Pilot Study: Short Term Impact of Radiation Therapy on Bone Mineral Density and Bone Metabolism.

Despite the risk of complications, high dose radiation therapy is increasingly utilized in the management of selected bone malignancies. In this study, we investigate the impact of moderate to high dose radiation (over 50 Gy) on bone metabolism and structure. Between 2015 and 2018, patients with a primary malignant bone tumor of the sacrum that were either treated with high dose definitive radiation only or a combination of moderate to high dose radiation and surgery were prospectively enrolled at a single institution. Quantitative CTs were performed before and after radiation to determine changes in volumetric bone mineral density (BMD) of the irradiated and non-irradiated spine. Bone histomorphometry was performed on biopsies of the irradiated sacrum and the non-irradiated iliac crest of surgical patients using a quadruple tetracycline labeling protocol. In total, 9 patients were enrolled. Two patients received radiation only (median dose 78.3 Gy) and 7 patients received a combination of preoperative radiation (median dose 50.4 Gy), followed by surgery. Volumetric BMD of the non-irradiated lumbar spine did not change significantly after radiation, while the BMD of the irradiated sacrum did (pre-radiation median: 108.0 mg/cm3 (IQR 91.8-167.1); post-radiation median: 75.3 mg/cm3 (IQR 57.1-110.2); p = 0.010). The cancellous bone of the non-irradiated iliac crest had a stable bone formation rate, while the irradiated sacrum showed a significant decrease in bone formation rate [pre-radiation median: 0.005 mm3/mm2/year (IQR 0.003-0.009), post-radiation median: 0.001 mm3/mm2/year (IQR 0.001-0.001); p = 0.043]. Similar effects were seen in the cancellous and endocortical envelopes. This pilot study shows a decrease of volumetric BMD and bone formation rate after high-dose radiation therapy. Further studies with larger cohorts and other endpoints are needed to get more insight into the effect of radiation on bone. Level of evidence: IV.

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.

Thirty-day Postoperative Complications After Surgery For Metastatic Long Bone Disease Are Associated With Higher Mortality at 1 Year.

BACKGROUND: The benefits of surgical treatment of a metastasis of the extremities may be offset by drawbacks such as potential postoperative complications. For this group of patients, the primary goal of surgery is to improve quality of life in a palliative setting. A better comprehension of factors associated with complications and the impact of postoperative complications on mortality may prevent negative outcomes and help surgeons in surgical decision-making. QUESTIONS/PURPOSES: (1) What is the risk of 30-day postoperative complications after surgical treatment of osseous metastatic disease of the extremities? (2) What predisposing factors are associated with a higher risk of 30-day complications? (3) Are minor and major 30-day complications associated with higher mortality at 1 year? METHODS: Between 1999 and 2016, 1090 patients with osseous metastatic disease of the long bones treated surgically at our institution were retrospectively included in the study. Surgery included intramedullary nailing (58%), endoprosthetic reconstruction (22%), plate-screw fixation (14%), dynamic hip screw fixation (2%), and combined approaches (4%). Surgery was performed if patients were deemed healthy enough to proceed to surgery and wished to undergo surgery. All data were retrieved by manually reviewing patients' records. The overall frequency of complications, which were defined using the Clavien-Dindo classification system, was calculated. We did not include Grade I complications as postoperative complications and complications were divided into minor (Grade II) and major (Grades III-V) complications. A multivariate logistic regression analysis was used to identify factors associated with 30-day postoperative complications. A Cox regression analysis was used to assess the association between postoperative complications and overall survival. RESULTS: Overall, 31% of the patients (333 of 1090) had a postoperative complication within 30 days. The following factors were independently associated with 30-day postoperative complications: rapidly growing primary tumors classified according to the modified Katagiri classification (odds ratio 1.6; 95% confidence interval, 1.1-2.2; p = 0.011), multiple bone metastases (OR 1.6; 95% CI, 1.1-2.3; p = 0.008), pathologic fracture (OR 1.5; 95% CI, 1.1-2.0; p = 0.010), lower-extremity location (OR 2.2; 95% CI, 1.6-3.2; p < 0.001), hypoalbuminemia (OR 1.7; 95% CI, 1.2-2.4; p = 0.002), hyponatremia (OR 1.5; 95% CI, 1.0-2.2; p = 0.044), and elevated white blood cell count (OR 1.6; 95% CI, 1.1-2.4; p = 0.007). Minor and major postoperative complications within 30 days after surgery were both associated with greater 1-year mortality (hazard ratio 1.6; 95% CI, 1.3-1.8; p < 0.001 and HR 3.4; 95% CI, 2.8-4.2, respectively; p < 0.001). CONCLUSION: Patients with metastatic disease in the long bones are vulnerable to postoperative adverse events. When selecting patients for surgery, surgeons should carefully assess a patient's cancer status, and several preoperative laboratory values should be part of the standard work-up before surgery. Furthermore, 30-day postoperative complications decrease survival within 1 year after surgery. Therefore, patients at a high risk of having postoperative complications are less likely to profit from surgery and should be considered for nonoperative treatment or be monitored closely after surgery. LEVEL OF EVIDENCE: Level III, therapeutic study.

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.

Prognostic value of serum alkaline phosphatase in spinal metastatic disease.

BACKGROUND: Determination of the appropriateness of invasive management in patients with spinal metastatic disease requires accurate pre-operative estimation of survival. The purpose of this study was to examine serum alkaline phosphatase as a prognostic marker in spinal metastatic disease. METHODS: Chart reviews from two tertiary care centres were used to identify spinal metastatic disease patients. Bivariate and multivariate analyses were used to determine if serum alkaline phosphatase was an independent prognostic marker for survival. RESULTS: Overall, 732 patients were included with 90-day and 1-year survival of n = 539 (74.9%) and n = 324 (45.7%), respectively. The 1-year survival of patients in the first quartile of alkaline phosphatase (≤73 IU/L) was 78 (57.8%) compared to 31 (24.0%) for patients in the fourth quartile (>140 IU/L). Preoperative serum alkaline phosphatase levels were significantly elevated in patients with multiple spine metastases, non-spine bone metastasis, and visceral metastasis but not in patients with brain metastasis. On multivariate analysis, elevated serum alkaline phosphatase was identified as an independent prognostic factor for survival in spinal metastatic disease. CONCLUSION: Serum alkaline phosphatase is associated with preoperative metastatic tumour burden and is a biomarker for overall survival in spinal metastatic disease.

Physical function and pain intensity in patients with metastatic bone disease.

BACKGROUND: Patient reported outcome data in bone metastatic disease are scarce and it would be useful to have normative data and understand what patients are at risk for poor function and more pain. OBJECTIVES: We aimed to assess what factors are independently associated with physical function and pain intensity in patients with bone metastasis. METHODS: We included data from 211 patients with bone metastasis who completed a survey (2014-2016) including the PROMIS Physical Function Cancer and PROMIS Pain Intensity questionnaires. RESULTS: Prostate (P < .001) and thyroid carcinoma (P = .007) were associated with better function and having other disabling conditions (P = 0.035) was associated with worse function. Prostate carcinoma (P = .001) and lymphoma (P = .007) were associated with less pain. There was a moderate correlation between pain and function (P < .001). Function was substantially worse as compared to a US reference population of patients with cancer (P < .001), whereas pain was slightly less compared to the US general population average (P < .001). CONCLUSIONS: Patients with bone metastasis have a poor physical function. Physical function and pain intensity depend on tumor histology, but also on potentially modifiable factors such as other disabling conditions. LEVEL OF EVIDENCE: Level III, prognostic study.

Development of a machine learning algorithm predicting discharge placement after surgery for spondylolisthesis.

PURPOSE: We aimed to develop a machine learning algorithm that can accurately predict discharge placement in patients undergoing elective surgery for degenerative spondylolisthesis. METHODS: The National Surgical Quality Improvement Program (NSQIP) database was used to select patients that underwent surgical treatment for degenerative spondylolisthesis between 2009 and 2016. Our primary outcome measure was non-home discharge which was defined as any discharge not to home for which we grouped together all non-home discharge destinations including rehabilitation facility, skilled nursing facility, and unskilled nursing facility. We used Akaike information criterion to select the most appropriate model based on the outcomes of the stepwise backward logistic regression. Four machine learning algorithms were developed to predict discharge placement and were assessed by discrimination, calibration, and overall performance. RESULTS: Nine thousand three hundred and thirty-eight patients were included. Median age was 63 (interquartile range [IQR] 54-71), and 63% (n = 5,887) were female. The non-home discharge rate was 18.6%. Our models included age, sex, diabetes, elective surgery, BMI, procedure, number of levels, ASA class, preoperative white blood cell count, and preoperative creatinine. The Bayes point machine was considered the best model based on discrimination (AUC = 0.753), calibration (slope = 1.111; intercept = - 0.002), and overall model performance (Brier score = 0.132). CONCLUSION: This study has shown that it is possible to create a predictive machine learning algorithm with both good accuracy and calibration to predict discharge placement. Using our methodology, this type of model can be developed for many other conditions and (elective) treatments. These slides can be retrieved under Electronic Supplementary Material.

Predicting discharge placement after elective surgery for lumbar spinal stenosis using machine learning methods.

PURPOSE: An excessive amount of total hospitalization is caused by delays due to patients waiting to be placed in a rehabilitation facility or skilled nursing facility (RF/SNF). An accurate preoperative prediction of who would need a RF/SNF place after surgery could reduce costs and allow more efficient organizational planning. We aimed to develop a machine learning algorithm that predicts non-home discharge after elective surgery for lumbar spinal stenosis. METHODS: We used the American College of Surgeons National Surgical Quality Improvement Program to select patient that underwent elective surgery for lumbar spinal stenosis between 2009 and 2016. The primary outcome measure for the algorithm was non-home discharge. Four machine learning algorithms were developed to predict non-home discharge. Performance of the algorithms was measured with discrimination, calibration, and an overall performance score. RESULTS: We included 28,600 patients with a median age of 67 (interquartile range 58-74). The non-home discharge rate was 18.2%. Our final model consisted of the following variables: age, sex, body mass index, diabetes, functional status, ASA class, level, fusion, preoperative hematocrit, and preoperative serum creatinine. The neural network was the best model based on discrimination (c-statistic = 0.751), calibration (slope = 0.933; intercept = 0.037), and overall performance (Brier score = 0.131). CONCLUSIONS: A machine learning algorithm is able to predict discharge placement after surgery for lumbar spinal stenosis with both good discrimination and calibration. Implementing this type of algorithm in clinical practice could avert risks associated with delayed discharge and lower costs. These slides can be retrieved under Electronic Supplementary Material.

Does the SORG Algorithm Predict 5-year Survival in Patients with Chondrosarcoma? An External Validation.

BACKGROUND: We developed a machine learning algorithm to predict the survival of patients with chondrosarcoma. The algorithm demonstrated excellent discrimination and calibration on internal validation in a derivation cohort based on data from the Surveillance, Epidemiology, and End Results (SEER) registry. However, the algorithm has not been validated in an independent external dataset. QUESTIONS/PURPOSES: Does the Skeletal Oncology Research Group (SORG) algorithm accurately predict 5-year survival in an independent patient population surgically treated for chondrosarcoma? METHODS: The SORG algorithm was developed using the SEER registry, which contains demographic data, tumor characteristics, treatment, and outcome values; and includes approximately 30% of the cancer patients in the United States. The SEER registry was ideal for creating the derivation cohort, and consequently the SORG algorithm, because of the high number of eligible patients and the availability of most (explanatory) variables of interest. Between 1992 to 2013, 326 patients were treated surgically for extracranial chondrosarcoma of the bone at two tertiary care referral centers. Of those, 179 were accounted for at a minimum of 5 years after diagnosis in a clinical note at one of the two institutions, unless they died earlier, and were included in the validation cohort. In all, 147 (45%) did not meet the minimum 5 years of followup at the institution and were not included in the validation of the SORG algorithm. The outcome (survival at 5 years) was checked for all 326 patients in the Social Security death index and were included in the supplemental validation cohort, to also ascertain validity for patients with less than 5 years of institutional followup. Variables used in the SORG algorithm to predict 5-year survival including sex, age, histologic subtype, tumor grade, tumor size, tumor extension, and tumor location were collected manually from medical records. The tumor characteristics were collected from the postoperative musculoskeletal pathology report. Predicted probabilities of 5-year survival were calculated for each patient in the validation cohort using the SORG algorithm, followed by an assessment of performance using the same metrics as used for internal validation, namely: discrimination, calibration, and overall performance. Discrimination was calculated using the concordance statistic (or the area under the Receiver Operating Characteristic (ROC) curve) to determine how well the algorithm discriminates between the outcome, which ranges from 0.5 (no better than a coin-toss) to 1.0 (perfect discrimination). Calibration was assessed using the calibration slope and intercept from a calibration plot to measure the agreement between predicted and observed outcomes. A perfect calibration plot should show a 45° upwards line. Overall performance was determined using the Brier score, ranging from 0 (excellent prediction) to 1 (worst prediction). The Brier score was compared with the null-model Brier score, which showed the performance of a model that ignored all the covariates. A Brier score lower than the null model Brier score indicated greater performance of the algorithm. For the external validation an F1-score was added to measure the overall accuracy of the algorithm, which ranges between 0 (total failure of an algorithm) and 1 (perfect algorithm).The 5-year survival was lower in the validation cohort than it was in the derivation cohort from SEER (61.5% [110 of 179] versus 76% [1131 of 1544] ; p < 0.001). This difference was driven by higher proportion of dedifferentiated chondrosarcoma in the institutional population than in the derivation cohort (27% [49 of 179] versus 9% [131 of 1544]; p < 0.001). Patients in the validation cohort also had larger tumor sizes, higher grades, and nonextremity tumor locations than did those in the derivation cohort. These differences between the study groups emphasize that the external validation is performed not only in a different patient cohort, but also in terms of disease characteristics. Five-year survival was not different for both patient groups between subpopulations of patients with conventional chondrosarcomas and those with dedifferentiated chondrosarcomas. RESULTS: The concordance statistic for the validation cohort was 0.87 (95% CI, 0.80-0.91). Evaluation of the algorithm's calibration in the institutional population resulted in a calibration slope of 0.97 (95% CI, 0.68-1.3) and calibration intercept of -0.58 (95% CI, -0.20 to -0.97). Finally, on overall performance, the algorithm had a Brier score of 0.152 compared with a null-model Brier score of 0.237 for a high level of overall performance. The F1-score was 0.836. For the supplementary validation in the total of 326 patients, the SORG algorithm had a validation of 0.89 (95% CI, 0.85-0.93). The calibration slope was 1.13 (95% CI, 0.87-1.39) and the calibration intercept was -0.26 (95% CI, -0.57 to 0.06). The Brier score was 0.11, with a null-model Brier score of 0.19. The F1-score was 0.901. CONCLUSIONS: On external validation, the SORG algorithm retained good discriminative ability and overall performance but overestimated 5-year survival in patients surgically treated for chondrosarcoma. This internet-based tool can help guide patient counseling and shared decision making. LEVEL OF EVIDENCE: Level III, prognostic study.

Prognostic role of neutrophil-to-lymphocyte ratio and platelet-to-lymphocyte ratio in patients with bone metastases.

BACKGROUND: Skeletal metastases are a common problem in patients with cancer, and surgical decision making depends on multiple factors including life expectancy. Identification of new prognostic factors can improve survival estimation and guide healthcare providers in surgical decision making. In this study, we aim to determine the prognostic value of neutrophil/lymphocyte ratio (NLR) and platelet/lymphocyte ratio (PLR) in patients with bone metastasis. METHODS: One thousand and twelve patients from two tertiary referral centers between 2002 and 2014 met the inclusion criteria. Bivariate and multivariate Cox regression analyses were performed to determine the association of NLR and PLR with survival. RESULTS: At 3 months, 84.0% of the patients with low NLR were alive versus 61.3% of the patients with a high NLR (p < 0.001), and 75.8% of the patients with a low PLR were alive versus 55.6% of the patients with a high PLR (p < 0.001). Both elevated NLR and elevated PLR were independently associated with worse survival (hazard ratio (HR): 1.311; 95% confidence interval (CI): 1.117-1.538; p = 0.001) and (HR: 1.358; 95% CI: 1.152-1.601; p < 0.001), respectively. CONCLUSION: This study showed both NLR and PLR to be independently associated with survival in patients who were treated for skeletal metastasis.

Serum alkaline phosphatase and 30-day mortality after surgery for spinal metastatic disease.

BACKGROUND: Elevated serum alkaline phosphatase has been previously studied as a biomarker for progression of metastatic disease and implicated in adverse skeletal events and worsened survival. The purpose of this study was to determine if serum alkaline phosphatase was a predictor of short-term mortality of patients undergoing surgery for spinal metastatic disease. METHODS: The American College of Surgeons National Surgical Quality Improvement Program was queried for patients undergoing spinal surgery for metastatic disease. Bivariate and multivariable analyses was undertaken to determine the relationship between serum alkaline phosphatase and 30-day mortality. RESULTS: For the 1788 patients undergoing operative intervention for spinal metastatic disease between 2009 and 2016 the 30-day mortality was 8.49% (n = 151). In patients who survived beyond 30-days after surgery, n = 1627 (91.5%) the median [interquartile range] serum alkaline phosphatase levels were 126.4 [75-138], whereas in patients who had 30-day mortality, the serum alkaline phosphatase levels were 179.8 [114-187]. The optimal cut-off for alkaline phosphatase was determined to be 113 IU/L. On multivariable analysis, elevated serum alkaline phosphatase levels were associated with 30-day mortality (OR 1.61, 95% CI 1.12-2.32, p = 0.011). CONCLUSION: Elevated preoperative serum alkaline phosphatase is a marker for 30-day mortality in patients undergoing surgery for spinal metastatic disease. Future retrospective and prospective study designs should incorporate assessment of this serum biomarker to better understand the role for serum alkaline phosphatase in improving prognostication in spinal metastatic disease.

Can Machine-learning Techniques Be Used for 5-year Survival Prediction of Patients With Chondrosarcoma?

BACKGROUND: Several studies have identified prognostic factors for patients with chondrosarcoma, but there are few studies investigating the accuracy of computationally intensive methods such as machine learning. Machine learning is a type of artificial intelligence that enables computers to learn from data. Studies using machine learning are potentially appealing, because of its possibility to explore complex patterns in data and to improve its models over time. QUESTIONS/PURPOSES: The purposes of this study were (1) to develop machine-learning algorithms for the prediction of 5-year survival in patients with chondrosarcoma; and (2) to deploy the best algorithm as an accessible web-based app for clinical use. METHODS: All patients with a microscopically confirmed diagnosis of conventional or dedifferentiated chondrosarcoma were extracted from the Surveillance, Epidemiology, and End Results (SEER) Registry from 2000 to 2010. SEER covers approximately 30% of the US population and consists of demographic, tumor characteristic, treatment, and outcome data. In total, 1554 patients met the inclusion criteria. Mean age at diagnosis was 52 years (SD 17), ranging from 7 to 102 years; 813 of the 1554 patients were men (55%); and mean tumor size was 8 cm (SD 6), ranging from 0.1 cm to 50 cm. Exact size was missing in 340 of 1544 patients (22%), grade in 88 of 1544 (6%), tumor extension in 41 of 1544 (3%), and race in 16 of 1544 (1%). Data for 1-, 3-, 5-, and 10-year overall survival were available for 1533 (99%), 1512 (98%), 1487 (96%), and 977 (63%) patients, respectively. One-year survival was 92%, 3-year survival was 82%, 5-year survival was 76%, and 10-year survival was 54%. Missing data were imputed using the nonparametric missForest method. Boosted decision tree, support vector machine, Bayes point machine, and neural network models were developed for 5-year survival. These models were chosen as a result of their capability of predicting two outcomes based on prior work on machine-learning models for binary classification. The models were assessed by discrimination, calibration, and overall performance. The c-statistic is a measure of discrimination. It ranges from 0.5 to 1.0 with 1.0 being perfect discrimination and 0.5 that the model is no better than chance at making a prediction. The Brier score measures the squared difference between the predicted probability and the actual outcome. A Brier score of 0 indicates perfect prediction, whereas a Brier score of 1 indicates the poorest prediction. The Brier scores of the models are compared with the null model, which is calculated by assigning each patient a probability equal to the prevalence of the outcome. RESULTS: Four models for 5-year survival were developed with c-statistics ranging from 0.846 to 0.868 and Brier scores ranging from 0.117 to 0.135 with a null model Brier score of 0.182. The Bayes point machine was incorporated into a freely available web-based application. This application can be accessed through https://sorg-apps.shinyapps.io/chondrosarcoma/. CONCLUSIONS: Although caution is warranted, because the prediction model has not been validated yet, healthcare providers could use the online prediction tool in daily practice when survival prediction of patients with chondrosarcoma is desired. Future studies should seek to validate the developed prediction model. LEVEL OF EVIDENCE: Level III, prognostic study.

Estimating survival and choosing treatment for spinal metastases: Do spine surgeons agree with each other?

PURPOSE: This study aimed to investigate spine surgeons' ability to estimate survival in patients with spinal metastases and whether survival estimates influence treatment recommendations. METHODS: 60 Spine surgeons were asked a survival estimate and treatment recommendation in 12 cases. Intraclass correlation coefficients and descriptive statistics were used to evaluate variability, accuracy and association of survival estimates with treatment recommendation. RESULTS: There was substantial variability in survival estimates amongst the spine surgeons. Survival was generally overestimated, and longer estimated survival seemed to lead to more invasive procedures. CONCLUSIONS: Prognostic models to estimate survival may aid surgeons treating patients with spinal metastases.

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.

Serum alkaline phosphatase is a prognostic marker in bone metastatic disease of the extremity.

PURPOSE: The purpose of this study was to determine the prognostic value of serum alkaline phosphatase for treatment decision making in metastatic bone disease. METHODS: 1090 patients who underwent surgery for extremity metastatic disease were retrospectively identified at two tertiary care centers. The association between alkaline phosphatase and mortality was assessed by bivariate and multivariate analyses. RESULTS: Three-month and one-year mortality rates were 305 (29%) and 639 (62%), respectively. Alkaline phosphatase was associated with mortality at both three months and one year. CONCLUSION: Serum alkaline phosphatase may be a useful marker in prognostic algorithms for patients with extremity metastatic disease.

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.

Predicting 90-Day and 1-Year Mortality in Spinal Metastatic Disease: Development and Internal Validation.

BACKGROUND: Increasing prevalence of metastatic disease has been accompanied by increasing rates of surgical intervention. Current tools have poor to fair predictive performance for intermediate (90-d) and long-term (1-yr) mortality. OBJECTIVE: To develop predictive algorithms for spinal metastatic disease at these time points and to provide patient-specific explanations of the predictions generated by these algorithms. METHODS: Retrospective review was conducted at 2 large academic medical centers to identify patients undergoing initial operative management for spinal metastatic disease between January 2000 and December 2016. Five models (penalized logistic regression, random forest, stochastic gradient boosting, neural network, and support vector machine) were developed to predict 90-d and 1-yr mortality. RESULTS: Overall, 732 patients were identified with 90-d and 1-yr mortality rates of 181 (25.1%) and 385 (54.3%), respectively. The stochastic gradient boosting algorithm had the best performance for 90-d mortality and 1-yr mortality. On global variable importance assessment, albumin, primary tumor histology, and performance status were the 3 most important predictors of 90-d mortality. 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 at https://sorg-apps.shinyapps.io/spinemetssurvival/. CONCLUSION: Preoperative estimation of 90-d and 1-yr mortality was achieved with assessment of more flexible modeling techniques such as machine learning. Integration of these models into applications and patient-centered explanations of predictions represent opportunities for incorporation into healthcare systems as decision tools in the future.

Machine learning for prediction of sustained opioid prescription after anterior cervical discectomy and fusion.

BACKGROUND CONTEXT: The severity of the opioid epidemic has increased scrutiny of opioid prescribing practices. Spine surgery is a high-risk episode for sustained postoperative opioid prescription. PURPOSE: To develop machine learning algorithms for preoperative prediction of sustained opioid prescription after anterior cervical discectomy and fusion (ACDF). STUDY DESIGN/SETTING: Retrospective, case-control study at two academic medical centers and three community hospitals. PATIENT SAMPLE: Electronic health records were queried for adult patients undergoing ACDF for degenerative disorders between January 1, 2000 and March 1, 2018. OUTCOME MEASURES: Sustained postoperative opioid prescription was defined as uninterrupted filing of prescription opioid extending to at least 90-180 days after surgery. METHODS: Five machine learning models were developed to predict postoperative opioid prescription and assessed for overall performance. RESULTS: Of 2,737 patients undergoing ACDF, 270 (9.9%) demonstrated sustained opioid prescription. Variables identified for prediction of sustained opioid prescription were male sex, multilevel surgery, myelopathy, tobacco use, insurance status (Medicaid, Medicare), duration of preoperative opioid use, and medications (antidepressants, benzodiazepines, beta-2-agonist, angiotensin-converting enzyme-inhibitors, gabapentin). The stochastic gradient boosting algorithm achieved the best performance with c-statistic=0.81 and good calibration. Global explanations of the model demonstrated that preoperative opioid duration, antidepressant use, tobacco use, and Medicaid insurance were the most important predictors of sustained postoperative opioid prescription. CONCLUSIONS: One-tenth of patients undergoing ACDF demonstrated sustained opioid prescription following surgery. Machine learning algorithms could be used to preoperatively stratify risk these patients, possibly enabling early intervention to reduce the potential for long-term opioid use in this population.