SurvivalML: an integrative platform for the discovery and exploration of prognostic models in multi-center cancer cohorts DOI Open Access
Zaoqu Liu, Hui Xu, Long Liu

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2022, Volume and Issue: unknown

Published: Oct. 26, 2022

Abstract Advances in multi-omics and big-data technologies have led to numerous prognostic signatures aimed at improving current clinicopathological staging systems. Due the lack of reproducibility independent confirmation, few been translated into clinical routine. As high-quality datasets accumulate, identifying robust across multiple cohorts becomes possible. Nonetheless, inaccurate data retrieval, different versions genome annotations, disparate expression distributions, difficult cleaning, inconsistent information, algorithm selection, parameter tuning impeded model development validation multi-center datasets. Hence, for first time, we introduced SurvivalML ( https://rookieutopia.com/app_direct/SurvivalML/ ), a web application helping develop validate models included 37,325 samples (253 eligible datasets) with both transcriptome survival information from 21 cancer types, which were renewedly uniformly re-annotated, normalized, cleaned. This provided 10 machine-learning algorithms flexibly training via essential parameters online delivered four aspects evaluation, including Kaplan-Meier analysis, time-dependent ROC, calibration curve, decision curve analysis. Overall, believe that can serve as an attractive platform discovery

Language: Английский

Artificial intelligence-based multi-omics analysis fuels cancer precision medicine DOI Open Access
Xiujing He, Xiaowei Liu,

Fengli Zuo

et al.

Seminars in Cancer Biology, Journal Year: 2022, Volume and Issue: 88, P. 187 - 200

Published: Dec. 31, 2022

Language: Английский

Citations

156
Artificial intelligence for predictive biomarker discovery in immuno-oncology: a systematic review DOI
Arsela Prelaj, Vanja Mišković,

Michele Zanitti

et al.

Annals of Oncology, Journal Year: 2023, Volume and Issue: 35(1), P. 29 - 65

Published: Oct. 23, 2023

Language: Английский

Citations

106
Integration analysis of cell division cycle-associated family genes revealed potential mechanisms of gliomagenesis and constructed an artificial intelligence-driven prognostic signature DOI

Kai Yu,

Qi Tian,

Shi Feng

et al.

Cellular Signalling, Journal Year: 2024, Volume and Issue: 119, P. 111168 - 111168

Published: April 9, 2024

Language: Английский

Citations

5
Machine learning-based identification of a consensus immune-derived gene signature to improve head and neck squamous cell carcinoma therapy and outcome DOI Creative Commons

Xueying Hu,

Haiqun Dong,

Qin Wen

et al.

Frontiers in Pharmacology, Journal Year: 2024, Volume and Issue: 15

Published: April 10, 2024

Head and neck squamous cell carcinoma (HNSCC), an extremely aggressive tumor, is often associated with poor outcomes. The standard anatomy-based tumor-node-metastasis staging system does not satisfy the requirements for screening treatment-sensitive patients. Thus, ideal biomarker leading to precise treatment of HNSCC urgently needed.

Language: Английский

Citations

4
Applications of artificial intelligence in urologic oncology DOI Creative Commons
Sahyun Pak, Sung Gon Park, Jeonghyun Park

et al.

Investigative and Clinical Urology, Journal Year: 2024, Volume and Issue: 65(3), P. 202 - 202

Published: Jan. 1, 2024

With the recent rising interest in artificial intelligence (AI) medicine, many studies have explored potential and usefulness of AI urological diseases. This study aimed to comprehensively review applications urologic oncology.

Language: Английский

Citations

4
Application of artificial intelligence in the diagnosis of malignant digestive tract tumors: focusing on opportunities and challenges in endoscopy and pathology DOI Creative Commons

Yinhu Gao,

Peizhen Wen,

Yuan Liu

et al.

Journal of Translational Medicine, Journal Year: 2025, Volume and Issue: 23(1)

Published: April 9, 2025

Language: Английский

Citations

0
Combining bulk and single-cell RNA-sequencing data to develop an NK cell-related prognostic signature for hepatocellular carcinoma based on an integrated machine learning framework DOI Creative Commons
Qian Feng, Zhihao Huang, Lei Song

et al.

European journal of medical research, Journal Year: 2023, Volume and Issue: 28(1)

Published: Aug. 30, 2023

Abstract Background The application of molecular targeting therapy and immunotherapy has notably prolonged the survival patients with hepatocellular carcinoma (HCC). However, multidrug resistance high heterogeneity HCC still prevent further improvement clinical benefits. Dysfunction tumor-infiltrating natural killer (NK) cells was strongly related to progression benefits patients. Hence, an NK cell-related prognostic signature built up predict patients’ prognosis immunotherapeutic response. Methods cell markers were selected from scRNA-Seq data obtained GSE162616 set. A consensus machine learning framework including a total 77 algorithms developed establish gene in TCGA–LIHC set, GSE14520 GSE76427 set ICGC–LIRI–JP Moreover, predictive efficacy on ICI response externally validated by GSE91061 PRJEB23709 Results With highest C-index among algorithms, 11-gene established combination LASSO CoxBoost algorithm, which classified into high- low-risk group. displayed good performance for overall rate, moderate accuracy independent risk factor TCGA, GEO ICGC cohorts. Compared high-risk group, showed higher IPS–PD1 blocker, IPS–CTLA4 common immune checkpoints expression but lower TIDE score, indicated might be prone benefiting treatment. real-world cohort, PRJEB23709, also revealed better Conclusions Overall, present study based genes, offered novel platform evaluation

Language: Английский

Citations

10
Epigenetically regulated gene expression profiles decipher four molecular subtypes with prognostic and therapeutic implications in gastric cancer DOI Creative Commons
Siyuan Weng, Minghao Li, Jinhai Deng

et al.

Clinical Epigenetics, Journal Year: 2023, Volume and Issue: 15(1)

Published: April 15, 2023

Abstract Background Gastric cancer (GC) is one of the most common malignant tumors digestive tract which seriously endangers health human beings worldwide. Transcriptomic deregulation by epigenetic mechanisms plays a crucial role in heterogeneous progression GC. This study aimed to investigate impact epigenetically regulated genes on prognosis, immune microenvironment, and potential treatment Results Under premise verifying significant co-regulation aberrant frequencies microRNA (miRNA) correlated (MIRcor) DNA methylation-correlated (METcor) genes. Four GC molecular subtypes were identified validated comprehensive clustering MIRcor METcor GEPs 1521 samples from five independent multicenter cohorts: cluster 1 was characterized up-regulated cell proliferation transformation pathways, with good prognosis outcomes, driven mutations, sensitive 5-fluorouracil paclitaxel; 2 performed moderate benefited more apatinib cisplatin; 3 featured an ligand–receptor formation-related poor immunosuppression phenotype low tumor purity, resistant chemotherapy (e.g., 5-fluorouracil, paclitaxel, cisplatin), targeted therapy drug (apatinib) dasatinib; 4 as immune-activating phenotype, advanced stages, benefit immunotherapy displayed worst prognosis. Conclusions According GEPs, we developed four robust subtypes, facilitated understanding underlying heterogeneity, offering optimized decision-making surveillance platform for patients.

Language: Английский

Citations

8
The Present and Future of Artificial Intelligence in Urological Cancer DOI Open Access
Xun Liu, Jianxi Shi,

Zhaopeng Li

et al.

Journal of Clinical Medicine, Journal Year: 2023, Volume and Issue: 12(15), P. 4995 - 4995

Published: July 29, 2023

Artificial intelligence has drawn more and attention for both research application in the field of medicine. It considerable potential urological cancer detection, therapy, prognosis prediction due to its ability choose features data complete a particular task autonomously. Although clinical AI is still immature faces drawbacks such as insufficient lack prospective trials, will play an essential role individualization whole management cancers progresses. In this review, we summarize applications studies major cancers, including tumor diagnosis, treatment, prediction. Moreover, discuss current challenges future AI.

Language: Английский

Citations

7
Artificial Intelligence in Bladder Cancer Diagnosis: Current Applications and Future Perspectives DOI Creative Commons

Giulio Rossin,

Federico Zorzi, Luca Ongaro

et al.

BioMedInformatics, Journal Year: 2023, Volume and Issue: 3(1), P. 104 - 114

Published: Feb. 1, 2023

Bladder cancer (BCa) is one of the most diagnosed urological malignancies. A timely and accurate diagnosis crucial at first assessment as well follow up after curative treatments. Moreover, in era precision medicine, proper molecular characterization pathological evaluation are key drivers a patient-tailored management. However, currently available diagnostic tools still suffer from significant operator-dependent variability. To fill this gap, physicians have shown constantly increasing interest towards new resources able to enhance performances. In regard, several reports highlighted how artificial intelligence (AI) can produce promising results BCa field. narrative review, we aimed analyze recent literature exploring current experiences future perspectives on role AI scenario. We summarized recently investigated applications management, focusing technology could impact physicians’ accuracy three widespread areas: cystoscopy, clinical tumor (cT) staging, diagnosis. Our showed wide potential BCa, although larger prospective well-designed trials pending draw definitive conclusions allowing be routinely applied everyday practice.

Language: Английский

Citations

5