Developing machine learning–based prognostic models for gestational choriocarcinoma: Insights into treatment efficacy and patient survival.

person Mustafa Alshwayyat Jordan University of Science and Technology, Aydoun-Irbid, Jordan info_outline Mustafa Alshwayyat, Sakhr Abdulsalam Alshwayyat, Haya Kamal, Tala Abdulsalam Alshwayyat, Abdalwahab Alenezy

Authors person Mustafa Alshwayyat Jordan University of Science and Technology, Aydoun-Irbid, Jordan info_outline Mustafa Alshwayyat, Sakhr Abdulsalam Alshwayyat, Haya Kamal, Tala Abdulsalam Alshwayyat, Abdalwahab Alenezy Organizations Jordan University of Science and Technology, Aydoun-Irbid, Jordan, Jordan University of Science and Technology, Irbid, Jordan, Jordan University of Science & Technology, Irbid, Jordan, Jordan University of Science and Technology, Jordan, Irbid, Jordan Abstract Disclosures Research Funding No funding sources reported Background: Gestational Choriocarcinoma (GCC) is a highly aggressive tumor derived from syncytiotrophoblasts. There is currently controversy surrounding the initiation of chemotherapy for patients with GCC. We aimed to investigate the influence of chemotherapy on survival rates and develop machine-learning-based prognostic models for GCC patients to improve treatment decisions and personalized medicine. Methods: Data were obtained from the Surveillance, Epidemiology, and End Results database (2000–2020). Patients who met any of the following criteria were excluded: diagnosis not confirmed by histology, previous history of cancer or with other concurrent malignancies, and unknown data. To identify prognostic variables, we conducted Cox regression analysis and constructed prognostic models using machine learning (ML) algorithms to predict the 5-year survival. Patient records were randomly divided into training (70 %) and validation (30 %) sets. A validation method incorporating the area under the curve (AUC) of the receiver operating characteristic curve was used to validate the accuracy and reliability of the ML models. We also investigated the role of multiple therapeutic options using Kaplan-Meier survival analysis. Results: This study included 732 patients, of whom 283 received chemotherapy, 116 underwent surgery alone, and 333 underwent both surgery and chemotherapy. Most patients (54.5%) were aged 30 years or older, with a median age of 32 years. The largest racial group was white, comprising 66.4% of cases, followed by black (16.7 %). Furthermore, most cases were localized (n=262), and only 13% presented with stage IV disease and 44.3% with metastasis. Survival analysis showed no significant differences in survival between the treatment modalities. Multivariate Cox regression analysis identified older age, unmarried status, and AJCC stage II as significant prognostic factors. The random forest classifier (RFC) and K-Nearest Neighbors (KNN) were the most accurate ML models, with the AJCC stage, race, and SEER stage as key factors. Performance metrics for all ML algorithms are summarized in the Table. Conclusions: Our study provides a novel and practical tool for GCC prognosis and management. Although our tool offers a valuable resource for personalized clinical decisions, further research is needed to better understand the role of chemotherapy in GCC treatment and its impact on patient outcomes. Machine learning (ML) algorithms performance. ML Algorithm 10-fold Cross Validation Accuracy Mean Bootstrap Estimate [95% CI] AUC LR 0.704 0.65 0.75 [0.63–0.83] 0.715 KNN 0.829 0.68 0.64 [0.56–0.81] 0.879 RFC 0.783 0.79 0.81 [0.72–0.90] 0.879 GBC 0.775 0.76 0.80 [0.71–0.89] 0.853 MLP 0.720 0.65 0.76 [0.67–0.85] 0.732