Table 7.

Contributions of recent studies with generic deep learning with modifications.

Author and Citation	Contributions
Hou et al. [92]	Proposed an integrative histology-genomic analysis for HCC prognosis using deep learning, integrating histopathology risk scores and hub genes.
Lee et al. [93]	Proposed a deep learning model for predicting cancer occurrence by utilizing whole-genome data, demonstrating exceptional performance on the TCGA dataset.
Jha et al. [94]	Utilized neural networks to identify transcriptomic features shared across different cancer types, discovering common cancer transcriptome signatures.
Zheng et al. [95]	Developed deep learning-based models for accurate diagnosis and survival prediction in bladder cancer using histological images.
Al-Fatlawi et al. [96]	Utilized deep learning models to improve the diagnosis of pancreatic cancer using RNA-based variants from blood samples.
Elsharawy et al. [97]	Demonstrated the potential of an AI-based breast cancer grading model, trained using CNN on images from TCGA.
Ye et al. [98]	Proposed a deep learning-based method to predict genes susceptible to ovarian cancer, using a graph attention network (GAT) and a deep neural network (DNN).
Guo et al. [99]	Proposed a deep learning-based model, DLFscore, for the prognosis prediction and potential chemotherapy sensitivity in prostate cancer.
Ramirez et al. [100]	Introduced Surv_GCNN, a novel GCNN approach for cancer survival rate prediction, outperforming other models in multiple cancer types.
Chen et al. [101]	Identified immune subtypes and landscape of gastric cancer using a deep learning model trained on whole-slide images.
Park et al. [102]	Developed a deep learning method to diagnose different stages in NAFLD and its relationship with HCC.
Ma et al. [104]	Optimized the prognostic model of cervical cancer using AI and data mining technology, identifying DMCs and constructing a prognostic model.
Del Carmen et al. [105]	Studied the relationship between genetic lesions and response to neoadjuvant radiochemotherapy in locally advanced rectal cancer, identifying a genetic signature predicting response to treatment.
Huang et al. [106]	Explored the roles of immune microenvironment-related factors in hepatitis B virus-related diseases using AI-based model.
Yang et al. [107]	Investigated the role of ACSL4 in NSCLC and its link to the ferroptosis process using deep learning.
Mehmood et al. [108]	Employed deep learning to identify compounds potentially possessing superior affinity for KRAS mutants in colorectal cancer.
Wang et al. [109]	Proposed a method to predict long-term survival in lung cancer patients using gene expression data and a CNN-based deep learning model.