Predicting overall survival of patients with hepatocellular carcinoma using a three‐category method based on DNA methylation and machine learning

Dong, Rui‐Zhao; Yang, Xuan; Zhang, Xinyu; Gao, Ping; Ke, Ai–Wu; Sun, Hui‐Chuan; Zhou, Jian; Fan, Jia; Cai, Jia‐Bin; Shi, Guo‐Ming

doi:10.1111/jcmm.14231

Cited by 29 publications

(17 citation statements)

References 24 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is at least in part due to this ability to make 'evidence-based' decisions that, as AI-health research has shown, AI techniques can considerably augment or surpass human capabilities when it comes to tasks including: (1) analysis of risk factors ( prediction of outcome and/or likelihood of survival (Dong et al, 2019;Popkes et al, 2019;Topuz, Zengul, Dag, Almehmi, & Yildirim, 2018); and (7) analysing electronic health records (Shickel, Tighe, Bihorac, & Rashidi, 2018). These capabilities should not be underestimated, particularly as AI-Health solutions can operate at scale, diagnosing or predicting outcomes for multiple people at once -something that an HCP could never do.…”

Section: Epistemic Concerns: Inconclusive Inscrutable and Misguidedmentioning

confidence: 99%

The Debate on the Ethics of AI in Health Care: a Reconstruction and Critical Review

Morley¹

2019

Preprint

View full text Add to dashboard Cite

Healthcare systems across the globe are struggling with increasing costs and worsening outcomes. This presents those responsible for overseeing healthcare with a challenge. Increasingly, policymakers, politicians, clinical entrepreneurs and computer and data scientists argue that a key part of the solution will be ‘Artificial Intelligence’ (AI) – particularly Machine Learning (ML). This argument stems not from the belief that all healthcare needs will soon be taken care of by “robot doctors.” Instead, it is an argument that rests on the classic counterfactual definition of AI as an umbrella term for a range of techniques that can be used to make machines complete tasks in a way that would be considered intelligent were they to be completed by a human. Automation of this nature could offer great opportunities for the improvement of healthcare services and ultimately patients’ health by significantly improving human clinical capabilities in diagnosis, drug discovery, epidemiology, personalised medicine, and operational efficiency. However, if these AI solutions are to be embedded in clinical practice, then at least three issues need to be considered: the technical possibilities and limitations; the ethical, regulatory and legal framework; and the governance framework. In this article, we report on the results of a systematic analysis designed to provide a clear overview of the second of these elements: the ethical, regulatory and legal framework. We find that ethical issues arise at six levels of abstraction (individual, interpersonal, group, institutional, sectoral, and societal) and can be categorised as epistemic, normative, or overarching. We conclude by stressing how important it is that the ethical challenges raised by implementing AI in healthcare settings are tackled proactively rather than reactively and map the key considerations for policymakers to each of the ethical concerns highlighted.

show abstract

Section: Epistemic Concerns: Inconclusive Inscrutable and Misguidedmentioning

confidence: 99%

The Debate on the Ethics of AI in Health Care: a Reconstruction and Critical Review

Morley¹

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Lee et al proposed a data-driven construction method for survival risk-gene networks as well as a survival risk prediction method using the network structure [8]. Dong et al used machine learning to analyze DNA methylation data to build a model with three risk categories for predicting survival of hepatocellular carcinoma patients [9]. Prognostic risk model was constructed in glioblastoma multiform based on mRNA/microRNA/long non-coding RNA analysis using random survival forest method [10].…”

Section: Discussionmentioning

confidence: 99%

Identifying Potential Prognostic Expression Quantitative Trait Methylation for Predicting Survival in Osteosarcoma

Dong

Zhu

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Osteosarcoma (OS) is a complex cancer and depends on multiple biological processes and pathways. Therefore, there is an urgent need to identify reliable prognostic biomarkers for predicting clinical outcomes and helping personalize treatment of OS. Results: An expression Quantitative Trait Methylations (eQTMs)-based risk score model was developed to infer the prognostic efficacy for OS based on gene expression and methylation level. Some OS-specific eQTMs were identified and divided to positive and negative eQTMs. We found that some OS-specific eQTMs were significantly associated with survival in OS according to the eQTM-based risk score. The global characteristics for these prognosis-associated eQTMS were depicted and analyzed. These prognosis-associated eQTMS are stable in multiple experiments and showed better performance in predicting survival than single gene expression, age and gender of OS. Functional analysis indicated that the genes in prognosis-associated eQTMS were associated with essential biology processes of cancer development. In addition, these genes were also drug targets for many kinds of drugs and may provide assistance for studying drug repurposing of OS. Conclusion: These results highlight the potential of eQTMs as novel diagnostic, prognostic and therapeutic targets for OS.

show abstract

“…Cox regression, SVM‐RFE and FW‐SVM algorithms were used to screen out differentially methylated sites. And this study was performed based on TCGA (training set) and GSE77269 (validation set), the sample size of our study was limited, and large‐scale cohort studies are needed . In this study, we constructed a signature involving only 10 lncRNAs.…”

Section: Discussionmentioning

confidence: 99%

A prognostic 10‐lncRNA expression signature for predicting the risk of tumour recurrence in breast cancer patients

Tang

Ren

Cui

et al. 2019

J Cellular Molecular Medi

View full text Add to dashboard Cite

Breast cancer is one of the most frequently diagnosed malignancies and a leading cause of cancer death among females. Multiple molecular alterations are observed in breast cancer. LncRNA transcripts were proved to play important roles in the biology of tumorigenesis. In this study, we aimed to identify lncRNA expression signature that can predict breast cancer patient survival. We developed a 10‐lncRNA signature‐based risk score which was used to separate patients into high‐risk and low‐risk groups. Patients in the low‐risk group had significantly better survival than those in the high‐risk group. Receiver operating characteristic analysis indicated that this signature exhibited excellent diagnostic efficiency for 1‐, 3‐ and 5‐year disease‐relapse events. Moreover, multivariate Cox regression analysis demonstrated that this 10‐lncRNA signature was an independent risk factor when adjusting for several clinical signatures such as age, tumour size and lymph node status. The prognostic value of risk scores was validated in the validation set. In addition, a nomogram was established and the calibration plots analysis indicated the good performance and clinical utility of the nomogram. In conclusion, our results demonstrated that this 10‐lncRNA signature effectively grouped patients at low and high risk of disease recurrence.

show abstract

Predicting overall survival of patients with hepatocellular carcinoma using a three‐category method based on DNA methylation and machine learning

Cited by 29 publications

References 24 publications

The Debate on the Ethics of AI in Health Care: a Reconstruction and Critical Review

The Debate on the Ethics of AI in Health Care: a Reconstruction and Critical Review

Identifying Potential Prognostic Expression Quantitative Trait Methylation for Predicting Survival in Osteosarcoma

A prognostic 10‐lncRNA expression signature for predicting the risk of tumour recurrence in breast cancer patients

Contact Info

Product

Resources

About