The Skeletal Oncology Research Group Machine Learning Algorithm (SORG-MLA) for predicting prolonged postoperative opioid prescription after total knee arthroplasty: an international validation study using 3,495 patients from a Taiwanese cohort.

BACKGROUND: Preoperative prediction of prolonged postoperative opioid use (PPOU) after total knee arthroplasty (TKA) could identify high-risk patients for increased surveillance. The Skeletal Oncology Research Group machine learning algorithm (SORG-MLA) has been tested internally while lacking external support to assess its generalizability. The aims of this study were to externally validate this algorithm in an Asian cohort and to identify other potential independent factors for PPOU. METHODS: In a tertiary center in Taiwan, 3,495 patients receiving TKA from 2010-2018 were included. Baseline characteristics were compared between the external validation cohort and the original developmental cohorts. Discrimination (area under receiver operating characteristic curve [AUROC] and precision-recall curve [AUPRC]), calibration, overall performance (Brier score), and decision curve analysis (DCA) were applied to assess the model performance. A multivariable logistic regression was used to evaluate other potential prognostic factors. RESULTS: There were notable differences in baseline characteristics between the validation and the development cohort. Despite these variations, the SORG-MLA ( https://sorg-apps.shinyapps.io/tjaopioid/ ) remained its good discriminatory ability (AUROC, 0.75; AUPRC, 0.34) and good overall performance (Brier score, 0.029; null model Brier score, 0.032). The algorithm could bring clinical benefit in DCA while somewhat overestimating the probability of prolonged opioid use. Preoperative acetaminophen use was an independent factor to predict PPOU (odds ratio, 2.05). CONCLUSIONS: The SORG-MLA retained its discriminatory ability and good overall performance despite the different pharmaceutical regulations. The algorithm could be used to identify high-risk patients and tailor personalized prevention policy.

External validation of machine learning algorithm predicting prolonged opioid prescriptions in opioid-naïve lumbar spine surgery patients using a Taiwanese cohort.

BACKGROUND/PURPOSE: Identifying patients at risk of prolonged opioid use after surgery prompts appropriate prescription and personalized treatment plans. The Skeletal Oncology Research Group machine learning algorithm (SORG-MLA) was developed to predict the risk of prolonged opioid use in opioid-naive patients after lumbar spine surgery. However, its utility in a distinct country remains unknown. METHODS: A Taiwanese cohort containing 2795 patients who were 20 years or older undergoing primary surgery for lumbar decompression from 2010 to 2018 were used to validate the SORG-MLA. Discrimination (area under receiver operating characteristic curve [AUROC] and area under precision-recall curve [AUPRC]), calibration, overall performance (Brier score), and decision curve analysis were applied. RESULTS: Among 2795 patients, the prolonged opioid prescription rate was 5.2%. The validation cohort were older, more inpatient disposition, and more common pharmaceutical history of NSAIDs. Despite the differences, the SORG-MLA provided a good discriminative ability (AUROC of 0.71 and AURPC of 0.36), a good overall performance (Brier score of 0.044 compared to that of 0.039 in the developmental cohort). However, the probability of prolonged opioid prescription tended to be overestimated (calibration intercept of -0.07 and calibration slope of 1.45). Decision curve analysis suggested greater clinical net benefit in a wide range of clinical scenarios. CONCLUSION: The SORG-MLA retained good discriminative abilities and overall performances in a geologically and medicolegally different region. It was suitable for predicting patients in risk of prolonged postoperative opioid use in Taiwan.

Social determinants of health in prognostic machine learning models for orthopaedic outcomes: A systematic review.

RATIONAL: Social determinants of health (SDOH) are being considered more frequently when providing orthopaedic care due to their impact on treatment outcomes. Simultaneously, prognostic machine learning (ML) models that facilitate clinical decision making have become popular tools in the field of orthopaedic surgery. When ML-driven tools are developed, it is important that the perpetuation of potential disparities is minimized. One approach is to consider SDOH during model development. To date, it remains unclear whether and how existing prognostic ML models for orthopaedic outcomes consider SDOH variables. OBJECTIVE: To investigate whether prognostic ML models for orthopaedic surgery outcomes account for SDOH, and to what extent SDOH variables are included in the final models. METHODS: A systematic search was conducted in PubMed, Embase and Cochrane for studies published up to 17 November 2020. Two reviewers independently extracted SDOH features using the PROGRESS+ framework (place of residence, race/ethnicity, Occupation, gender/sex, religion, education, social capital, socioeconomic status, 'Plus+' age, disability, and sexual orientation). RESULTS: The search yielded 7138 studies, of which 59 met the inclusion criteria. Across all studies, 96% (57/59) considered at least one PROGRESS+ factor during development. The most common factors were age (95%; 56/59) and gender/sex (96%; 57/59). Differential effect analyses, such as subgroup analysis, covariate adjustment, and baseline comparison, were rarely reported (10%; 6/59). The majority of models included age (92%; 54/59) and gender/sex (69%; 41/59) as final input variables. However, factors such as insurance status (7%; 4/59), marital status (7%; 4/59) and income (3%; 2/59) were seldom included. CONCLUSION: The current level of reporting and consideration of SDOH during the development of prognostic ML models for orthopaedic outcomes is limited. Healthcare providers should be critical of the models they consider using and knowledgeable regarding the quality of model development, such as adherence to recognized methodological standards. Future efforts should aim to avoid bias and disparities when developing ML-driven applications for orthopaedics.

Preoperative embolization in surgical treatment of spinal metastases originating from non-hypervascular primary tumors: a propensity score matched study using 495 patients.

BACKGROUND CONTEXT: Preoperative embolization (PE) reduces intraoperative blood loss during surgery for spinal metastases of hypervascular primary tumors such as thyroid and renal cell tumors. However, most spinal metastases originate from primary breast, prostate, and lung tumors and it remains unclear whether these and other spinal metastases benefit from PE. PURPOSE: To assess the (1) efficacy of PE on the amount of intraoperative blood loss and safety in patients with spinal metastases originating from non-hypervascular primary tumors, and (2) secondary outcomes including perioperative allogeneic blood transfusion, anesthesia time, hospitalization, postoperative complication within 30 days, reoperation, 90-day mortality, and 1-year mortality. STUDY DESIGN: Retrospective propensity-score matched, case-control study at 2 academic tertiary medical centers. PATIENT SAMPLE: Patients 18 years of age or older undergoing surgery for spinal metastases originating from primary non-thyroid, non-renal cell, and non-hepatocellular tumors between January 1, 2002 and December 31, 2016 were included. OUTCOME MEASURES: The primary outcomes were estimated amount of intraoperative blood loss and complications attributable to PE, such as neurologic injury, wound infection, thrombosis, or dissection. The secondary outcomes included perioperative allogeneic blood transfusion, anesthesia time, hospitalization, postoperative complication within 30 days, reoperation, 90-day mortality, and 1-year mortality. METHODS: In total, 495 patients were identified, of which 54 (11%) underwent PE. After propensity score matching on 21 variables, including primary tumor, number of spinal levels, and surgical treatment, 53 non-PE patients were matched to 53 PE patients. Matching was adequate measured by comparing the matched variables, testing the standardized mean differences (<0.25), and inspecting Kernel density plots. The degree of embolization was noted to be complete, until stasis, or successful in 43 (80%) patients. RESULTS: Intraoperative blood loss did not differ between both groups with a median blood loss in liters of 0.6 (IQR, 0.4-1.2) for non-PE patients and 0.9 (IQR, 0.6-1.2) for PE patients (p=.32). No complications occurred during embolization or the time between embolization and surgery. No differences were found in terms of the secondary outcomes. CONCLUSIONS: Our data suggest that, although no complications occurred and the embolization procedure can be considered safe, patients with non-hypervascular spinal metastases might not benefit from PE. A larger, prospective study could confirm or refute these study findings and aid in elucidating a subset of spinal metastases that might benefit from PE.

Practice Variation Within a Single Institution in Management of Degenerative Spondylolisthesis.

STUDY DESIGN: This was a retrospective cohort study. OBJECTIVE: The objective of this study was to assess variation in care for degenerative spondylolisthesis (DS) among surgeons at the same institution, to establish diagnostic and therapeutic variables contributing to this variation, and to determine whether variation in care changed over time. SUMMARY OF BACKGROUND DATA: Like other degenerative spinal disorders, DS is prone to practice variation due to the wide array of treatment options. Focusing on a single institution can identify more individualized drivers of practice variation by omitting geographic variability of demographics and socioeconomic factors. MATERIALS AND METHODS: We collected number of office visits, imaging procedures, injections, electromyography (EMG), and surgical procedures within 1 year after diagnosis. Multivariable logistic regression was used to determine predictors of surgery. The coefficient of variation (CV) was calculated to compare the variation in practice over time. RESULTS: Patients had a mean 2.5 (±0.6) visits, 1.8 (±0.7) imaging procedures, and 0.16 (±0.09) injections in the first year after diagnosis. Thirty-six percent (1937/5091) of patients had physical therapy in the 3 months after diagnosis. CV was highest for EMG (95%) and lowest for office visits (22%). An additional spinal diagnosis [odds ratio (OR)=3.99, P <0.001], visiting a neurosurgery clinic (OR=1.81, P =0.016), and diagnosis post-2007 (OR=1.21, P =0.010) were independently associated with increased surgery rates. The CVs for all variables decreased after 2007, with the largest decrease seen for EMG (132% vs. 56%). CONCLUSIONS: While there is variation in the management of patients diagnosed with DS between surgeons of a single institution, this variation seems to have gone down in recent years. All practice variables showed diminished variation. The largest variation and subsequent decrease of variation was seen in the use of EMG. Despite the smaller amount of variation, the rate of surgery has gone up since 2007.

A machine learning algorithm for predicting prolonged postoperative opioid prescription after lumbar disc herniation surgery. An external validation study using 1,316 patients from a Taiwanese cohort.

BACKGROUND CONTEXT: Preoperative prediction of prolonged postoperative opioid prescription helps identify patients for increased surveillance after surgery. The SORG machine learning model has been developed and successfully tested using 5,413 patients from the United States (US) to predict the risk of prolonged opioid prescription after surgery for lumbar disc herniation. However, external validation is an often-overlooked element in the process of incorporating prediction models in current clinical practice. This cannot be stressed enough in prediction models where medicolegal and cultural differences may play a major role. PURPOSE: The authors aimed to investigate the generalizability of the US citizens prediction model SORG to a Taiwanese patient cohort. STUDY DESIGN: Retrospective study at a large academic medical center in Taiwan. PATIENT SAMPLE: Of 1,316 patients who were 20 years or older undergoing initial operative management for lumbar disc herniation between 2010 and 2018. OUTCOME MEASURES: The primary outcome of interest was prolonged opioid prescription defined as continuing opioid prescription to at least 90 to 180 days after the first surgery for lumbar disc herniation at our institution. METHODS: Baseline characteristics were compared between the external validation cohort and the original developmental cohorts. Discrimination (area under the receiver operating characteristic curve and the area under the precision-recall curve), calibration, overall performance (Brier score), and decision curve analysis were used to assess the performance of the SORG ML algorithm in the validation cohort. This study had no funding source or conflict of interests. RESULTS: Overall, 1,316 patients were identified with sustained postoperative opioid prescription in 41 (3.1%) patients. The validation cohort differed from the development cohort on several variables including 93% of Taiwanese patients receiving NSAIDS preoperatively compared with 22% of US citizens patients, while 30% of Taiwanese patients received opioids versus 25% in the US. Despite these differences, the SORG prediction model retained good discrimination (area under the receiver operating characteristic curve of 0.76 and the area under the precision-recall curve of 0.33) and good overall performance (Brier score of 0.028 compared with null model Brier score of 0.030) while somewhat overestimating the chance of prolonged opioid use (calibration slope of 1.07 and calibration intercept of -0.87). Decision-curve analysis showed the SORG model was suitable for clinical use. CONCLUSIONS: Despite differences at baseline and a very strict opioid policy, the SORG algorithm for prolonged opioid use after surgery for lumbar disc herniation has good discriminative abilities and good overall performance in a Han Chinese patient group in Taiwan. This freely available digital application can be used to identify high-risk patients and tailor prevention policies for these patients that may mitigate the long-term adverse consequence of opioid dependence: https://sorg-apps.shinyapps.io/lumbardiscopioid/.

Machine learning prediction models in orthopedic surgery: A systematic review in transparent reporting.

Machine learning (ML) studies are becoming increasingly popular in orthopedics but lack a critically appraisal of their adherence to peer-reviewed guidelines. The objective of this review was to (1) evaluate quality and transparent reporting of ML prediction models in orthopedic surgery based on the transparent reporting of multivariable prediction models for individual prognosis or diagnosis (TRIPOD), and (2) assess risk of bias with the Prediction model Risk Of Bias ASsessment Tool. A systematic review was performed to identify all ML prediction studies published in orthopedic surgery through June 18th, 2020. After screening 7138 studies, 59 studies met the study criteria and were included. Two reviewers independently extracted data and discrepancies were resolved by discussion with at least two additional reviewers present. Across all studies, the overall median completeness for the TRIPOD checklist was 53% (interquartile range 47%-60%). The overall risk of bias was low in 44% (n = 26), high in 41% (n = 24), and unclear in 15% (n = 9). High overall risk of bias was driven by incomplete reporting of performance measures, inadequate handling of missing data, and use of small datasets with inadequate outcome numbers. Although the number of ML studies in orthopedic surgery is increasing rapidly, over 40% of the existing models are at high risk of bias. Furthermore, over half incompletely reported their methods and/or performance measures. Until these issues are adequately addressed to give patients and providers trust in ML models, a considerable gap remains between the development of ML prediction models and their implementation in orthopedic practice.

Albumin and Survival in Extremity Metastatic Bone Disease: An Analysis of Two Independent Datasets.

INTRODUCTION: Numerous prognostication models have been developed to estimate survival in patients with extremity metastatic bone disease, but few include albumin despite albumin's role in malnutrition and inflammation. The purpose of this study was to examine two independent datasets to determine the value for albumin in prognosticating survival in this population. MATERIALS AND METHODS: Extremity metastatic bone disease patients undergoing surgical management were identified from two independent populations. Population 1: Retrospective chart review at two tertiary care centers. Population 2: A large, national, North American multicenter surgical registry with 30-day follow-up. Bivariate and multivariate analyses were used to examine albumin's value for prognostication at 1-, 3-, and 12-month after surgery. RESULTS: In Population 1, 1,090 patients were identified with 1-, 3-, and 12-month mortality rates of 95 (8.8%), 305 (28.9%), and 639 (62.0%), respectively. In Population 2, 1,675 patients were identified with one-month postoperative mortality rates of 148 (8.8%). In both populations, hypoalbuminemia was an independent prognostic factor for mortality at 30 days. In the institutional set, hypoalbuminemia was additionally associated with 3- and 12-month mortality. CONCLUSIONS: Hypoalbuminemia is a marker for mortality in extremity metastatic bone disease. Further consideration of this marker could improve existing prognostication models in this population. LEVEL OF EVIDENCE: III.

Wide range of applications for machine-learning prediction models in orthopedic surgical outcome: a systematic review.

Background and purpose - Advancements in software and hardware have enabled the rise of clinical prediction models based on machine learning (ML) in orthopedic surgery. Given their growing popularity and their likely implementation in clinical practice we evaluated which outcomes these new models have focused on and what methodologies are being employed.Material and methods - We performed a systematic search in PubMed, Embase, and Cochrane Library for studies published up to June 18, 2020. Studies reporting on non-ML prediction models or non-orthopedic outcomes were excluded. After screening 7,138 studies, 59 studies reporting on 77 prediction models were included. We extracted data regarding outcome, study design, and reported performance metrics.Results - Of the 77 identified ML prediction models the most commonly reported outcome domain was medical management (17/77). Spinal surgery was the most commonly involved orthopedic subspecialty (28/77). The most frequently employed algorithm was neural networks (42/77). Median size of datasets was 5,507 (IQR 635-26,364). The median area under the curve (AUC) was 0.80 (IQR 0.73-0.86). Calibration was reported for 26 of the models and 14 provided decision-curve analysis.Interpretation - ML prediction models have been developed for a wide variety of topics in orthopedics. Topics regarding medical management were the most commonly studied. Heterogeneity between studies is based on study size, algorithm, and time-point of outcome. Calibration and decision-curve analysis were generally poorly reported.

Availability and reporting quality of external validations of machine-learning prediction models with orthopedic surgical outcomes: a systematic review.

Background and purpose - External validation of machine learning (ML) prediction models is an essential step before clinical application. We assessed the proportion, performance, and transparent reporting of externally validated ML prediction models in orthopedic surgery, using the Transparent Reporting for Individual Prognosis or Diagnosis (TRIPOD) guidelines.Material and methods - We performed a systematic search using synonyms for every orthopedic specialty, ML, and external validation. The proportion was determined by using 59 ML prediction models with only internal validation in orthopedic surgical outcome published up until June 18, 2020, previously identified by our group. Model performance was evaluated using discrimination, calibration, and decision-curve analysis. The TRIPOD guidelines assessed transparent reporting.Results - We included 18 studies externally validating 10 different ML prediction models of the 59 available ML models after screening 4,682 studies. All external validations identified in this review retained good discrimination. Other key performance measures were provided in only 3 studies, rendering overall performance evaluation difficult. The overall median TRIPOD completeness was 61% (IQR 43-89), with 6 items being reported in less than 4/18 of the studies.Interpretation - Most current predictive ML models are not externally validated. The 18 available external validation studies were characterized by incomplete reporting of performance measures, limiting a transparent examination of model performance. Further prospective studies are needed to validate or refute the myriad of predictive ML models in orthopedics while adhering to existing guidelines. This ensures clinicians can take full advantage of validated and clinically implementable ML decision tools.

Do Cohabitants Reliably Complete Questionnaires for Patients in a Terminal Cancer Stage when Assessing Quality of Life, Pain, Depression, and Anxiety?

BACKGROUND: Patients with bone metastases often are unable to complete quality of life (QoL) questionnaires, and cohabitants (such as spouses, domestic partners, offspring older than 18 years, or other people who live with the patient) could be a reliable alternative. However, the extent of reliability in this complicated patient population remains undefined, and the influence of the cohabitant's condition on their assessment of the patient's QoL is unknown. QUESTIONS/PURPOSES: (1) Do QoL scores, measured by the 5-level EuroQol-5D (EQ-5D-5L) version and the Patient-reported Outcomes Measurement Information System (PROMIS) version 1.0 in three domains (anxiety, pain interference, and depression), reported by patients differ markedly from scores as assessed by their cohabitants? (2) Do cohabitants' PROMIS-Depression scores correlate with differences in measured QoL results? METHODS: This cross-sectional study included patients and cohabitants older than 18 years of age. Patients included those with presence of histologically confirmed bone metastases (including lymphoma and multiple myeloma), and cohabitants must have been present at the clinic visit. Patients were eligible for inclusion in the study regardless of comorbidities, prognosis, prior surgery, or current treatment. Between June 1, 2016 and March 1, 2017 and between October 1, 2017 and February 26, 2018, all 96 eligible patients were approached, of whom 49% (47) met the selection criteria and were willing to participate. The included 47 patient-cohabitant pairs independently completed the EQ-5D-5L and the eight-item PROMIS for three domains (anxiety, pain, and depression) with respect to the patients' symptoms. The cohabitants also completed the four-item PROMIS-Depression survey with respect to their own symptoms. RESULTS: There were no clinically important differences between the scores of patients and their cohabitants for all questionnaires, and the agreement between patient and cohabitant scores was moderate to strong (Spearman correlation coefficients ranging from 0.52 to 0.72 on the four questionnaires; all p values < 0.05). However, despite the good agreement in QoL scores, an increased cohabitant's depression score was correlated with an overestimation of the patient's symptom burden for the anxiety and depression domains (weak Spearman correlation coefficient of 0.33 [95% confidence interval 0.08 to 0.58]; p = 0.01 and moderate Spearman correlation coefficient of 0.52 [95% CI 0.29 to 0.74]; p < 0.01, respectively). CONCLUSION: The present findings support that cohabitants might be reliable raters of the QoL of patients with bone metastases. However, if a patient's cohabitant has depression, the cohabitant may overestimate a patient's symptoms in emotional domains such as anxiety and depression, warranting further research that includes cohabitants with and without depression to elucidate the effect of depression on the level of agreement. For now, clinicians may want to reconsider using the cohabitant's judgement if depression is suspected. CLINICAL RELEVANCE: These findings suggest that a cohabitant's impressions of a patient's quality of life are, in most instances, accurate; this is potentially helpful in situations where the patient cannot weigh in. Future studies should employ longitudinal designs to see how or whether our findings change over time and with disease progression, and how specific interventions-like different chemotherapeutic regimens or surgery-may factor in.

The use of autologous free vascularized fibula grafts in reconstruction of the mobile spine following tumor resection: surgical technique and outcomes.

OBJECTIVE: Reconstruction of the mobile spine following total en bloc spondylectomy (TES) of one or multiple vertebral bodies in patients with malignant spinal tumors is a challenging procedure with high failure rates. A common reason for reconstructive failure is nonunion, which becomes more problematic when using local radiation therapy. Radiotherapy is an integral part of the management of primary malignant osseous tumors in the spine. Vascularized grafts may help prevent nonunion in the radiotherapy setting. The authors have utilized free vascularized fibular grafts (FVFGs) for reconstruction of the spine following TES. The purpose of this article is to describe the surgical technique for vascularized reconstruction of defects after TES. Additionally, the outcomes of consecutive cases treated with this technique are reported. METHODS: Thirty-nine patients were treated at the authors' tertiary care institution for malignant tumors in the mobile spine using FVFG following TES between 2010 and 2018. Postoperative union, reoperations, complications, neurological outcome, and survival were reported. The median follow-up duration was 50 months (range 14-109 months). RESULTS: The cohort consisted of 26 males (67%), and the median age was 58 years. Chordoma was the most prevalent tumor (67%), and the lumbar spine was most affected (46%). Complete union was seen in 26 patients (76%), the overall complication rate was 54%, and implant failure was the most common complication, with 13 patients (33%) affected. In 18 patients (46%), one or more reoperations were needed, and the fixation was surgically revised 15 times (42% of reoperations) in 10 patients (26%). A reconstruction below the L1 vertebra had a higher proportion of implant failure (67%; 8 of 12 patients) compared with higher resections (21%; 5 of 24 patients) (p = 0.011). Graft length, number of resected vertebrae, and docking the FVFG on the endplate or cancellous bone was not associated with union or implant failure on univariate analysis. CONCLUSIONS: The FVFG is an effective reconstruction technique, particularly in the cervicothoracic spine. However, high implant failure rates in the lumbar spine have been seen, which occurred even in cases in which the graft completely healed. Methods to increase the weight-bearing capacity of the graft in the lumbar spine should be considered in these reconstructions. Overall, the rates of failure and revision surgery for FVFG compare with previous reports on reconstruction after TES.

Does Artificial Intelligence Outperform Natural Intelligence in Interpreting Musculoskeletal Radiological Studies? A Systematic Review.

BACKGROUND: Machine learning (ML) is a subdomain of artificial intelligence that enables computers to abstract patterns from data without explicit programming. A myriad of impactful ML applications already exists in orthopaedics ranging from predicting infections after surgery to diagnostic imaging. However, no systematic reviews that we know of have compared, in particular, the performance of ML models with that of clinicians in musculoskeletal imaging to provide an up-to-date summary regarding the extent of applying ML to imaging diagnoses. By doing so, this review delves into where current ML developments stand in aiding orthopaedists in assessing musculoskeletal images. QUESTIONS/PURPOSES: This systematic review aimed (1) to compare performance of ML models versus clinicians in detecting, differentiating, or classifying orthopaedic abnormalities on imaging by (A) accuracy, sensitivity, and specificity, (B) input features (for example, plain radiographs, MRI scans, ultrasound), (C) clinician specialties, and (2) to compare the performance of clinician-aided versus unaided ML models. METHODS: A systematic review was performed in PubMed, Embase, and the Cochrane Library for studies published up to October 1, 2019, using synonyms for machine learning and all potential orthopaedic specialties. We included all studies that compared ML models head-to-head against clinicians in the binary detection of abnormalities in musculoskeletal images. After screening 6531 studies, we ultimately included 12 studies. We conducted quality assessment using the Methodological Index for Non-randomized Studies (MINORS) checklist. All 12 studies were of comparable quality, and they all clearly included six of the eight critical appraisal items (study aim, input feature, ground truth, ML versus human comparison, performance metric, and ML model description). This justified summarizing the findings in a quantitative form by calculating the median absolute improvement of the ML models compared with clinicians for the following metrics of performance: accuracy, sensitivity, and specificity. RESULTS: ML models provided, in aggregate, only very slight improvements in diagnostic accuracy and sensitivity compared with clinicians working alone and were on par in specificity (3% (interquartile range [IQR] -2.0% to 7.5%), 0.06% (IQR -0.03 to 0.14), and 0.00 (IQR -0.048 to 0.048), respectively). Inputs used by the ML models were plain radiographs (n = 8), MRI scans (n = 3), and ultrasound examinations (n = 1). Overall, ML models outperformed clinicians more when interpreting plain radiographs than when interpreting MRIs (17 of 34 and 3 of 16 performance comparisons, respectively). Orthopaedists and radiologists performed similarly to ML models, while ML models mostly outperformed other clinicians (outperformance in 7 of 19, 7 of 23, and 6 of 10 performance comparisons, respectively). Two studies evaluated the performance of clinicians aided and unaided by ML models; both demonstrated considerable improvements in ML-aided clinician performance by reporting a 47% decrease of misinterpretation rate (95% confidence interval [CI] 37 to 54; p < 0.001) and a mean increase in specificity of 0.048 (95% CI 0.029 to 0.068; p < 0.001) in detecting abnormalities on musculoskeletal images. CONCLUSIONS: At present, ML models have comparable performance to clinicians in assessing musculoskeletal images. ML models may enhance the performance of clinicians as a technical supplement rather than as a replacement for clinical intelligence. Future ML-related studies should emphasize how ML models can complement clinicians, instead of determining the overall superiority of one versus the other. This can be accomplished by improving transparent reporting, diminishing bias, determining the feasibility of implantation in the clinical setting, and appropriately tempering conclusions. LEVEL OF EVIDENCE: Level III, diagnostic study.

The Prevalence of Calcifications at the Origin of the Extensor Carpi Radialis Brevis Increases with Age.

BACKGROUND: Enthesopathy of the extensor carpi radialis brevis origin [eECRB] is a common idiopathic, non-inflammatory disease of middle age that is characterized by excess glycosaminoglycan production and frequently associated with radiographic calcification of its origin. The purpose of our study was to assess the relationship of calcification of the ECRB and advancing age. METHODS: We included 28,563 patients who received an elbow radiograph and assessed the relationship of calcifications of the ECRB identified on radiograph reports with patient age, sex, race, affected side, and ordering indication using multivariable logistic regression. RESULTS: Calcifications of the ECRB were independently associated with age (OR:1.04; P<0.001); radiographs ordered for atraumatic pain (OR2.6; P<0.001) or lateral epicondylitis (OR5.5; P<0.001); and Hispanic ethnicity (OR1.5; P<0.001) and less likely to be found at the left side (OR0.68; P<0.001). Similarly, incidental calcifications of the ECRB, those on radiographs not ordered for atraumatic pain or lateral epicondylitis, were independently associated with age (OR1.03; P<0.001) and Hispanic ethnicity (OR1.5; P<0.024) and less likely to be found on the left side (OR0.71; P<0.001). CONCLUSION: We observed that about nine percent of people have ECRB calcification by the time they are in their sixth decade of life and calcifications persist in the absence of symptoms which supports the idea that eECRB is a common, self-limited diagnosis of middle age.

External validation of the SORG 90-day and 1-year machine learning algorithms for survival in spinal metastatic disease.

BACKGROUND CONTEXT: Preoperative survival estimation in spinal metastatic disease helps determine the appropriateness of invasive management. The SORG ML 90-day and 1-year machine learning algorithms for survival in spinal metastatic disease were previously developed in a single institutional sample but remain to be externally validated. PURPOSE: The purpose of this study was to externally validate these algorithms in an independent population from another institution. STUDY DESIGN/SETTING: Retrospective study at a large, tertiary care center. PATIENT SAMPLE: Patients 18 years or older who underwent surgery between 2003 and 2016. OUTCOME MEASURES: Ninety-day and 1-year mortality. METHODS: Baseline characteristics of the validation cohort were compared to the developmental cohort for the SORG ML algorithms. Discrimination (c-statistic and receiver operating curve), calibration (calibration slope, intercept, calibration plot, and observed proportions by predicted risk groups), overall performance (Brier score), and decision curve analysis were used to assess the performance of the SORG ML algorithms in the validation cohort. RESULTS: Overall, 176 patients underwent surgery for spinal metastatic disease, of which 44 (22.7%) experienced 90-day mortality and 99 (56.2%) experienced 1-year mortality. The validation cohort differed significantly from the developmental cohort on primary tumor histology, metastatic tumor burden, previous systemic therapy, overall comorbidity burden, and preoperative laboratory characteristics. Despite these differences, the SORG ML algorithms generalized well to the validation cohort on discrimination (c-statistic 0.75-0.81 for 90-day mortality and 0.77-0.78 for 1-year mortality), calibration, Brier score, and decision curve analysis. CONCLUSION AND RELEVANCE: Initial results from external validation of the SORG ML 90-day and 1-year algorithms for survival prediction in spinal metastatic disease suggest potential utility of these digital decision aids in clinical practice. Further studies are needed to validate or refute these algorithms in large patient samples from prospective, international, multi-institutional trials.

Development and Internal Validation of Machine Learning Algorithms for Preoperative Survival Prediction of Extremity Metastatic Disease.

BACKGROUND: A preoperative estimation of survival is critical for deciding on the operative management of metastatic bone disease of the extremities. Several tools have been developed for this purpose, but there is room for improvement. Machine learning is an increasingly popular and flexible method of prediction model building based on a data set. It raises some skepticism, however, because of the complex structure of these models. QUESTIONS/PURPOSES: The purposes of this study were (1) to develop machine learning algorithms for 90-day and 1-year survival in patients who received surgical treatment for a bone metastasis of the extremity, and (2) to use these algorithms to identify those clinical factors (demographic, treatment related, or surgical) that are most closely associated with survival after surgery in these patients. METHODS: All 1090 patients who underwent surgical treatment for a long-bone metastasis at two institutions between 1999 and 2017 were included in this retrospective study. The median age of the patients in the cohort was 63 years (interquartile range [IQR] 54 to 72 years), 56% of patients (610 of 1090) were female, and the median BMI was 27 kg/m (IQR 23 to 30 kg/m). The most affected location was the femur (70%), followed by the humerus (22%). The most common primary tumors were breast (24%) and lung (23%). Intramedullary nailing was the most commonly performed type of surgery (58%), followed by endoprosthetic reconstruction (22%), and plate screw fixation (14%). Missing data were imputed using the missForest methods. Features were selected by random forest algorithms, and five different models were developed on the training set (80% of the data): stochastic gradient boosting, random forest, support vector machine, neural network, and penalized logistic regression. These models were chosen as a result of their classification capability in binary datasets. Model performance was assessed on both the training set and the validation set (20% of the data) by discrimination, calibration, and overall performance. RESULTS: We found no differences among the five models for discrimination, with an area under the curve ranging from 0.86 to 0.87. All models were well calibrated, with intercepts ranging from -0.03 to 0.08 and slopes ranging from 1.03 to 1.12. Brier scores ranged from 0.13 to 0.14. The stochastic gradient boosting model was chosen to be deployed as freely available web-based application and explanations on both a global and an individual level were provided. For 90-day survival, the three most important factors associated with poorer survivorship were lower albumin level, higher neutrophil-to-lymphocyte ratio, and rapid growth primary tumor. For 1-year survival, the three most important factors associated with poorer survivorship were lower albumin level, rapid growth primary tumor, and lower hemoglobin level. CONCLUSIONS: Although the final models must be externally validated, the algorithms showed good performance on internal validation. The final models have been incorporated into a freely accessible web application that can be found at https://sorg-apps.shinyapps.io/extremitymetssurvival/. Pending external validation, clinicians may use this tool to predict survival for their individual patients to help in shared treatment decision making. LEVEL OF EVIDENCE: Level III, therapeutic study.

Discharge Disposition After Anterior Cervical Discectomy and Fusion.

OBJECTIVE: Age and comorbidity burden of patients going anterior cervical discectomy and fusion (ACDF) have increased significantly over the past 2 decades, resulting in increased expenditures. Non-home discharge after ACDF contributes to increased direct and indirect costs of postoperative care. The purpose of this study was to identify independent prognostic factors for discharge disposition in patients undergoing ACDF. METHODS: A retrospective review was conducted at 5 medical centers to identify patients undergoing ACDF for degenerative conditions. The primary outcome was non-home discharge. Additional outcomes considered included discharge to rehabilitation and home discharge with services. Bivariate and multivariable analyses were used to identify independent prognostic factors for non-home discharge. RESULTS: Of 2070 patients undergoing ACDF, 114 (5.5%) had non-home discharge and 63 (3.0%) had discharge to inpatient rehabilitation. Factors independently associated with non-home discharge included older age, marital status, Medicare insurance, Medicaid insurance, previous spine surgery, myelopathy, preoperative comorbidities (hemiplegia/paraplegia, congestive heart failure, cerebrovascular accident), anemia, and leukocytosis. C-statistic for the overall model was 0.85. Results were relatively similar for patients younger than the age of 65 years as well as for discharge to inpatient rehabilitation and discharge home with services. CONCLUSIONS: Numerous sociodemographic and clinical characteristics influence the risk of non-home discharge and discharge to inpatient rehabilitation in patients undergoing ACDF. Policy makers and payers should consider these factors when determining appropriate preoperative adjustment for risk-based reimbursements.

Development of machine learning algorithms for prediction of prolonged opioid prescription after surgery for lumbar disc herniation.

BACKGROUND CONTEXT: Spine surgery has been identified as a risk factor for prolonged postoperative opioid use. Preoperative prediction of opioid use could improve risk stratification, shared decision-making, and patient counseling before surgery. PURPOSE: The primary purpose of this study was to develop algorithms for prediction of prolonged opioid prescription after surgery for lumbar disc herniation. STUDY DESIGN/SETTING: Retrospective, case-control study at five medical centers. PATIENT SAMPLE: Chart review was conducted for patients undergoing surgery for lumbar disc herniation between January 1, 2000 and March 1, 2018. OUTCOME MEASURES: The primary outcome of interest was sustained opioid prescription after surgery to at least 90 to 180 days postoperatively. METHODS: Five models (elastic-net penalized logistic regression, random forest, stochastic gradient boosting, neural network, and support vector machine) were developed to predict prolonged opioid prescription. Explanations of predictions were provided globally (averaged across all patients) and locally (for individual patients). RESULTS: Overall, 5,413 patients were identified, with sustained postoperative opioid prescription of 416 (7.7%) at 90 to 180 days after surgery. The elastic-net penalized logistic regression model had the best discrimination (c-statistic 0.81) and good calibration and overall performance; the three most important predictors were: instrumentation, duration of preoperative opioid prescription, and comorbidity of depression. The final models were incorporated into an open access web application able to provide predictions as well as patient-specific explanations of the results generated by the algorithms. The application can be found here: https://sorg-apps.shinyapps.io/lumbardiscopioid/ CONCLUSION: Preoperative prediction of prolonged postoperative opioid prescription can help identify candidates for increased surveillance after surgery. Patient-centered explanations of predictions can enhance both shared decision-making and quality of care.

Sagittal spinal parameters after en bloc resection of mobile spine tumors.

BACKGROUND CONTEXT: En bloc resection and reconstruction (EBR) in patients with spinal malignancy aims to achieve local disease control. This is an invasive procedure with significant alterations of the physiological anatomy and subsequently, the spino-pelvic alignment. Sagittal spinal parameters are useful measurements to objectively identify disproportionate alignment on a radiograph. In the field of spinal deformities, there is increasing evidence for a relationship between sagittal alignment and patient reported outcomes. PURPOSE: To determine sagittal spino-pelvic alignment after EBR in patients with spinal malignancies and the effect of these parameters on surgical and patient reported outcomes. STUDY DESIGN: A retrospective case series. METHODS: We included 35 patients who underwent EBR for spinal malignancies between 2000 and 2018. Radiographic measurements were performed using semi-automatic software; the parameters included were pelvic incidence (PI), sacral slope, pelvic tilt (PT), global tilt and lumbar lordosis. We calculated PI-based Global Alignment and Proportion (GAP) scores and prospective patient reported outcome scores Patient-Reported Outcome Measurement Information System-Physical Function (PROMIS-PF) were used. RESULTS: Twenty-one (60%) patients filled out the PROMIS-PF score at a median of 16 months (Interquartile Range (IQR) 4-108) after surgery with a median score of 39 (IQR 32-42), the median GAP score was 7 (IQR 5-9). Bivariate analysis showed no statistically significant relationship between GAP score and instrumentation failure or need for revision surgery. Multivariable analysis of GAP score and PROMIS-PF score corrected for local disease recurrence showed a statistically significant correlation coefficient of -1.721 (p=.026; 95%CI=-3.216, -0.226). CONCLUSION: In this cohort, all patients had a moderate or severe disproportioned spinal alignment after EBR and reconstruction surgery. The degree of sagittal spino-pelvic misalignment after EBR for spinal malignancies seems to be associated with patient reported health status in terms of PROMIS-PF scores. Further research with a larger patient cohort and standardized imaging and follow-up protocols is necessary in order to accurately use sagittal alignment as a predictive value for instrumentation failure and revision surgery.