Treating metastatic disease: Which survival model is best suited for the clinic?

Life Expectancy After Treatment of Metastatic Bone Disease: An International Trend Analysis

INTRODUCTION

The decision to treat metastatic bone disease (MBD) surgically depends in part on patient life expectancy. We are unaware of an international analysis of how life expectancy among these patients has changed over time. Therefore, we asked (1) how has the life expectancy for patients treated for MBD changed over time, and (2) which, if any, of the common primary cancer types are associated with longer survival after treatment of MBD?

METHODS

We reviewed data collected from 2000 to 2022 in an international MBD database, as well as data used for survival model validation. We included 3,353 adults who underwent surgery and/or radiation. No patients were excluded. Patients were grouped by treatment date into period 1 (2000 to 2009), period 2 (2010 to 2019), and period 3 (2020 to 2022). Cumulative survival was portrayed using Kaplan-Meier curves; log-rank tests were used to determine significance at P < 0.05. Subgroup analyses by primary cancer diagnosis were performed.

RESULTS

Median survival in period 2 was longer than in period 1 ( P < 0.001). Median survival (at which point 50% of patients survived) had not been reached for period 3. Median survival was longer in period 2 for all cancer types ( P < 0.001) except thyroid. Only lung cancer reached median survival in period 3, which was longer compared with periods 1 and 2 ( P < 0.001). Slow-growth, moderate-growth, and rapid-growth tumors all demonstrated longer median survival from period 1 to period 2; only rapid-growth tumors reached median survival for period 3, which was longer compared with periods 1 and 2 ( P < 0.001).

DISCUSSION

Median duration of survival after treatment of MBD has increased, which was a consistent finding in nearly all cancer types. Longer survival is likely attributable to improvements in both medical and surgical treatments. As life expectancy for patients with MBD increases, surgical methods should be selected with this in mind.

LEVEL OF EVIDENCE

VI.

Development and external validation of a machine learning model for prediction of survival in undifferentiated pleomorphic sarcoma

PURPOSE

Machine learning (ML) algorithms to predict cancer survival have recently been reported for a number of sarcoma subtypes, but none have investigated undifferentiated pleomorphic sarcoma (UPS). ML is a powerful tool that has the potential to better prognosticate UPS.

METHODS

The Surveillance, Epidemiology, and End Results (SEER) database was queried for cases of histologically confirmed undifferentiated pleomorphic sarcoma (UPS) (n = 665). Patient, tumor, and treatment characteristics were recorded, and ML models were developed to predict 1-, 3-, and 5-year survival. The best performing ML model was externally validated using an institutional cohort of UPS patients (n = 151).

RESULTS

All ML models performed best at the 1-year time point and worst at the 5-year time point. On internal validation within the SEER cohort, the best models had c-statistics of 0.67-0.69 at the 5-year time point. The Multi-Layer Perceptron Neural Network (MLP) model was the best performing model and used for external validation. Similarly, the MLP model performed best at 1-year and worst at 5-year on external validation with c-statistics of 0.85 and 0.81, respectively. The MLP model was well calibrated on external validation. The MLP model has been made publicly available at https://rachar.shinyapps.io/ups_app/ .

CONCLUSION

Machine learning models perform well for survival prediction in UPS, though this sarcoma subtype may be more difficult to prognosticate than other subtypes. Future studies are needed to further validate the machine learning approach for UPS prognostication.

Operative management of metastatic disease of the acetabulum: review of the literature and prevailing concepts

Metastatic disease of the periacetabular region is a common problem in orthopaedic oncology, associated with severe pain, decreased mobility, and substantial decline of the quality of life. Conservative management includes optimisation of pain management, activity modification, and radiation therapy. However, patients with destructive lesions affecting the weight-bearing portion of the acetabulum often require reconstructive surgery to decrease pain and restore mobility. The goal of surgery is to provide an immediately stable and durable construct, allowing immediate postoperative weight-bearing and maintaining functional independence for the remaining lifetime of the patient. A variety of surgical techniques have been reported, most of which are based upon cemented total hip arthroplasty, but also include porous tantalum implants and percutaneous cementoplasty. This review discusses the various reconstructive concepts and options, including their respective indications and outcome. A reconstructive algorithm incorporating different techniques and strategies based upon location and quality of remaining bone is also presented.

The Prediction of Survival after Surgical Management of Bone Metastases of the Extremities—A Comparison of Prognostic Models

Individualized survival prognostic models for symptomatic patients with appendicular metastatic bone disease are key to guiding clinical decision-making for the orthopedic surgeon. Several prognostic models have been developed in recent years; however, most orthopedic surgeons have not incorporated these models into routine practice. This is possibly due to uncertainty concerning their accuracy and the lack of comparison publications and recommendations. Our aim was to conduct a review and quality assessment of these models. A computerized literature search in MEDLINE, EMBASE and PubMed up to February 2022 was done, using keywords: “Bone metastasis”, “survival”, “extremity” and “prognosis”. We evaluated each model’s performance, assessing the estimated discriminative power and calibration accuracy for the analyzed patients. We included 11 studies out of the 1779 citations initially retrieved. The 11 studies included seven different models for estimating survival. Among externally validated survival prediction scores, PATHFx 3.0, 2013-SPRING and potentially Optimodel were found to be the best models in terms of performance. Currently, it is still a challenge to recommend any of the models as the standard for predicting survival for these patients. However, some models show better performance status and other quality characteristics. We recommend future, large, multicenter, prospective studies to compare between PATHfx 3.0, SPRING 2013 and OptiModel using the same external validation dataset.

Machine learning algorithms to estimate 10-Year survival in patients with bone metastases due to prostate cancer: toward a disease-specific survival estimation tool

BACKGROUND

Prognostic indicators, treatments, and survival estimates vary by cancer type. Therefore, disease-specific models are needed to estimate patient survival. Our primary aim was to develop models to estimate survival duration after treatment for skeletal-related events (SREs) (symptomatic bone metastasis, including impending or actual pathologic fractures) in men with metastatic bone disease due to prostate cancer. Such disease-specific models could be added to the PATHFx clinical-decision support tool, which is available worldwide, free of charge. Our secondary aim was to determine disease-specific factors that should be included in an international cancer registry.

METHODS

We analyzed records of 438 men with metastatic prostate cancer who sustained SREs that required treatment with radiotherapy or surgery from 1989-2017. We developed and validated 6 models for 1-, 2-, 3-, 4-, 5-, and 10-year survival after treatment. Model performance was evaluated using calibration analysis, Brier scores, area under the receiver operator characteristic curve (AUC), and decision curve analysis to determine the models' clinical utility. We characterized the magnitude and direction of model features.

RESULTS

The models exhibited acceptable calibration, accuracy (Brier scores < 0.20), and classification ability (AUCs > 0.73). Decision curve analysis determined that all 6 models were suitable for clinical use. The order of feature importance was distinct for each model. In all models, 3 factors were positively associated with survival duration: younger age at metastasis diagnosis, proximal prostate-specific antigen (PSA) < 10 ng/mL, and slow-rising alkaline phosphatase velocity (APV).

CONCLUSIONS

We developed models that estimate survival duration in patients with metastatic bone disease due to prostate cancer. These models require external validation but should meanwhile be included in the PATHFx tool. PSA and APV data should be recorded in an international cancer registry.

Development and comparison of 1-year survival models in patients with primary bone sarcomas: External validation of a Bayesian belief network model and creation and external validation of a new gradient boosting machine model

Background:

Bone sarcomas often present late with advanced stage at diagnosis and an according, varying short-term survival. In 2016, Nandra et al. generated a Bayesian belief network model for 1-year survival in patients with bone sarcomas. The purpose of this study is: (1) to externally validate the prior 1-year Bayesian belief network prediction model for survival in patients with bone sarcomas and (2) to develop a gradient boosting machine model using Nandra et al.’s cohort and evaluate whether the gradient boosting machine model outperforms the Bayesian belief network model when externally validated in an independent Danish population cohort.

Material and Methods:

The training cohort comprised 3493 patients newly diagnosed with bone sarcoma from the institutional prospectively maintained database at the Royal Orthopaedic Hospital, Birmingham, UK. The validation cohort comprised 771 patients with newly diagnosed bone sarcoma included from the Danish Sarcoma Registry during January 1, 2000–June 22, 2016. We performed area under receiver operator characteristic curve analysis, Brier score and decision curve analysis to evaluate the predictive performance of the models.

Results:

External validation of the Bayesian belief network 1-year prediction model demonstrated an area under receiver operator characteristic curve of 68% (95% confidence interval, 62%-73%). Area under receiver operator characteristic curve of the gradient boosting machine model demonstrated: 75% (95% confidence interval: 70%-80%), overall model performance by the Brier score was 0.09 (95% confidence interval: 0.077–0.11) and decision curve analysis demonstrated a positive net benefit for threshold probabilities above 0.5. External validation of the developed gradient boosting machine model demonstrated an area under receiver operator characteristic curve of 63% (95% confidence interval: 57%-68%), and the Brier score was 0.14 (95% confidence interval: 0.12–0.16).

Conclusion:

External validation of the 1-year Bayesian belief network survival model yielded a poor outcome based on a Danish population cohort validation. We successfully developed a gradient boosting machine 1-year survival model. The gradient boosting machine did not outperform the Bayesian belief network model based on external validation in a Danish population-based cohort.

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.

Pretreatment Plasma IL-6 and YKL-40 and Overall Survival after Surgery for Metastatic Bone Disease of the Extremities

Simple Summary

Estimating postoperative survival in patients undergoing surgery for metastatic bone disease of the extremities is important in order to choose an implant that will outlive the patient. The present study suggests that plasma IL-6, reflecting the inflammatory state of the patient, is predictive for postoperative overall survival (OS).

Abstract

Background: Plasma IL-6 and YKL-40 are prognostic biomarkers for OS in patients with different types of solid tumors, but they have not been studied in patients before surgery of metastatic bone disease (MBD) of the extremities. The aim was to evaluate the prognostic value of plasma IL-6 and YKL-40 in patients undergoing surgery for MBD of the extremities. Patients and Methods: A prospective study included all patients undergoing surgery for MBD in the extremities at a tertiary referral center during the period 2014–2018. Preoperative blood samples from index surgery were included. IL-6 and YKL-40 concentrations in plasma were determined by commercial ELISA. A total of 232 patients (median age 66 years, IQR 58–74; female 51%) were included. Results: Cox regression analysis was performed to identify independent prognostic factors for OS. IL-6 correlated with YKL-40 (rho = 0.46, p < 0.01). In univariate analysis (log₂ continuous variable) IL-6 (HR = 1.26, 95% CI 1.16–1.37), CRP (HR = 1.20, 95% CI 1.12–1.29) and YKL-40 (HR = 1.25, 95% CI 1.15–1.37) were associated with short OS. In multivariable analysis, adjusted for known risk factors for survival, only log₂(IL-6) was independently associated with OS (HR = 1.24, 95% CI 1.08–1.43), whereas CRP and YKL-40 were not. Conclusion: High preoperative plasma IL-6 is an independent biomarker of short OS in patients undergoing surgery for MBD.

Validation of PATHFx 2.0: An open-source tool for estimating survival in patients undergoing pathologic fracture fixation

Treatment decisions in patients with metastatic bone disease rely on accurate survival estimation. We developed the original PATHFx models using expensive, proprietary software and now seek to provide a more cost-effective solution. Using open-source machine learning software to create PATHFx version 2.0, we asked whether PATHFx 2.0 could be created using open-source methods and externally validated in two unique patient populations. The training set of a well-characterized, database records of 189 patients and the bnlearn package within R Version 3.5.1 (R Foundation for Statistical Computing), was used to establish a series of Bayesian belief network models designed to predict survival at 1, 3, 6, 12, 18, and 24 months. Each was externally validated in both a Scandinavian (n = 815 patients) and a Japanese (n = 261 patients) data set. Brier scores and receiver operating characteristic curves to assessed discriminatory ability. Decision curve analysis (DCA) evaluated whether models should be used clinically. DCA showed that the model should be used clinically at all time points in the Scandinavian data set. For the 1-month time point, DCA of the Japanese data set suggested to expect better outcomes assuming all patients will survive greater than 1 month. Brier scores for each curve demonstrate that the models are accurate at each time point. Statement of Clinical Significance: we successfully transitioned to PATHFx 2.0 using open-source software and externally validated it in two unique patient populations, which can be used as a cost-effective option to guide surgical decisions in patients with metastatic bone disease.

Fracture risk assessment and clinical decision making for patients with metastatic bone disease

Metastatic breast, prostate, lung, and other cancers often affect bone, causing pain, increasing fracture risk, and decreasing function. Management of metastatic bone disease (MBD) is clinically challenging when there is potential but uncertain risk of pathological fracture. Management of MBD has become a major focus within orthopedic oncology with respect to fracture and impending fracture care. If impending skeletal-related events (SREs), particularly pathologic fracture, could be predicted, increasing evidence suggests that prophylactic surgical treatment improves patient outcomes. However, current fracture risk assessment and radiographic metrics do not have high accuracy and have not been combined with relevant patient survival tools. This review first explores the prevalence, incidence, and morbidity of MBD and associated SREs for different cancer types. Strengths and limitations of current fracture risk scoring systems for spinal stability and long bone fracture are highlighted. More recent computed tomography (CT)-based structural rigidity analysis (CTRA) and finite element (FE) analysis methods offer advantages of increased specificity (true negative rate), but are limited in availability. Other fracture prediction approaches including parametric response mapping and positron emission tomography/computed tomography measures show early promise. Substantial new information to inform clinical decision-making includes measures of survival, clinical benefits, and economic analysis of prophylactic treatment compared to after-fracture stabilization. Areas of future research include use of big data and machine learning to predict SREs, greater access and refinement of CTRA/FE approaches, combination of clinical survival prediction tools with radiographically based fracture risk assessment, and net benefit analysis for fracture risk assessment and prophylactic treatment.

Improving treatment decisions using personalized risk assessment from the International IgA Nephropathy Prediction Tool

Immunosuppression in IgA nephropathy (IgAN) should be reserved for patients at high-risk of disease progression, which KDIGO guidelines determine based solely on proteinuria 1g or more/day. To investigate if treatment decisions can be more accurately accomplished using individualized risk from the International IgAN Prediction Tool, we simulated allocation of a hypothetical immunosuppression therapy in an international cohort of adults with IgAN. Two decision rules for treatment were applied based on proteinuria of 1g or more/day or predicted risk from the Prediction Tool above a threshold probability. An appropriate decision was defined as immunosuppression allocated to patients experiencing the primary outcome (50% decline in eGFR or ESKD) and withheld otherwise. The net benefit and net reduction in treatment are the proportion of patients appropriately allocated to receive or withhold immunosuppression, adjusted for the harm from inappropriate decisions, calculated for all threshold probabilities from 0-100%. Of 3299 patients followed for 5.1 years, 522 (15.8%) experienced the primary outcome. Treatment allocation based solely on proteinuria of 1g or more/day had a negative net benefit (was harmful) because immunosuppression was increasingly allocated to patients without progressive disease. Compared to using proteinuria, treatment allocation using the Prediction Tool had a larger net benefit up to 23.4% (95% confidence interval 21.5-25.2%) and a larger net reduction in treatment up to 35.1% (32.3-37.8%). Thus, allocation of immunosuppression to high-risk patients with IgAN can be substantially improved using the Prediction Tool compared to using proteinuria.

External Validation of PATHFx Version 3.0 in Patients Treated Surgically and Nonsurgically for Symptomatic Skeletal Metastases

BACKGROUND

PATHFx is a clinical decision-support tool based on machine learning capable of estimating the likelihood of survival after surgery for patients with skeletal metastases. The applicability of any machine-learning tool depends not only on successful external validation in unique patient populations but also on remaining relevant as more effective systemic treatments are introduced. With advancements in the treatment of metastatic disease, it is our responsibility to patients to ensure clinical support tools remain contemporary and accurate.

QUESTION/PURPOSES

Therefore, we sought to (1) generate updated PATHFx models using recent data from patients treated at one large, urban tertiary referral center and (2) externally validate the models using two contemporary patient populations treated either surgically or nonsurgically with external-beam radiotherapy alone for symptomatic skeletal metastases for symptomatic lesions.

METHODS

After obtaining institutional review board approval, we collected data on 208 patients undergoing surgical treatment for pathologic fractures at Memorial Sloan Kettering Cancer Center between 2015 and 2018. These data were combined with the original PATHFx training set (n = 189) to create the final training set (n = 397). We then created six Bayesian belief networks designed to estimate the likelihood of 1-month, 3-month, 6-month, 12-month, 18-month, and 24-month survival after treatment. Bayesian belief analysis is a statistical method that allows data-driven learning to arise from conditional probabilities by exploring relationships between variables to estimate the likelihood of an outcome using observed data. For external validation, we extracted the records of patients treated between 2016 and 2018 from the International Bone Metastasis Registry and records of patients treated nonoperatively with external-beam radiation therapy for symptomatic skeletal metastases from 2012 to 2016 using the Military Health System Data Repository (radiotherapy-only group). From each record, we collected the date of treatment, laboratory values at the time of treatment initiation, demographic data, details of diagnosis, and the date of death. All records reported sufficient follow-up to establish survival (yes/no) at 24-months after treatment. For external validation, we applied the data from each record to the new PATHFx models. We assessed calibration (calibration plots), accuracy (Brier score), discriminatory ability (area under the receiver operating characteristic curve [AUC]).

RESULTS

The updated PATHFx version 3.0 models successfully classified survival at each time interval in both external validation sets and demonstrated appropriate discriminatory ability and model calibration. The Bayesian models were reasonably calibrated to the Memorial Sloan Kettering Cancer Center training set. External validation with 197 records from the International Bone Metastasis Registry and 192 records from the Military Health System Data Repository for analysis found Brier scores that were all less than 0.20, with upper bounds of the 95% confidence intervals all less than 0.25, both for the radiotherapy-only and International Bone Metastasis Registry groups. Additionally, AUC estimates were all greater than 0.70, with lower bounds of the 95% CI all greater than 0.68, except for the 1-month radiotherapy-only group. To complete external validation, decision curve analysis demonstrated clinical utility. This means it was better to use the PATHFx models when compared to the default assumption that all or no patients would survive at all time periods except for the 1-month models. We believe the favorable Brier scores (< 0.20) as well as DCA indicate these models are suitable for clinical use.

CONCLUSIONS

We successfully updated PATHFx using contemporary data from patients undergoing either surgical or nonsurgical treatment for symptomatic skeletal metastases. These models have been incorporated for clinical use on PATHFx version 3.0 (https://www.pathfx.org). Clinically, external validation suggests it is better to use PATHFx version 3.0 for all time periods except when deciding whether to give radiotherapy to patients with the life expectancy of less than 1 month. This is partly because most patients survived 1-month after treatment. With the advancement of medical technology in treatment and diagnosis for patients with metastatic bone disease, part of our fiduciary responsibility is to the main current clinical support tools.

LEVEL OF EVIDENCE

Level III, therapeutic study.

Prediction of mortality at one year after surgery for pertrochanteric fracture in the elderly via a Bayesian belief network

BACKGROUND

Pertrochanteric fractures in the elderly are common and associated with considerable mortality and disability. However, the predictors of the fracture mortality have been somewhat controversial. The aim of this study was to use univariate, multivariate analyses and a Bayesian belief network (BBN) model, which are graphic and intuitive to the clinician, to understand of the prognosis of pertrochanteric fractures.

METHODS

Records of patients undergoing surgery at our hospital between January 2013 and June 2018 were retrospectively reviewed. Univariate and multivariate regression as well as a machine-learned BBN model were used to estimate mortality at one year after surgery for pertrochanteric fracture in the elderly.

RESULTS

Complete data were available for 448 surgically treated patients who were followed up for 12 months (age ≥60 years). Multivariate regression analysis revealed that hypertension, diabetes mellitus, chronic obstructive pulmonary disease, albumin, serum potassium, blood urea nitrogen and blood lactate were independent risk factors for death in surgical treatment patients (P < 0.05). First-degree predictors of mortality following surgery were established: the number of comorbid diseases, serum albumin, blood lactate and blood urea nitrogen. Following cross-validation, the area under the ROC curve was 0.85 (95% CI: 0.76-0.91) for the one-year probability of postoperative mortality.

CONCLUSION

We believe cohesive models such as the Bayesian belief network can be useful as clinical decision-support tools and provide clinicians with information to the treatment of old pertrochanteric fracture. This method warrants further development and must be externally validated in other patient populations.

Principles of Management of Extremity Skeletal Metastasis

Understanding the epidemiology of extremity skeletal metastasis and the factors deciding the treatment decision-making are essential in developing a diagnostic and treatment strategy. This leads to optimum care and reduces disease-related burden. With the evolution of medical, radiation therapy, and surgical methods, cancer care has improved the quality of life for patients with improved survival and functional status in patients with skeletal metastasis. Based on the currently available literature, we have described a step-wise evaluation and management strategy of metastatic extremity bone disease. The present review article addresses various aspects and related controversies related to evaluation, staging, and treatment options in the management of extremity bone metastasis. This article also highlights the role of multidisciplinary involvement in management of extremity skeletal metastasis.

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.

Comparison of Logistic Regression and Bayesian Networks for Risk Prediction of Breast Cancer Recurrence

Purpose. For individualized follow-up, accurate prediction of locoregional recurrence (LRR) and second primary (SP) breast cancer risk is required. Current prediction models employ regression, but with large data sets, machine-learning techniques such as Bayesian Networks (BNs) may be better alternatives. In this study, logistic regression was compared with different BNs, built with network classifiers and constraint- and score-based algorithms. Methods. Women diagnosed with early breast cancer between 2003 and 2006 were selected from the Netherlands Cancer Registry (NCR) ( N = 37,320). BN structures were developed using 1) Bayesian network classifiers, 2) correlation coefficients with different cutoffs, 3) constraint-based learning algorithms, and 4) score-based learning algorithms. The different models were compared with logistic regression using the area under the receiver operating characteristic curve, an external validation set obtained from the NCR from 2007 and 2008 ( N = 12,308), and subgroup analyses for a high- and low-risk group. Results. The BNs with the most links showed the best performance in both LRR and SP prediction (c-statistic of 0.76 for LRR and 0.69 for SP). In the external validation, logistic regression generally outperformed the BNs in both SP and LRR (c-statistic of 0.71 for LRR and 0.64 for SP). The differences were nonetheless small. Although logistic regression performed best on most parts of the subgroup analysis, BNs outperformed regression with respect to average risk for SP prediction in low- and high-risk groups. Conclusions. Although estimates of regression coefficients depend on other independent variables, there is no assumed dependence relationship between coefficient estimators and the change in value of other variables as in the case of BNs. Nonetheless, this analysis suggests that regression is still more accurate or at least as accurate as BNs for risk estimation for both LRRs and SP tumors.

Is endoprosthesis safer than internal fixation for metastatic disease of the proximal femur? A systematic review

INTRODUCTION

Metastases to the proximal femur are usually managed surgically by tumor resection and reconstruction with an endoprosthesis, or by fixation with osteosynthesis. Still controversy remains regarding the most appropriate surgical treatment. We posed the following questions: (1) Is the frequency of surgical revision greater in patients treated with internal fixation than endoprosthetic reconstruction, and (2) Do complications that do not require surgery occur more frequently in patients treated with internal fixation rather than in those with endoprosthetic reconstruction?

MATERIALS AND METHODS

A systematic review was performed of those studies reporting on surgical revision and complication rates comparing the two surgical methods. Ten studies including 1107 patients met the inclusion criteria, three with high methodological quality, three intermediate, and four with lowquality, according to the STROBE guidelines.

RESULTS

At present, prosthetic dislocation is the most common complication observed in patients managed by prosthesis replacement of the proximal femur, while loosening was the main cause of reoperation in the fixation group. Time to reintervention ranged from 3 to 11.6 months for the prosthetic replacement and from 7.8 to 22.3 months for the fixation group. Non surgical complications, (mainly dislocations and infections) were more commonly observed in patients operated on by prosthetic replacement.

CONCLUSIONS

Implant related complications and surgery-related morbidity should be taken into account in the decision-making process for the surgical management of these patients. These data can improve the surgeon-patient communication and guide further studies on patients' survival and complications with respect to surgery.

Prediction of Low Birth Weight Delivery by Maternal Status and Its Validation: Decision Curve Analysis

Background:

In this study, we evaluated assessed elements connected with low birth weight (LBW) and used decision curve analysis (DCA) to define a scale to anticipate the probability of having a LBW newborn child.

Methods:

This hospital-based case–control study was led in Arak Hospital in Iran. The study included 470 mothers with LBW neonate and 470 mothers with natural neonates. Information were gathered by meeting moms utilizing preplanned organized questionnaire and from hospital records. The estimated probabilities of detecting LBW were calculated using the logistic regression and DCA to quantify the clinical consequences and its validation.

Results:

Factors significantly associated with LBW were premature membrane rupture (odds ratio [OR] = 3.18 [1.882–5.384]), former LBW infants (OR = 2.99 [1.510–5.932]), premature pain (OR = 2.70 [1.659–4.415]), hypertension in pregnancy (OR = 2.39 [1.429–4.019]), last trimester of pregnancy bleeding (OR = 2.58 [1.018–6.583]), mother age >30 (OR = 2.17 [1.350–3.498]). However, with DCA, the prediction model made on these 15 variables has a net benefit (NB) of 0.3110 is best predictive with the highest NB. NB has simple clinical interpretation and utilizing the model is what might as well be called a procedure that distinguished what might as well be called 31.1 LBW per 100 cases with no superfluous recognize.

Conclusions:

It is conceivable to foresee LBW utilizing a prediction model show in light of noteworthy hazard components connected with LBW. The majority of the hazard elements for LBW are preventable, and moms can be alluded amid early pregnancy to a middle which is furnished with facilities for administration of high hazard pregnancy and LBW infant.

Can a Bayesian Belief Network Be Used to Estimate 1-year Survival in Patients With Bone Sarcomas?

BACKGROUND

Extremity sarcoma has a preponderance to present late with advanced stage at diagnosis. It is important to know why these patients die early from sarcoma and to predict those at high risk. Currently we have mid- to long-term outcome data on which to counsel patients and support treatment decisions, but in contrast to other cancer groups, very little on short-term mortality. Bayesian belief network modeling has been used to develop decision-support tools in various oncologic diagnoses, but to our knowledge, this approach has not been applied to patients with extremity sarcoma.

QUESTIONS/PURPOSES

We sought to (1) determine whether a Bayesian belief network could be used to estimate the likelihood of 1-year mortality using receiver operator characteristic analysis; (2) describe the hierarchal relationships between prognostic and outcome variables; and (3) determine whether the model was suitable for clinical use using decision curve analysis.

METHODS

We considered all patients treated for primary bone sarcoma between 1970 and 2012, and excluded secondary metastasis, presentation with local recurrence, and benign tumors. The institution's database yielded 3499 patients, of which six (0.2%) were excluded. Data extracted for analysis focused on patient demographics (age, sex), tumor characteristics at diagnosis (size, metastasis, pathologic fracture), survival, and cause of death. A Bayesian belief network generated conditional probabilities of variables and survival outcome at 1 year. A lift analysis determined the hierarchal relationship of variables. Internal validation of 699 test patients (20% dataset) determined model accuracy. Decision curve analysis was performed comparing net benefit (capped at 85.5%) for all threshold probabilities (survival output from model).

RESULTS

We successfully generated a Bayesian belief network with five first-degree associates and describe their conditional relationship with survival after the diagnosis of primary bone sarcoma. On internal validation, the resultant model showed good predictive accuracy (area under the curve [AUC] = 0.767; 95% CI, 0.72-0.83). The factors that predict the outcome of interest, 1-year mortality, in order of relative importance are synchronous metastasis (6.4), patient's age (3), tumor size (2.1), histologic grade (1.8), and presentation with a pathologic fracture (1). Patient's sex, tumor location, and inadvertent excision were second-degree associates and not directly related to the outcome of interest. Decision curve analysis shows that clinicians can accurately base treatment decisions on the 1-year model rather than assuming all patients, or no patients, will survive greater than 1 year. For threshold probabilities less than approximately 0.5, the model is no better or no worse than assuming all patients will survive.

CONCLUSIONS

We showed that a Bayesian belief network can be used to predict 1-year mortality in patients presenting with a primary malignancy of bone and quantified the primary factors responsible for an increased risk of death. Synchronous metastasis, patient's age, and the size of the tumor had the largest prognostic effect. We believe models such as these can be useful as clinical decision-support tools and, when properly externally validated, provide clinicians and patients with information germane to the treatment of bone sarcomas.

CLINICAL RELEVANCE

Bone sarcomas are difficult to treat requiring multidisciplinary input to strategize management. An evidence-based survival prediction can be a powerful adjunctive to clinicians in this scenario. We believe the short-term predictions can be used to evaluate services, with 1-year mortality already being a quality indicator. Mortality predictors also can be incorporated in clinical trials, for example, to identify patients who are least likely to experience the side effects of experimental toxic chemotherapeutic agents.

Can We Estimate Short- and Intermediate-term Survival in Patients Undergoing Surgery for Metastatic Bone Disease?

BACKGROUND

Objective means of estimating survival can be used to guide surgical decision-making and to risk-stratify patients for clinical trials. Although a free, online tool ( www.pathfx.org ) can estimate 3- and 12-month survival, recent work, including a survey of the Musculoskeletal Tumor Society, indicated that estimates at 1 and 6 months after surgery also would be helpful. Longer estimates help justify the need for more durable and expensive reconstructive options, and very short estimates could help identify those who will not survive 1 month and should not undergo surgery. Thereby, an important use of this tool would be to help avoid unsuccessful and expensive surgery during the last month of life.

QUESTIONS/PURPOSES

We seek to provide a reliable, objective means of estimating survival in patients with metastatic bone disease. After generating models to derive 1- and 6-month survival estimates, we determined suitability for clinical use by applying receiver operator characteristic (ROC) (area under the curve [AUC] > 0.7) and decision curve analysis (DCA), which determines whether using PATHFx can improve outcomes, but also discerns in which kinds of patients PATHFx should not be used.

METHODS

We used two, existing, skeletal metastasis registries chosen for their quality and availability. Data from Memorial Sloan-Kettering Cancer Center (training set, n = 189) was used to develop two Bayesian Belief Networks trained to estimate the likelihood of survival at 1 and 6 months after surgery. Next, data from eight major referral centers across Scandinavia (n = 815) served as the external validation set-that is, as a means to test model performance in a different patient population. The diversity of the data between the training set from Memorial Sloan-Kettering Cancer Center and the Scandinavian external validation set is important to help ensure the models are applicable to patients in various settings with differing demographics and treatment philosophies. We considered disease-specific, laboratory, and demographic information, and the surgeon's estimate of survival. For each model, we calculated the area under the ROC curve (AUC) as a metric of discriminatory ability and the Net Benefit using DCA to determine whether the models were suitable for clinical use.

RESULTS

On external validation, the AUC for the 1- and 6-month models were 0.76 (95% CI, 0.72-0.80) and 0.76 (95% CI, 0.73-0.79), respectively. The models conferred a positive net benefit on DCA, indicating each could be used rather than assume all patients or no patients would survive greater than 1 or 6 months, respectively.

CONCLUSIONS

Decision analysis confirms that the 1- and 6-month Bayesian models are suitable for clinical use.

CLINICAL RELEVANCE

These data support upgrading www.pathfx.org with the algorithms described above, which is designed to guide surgical decision-making, and function as a risk stratification method in support of clinical trials. This updating has been done, so now surgeons may use any web browser to generate survival estimates at 1, 3, 6, and 12 months after surgery, at no cost. Just as short estimates of survival help justify palliative therapy or less-invasive approaches to stabilization, more favorable survival estimates at 6 or 12 months are used to justify more durable, complicated, and expensive reconstructive options.

Prediction of survival after surgery due to skeletal metastases in the extremities

AIMS

The purpose of this study was to develop a prognostic model for predicting survival of patients undergoing surgery owing to metastatic bone disease (MBD) in the appendicular skeleton.

METHODS

We included a historical cohort of 130 consecutive patients (mean age 64 years, 30 to 85; 76 females/54 males) who underwent joint arthroplasty surgery (140 procedures) owing to MBD in the appendicular skeleton during the period between January 2003 and December 2008. Primary cancer, pre-operative haemoglobin, fracture versus impending fracture, Karnofsky score, visceral metastases, multiple bony metastases and American Society of Anaesthesiologist's score were included into a series of logistic regression models. The outcome was the survival status at three, six and 12 months respectively. Results were internally validated based on 1000 cross-validations and reported as time-dependent area under the receiver-operating characteristic curves (AUC) for predictions of outcome.

RESULTS

The predictive scores obtained showed AUC values of 79.1% (95% confidence intervals (CI) 65.6 to 89.6), 80.9% (95% CI 70.3 to 90.84) and 85.1% (95% CI 73.5 to 93.9) at three, six and 12 months.

DISCUSSION

In conclusion, we have presented and internally validated a model for predicting survival after surgery owing to MBD in the appendicular skeleton. The model is the first, to our knowledge, built solely on material from patients who only had surgery in the appendicular skeleton.

TAKE HOME MESSAGE

Applying this prognostic model will help determine whether the patients' anticipated survival makes it reasonable to subject them to extensive reconstructive surgery for which there may be an extended period of rehabilitation. Cite this article: Bone Joint J 2016;98-B:271-7.

Metastatic bone disease: A review of survival, prognostic factors and outcomes following surgical treatment of the appendicular skeleton

Survival data and prognostic factors may help to provide insight when deciding on the appropriate orthopaedic treatment for patients presenting with metastatic bone disease. This review was conducted to look at the outcomes following orthopaedic surgery for metastatic lesions in the extremities. The literature was identified through the Medline and Embase database and further refined via a set of inclusion and exclusion criteria. Overall, patients presenting with metastatic bone disease from renal cell cancer or breast cancer had the longest survival rate. Important factors found to predict prognosis was the presence of visceral metastasis, multiple metastases, pathological fracture and the type of primary tumour involved. These prognostic factors may help to direct future inquiry into metastatic bone disease and help determine the type of surgery to use in a metastatic setting in order to avoid complications and unnecessary revisions as well as provide durability.

Extent of Surgery Does Not Influence 30-Day Mortality in Surgery for Metastatic Bone Disease: An Observational Study of a Historical Cohort

Estimating patient survival has hitherto been the main focus when treating metastatic bone disease (MBD) in the appendicular skeleton. This has been done in an attempt to allocate the patient to a surgical procedure that outlives them. No questions have been addressed as to whether the extent of the surgery and thus the surgical trauma reduces survival in this patient group. We wanted to evaluate if perioperative parameters such as blood loss, extent of bone resection, and duration of surgery were risk factors for 30-day mortality in patients having surgery due to MBD in the appendicular skeleton. We retrospectively identified 270 consecutive patients who underwent joint replacement surgery or intercalary spacing for skeletal metastases in the appendicular skeleton from January 1, 2003 to December 31, 2013. We collected intraoperative (duration of surgery, extent of bone resection, and blood loss), demographic (age, gender, American Society of Anesthesiologist score [ASA score], and Karnofsky score), and disease-specific (primary cancer) variables. An association with 30-day mortality was addressed using univariate and multivariable analyses and calculation of odds ratio (OR). All patients were included in the analysis. ASA score 3 + 4 (OR 4.16 [95% confidence interval, CI, 1.80-10.85], P = 0.002) and Karnofsky performance status below 70 (OR 7.34 [95% CI 3.16-19.20], P < 0.001) were associated with increased 30-day mortality in univariate analysis. This did not change in multivariable analysis. No parameters describing the extent of the surgical trauma were found to be associated with 30-day mortality. The 30-day mortality in patients undergoing surgery for MBD is highly dependent on the general health status of the patients as measured by the ASA score and the Karnofsky performance status. The extent of surgery, measured as duration of surgery, blood loss, and degree of bone resection were not associated with 30-day mortality.

Prognostic factors for patients with skeletal metastases from carcinoma of the breast

Aims

Surgical intervention in patients with bone metastases from breast cancer is dependent on the estimated survival of the patient. The purpose of this paper was to identify factors that would predict survival so that specific decisions could be made in terms of surgical (or non-surgical) management.

Methods

The records of 113 consecutive patients (112 women) with metastatic breast cancer were analysed for clinical, radiological, serological and surgical outcomes. Their median age was 61 years (interquartile range 29 to 90) and the median duration of follow-up was 1.6 years (standard deviation (sd) 1.9, 95% confidence interval (CI) 0 to 5.9). The cumulative one- and five-year rates of survival were 68% and 16% (95% Cl 60 to 77 and 95% CI 10 to 26, respectively).

Results

Linear discriminant analysis identified a ‘quadruple A’ predictor of survival by reclassifying the sum of the albumin, adjusted calcium, alkaline phosphatase and age covariates each multiplied by a determined factor. The accuracy of this ‘quadruple A’ predictor was 90% with a sensitivity of 100% and a specificity of 88%. A receiver operating characteristic (ROC) curve revealed an area under the curve of 79%. Survival analysis for this ‘quadruple A’ predictor (<  = one or > one year survival) was statistically significant using the log rank test (p = 0.0004) and Cox proportional hazard (p = 0.001). Multivariate analysis showed the 'quadruple A' predictor to be the only independent predictor of survival (p = 0.01).

Discussion

The 'quadruple A' predictor, together with other positive predictors of survival, can be used by oncologists, orthopaedic and breast surgeons to estimate survival and therefore guide management. Cite this article: Bone Joint J 2016;98-B:266–70.

Preventing Heterotopic Ossification in Combat Casualties-Which Models Are Best Suited for Clinical Use?

BACKGROUND

To prevent symptomatic heterotopic ossification (HO) and guide primary prophylaxis in patients with combat wounds, physicians require risk stratification methods that can be used early in the postinjury period. There are no validated models to help guide clinicians in the treatment for this common and potentially disabling condition.

QUESTIONS/PURPOSES

We developed three prognostic models designed to estimate the likelihood of wound-specific HO formation and compared them using receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) to determine (1) which model is most accurate; and (2) which technique is best suited for clinical use.

METHODS

We obtained muscle biopsies from 87 combat wounds during the first débridement in the United States, all of which were evaluated radiographically for development of HO at a minimum of 2 months postinjury. The criterion for determining the presence of HO was the ability to see radiographic evidence of ectopic bone formation within the zone of injury. We then quantified relative gene expression from 190 wound healing, osteogenic, and vascular genes. Using these data, we developed an Artificial Neural Network, Random Forest, and a Least Absolute Shrinkage and Selection Operator (LASSO) Logistic Regression model designed to estimate the likelihood of eventual wound-specific HO formation. HO was defined as any HO visible on the plain film within the zone of injury. We compared the models accuracy using area under the ROC curve (area under the curve [AUC]) as well as DCA to determine which model, if any, was better suited for clinical use. In general, the AUC compares models based solely on accuracy, whereas DCA compares their clinical utility after weighing the consequences of under- or overtreatment of a particular disorder.

RESULTS

Both the Artificial Neural Network and the LASSO logistic regression models were relatively accurate with AUCs of 0.78 (95% confidence interval [CI], 0.72-0.83) and 0.75 (95% CI, 0.71-0.78), respectively. The Random Forest model returned an AUC of only 0.53 (95% CI, 0.48-0.59), marginally better than chance alone. Using DCA, the Artificial Neural Network model demonstrated the highest net benefit over the broadest range of threshold probabilities, indicating that it is perhaps better suited for clinical use than the LASSO logistic regression model. Specifically, if only patients with greater than 25% risk of developing HO received prophylaxis, for every 100 patients, use of the Artificial Network Model would result in six fewer patients who unnecessarily receive prophylaxis compared with using the LASSO regression model while not missing any patients who might benefit from it.

CONCLUSIONS

Our findings suggest that it is possible to risk-stratify combat wounds with regard to eventual HO formation early in the débridement process. Using these data, the Artificial Neural Network model may lead to better patient selection when compared with the LASSO logistic regression approach. Future prospective studies are necessary to validate these findings while focusing on symptomatic HO as the endpoint of interest.

LEVEL OF EVIDENCE

Level III, prognostic study.

How do we estimate survival? External validation of a tool for survival estimation in patients with metastatic bone disease-decision analysis and comparison of three international patient populations

Background

We recently developed a clinical decision support tool, capable of estimating the likelihood of survival at 3 and 12 months following surgery for patients with operable skeletal metastases. After making it publicly available on www.PATHFx.org, we attempted to externally validate it using independent, international data.

Methods

We collected data from patients treated at 13 Italian orthopaedic oncology referral centers between 2010 and 2013, then applied to PATHFx, which generated a probability of survival at three and 12-months for each patient. We assessed accuracy using the area under the receiver-operating characteristic curve (AUC), clinical utility using Decision Curve Analysis (DCA), and compared the Italian patient data to the training set (United States) and first external validation set (Scandinavia).

Results

The Italian dataset contained 287 records with at least 12 months follow-up information. The AUCs for the three-month and 12-month estimates was 0.80 and 0.77, respectively. There were missing data, including the surgeon’s estimate of survival that was missing in the majority of records. Physiologically, Italian patients were similar to patients in the training and first validation sets. However notable differences were observed in the proportion of those surviving three and 12-months, suggesting differences in referral patterns and perhaps indications for surgery.

Conclusions

PATHFx was successfully validated in an Italian dataset containing missing data. This study demonstrates its broad applicability to European patients, even in centers with differing treatment philosophies from those previously studied.

A model to predict limb salvage in severe combat-related open calcaneus fractures

BACKGROUND

Open calcaneus fractures can be limb threatening and almost universally result in some measure of long-term disability. A major goal of initial management in patients with these injuries is setting appropriate expectations and discussing the likelihood of limb salvage, yet there are few tools that assist in predicting the outcome of this difficult fracture pattern.

QUESTIONS/PURPOSES

We developed two decision support tools, an artificial neural network and a logistic regression model, based on presenting data from severe combat-related open calcaneus fractures. We then determined which model more accurately estimated the likelihood of amputation and which was better suited for clinical use.

METHODS

Injury-specific data were collected from wounded active-duty service members who sustained combat-related open calcaneus fractures between 2003 and 2012. One-hundred fifty-five open calcaneus fractures met inclusion criteria. Median followup was 3.5 years (interquartile range: 1.5, 5.1 years), and amputation rate was 44%. We developed an artificial neural network designed to estimate the likelihood of amputation, using information available on presentation. For comparison, a conventional logistic regression model was developed with variables identified on univariate analysis. We determined which model more accurately estimated the likelihood of amputation using receiver operating characteristic analysis. Decision curve analysis was then performed to determine each model's clinical utility.

RESULTS

An artificial neural network that contained eight presenting features resulted in smaller error. The eight features that contributed to the most predictive model were American Society of Anesthesiologist grade, plantar sensation, fracture treatment before arrival, Gustilo-Anderson fracture type, Sanders fracture classification, vascular injury, male sex, and dismounted blast mechanism. The artificial neural network was 30% more accurate, with an area under the curve of 0.8 (compared to 0.65 for logistic regression). Decision curve analysis indicated the artificial neural network resulted in higher benefit across the broadest range of threshold probabilities compared to the logistic regression model and is perhaps better suited for clinical use.

CONCLUSIONS

This report demonstrates an artificial neural network was capable of accurately estimating the likelihood of amputation. Furthermore, decision curve analysis suggested the artificial neural network is better suited for clinical use than logistic regression. Once properly validated, this may provide a tool for surgeons and patients faced with combat-related open calcaneus fractures in which decisions between limb salvage and amputation remain difficult.