MATERIALS AND METHODS: This study adhered rigorously to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for literature searches. The literature databases, including PubMed, Embase, Cochrane, and Scopus were systematically searched individually. The methodological quality of the incorporated studies underwent assessment utilizing the radiomics quality score (RQS) tool. A random-effects meta-analysis employing the Harrell concordance index (C-index) was conducted to evaluate the performance of all radiomics models.

RESULTS: Among the 388 studies retrieved, 24 studies encompassing a total of 6,978 cases were incorporated into the systematic review. Furthermore, eight studies, focusing on overall survival as an endpoint, were included in the meta-analysis. The meta-analysis revealed that the estimated random effect of the C-index for all studies utilizing radiomics alone was 0.77 (0.71-0.82), with a substantial degree of heterogeneity indicated by an I2 of 80.17%.

METHODS: Positron emission tomography (PET) and computed tomography (CT) image data from 97 patients with LC and 77 patients with TB nodules were collected. One hundred radiomic features were extracted from both PET and CT imaging using the pyradiomics platform, and 2048 deep learning features were obtained through a residual neural network approach. Four models included traditional machine learning model with radiomic features as input (traditional radiomics), a deep learning model with separate input of image features (deep convolutional neural networks [DCNN]), a deep learning model with two inputs of radiomic features and deep learning features (radiomics-DCNN) and a deep learning model with inputs of radiomic features and deep learning features and clinical information (integrated model). The models were evaluated using area under the curve (AUC), sensitivity, accuracy, specificity, and F1-score metrics.

RESULTS: The results of the classification of TB nodules and LC showed that the integrated model achieved an AUC of 0.84 (0.82-0.88), sensitivity of 0.85 (0.80-0.88), and specificity of 0.84 (0.83-0.87), performing better than the other models.

PATIENTS AND METHODS: A total of 7476 patients with routine health check-up data who underwent prostate biopsies from January 2008 to December 2021 in eight referral centres in Asia were screened. After data pre-processing and cleaning, 5037 patients and 117 features were analyzed. Seven AI-based algorithms were tested for feature selection and seven AI-based algorithms were tested for classification, with the best combination applied for model construction. The APAC score was established in the CH cohort and validated in a multi-centre cohort and in each validation cohort to evaluate its generalizability in different Asian regions. The performance of the models was evaluated using area under the receiver operating characteristic curve (ROC), calibration plot, and decision curve analyses.

RESULTS: Eighteen features were involved in the APCA score predicting HGPCa, with some of these markers not previously used in prostate cancer diagnosis. The area under the curve (AUC) was 0.76 (95% CI:0.74-0.78) in the multi-centre validation cohort and the increment of AUC (APCA vs. PSA) was 0.16 (95% CI:0.13-0.20). The calibration plots yielded a high degree of coherence and the decision curve analysis yielded a higher net clinical benefit. Applying the APCA score could reduce unnecessary biopsies by 20.2% and 38.4%, at the risk of missing 5.0% and 10.0% of HGPCa cases in the multi-centre validation cohort, respectively.