Table 7.

Summary of representative studies on ¹⁸F-FDG PET/CT radiomics-based machine learning analyses in other types of tumors

Authors	Years	Tumor type	Aim	Sample size	Constructed ML models	Core ML algorithm	Best ML model	Validation	Resultsa
Differentiating primary from metastatic tumors
Mannam et al. [125]	2022	MM	MM vs. skeletal metastasis	n = 40	CT radiomics-based model PET radiomics-based model Combined model	Multilayer perceptron	Combined model	Training and validation cohorts	AUC: 0.9538
Predicting tumor stage, treatment response, or survival
Mesguich et al. [126]	2021	MM	Diffuse infiltration in the bone marrow	n = 30	Combined CT + PET radiomics-based model	RF	–	Training and validation cohorts	AUC: 0.90
Li et al. [127]	2019	Acute leukemia	Diffuse infiltration in the bone marrow	n = 41	Combined CT + PET radiomics-based model	RF	–	Training and validation cohorts	Accuracy: 0.886
Ni et al. [128]	2023	MM	PFS	n = 98	Clinical model Combined PET and CT radiomics-based model Combined clinical, PET radiomics-based, and CT radiomics-based model	LASSO + cox regression	Combined clinical, PET radiomics-based, and CT radiomics-based model	Training and validation cohorts	C-index: 0.698
Feng et al. [130]	2022	Neuroblastoma	MKI status	n = 102	Clinical model Combined PET and CT radiomics-based model Combined clinical, PET, and CT radiomics-based model	XGB	Combined PET and CT radiomics-based model	Training and validation cohorts	AUC: 0.951

AUC area under the receiver operating characteristic curve, C-index concordance index, LASSO least absolute shrinkage and selection operator algorithm, MKI mitosis-karyorrhexis index, ML machine learning, MM multiple myeloma, PFS progression-free survival, RF random forest, XGB gradient tree boosting

^aPerformance only presents the result of the best machine learning model