Development and external validation of a machine learning model for prediction of survival in extremity leiomyosarcoma

PURPOSE

Machine learning (ML) models have been used to predict cancer survival in several sarcoma subtypes. However, none have investigated extremity leiomyosarcoma (LMS). ML is a powerful tool that has the potential to better prognosticate extremity LMS.

METHODS

The Surveillance, Epidemiology, and End Results (SEER) database was queried for cases of histologic extremity LMS (n = 634). 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 extremity LMS patients (n = 46).

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 0.75-0.76 at the 5-year time point. The Random Forest (RF) model was the best performing model and used for external validation. This model also performed best at 1-year and worst at 5-year on external validation with c-statistics of 0.90 and 0.87, respectively. The RF model was well calibrated on external validation. This model has been made publicly available at https://rachar.shinyapps.io/lms_app/ CONCLUSIONS: ML models had excellent performance for survival prediction of extremity LMS. Future studies incorporating a larger institutional cohort may be needed to further validate the ML model for LMS prognostication.

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.

Total Knee Arthroplasty for Osteoarthritis Is Uncommon after Intralesional Curettage in Giant Cell Tumor of Bone

Giant cell tumor of bone (GCTB) is most often treated with intralesional curettage; however, periarticular lesions have been shown to increase risk for osteoarthritis. Additionally, the location of these lesions may occasionally preclude a joint-sparing procedure in recurrent tumors. This study sought to investigate rates of secondary arthroplasty in long-term follow-up of knee GCTB. Cases of knee GCTB treated at our institution were reviewed. Rates of recurrence and secondary arthroplasty were recorded, and Kaplan-Meier survival analyses were performed. The records of 40 patients were reviewed. Local recurrence occurred in 25% of patients. The 1-, 5-, and 10-year recurrence-free survival (RFS) probability was 87.4% (95% CI, 77.0-97.7), 72.4% (95% CI, 57.6-87.2), and 72.4% (95% CI, 57.6-87.2), respectively. Function improved after surgery with a mean preoperative MSTS score of 14.9 (standard deviation [SD] 8.4) and mean postoperative MSTS score of 25.1 (SD 5.6) (p <0.001). Three patients had evidence of radiographic osteoarthritis at the last follow-up though they did not require arthroplasty. Arthroplasty was performed as a secondary procedure in six patients. Five patients underwent arthroplasty for recurrent tumors after initial treatment with curettage and one patient underwent patellar arthroplasty for osteoarthritis after initial treatment with an allograft composite arthroplasty. Arthroplasty is performed as a secondary procedure in patients with GCTB at a relatively infrequent rate and more often for cases of recurrent disease than for osteoarthritis. Overall, patients treated for GCTB have improved functional outcomes after surgery than before. Large, multi-institutional studies may be required to assess the incidence of secondary osteoarthritis requiring arthroplasty as this was an infrequent finding in our cohort.

External validation of machine learning models for prediction of survival in undifferentiated pleomorphic sarcoma

e13551

Background: 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 from 2004 to 2015 for cases of histologically confirmed undifferentiated pleomorphic sarcoma (UPS) and malignant fibrous histiocytoma (MFH). Patient, tumor, and treatment characteristics were recorded, and various machine learning (ML) models were built to predict 1-, 3-, and 5-year survival. The best performing ML models were externally validated using an institutional cohort of UPS patients. 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 0.71 to 0.73 at the 5-year time point. Similarly, all ML models performed best at 1-year and worst at 5-year on external validation. The best performing models had c-statistics of 0.81 at the 5-year time point on external validation, demonstrating good performance in survival prediction. Conclusions: 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. [Table: see text]