External validation: a simulation study to compare cross-validation versus holdout or external testing to assess the performance of clinical prediction models using PET data from DLBCL patients

Article Oncology

Generation and validation of a PET radiomics model that predicts survival in diffuse large B cell lymphoma treated with R-CHOP14: A SAKK 38/07 trial post-hoc analysis

Luca Ceriani et al.

Summary: Functional parameters from positron emission tomography (PET) show promise as biomarkers in different lymphoma subtypes, with radiomics features extracted using PyRadiomics Python package. A prognostic radiomics score (RS) based on PET-derived data was able to significantly predict progression-free survival (PFS), cause-specific survival (CSS), and overall survival (OS) in both testing and validation sets of DLBCL patients, showing better predictive accuracy compared to clinical international indices.

HEMATOLOGICAL ONCOLOGY (2022)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

18F-FDG PET baseline radiomics features improve the prediction of treatment outcome in diffuse large B-cell lymphoma

Jakoba J. Eertink et al.

Summary: The study found that combining baseline radiomics with currently used clinical predictors in DLBCL patients can more accurately identify high-risk patients. Adding radiomics features to clinical predictors significantly improves positive predictive value, leading to a more accurate selection of high-risk patients compared to using the IPI model alone.

EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING (2022)

添加到收藏夹

Article Health Care Sciences & Services

Re-evaluation of the comparative effectiveness of bootstrap-based optimism correction methods in the development of multivariable clinical prediction models

Katsuhiro Iba et al.

Summary: This study compared the effectiveness of Harrell's bias correction, .632, and .632+ estimators, finding that the .632+ estimator performed relatively well under small sample settings, especially when regularized estimation methods are adopted.

BMC MEDICAL RESEARCH METHODOLOGY (2021)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

[18F]FDG PET radiomics to predict disease-free survival in cervical cancer: a multi-scanner/center study with external validation

Marta Ferreira et al.

Summary: This study demonstrates the value of combining [F-18]FDG PET radiomic features with machine learning for predicting cancer recurrence in LACC patients. However, the performance of these models varies across different PET/CT devices, and ComBat does not improve the predictive performance of the best models.

EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING (2021)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging