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.

BACKGROUND Preoperative prognostication of short-term postoperative mortality in patients with spinal metastatic disease can improve shared decision making around end-of-life care. OBJECTIVE To (1) develop machine learning algorithms for prediction of short-term mortality and (2) deploy these models in an open access web application. METHODS The American College of Surgeons, National Surgical Quality Improvement Program was used to identify patients that underwent operative intervention for metastatic disease. Four machine learning algorithms were developed, and the algorithm with the best performance across discrimination, calibration, and overall performance was integrated into an open access web application. RESULTS The 30-d mortality for the 1790 patients undergoing surgery for spinal metastatic disease was 8.49%. Preoperative factors used for prognostication were albumin, functional status, white blood cell count, hematocrit, alkaline phosphatase, spinal location (cervical, thoracic, lumbosacral), and severity of comorbid systemic disease (American Society of Anesthesiologist Class). In this population, machine learning algorithms developed to predict 30-d mortality performed well on discrimination (c-statistic), calibration (assessed by calibration slope and intercept), Brier score, and decision analysis. An open access web application was developed for the best performing model and this web application can be found here: https://sorg-apps.shinyapps.io/spinemets/. CONCLUSION Machine learning algorithms are promising for prediction of postoperative outcomes in spinal oncology and these algorithms can be integrated into clinically useful decision tools. As the volume of data in oncology continues to grow, creation of learning systems and deployment of these systems as accessible tools may significantly enhance prognostication and management.

No abstract

No abstract

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/m2 (IQR 23 to 30 kg/m2). 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.

Arthroscopic debridement and microfracture for advanced capitellar osteochondritis dissecans provide good clinical results, especially in patients with open growth plate, loose body removal, and shorter duration of symptoms. However, only 62% of patients in this study returned to sports.

PurposeTo determine the rate of donor-site morbidity after osteochondral autologous transplantation (OATS) for capitellar osteochondritis dissecans.MethodsA literature search was performed in PubMed/MEDLINE, Embase, and Cochrane Library to identify studies up to November 6, 2016. Criteria for inclusion were OATS for capitellar osteochondritis dissecans, reported outcomes related to donor sites, ≥10 patients, ≥1 year follow-up, and written in English. Donor-site morbidity was defined as persistent symptoms (≥1 year) or cases that required subsequent intervention. Patient and harvest characteristics were described, as well as the rate of donor-site morbidity. A random effects model was used to calculate and compare weighted group proportions.ResultsEleven studies including 190 patients were included. In eight studies, grafts were harvested from the femoral condyle, in three studies, from either the 5th or 6th costal-osteochondral junction. The average number of grafts was 2 (1–5); graft diameter ranged from 2.6 to 11 mm. In the knee-to-elbow group, donor-site morbidity was reported in 10 of 128 patients (7.8%), knee pain during activity (7.0%) and locking sensations (0.8%). In the rib-to-elbow group, one of 62 cases (1.6%) was complicated, a pneumothorax. The proportion in the knee-to-elbow group was 0.04 (95% CI 0.0–0.15), and the proportion in the rib-to-elbow group was 0.01 (95% CI 0.00–0.06). There were no significant differences between both harvest techniques (n.s.).ConclusionsDonor-site morbidity after OATS for capitellar osteochondritis dissecans was reported in a considerable group of patients.Level of evidenceLevel IV, systematic review of level IV studies.Electronic supplementary materialThe online version of this article (doi:10.1007/s00167-017-4516-8) contains supplementary material, which is available to authorized users.

OBJECTIVEIf not anticipated and prearranged, hospital stay can be prolonged while the patient awaits placement in a rehabilitation unit or skilled nursing facility following elective spine surgery. Preoperative prediction of the likelihood of postoperative discharge to any setting other than home (i.e., nonroutine discharge) after elective inpatient spine surgery would be helpful in terms of decreasing hospital length of stay. The purpose of this study was to use machine learning algorithms to develop an open-access web application for preoperative prediction of nonroutine discharges in surgery for elective inpatient lumbar degenerative disc disorders.METHODSThe American College of Surgeons National Surgical Quality Improvement Program was queried to identify patients who underwent elective inpatient spine surgery for lumbar disc herniation or lumbar disc degeneration between 2011 and 2016. Four machine learning algorithms were developed to predict nonroutine discharge and the best algorithm was incorporated into an open-access web application.RESULTSThe rate of nonroutine discharge for 26,364 patients who underwent elective inpatient surgery for lumbar degenerative disc disorders was 9.28%. Predictive factors selected by random forest algorithms were age, sex, body mass index, fusion, level, functional status, extent and severity of comorbid disease (American Society of Anesthesiologists classification), diabetes, and preoperative hematocrit level. On evaluation in the testing set (n = 5273), the neural network had a c-statistic of 0.823, calibration slope of 0.935, calibration intercept of 0.026, and Brier score of 0.0713. On decision curve analysis, the algorithm showed greater net benefit for changing management over all threshold probabilities than changing management on the basis of the American Society of Anesthesiologists classification alone or for all patients or for no patients. The model can be found here: https://sorg-apps.shinyapps.io/discdisposition/.CONCLUSIONSMachine learning algorithms show promising results on internal validation for preoperative prediction of nonroutine discharges. If found to be externally valid, widespread use of these algorithms via the open-access web application by healthcare professionals may help preoperative risk stratification of patients undergoing elective surgery for lumbar degenerative disc disorders.