Factors associated with skeletal-related events in patients with bone metastatic melanoma: A retrospective study of 481 patients.

OBJECTIVES: Metastatic bone disease is estimated to develop in up to 17% of patients with melanoma, compromising skeleton integrity resulting in skeletal-related events (SREs), which impair quality of life and reduce survival. The objective of the study was to investigate (1) the proportion of melanoma patients developing SREs following diagnosis of bone metastasis and (2) the predictors for SREs in this patient cohort. METHODS: Four hundred and eighty-one patients with bone metastatic melanoma from two tertiary centers in the United States from 2008 to 2018 were included. The primary outcome was 90-day and 1-year occurrence of a SRE, including pathological fractures of bones, cord compression, hypercalcemia, radiotherapy, and surgery. Fine-Gray regression analysis was performed for overall SREs and pathological fracture, with death as a competing risk. RESULTS: By 1-year, 52% (258/481) of patients experienced SREs, and 28% (137/481) had a pathological fracture. At 90-day, lytic lesions, bone pain, elevated calcium and absolute lymphocyte, and decreased albumin and hemoglobin were associated with higher SRE risk. The same factors, except for decreased hemoglobin, were shown to predict development of SREs at 1-year. CONCLUSION: The high incidence of SREs and pathological fractures warrants vigilance using the identified factors in this study and preventative measures during clinical oncological care.

Incidence, Risk Factors, and Survival of Bone Metastases and Skeletal-Related Events in Melanoma Patients: A Systematic Review and Quality Assessment of 29 Studies.

Background: Skeletal metastases make up 17% of all metastases from advanced-stage melanoma. Bone metastases are associated with increased morbidity and mortality and decreased quality of life due to their association with skeletal-related events (SREs), including pathological fracture, spinal cord compression, hypercalcemia, radiotherapy, and surgery. The study aimed to determine the incidence of bone metastases and SREs in melanoma, identify possible risk factors for the development of bone metastases and SREs, and investigate survival rates in this patient population. Methods: A computer-based literature search was conducted using Pubmed, Embase, and Cochrane Central Register of Controlled Trials up to July 2023. The Newcastle-Ottawa Quality Assessment Scale (NOS) was utilized for quality assessment. Study characteristics, patient information, risk factors for developing bone metastases and SREs, and characteristics for survival were recorded. Results: We included 29 studies. The average bone metastasis-free interval ranged from four to 72 months. Incidence of bone metastases varied from 2 % to 49 % across 14 studies. 69 % (20/29) of studies described the location of bone metastases, with 24 % (7/29) focusing solely on spinal metastases. In one study, 129 SREs were recorded in 71 % (59/83) of the patient cohort, with various manifestations. The use of bone-directed agents was independently associated with lower risk of SREs. Survival after detection of bone metastasis ranged from three to 13 months. Factors associated with survival included clinical, tumor-related, and treatment features. Conclusion: This review highlights the notable prevalence and risk factors of developing bone metastases and subsequent SREs in patients with melanoma. The surge in bone metastases poses a challenge in complication management, given the high prevalence of SREs. While this study offers a comprehensive overview of the incidence, risk factors, and outcomes associated with bone metastases and SREs in melanoma patients that may guide patient and physician decision-making, a notable gap lies in the limited availability of high-quality data and the heterogeneous design of the existing literature. Future research should address predictive factors for bone metastases and SREs in melanoma to facilitate patient and physician decision-making and ultimately improve outcomes in this patient population.

Prediction of 30-Day Mortality Following Revision Total Hip and Knee Arthroplasty: Machine Learning Algorithms Outperform CARDE-B, 5-Item, and 6-Item Modified Frailty Index Risk Scores.

BACKGROUND: Although risk calculators are used to prognosticate postoperative outcomes following revision total hip and knee arthroplasty (total joint arthroplasty [TJA]), machine learning (ML) based predictive tools have emerged as a promising alternative for improved risk stratification. This study aimed to compare the predictive ability of ML models for 30-day mortality following revision TJA to that of traditional risk-assessment indices such as the CARDE-B score (congestive heart failure, albumin (< 3.5 mg/dL), renal failure on dialysis, dependence for daily living, elderly (> 65 years of age), and body mass index (BMI) of < 25 kg/m2), 5-item modified frailty index (5MFI), and 6MFI. METHODS: Adult patients undergoing revision TJA between 2013 and 2020 were selected from the American College of Surgeons National Surgical Quality Improvement Program database and randomly split 80:20 to compose the training and validation cohorts. There were 3 ML models - extreme gradient boosting, random forest, and elastic-net penalized logistic regression (NEPLR) - that were developed and evaluated using discrimination, calibration metrics, and accuracy. The discrimination of CARDE-B, 5MFI, and 6MFI scores was assessed individually and compared to that of ML models. RESULTS: All models were equally accurate (Brier score = 0.005) and demonstrated outstanding discrimination with similar areas under the receiver operating characteristic curve (AUCs, extreme gradient boosting = 0.94, random forest = NEPLR = 0.93). The NEPLR was the best-calibrated model overall (slope = 0.54, intercept = -0.004). The CARDE-B had the highest discrimination among the scores (AUC = 0.89), followed by 6MFI (AUC = 0.80), and 5MFI (AUC = 0.68). Albumin < 3.5 mg/dL and BMI (< 30.15) were the most important predictors of 30-day mortality following revision TJA. CONCLUSIONS: The ML models outperform traditional risk-assessment indices in predicting postoperative 30-day mortality after revision TJA. Our findings highlight the utility of ML for risk stratification in a clinical setting. The identification of hypoalbuminemia and BMI as prognostic markers may allow patient-specific perioperative optimization strategies to improve outcomes following revision TJA.