AUTHOR=He Tingshan , Huang Liwen , Li Jing , Wang Peng , Zhang Zhiqiao 

TITLE=Potential Prognostic Immune Biomarkers of Overall Survival in Ovarian Cancer Through Comprehensive Bioinformatics Analysis: A Novel Artificial Intelligence Survival Prediction System

JOURNAL=Frontiers in Medicine

VOLUME=Volume 8 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2021.587496

DOI=10.3389/fmed.2021.587496

ISSN=2296-858X

ABSTRACT=BACKGROUND: More and more evidences proved that tumor immune microenvironment plays an important role in the biological mechanisms of tumorigenesis and progression. The artificial intelligence medicine researches based on big data and advanced algorithms are helpful to improve the accuracy of prediction model for tumor prognosis. The current research aimed at exploring the potential prognostic immune biomarkers and developing a predictive model for overall survival of ovarian cancer (OC) based on artificial intelligence algorithms. 
METHODS: Differentially expression analyses were carried out between normal tissues and tumor tissues. Potential prognostic biomarkers were recognized by univariate Cox regression. Immune regulatory network was constructed on prognostic immune genes and their highly related transcription factors. 
RESULTS: Fourteen immune genes (PSMB9, FOXJ1, IFT57, MAL, ANXA4, CTSH, SCRN1, MIF, LTBR, CTSD, KIFAP3, PSMB8, HSPA5 and LTN1) were recognized as independent risk factors through multivariate Cox analyses. A prognostic nomogram was developed by using these prognostic genes. Concordance indexes were 0.760, 0.733, and 0.765 for 1-, 3- and 5- year overall survival. This prognostic model could identify high risk patients with poor overall survival from low risk patients. According to three artificial intelligence algorithms, the current study developed an Artificial intelligence survival predictive system, which could provide three individual mortality risk curves for ovarian cancer. 
CONCLUSION: In conclusion, the current study recognized fourteen prognostic immune biomarkers for ovarian cancer and revealed potential regulatory associations among immune genes and transcription factors. The current research further developed two artificial intelligence predictive tools for ovarian cancer, which were available at: https://zhangzhiqiao8.shinyapps.io/Smart_Cancer_Survival_Predictive_System_17_OC_F1001/ and https://zhangzhiqiao8.shinyapps.io/Gene_Survival_Subgroup_Analysis_17_OC_F1001/. Artificial intelligence survival predictive system is helpful to improve individualized treatment decision-making.