Machine learning selected smoking-associated DNA methylation signatures that predict HIV prognosis and mortality.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhang X
PROVIDER: S-EPMC6293604 | biostudies-literature | 2018 Dec
REPOSITORIES: biostudies-literature
Publications
Machine learning selected smoking-associated DNA methylation signatures that predict HIV prognosis and mortality.
Zhang Xinyu X Hu Ying Y Aouizerat Bradley E BE Peng Gang G Marconi Vincent C VC Corley Michael J MJ Hulgan Todd T Bryant Kendall J KJ Zhao Hongyu H Krystal John H JH Justice Amy C AC Xu Ke K
Clinical epigenetics 20181213 1
<h4>Background</h4>The effects of tobacco smoking on epigenome-wide methylation signatures in white blood cells (WBCs) collected from persons living with HIV may have important implications for their immune-related outcomes, including frailty and mortality. The application of a machine learning approach to the analysis of CpG methylation in the epigenome enables the selection of phenotypically relevant features from high-dimensional data. Using this approach, we now report that a set of smoking- ...[more]
Similar Datasets
Project description:Background: With the improved life expectancy of people living with HIV (PLWH), identifying vulnerable subpopulations at high mortality risk is important. Evidences showed that DNA methylation (DNAm) is associated with mortality in non-HIV populations. Here, we established a panel of DNAm biomarkers that can predict mortality risk among PLWH.Methods: 1,081 HIV-positive participants from the Veterans Ageing Cohort Study (VACS) were divided into training (N = 460), validation (N = 114), and testing (N = 507) sets. VACS index was used as a measure of mortality risk among PLWH. Model training and fine-tuning were conducted using the ensemble method in the training and validation sets and prediction performance was assessed in the testing set. The survival analysis comparing the predicted high and low mortality risk groups and the Gene Ontology enrichment analysis of the predictive CpG sites were performed.Results: We selected a panel of 393 CpGs for the ensemble prediction model that showed excellent performance in predicting high mortality risk with an auROC of 0.809 (95%CI: 0.767,0.851) and a balanced accuracy of 0.653 (95%CI: 0.611, 0.693) in the testing set. The high mortality risk group was significantly associated with 10-year mortality (hazard ratio = 1.79, p = 4E-05) compared with low risk group. These 393 CpGs were located in 280 genes enriched in immune and inflammation response pathways.Conclusions: We identified a panel of DNAm features associated with mortality risk in PLWH. These DNAm features may serve as predictive biomarkers for mortality risk among PLWH.Abbreviations: AUC: Area Under Curve; CI: Confidence interval; DMR: differentially methylated region; DNA: Deoxyribonucleic acid; DNAm: DNA methylation; DAVID: Database for Annotation, Visualization, and Integrated Discovery; EWA: epigenome-wide association; FDR: False discovery rate; FWER: Family-wise error rate; GLMNET: elastic-net-regularized generalized linear models; GO: Gene ontology; HIV: Human immunodeficiency virus; HM450K: Human Methylation 450 K BeadChip; k-NN: k-nearest neighbours; NK: Natural killer; PC: Principal component; PLWH: people living with HIV; QC: Quality control; SVM: Support Vector Machines; VACS: Veterans Ageing Cohort Study; XGBoost: Extreme Gradient Boosting Tree.
| S-EPMC8216205 | biostudies-literature
Project description:DNA methylation (DNAm) has been revealed to play a role in various diseases. Here we performed epigenome-wide screening and validation to identify mortality-related DNAm signatures in a general population-based cohort with up to 14 years follow-up. In the discovery panel in a case-cohort approach, 11,063 CpGs reach genome-wide significance (FDR<0.05). 58 CpGs, mapping to 38 well-known disease-related genes and 14 intergenic regions, are confirmed in a validation panel. A mortality risk score based on ten selected CpGs exhibits strong association with all-cause mortality, showing hazard ratios (95% CI) of 2.16 (1.10-4.24), 3.42 (1.81-6.46) and 7.36 (3.69-14.68), respectively, for participants with scores of 1, 2-5 and 5+ compared with a score of 0. These associations are confirmed in an independent cohort and are independent from the 'epigenetic clock'. In conclusion, DNAm of multiple disease-related genes are strongly linked to mortality outcomes. The DNAm-based risk score might be informative for risk assessment and stratification.
| S-EPMC5357865 | biostudies-literature
Project description:BackgroundCutaneous melanoma (CM) is one of the most life-threatening primary skin cancers and is prone to distant metastases. A widespread presence of posttranscriptional modification of RNA, 5-methylcytosine (m5C), has been observed in human cancers. However, the potential mechanism of the tumorigenesis and prognosis in CM by dysregulated m5C-related regulators is obscure.MethodsWe use comprehensive bioinformatics analyses to explore the expression of m5C regulators in CM, the prognostic implications of the m5C regulators, the frequency of the copy number variant (CNV), and somatic mutations in m5C regulators. Additionally, the CM patients were divided into three clusters for better predicting clinical features and outcomes via consensus clustering of m5C regulators. Then, the risk score was established via Lasso Cox regression analysis. Next, the prognosis value and clinical characteristics of m5C-related signatures were further explored. Then, machine learning was used to recognize the outstanding m5C regulators to risk score. Finally, the expression level and clinical value of USUN6 were analyzed via the tissue microarray (TMA) cohort.ResultsWe found that m5C regulators were dysregulated in CM, with a high frequency of somatic mutations and CNV alterations of the m5C regulatory gene in CM. Furthermore, 16 m5C-related proteins interacted with each other frequently, and we divided CM patients into three clusters to better predicting clinical features and outcomes. Then, five m5C regulators were selected as a risk score based on the LASSO model. The XGBoost algorithm recognized that NOP2 and NSUN6 were the most significant risk score contributors. Immunohistochemistry has verified that low expression of USUN6 was closely correlated with CM progression.ConclusionThe m5C-related signatures can be used as new prognostic biomarkers and therapeutic targets for CM, and NSUN6 might play a vital role in tumorigenesis and malignant progression.
| S-EPMC8360728 | biostudies-literature
Project description:BACKGROUND:Spastic cerebral palsy (CP) is a leading cause of physical disability. Most people with spastic CP are born with it, but early diagnosis is challenging, and no current biomarker platform readily identifies affected individuals. The aim of this study was to evaluate epigenetic profiles as biomarkers for spastic CP. A novel analysis pipeline was employed to assess DNA methylation patterns between peripheral blood cells of adolescent subjects (14.9?±?0.3 years old) with spastic CP and controls at single CpG site resolution. RESULTS:Significantly hypo- and hyper-methylated CpG sites associated with spastic CP were identified. Nonmetric multidimensional scaling fully discriminated the CP group from the controls. Machine learning based classification modeling indicated a high potential for a diagnostic model, and 252 sets of 40 or fewer CpG sites achieved near-perfect accuracy within our adolescent cohorts. A pilot test on significantly younger subjects (4.0?±?1.5 years old) identified subjects with 73% accuracy. CONCLUSIONS:Adolescent patients with spastic CP can be distinguished from a non-CP cohort based on DNA methylation patterns in peripheral blood cells. A clinical diagnostic test utilizing a panel of CpG sites may be possible using a simulated classification model. A pilot validation test on patients that were more than 10 years younger than the main adolescent cohorts indicated that distinguishing methylation patterns are present earlier in life. This study is the first to report an epigenetic assay capable of distinguishing a CP cohort.
| S-EPMC6011336 | biostudies-literature
Project description:Importance:Machine learning algorithms could identify patients with cancer who are at risk of short-term mortality. However, it is unclear how different machine learning algorithms compare and whether they could prompt clinicians to have timely conversations about treatment and end-of-life preferences. Objectives:To develop, validate, and compare machine learning algorithms that use structured electronic health record data before a clinic visit to predict mortality among patients with cancer. Design, Setting, and Participants:Cohort study of 26 525 adult patients who had outpatient oncology or hematology/oncology encounters at a large academic cancer center and 10 affiliated community practices between February 1, 2016, and July 1, 2016. Patients were not required to receive cancer-directed treatment. Patients were observed for up to 500 days after the encounter. Data analysis took place between October 1, 2018, and September 1, 2019. Exposures:Logistic regression, gradient boosting, and random forest algorithms. Main Outcomes and Measures:Primary outcome was 180-day mortality from the index encounter; secondary outcome was 500-day mortality from the index encounter. Results:Among 26 525 patients in the analysis, 1065 (4.0%) died within 180 days of the index encounter. Among those who died, the mean age was 67.3 (95% CI, 66.5-68.0) years, and 500 (47.0%) were women. Among those who were alive at 180 days, the mean age was 61.3 (95% CI, 61.1-61.5) years, and 15 922 (62.5%) were women. The population was randomly partitioned into training (18 567 [70.0%]) and validation (7958 [30.0%]) cohorts at the patient level, and a randomly selected encounter was included in either the training or validation set. At a prespecified alert rate of 0.02, positive predictive values were higher for the random forest (51.3%) and gradient boosting (49.4%) algorithms compared with the logistic regression algorithm (44.7%). There was no significant difference in discrimination among the random forest (area under the receiver operating characteristic curve [AUC], 0.88; 95% CI, 0.86-0.89), gradient boosting (AUC, 0.87; 95% CI, 0.85-0.89), and logistic regression (AUC, 0.86; 95% CI, 0.84-0.88) models (P for comparison = .02). In the random forest model, observed 180-day mortality was 51.3% (95% CI, 43.6%-58.8%) in the high-risk group vs 3.4% (95% CI, 3.0%-3.8%) in the low-risk group; at 500 days, observed mortality was 64.4% (95% CI, 56.7%-71.4%) in the high-risk group and 7.6% (7.0%-8.2%) in the low-risk group. In a survey of 15 oncology clinicians with a 52.1% response rate, 100 of 171 patients (58.8%) who had been flagged as having high risk by the gradient boosting algorithm were deemed appropriate for a conversation about treatment and end-of-life preferences in the upcoming week. Conclusions and Relevance:In this cohort study, machine learning algorithms based on structured electronic health record data accurately identified patients with cancer at risk of short-term mortality. When the gradient boosting algorithm was applied in real time, clinicians believed that most patients who had been identified as having high risk were appropriate for a timely conversation about treatment and end-of-life preferences.
| S-EPMC6822091 | biostudies-literature
Project description:Previous scoring models, such as the Acute Physiologic Assessment and Chronic Health Evaluation II (APACHE II) score, do not adequately predict the mortality of patients receiving mechanical ventilation in the intensive care unit. Therefore, this study aimed to apply machine learning algorithms to improve the prediction accuracy for 30-day mortality of mechanically ventilated patients. The data of 16,940 mechanically ventilated patients were divided into the training-validation (83%, n = 13,988) and test (17%, n = 2952) sets. Machine learning algorithms including balanced random forest, light gradient boosting machine, extreme gradient boost, multilayer perceptron, and logistic regression were used. We compared the area under the receiver operating characteristic curves (AUCs) of machine learning algorithms with those of the APACHE II and ProVent score results. The extreme gradient boost model showed the highest AUC (0.79 (0.77-0.80)) for the 30-day mortality prediction, followed by the balanced random forest model (0.78 (0.76-0.80)). The AUCs of these machine learning models as achieved by APACHE II and ProVent scores were higher than 0.67 (0.65-0.69), and 0.69 (0.67-0.71)), respectively. The most important variables in developing each machine learning model were APACHE II score, Charlson comorbidity index, and norepinephrine. The machine learning models have a higher AUC than conventional scoring systems, and can thus better predict the 30-day mortality of mechanically ventilated patients.
| S-EPMC8157228 | biostudies-literature
Project description:Stroke is among the leading causes of death and disability worldwide. Approximately 20-25% of stroke survivors present severe disability, which is associated with increased mortality risk. Prognostication is inherent in the process of clinical decision-making. Machine learning (ML) methods have gained increasing popularity in the setting of biomedical research. The aim of this study was twofold: assessing the performance of ML tree-based algorithms for predicting three-year mortality model in 1207 stroke patients with severe disability who completed rehabilitation and comparing the performance of ML algorithms to that of a standard logistic regression. The logistic regression model achieved an area under the Receiver Operating Characteristics curve (AUC) of 0.745 and was well calibrated. At the optimal risk threshold, the model had an accuracy of 75.7%, a positive predictive value (PPV) of 33.9%, and a negative predictive value (NPV) of 91.0%. The ML algorithm outperformed the logistic regression model through the implementation of synthetic minority oversampling technique and the Random Forests, achieving an AUC of 0.928 and an accuracy of 86.3%. The PPV was 84.6% and the NPV 87.5%. This study introduced a step forward in the creation of standardisable tools for predicting health outcomes in individuals affected by stroke.
| S-EPMC7674405 | biostudies-literature
Project description:PurposeSignificant advancements in improving ovarian cancer (OC) outcomes have been limited over the past decade. To predict prognosis and improve outcomes of OC, we plan to develop and validate a robust prognosis signature based on blood features.MethodsWe screened age and 33 blood features from 331 OC patients. Using ten machine learning algorithms, 88 combinations were generated, from which one was selected to construct a blood risk score (BRS) according to the highest C-index in the test dataset.ResultsStepcox (both) and Enet (alpha = 0.7) performed the best in the test dataset with a C-index of 0.711. Meanwhile, the low RBS group possessed observably prolonged survival in this model. Compared to traditional prognostic-related features such as age, stage, grade, and CA125, our combined model had the highest AUC values at 3, 5, and 7 years. According to the results of the model, BRS can provide accurate predictions of OC prognosis. BRS was also capable of identifying various prognostic stratifications in different stages and grades. Importantly, developing the nomogram may improve performance by combining BRS and stage.ConclusionThis study provides a valuable combined machine-learning model that can be used for predicting the individualized prognosis of OC patients.
| S-EPMC10895771 | biostudies-literature
Project description:Machine learning (ML) and deep learning (DL) can successfully predict high prevalence events in very large databases (big data), but the value of this methodology for risk prediction in smaller cohorts with uncommon diseases and infrequent events is uncertain. The clinical course of spontaneous coronary artery dissection (SCAD) is variable, and no reliable methods are available to predict mortality. Based on the hypothesis that machine learning (ML) and deep learning (DL) techniques could enhance the identification of patients at risk, we applied a deep neural network to information available in electronic health records (EHR) to predict in-hospital mortality in patients with SCAD. We extracted patient data from the EHR of an extensive urban health system and applied several ML and DL models using candidate clinical variables potentially associated with mortality. We partitioned the data into training and evaluation sets with cross-validation. We estimated model performance based on the area under the receiver-operator characteristics curve (AUC) and balanced accuracy. As sensitivity analyses, we examined results limited to cases with complete clinical information available. We identified 375 SCAD patients of which mortality during the index hospitalization was 11.5%. The best-performing DL algorithm identified in-hospital mortality with AUC 0.98 (95% CI 0.97-0.99), compared to other ML models (P < 0.0001). For prediction of mortality using ML models in patients with SCAD, the AUC ranged from 0.50 with the random forest method (95% CI 0.41-0.58) to 0.95 with the AdaBoost model (95% CI 0.93-0.96), with intermediate performance using logistic regression, decision tree, support vector machine, K-nearest neighbors, and extreme gradient boosting methods. A deep neural network model was associated with higher predictive accuracy and discriminative power than logistic regression or ML models for identification of patients with ACS due to SCAD prone to early mortality.
| S-EPMC8076284 | biostudies-literature
Project description:BackgroundFrailty is an important clinical concern for the aging population of people living with HIV (PLWH). The objective of this study was to identify the combination of risk features that distinguish frail from nonfrail individuals.SettingMachine learning analysis of highly dimensional risk features was performed on a clinical cohort of PLWH.MethodsParticipants included 105 older (average age = 55.6) PLWH, with at least a 3-month history of combination antiretroviral therapy (median CD4 = 546). Predictors included demographics, HIV clinical markers, comorbid health conditions, cognition, and neuroimaging (ie, volumetrics, resting-state functional connectivity, and cerebral blood flow). Gradient-boosted multivariate regressions were implemented to establish linear and interactive classification models. Model performance was determined by sensitivity/specificity (F1 score) with 5-fold cross validation.ResultsThe linear gradient-boosted multivariate regression classifier included lower current CD4 count, lower psychomotor performance, and multiple neuroimaging indices (volumes, network connectivity, and blood flow) in visual and motor brain systems (F1 score = 71%; precision = 84%; and sensitivity = 66%). The interactive model identified novel synergies between neuroimaging features, female sex, symptoms of depression, and current CD4 count.ConclusionsData-driven algorithms built from highly dimensional clinical and brain imaging features implicate disruption to the visuomotor system in older PLWH designated as frail individuals. Interactions between lower CD4 count, female sex, depressive symptoms, and neuroimaging features suggest potentiation of risk mechanisms. Longitudinal data-driven studies are needed to guide clinical strategies capable of preventing the development of frailty as PLWH reach advanced age.
| S-EPMC7903919 | biostudies-literature