Dataset Information

Predicting new-onset post-stroke depression from real-world data using machine learning algorithm.

ABSTRACT:

Introduction

Post-stroke depression (PSD) is a serious mental disorder after ischemic stroke. Early detection is important for clinical practice. This research aims to develop machine learning models to predict new-onset PSD using real-world data.

Methods

We collected data for ischemic stroke patients from multiple medical institutions in Taiwan between 2001 and 2019. We developed models from 61,460 patients and used 15,366 independent patients to test the models' performance by evaluating their specificities and sensitivities. The predicted targets were whether PSD occurred at 30, 90, 180, and 365 days post-stroke. We ranked the important clinical features in these models.

Results

In the study's database sample, 1.3% of patients were diagnosed with PSD. The average specificity and sensitivity of these four models were 0.83-0.91 and 0.30-0.48, respectively. Ten features were listed as important features related to PSD at different time points, namely old age, high height, low weight post-stroke, higher diastolic blood pressure after stroke, no pre-stroke hypertension but post-stroke hypertension (new-onset hypertension), post-stroke sleep-wake disorders, post-stroke anxiety disorders, post-stroke hemiplegia, and lower blood urea nitrogen during stroke.

Discussion

Machine learning models can provide as potential predictive tools for PSD and important factors are identified to alert clinicians for early detection of depression in high-risk stroke patients.

SUBMITTER: Chen YM

PROVIDER: S-EPMC10315461 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting new-onset post-stroke depression from real-world data using machine learning algorithm.

Chen Yu-Ming YM Chen Po-Cheng PC Lin Wei-Che WC Hung Kuo-Chuan KC Chen Yang-Chieh Brian YB Hung Chi-Fa CF Wang Liang-Jen LJ Wu Ching-Nung CN Hsu Chih-Wei CW Kao Hung-Yu HY

Frontiers in psychiatry 20230619

<h4>Introduction</h4>Post-stroke depression (PSD) is a serious mental disorder after ischemic stroke. Early detection is important for clinical practice. This research aims to develop machine learning models to predict new-onset PSD using real-world data.<h4>Methods</h4>We collected data for ischemic stroke patients from multiple medical institutions in Taiwan between 2001 and 2019. We developed models from 61,460 patients and used 15,366 independent patients to test the models' performance by e ...[more]

PMID: 37404713

Similar Datasets

Project description:BackgroundBeing one of the most widespread, pervasive, and troublesome illnesses in the world, depression causes dysfunction in various spheres of individual and social life. Regrettably, despite obtaining evidence-based antidepressant medication, up to 70% of people are going to continue to experience troublesome symptoms. Quetiapine, as one of the most commonly prescribed antipsychotic medication worldwide, has been reported as an effective augmentation strategy to antidepressants. The right quetiapine dose and personalized quetiapine treatment are frequently challenging for clinicians. This study aimed to identify important influencing variables for quetiapine dose by maximizing the use of data from real world, and develop a predictive model of quetiapine dose through machine learning techniques to support selections for treatment regimens.MethodsThe study comprised 308 depressed patients who were medicated with quetiapine and hospitalized in the First Hospital of Hebei Medical University, from November 1, 2019, to August 31, 2022. To identify the important variables influencing the dose of quetiapine, a univariate analysis was applied. The prediction abilities of nine machine learning models (XGBoost, LightGBM, RF, GBDT, SVM, LR, ANN, DT) were compared. Algorithm with the optimal model performance was chosen to develop the prediction model.ResultsFour predictors were selected from 38 variables by the univariate analysis (p < 0.05), including quetiapine TDM value, age, mean corpuscular hemoglobin concentration, and total bile acid. Ultimately, the XGBoost algorithm was used to create a prediction model for quetiapine dose that had the greatest predictive performance (accuracy = 0.69) out of nine models. In the testing cohort (62 cases), a total of 43 cases were correctly predicted of the quetiapine dose regimen. In dose subgroup analysis, AUROC for patients with daily dose of 100 mg, 200 mg, 300 mg and 400 mg were 0.99, 0.75, 0.93 and 0.86, respectively.ConclusionsIn this work, machine learning techniques are used for the first time to estimate the dose of quetiapine for patients with depression, which is valuable for the clinical drug recommendations.

Project description:ObjectivesPost-stroke depression (PSD) is a common and serious psychiatric complication which hinders functional recovery and social participation of stroke patients. Stroke is characterized by dynamic changes in metabolism and hemodynamics, however, there is still a lack of metabolism-associated effective and reliable diagnostic markers and therapeutic targets for PSD. Our study was dedicated to the discovery of metabolism related diagnostic and therapeutic biomarkers for PSD.MethodsExpression profiles of GSE140275, GSE122709, and GSE180470 were obtained from GEO database. Differentially expressed genes (DEGs) were detected in GSE140275 and GSE122709. Functional enrichment analysis was performed for DEGs in GSE140275. Weighted gene co-expression network analysis (WGCNA) was constructed in GSE122709 to identify key module genes. Moreover, correlation analysis was performed to obtain metabolism related genes. Interaction analysis of key module genes, metabolism related genes, and DEGs in GSE122709 was performed to obtain candidate hub genes. Two machine learning algorithms, least absolute shrinkage and selection operator (LASSO) and random forest, were used to identify signature genes. Expression of signature genes was validated in GSE140275, GSE122709, and GSE180470. Gene set enrichment analysis (GSEA) was applied on signature genes. Based on signature genes, a nomogram model was constructed in our PSD cohort (27 PSD patients vs. 54 controls). ROC curves were performed for the estimation of its diagnostic value. Finally, correlation analysis between expression of signature genes and several clinical traits was performed.ResultsFunctional enrichment analysis indicated that DEGs in GSE140275 enriched in metabolism pathway. A total of 8,188 metabolism associated genes were identified by correlation analysis. WGCNA analysis was constructed to obtain 3,471 key module genes. A total of 557 candidate hub genes were identified by interaction analysis. Furthermore, two signature genes (SDHD and FERMT3) were selected using LASSO and random forest analysis. GSEA analysis found that two signature genes had major roles in depression. Subsequently, PSD cohort was collected for constructing a PSD diagnosis. Nomogram model showed good reliability and validity. AUC values of receiver operating characteristic (ROC) curve of SDHD and FERMT3 were 0.896 and 0.964. ROC curves showed that two signature genes played a significant role in diagnosis of PSD. Correlation analysis found that SDHD (r = 0.653, P < 0.001) and FERM3 (r = 0.728, P < 0.001) were positively related to the Hamilton Depression Rating Scale 17-item (HAMD) score.ConclusionA total of 557 metabolism associated candidate hub genes were obtained by interaction with DEGs in GSE122709, key modules genes, and metabolism related genes. Based on machine learning algorithms, two signature genes (SDHD and FERMT3) were identified, they were proved to be valuable therapeutic and diagnostic biomarkers for PSD. Early diagnosis and prevention of PSD were made possible by our findings.

Project description:BackgroundPost-stroke depression (PSD) can be conceptualized as a complex network where PSD symptoms (PSDS) interact with each other. The neural mechanism of PSD and interactions among PSDS remain to be elucidated. This study aimed to investigate the neuroanatomical substrates of, as well as the interactions between, individual PSDS to better understand the pathogenesis of early-onset PSD.MethodsA total of 861 first-ever stroke patients admitted within 7 days poststroke were consecutively recruited from three independent hospitals in China. Sociodemographic, clinical and neuroimaging data were collected upon admission. PSDS assessment with Hamilton Depression Rating Scale was performed at 2 weeks after stroke. Thirteen PSDS were included to develop a psychopathological network in which central symptoms (i.e. symptoms most strongly correlated with other PSDS) were identified. Voxel-based lesion-symptom mapping (VLSM) was performed to uncover the lesion locations associated with overall PSDS severity and severities of individual PSDS, in order to test the hypothesis that strategic lesion locations for central symptoms could significantly contribute to higher overall PSDS severity.ResultsDepressed mood, Psychiatric anxiety and Loss of interest in work and activities were identified as central PSDS at the early stage of stroke in our relatively stable PSDS network. Lesions in bilateral (especially the right) basal ganglia and capsular regions were found significantly associated with higher overall PSDS severity. Most of the above regions were also correlated with higher severities of 3 central PSDS. The other 10 PSDS could not be mapped to any certain brain region.ConclusionsThere are stable interactions among early-onset PSDS with Depressed mood, Psychiatric anxiety and Loss of interest as central symptoms. The strategic lesion locations for central symptoms may indirectly induce other PSDS via the symptom network, resulting in higher overall PSDS severity.Trial registrationURL: http://www.chictr.org.cn/enIndex.aspx ; Unique identifier: ChiCTR-ROC-17013993.

Project description:ObjectiveThe study aimed to explore the miRNA and mRNA biomarkers in post-stroke depression (PSD) and to develop a miRNA-mRNA regulatory network to reveal its potential pathogenesis.MethodsThe transcriptomic expression profile was obtained from the GEO database using the accession numbers GSE117064 (miRNAs, stroke vs. control) and GSE76826 [mRNAs, late-onset major depressive disorder (MDD) vs. control]. Differentially expressed miRNAs (DE-miRNAs) were identified in blood samples collected from stroke patients vs. control using the Linear Models for Microarray Data (LIMMA) package, while the weighted correlation network analysis (WGCNA) revealed co-expressed gene modules correlated with the subject group. The intersection between DE-miRNAs and miRNAs identified by WGCNA was defined as stroke-related miRNAs, whose target mRNAs were stroke-related genes with the prediction based on three databases (miRDB, miRTarBase, and TargetScan). Using the GSE76826 dataset, the differentially expressed genes (DEGs) were identified. Overlapped DEGs between stroke-related genes and DEGs in late-onset MDD were retrieved, and these were potential mRNA biomarkers in PSD. With the overlapped DEGs, three machine-learning methods were employed to identify gene signatures for PSD, which were established with the intersection of gene sets identified by each algorithm. Based on the gene signatures, the upstream miRNAs were predicted, and a miRNA-mRNA network was constructed.ResultsUsing the GSE117064 dataset, we retrieved a total of 667 DE-miRNAs, which included 420 upregulated and 247 downregulated ones. Meanwhile, WGCNA identified two modules (blue and brown) that were significantly correlated with the subject group. A total of 117 stroke-related miRNAs were identified with the intersection of DE-miRNAs and WGCNA-related ones. Based on the miRNA-mRNA databases, we identified a list of 2,387 stroke-related genes, among which 99 DEGs in MDD were also embedded. Based on the 99 overlapped DEGs, we identified three gene signatures (SPATA2, ZNF208, and YTHDC1) using three machine-learning classifiers. Predictions of the three mRNAs highlight four miRNAs as follows: miR-6883-5p, miR-6873-3p, miR-4776-3p, and miR-6738-3p. Subsequently, a miRNA-mRNA network was developed.ConclusionThe study highlighted gene signatures for PSD with three genes (SPATA2, ZNF208, and YTHDC1) and four upstream miRNAs (miR-6883-5p, miR-6873-3p, miR-4776-3p, and miR-6738-3p). These biomarkers could further our understanding of the pathogenesis of PSD.

Dataset Information

Predicting new-onset post-stroke depression from real-world data using machine learning algorithm.

Introduction

Methods

Results

Discussion

Publications

Predicting new-onset post-stroke depression from real-world data using machine learning algorithm.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets