subspecialties, we estimated that $2.4 billion in savings and an 800.6 thousand metric ton reduction in carbon emissions could be achieved if all US surgeons reduced their supply use by this amount. CONCLUSIONS: This study revealed considerable variations in the use of disposable supplies among hand surgeons, highlighting the need for evidence-based tools, policies, and education campaigns to reduce hospital waste across health care systems. CLINICAL RELEVANCE: Optimal use of disposable supplies is necessary to reduce the cost and environmental burden of hand surgery care.

A Systematic Review of Health Disparities Research in Plastic Surgery.

BACKGROUND: In this systematic review, the authors report on the current state of health disparities research in plastic surgery and consider how equity-oriented interventions are taking shape at the patient, provider, and health care system levels. METHODS: The authors performed a systematic literature search of the PubMed/MEDLINE and Embase databases using search terms related to the social determinants of both health and plastic surgery. Two independent reviewers screened the article titles and abstracts for relevance and identified the plastic surgery focus and study characteristics of the included literature. The articles were then categorized as detecting, understanding, or reducing health disparities according to a conceptual framework. This review was conducted in line with the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. RESULTS: One hundred forty-seven articles published between 1997 and 2019 met the inclusion criteria. Health disparities research in gender-affirming, craniofacial, cosmetic, and hand surgery was lacking relative to breast reconstruction. Racial/ethnic and socioeconomic disparities were reported across subspecialties. Place of residence was also a large determinant of access to care and quality of surgical outcomes. Half of the included studies were in the detecting phase of research. Meanwhile, 40 and 10 percent were in the understanding and reducing phases, respectively. CONCLUSIONS: Investigators suggested several avenues for reducing health disparities in plastic surgery, yet there is limited evidence on the actual effectiveness of equity-oriented initiatives. More comprehensive research is needed to disentangle the patient, provider, and system-level factors that underlie inequity across subspecialties.

The Plastic Surgeon's Role in Health Equity Research and Policy.

Although a growing body of research explores the interplay of social, economic, and environmental conditions that underlie health disparities, there is no clear path forward to combat health inequity. Plastic surgeons continue to witness how changes in healthcare delivery processes, insurance coverage, and payment structures interfere with patients' access to specialty services. However, their perspectives are rarely incorporated into meaningful strategies that ensure equitable care for the diverse patient population. The goal of this article was to convey how plastic surgeons can play a more active role in the development of policies and initiatives to reduce health disparities. A greater focus on modifiable legislative, healthcare system, and provider factors is needed to catalyze progress.

Navigating the Intersection of Evidence and Policy in Hand Surgery Practice.

Collaboration with organizations beyond the clinical setting is necessary to identify safety hazards that contribute to the high incidence and severity of hand conditions. Hand surgeons are acutely aware of obstacles patients face while navigating the health care system. Advocacy efforts encourage the development of equitable insurance policies and improve health resource allocation so that hand surgeons can treat a larger patient population. Participation in quality initiatives supports the development of evidence-based clinical guidelines. Further evidence must be generated to ensure that surgeons remain proficient in the latest techniques and uphold high standards of care as hand surgery procedures evolve.