Dataset Information

Development of Machine Learning Models to Predict Platinum Sensitivity of High-Grade Serous Ovarian Carcinoma.

ABSTRACT: To support the implementation of individualized disease management, we aimed to develop machine learning models predicting platinum sensitivity in patients with high-grade serous ovarian carcinoma (HGSOC). We reviewed the medical records of 1002 eligible patients. Patients' clinicopathologic characteristics, surgical findings, details of chemotherapy, treatment response, and survival outcomes were collected. Using the stepwise selection method, based on the area under the receiver operating characteristic curve (AUC) values, six variables associated with platinum sensitivity were selected: age, initial serum CA-125 levels, neoadjuvant chemotherapy, pelvic lymph node status, involvement of pelvic tissue other than the uterus and tubes, and involvement of the small bowel and mesentery. Based on these variables, predictive models were constructed using four machine learning algorithms, logistic regression (LR), random forest, support vector machine, and deep neural network; the model performance was evaluated with the five-fold cross-validation method. The LR-based model performed best at identifying platinum-resistant cases with an AUC of 0.741. Adding the FIGO stage and residual tumor size after debulking surgery did not improve model performance. Based on the six-variable LR model, we also developed a web-based nomogram. The presented models may be useful in clinical practice and research.

SUBMITTER: Hwangbo S

PROVIDER: S-EPMC8070756 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Expression of the progesterone receptor (PR) has been reported to influence survival outcomes in patients with ovarian high-grade serous carcinoma (HGSC). In the present study, we attempted to investigate the association among PR and its isoforms' expression, platinum sensitivity, and survival in ovarian HGSC. This retrospective study reviewed ovarian HGSC patients who received surgery followed by adjuvant chemotherapy. We analyzed total PR and PR isoform-B (PR-B) expression by immunohistochemical staining and quantified using the H-score. Then, we compared platinum sensitivity and survival outcomes between those patients with weak and strong PR-B expression. Cisplatin viability assays were carried out in ovarian HGSC cell lines (OC-3-VGH and OVCAR-3) with different PR-B expression. Among 90 patients, 49 and 41 patients were considered to have platinum-sensitive and platinum-resistant disease, respectively. Pearson's correlation model showed that the H-score of total PR correlated positively with PR-B (r = 0.813). The PR-B H-score of tumors was significantly higher in the platinum-sensitive group (p = 0.004). Multivariate analysis revealed that the PR-B H-score and optimal debulking status were independent factors predicting platinum sensitivity. When compared with strong PR-B expression, patients with weak PR-B had significantly poorer progression-free (p = 0.021) and cancer-specific survival (p = 0.046). In a cell model, cisplatin-resistant OC-3-VGH cells expressed a lower level of PR-B than wild-type cells. Overexpression of PR-B or progesterone could increase cisplatin sensitivity in both OC-3-VGH and OVCAR-3 cells via the mechanism of promoting cisplatin-related apoptosis. When compared to weak PR-B, ovarian HGSC patients with a strong PR-B expression had a better chance of platinum sensitivity and survival, and this finding was compatible with our experimental results. Progesterone seemed to be a platinum sensitizer, but the value of adding progesterone in the treatment of ovarian HGSC should be further investigated.

Project description:We developed and validated a multimodal radiomic machine learning approach to noninvasively predict the expression of lymphocyte cell-specific protein-tyrosine kinase (LCK) expression and clinical prognosis of patients with high-grade serous ovarian cancer (HGSOC). We analyzed gene enrichment using 343 HGSOC cases extracted from The Cancer Genome Atlas. The corresponding biomedical computed tomography images accessed from The Cancer Imaging Archive were used to construct the radiomic signature (Radscore). A radiomic nomogram was built by combining the Radscore and clinical and genetic information based on multimodal analysis. We compared the model performances and clinical practicability via area under the curve (AUC), Kaplan-Meier survival, and decision curve analyses. LCK mRNA expression was associated with the prognosis of HGSOC patients, serving as a significant prognostic marker of the immune response and immune cells infiltration. Six radiomic characteristics were chosen to predict the expression of LCK and overall survival (OS) in HGSOC patients. The logistic regression (LR) radiomic model exhibited slightly better predictive abilities than the support vector machine model, as assessed by comparing combined results. The performance of the LR radiomic model for predicting the level of LCK expression with five-fold cross-validation achieved AUCs of 0.879 and 0.834, respectively, in the training and validation sets. Decision curve analysis at 60 months demonstrated the high clinical utility of our model within thresholds of 0.25 and 0.7. The radiomic nomograms were robust and displayed effective calibration. Abnormally high expression of LCK in HGSOC patients is significantly correlated with the tumor immune microenvironment and can be used as an essential indicator for predicting the prognosis of HGSOC. The multimodal radiomic machine learning approach can capture the heterogeneity of HGSOC, noninvasively predict the expression of LCK, and replace LCK for predictive analysis, providing a new idea for predicting the clinical prognosis of HGSOC and formulating a personalized treatment plan.

Dataset Information

Development of Machine Learning Models to Predict Platinum Sensitivity of High-Grade Serous Ovarian Carcinoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets