Development of machine learning model algorithm for prediction of 5‐year soft tissue myxoid liposarcoma survival

Abstract

Background: Predicting survival in myxoid liposarcoma (MLS) patients is very challenging given its propensity to metastasize and the controversial role of adjuvant therapy. The purpose of this study was to develop a machine-learning algorithm for the prediction of survival at five years for patients with MLS and externally validate it using our institutional cohort. Methods: Two databases, the surveillance, epidemiology, and end results program (SEER) database and an institutional database, were used in this study. Five machine learning models were created based on the SEER database and performance was rated using the TRIPOD criteria. The model that performed best on the SEER data was again tested on our institutional database. Results:The net-elastic penalized logistic regression model was the best according to our performance indicators. This model had an area under the curve (AUC) of 0.85 when compared to the SEER testing data and an AUC of 0.76 when tested against institutional database. An application to use this calculator is available at https://sorg-apps.shinyapps.io/myxoid_liposarcoma/. Conclusion:MLS is a soft-tissue sarcoma with adjunct treatment options that are, in part, decided by prognostic survival. We developed the first machine-learning predictive algorithm specifically for MLS using the SEER registry that retained performance during external validation with institutional data.

Comparison of nomogram with machine learning techniques for prediction of overall survival in patients with retroperitoneal liposarcoma

“…Several studies have validated the accuracy of machine learning techniques in prognostic assessment of patients with different types of liposarcoma and have helped RP-LPS patients with reasonable risk strati cation. [20][21][22] Kamalapathy et al developed a machine learning model for survival risk strati cation of patients with soft tissue myxoid liposarcoma using clinicopathological, social and demographic data. A machine learning-based model was developed to predict 5-year overall survival in myxoid liposarcoma patients.…”

“…A machine learning-based model was developed to predict 5-year overall survival in myxoid liposarcoma patients. [20] These studies concluded that machine learning-based approaches enhanced the ability of clinicians to correctly estimate the risk of survival in patients with myxoid liposarcoma. [20][21][22] Therefore, effective and e cient treatment plans-intensive or non-intensive regimens-can be developed to improve the quality of care and survival of patients with myxoid liposarcoma.…”

Predicting five-year mortality in soft-tissue sarcoma patients

“…Five popular machine learning models were created using random forest (RF), artificial neural network (ANN), gradient boosted tree (GBT), naïve Bayes (NB), and support vector machine (SVM) in order to predict patients with STS who would experience cancer-related mortality. These models were chosen based on previous machine learning studies that focused on binary classifications, 9,10 and have previously been examined and differentiated within the context of orthopaedics. 17…”

“…the seer database is commonly used in musculoskeletal oncology for large data population studies. 9,10 for this study, we selected the "seer 17 regs research data (2000 to 2019)" database from 2004 to 2017 by using seer*stat 8.3.8 software (Usa). this database published cancer incidence and survival data covering approximately 26.5% of the Usa population.…”

What’s New in Musculoskeletal Tumor Surgery

“…Advances in our knowledge of the evaluation, treatment, and outcome of patients with soft-tissue sarcomas continue. Table II shows several recent studies on soft-tissue tumors [26][27][28][29][30][31][32][33] . The role of radiation therapy in patients with superficial softtissue sarcomas has been controversial and poorly defined.…”