No abstract

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.

There have been significant advances in cancer treatment over the past several years through the use of chemotherapy, radiation therapy, molecularly targeted therapy, and immunotherapy. Despite these advances, treatments such as monotherapy or monomodality have significant limitations. There is increasing interest in using these strategies in combination; however, it is not completely clear how best to incorporate molecularly targeted and immune-targeted therapies into combination regimens. This is particularly pertinent when considering combinations with immunotherapy, as other types of therapy may have significant impact on host immunity, the tumor microenvironment, or both. Thus, the influence of chemotherapy, radiation therapy, and molecularly targeted therapy on the host anti-tumor immune response and the host anti-host response (ie, autoimmune toxicity) must be taken into consideration when designing immunotherapy-based combination regimens. We present data related to many of these combination approaches in the context of investigations in patients with melanoma and discuss their potential relationship to management of patients with other tumor types. Importantly, we also highlight challenges of these approaches and emphasize the need for continued translational research.