Publications by authors named "Sandrine Mercier"
Background: Phase I trials historically involved heavily pretreated patients (pts) with no more effective therapeutic options available and with poor expected outcomes. There are scare data regarding profile and outcomes of pts enrolled into modern phase I trials. Here, we sought to provide an overview of pts' profile and outcome into phase I trials at Gustave Roussy (GR).
View Article and Find Full Text PDFArticle Synopsis
- Early discontinuation in early-phase oncology trials impacts over one third of patients and complicates study timelines and costs; the research aims to predict successful completion of screening and dose-limiting toxicity periods using automated report analysis.
- A machine learning model was developed using a large dataset of consultation reports to predict patient outcomes, achieving solid performance metrics (F1 score 0.80, recall 0.81) and demonstrating potential to significantly reduce screening failure rates from 39.8% to 12.8%.
- The study highlights the importance of using machine learning with semantic analysis as a promising approach for improving patient selection in clinical trials, focusing on key terms related to disease characteristics and laboratory findings
Objective: To estimate the sensitivity of International Classification of Diseases, Tenth revision (ICD-10) hospital discharge diagnosis codes for identifying deep vein thrombosis (DVT) and pulmonary embolism (PE).
Study Design And Setting: We compared predefined ICD-10 discharge diagnosis codes with the diagnoses that were prospectively recorded for 1,375 patients with suspected DVT or PE who were enrolled at 25 hospitals in France. Sensitivity was calculated as the percentage of patients identified by predefined ICD-10 codes among positive cases of acute symptomatic DVT or PE confirmed by objective testing.