Depression and suicide risk prediction models using blood-derived multi-omics data

Bhak, Youngjune; Jeong, Hyoung oh; Cho, Yun Sung; Jeon, Sungwon; Cho, Juok; Gim, Jeong An; Jeon, Yeonsu; Blažytė, Asta; Park, Seung Gu; Kim, Hak Min; Shin, Eun Seok; Paik, Jong Woo; Lee, Hae Woo; Kang, Wooyoung; Kim, Aram; Kim, Yumi; Kim, Byung Chul; Ham, Byung Joo; Bhak, Jong; Lee, Semin

doi:10.1038/s41398-019-0595-2

Cited by 51 publications

(63 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve this problem, many works have been done to identify potential biomarkers for MDD patients with SI. 10–13 Our previous study found that the extrinsic coagulation pathway might be a biomarker for suicidal behavior in MDD. 11 Some researchers proposed that the neural representations or health records could be used to build the depression and suicide risk prediction models.…”

Section: Introductionmentioning

confidence: 97%

Potential Biomarkers for Diagnosing Major Depressive Disorder Patients with Suicidal Ideation

Bai

Fang

Xie

et al. 2021

JIR

View full text Add to dashboard Cite

Background Major depressive disorder (MDD) and suicide are two major health problems, but there are still no objective methods to diagnose MDD or suicidal ideation (SI). This study was conducted to identify potential biomarkers for diagnosing MDD patients with SI. Methods First-episode drug-naïve MDD patients with SI and demographics-matched healthy controls (HCs) were recruited. First-episode drug-naïve MDD patients without SI were also included. The serum lipids, C-reactive protein (CRP), transferring (TRSF), homocysteine (HCY) and alpha 1-antitrypsin (AAT) in serum were detected. The univariate and multivariate statistical analyses were used to identify and validate the potential biomarkers. Results The 86 HCs, 53 MDD patients with SI and 20 MDD patients without SI were included in this study. Four potential biomarkers were identified: AAT, TRSF, high-density lipoprotein cholesterol (HDLC), and apolipoprotein A1 (APOA1). After one month treatment, the levels of AAT and APOA1 were significantly improved. The panel consisting of these potential biomarkers had an excellent diagnostic performance, yielding an area under the ROC curve (AUC) of 0.994 and 0.990 in the training and testing set, respectively. Moreover, this panel could effectively distinguish MDD patients with SI from MDD patients without SI (AUC=0.928). Conclusion These results showed that these potential biomarkers could facilitate the development of an objective method for diagnosing MDD patients with SI, and the decreased AAT levels in MDD patients might lead to the appearance of SI by resulting in the elevated inflammation.

show abstract

Section: Introductionmentioning

confidence: 97%

Potential Biomarkers for Diagnosing Major Depressive Disorder Patients with Suicidal Ideation

Bai

Fang

Xie

et al. 2021

JIR

View full text Add to dashboard Cite

show abstract

“…In this context, reducing the burden of MDD is vital. This is achievable through the application of accurate risk prediction tools, which could enable the early identification of individuals more prone to the development of MDD [5]. For instance, alexithymia, a trait characterized by the difficulty of identifying feelings and emotions and by lack of motivation, may be considered a risk factor for the development of MDD, as well as suicide attempts [6].…”

Section: Introductionmentioning

confidence: 99%

Exploring the Role of Gut Microbiota in Major Depressive Disorder and in Treatment Resistance to Antidepressants

et al. 2020

View full text Add to dashboard Cite

Major depressive disorder (MDD) is a common severe psychiatric illness, exhibiting sub-optimal response to existing pharmacological treatments. Although its etiopathogenesis is still not completely understood, recent findings suggest that an altered composition of the gut microbiota might play a role. Here we aimed to explore potential differences in the composition of the gut microbiota between patients with MDD and healthy controls (HC) and to identify possible signatures of treatment response by analyzing two groups of MDD patients characterized as treatment-resistant (TR) or responders (R) to antidepressants. Stool samples were collected from 34 MDD patients (8 TR, 19 R and 7 untreated) and 20 HC. Microbiota was characterized using the 16S metagenomic approach. A penalized logistic regression analysis algorithm was applied to identify bacterial populations that best discriminate the diagnostic groups. Statistically significant differences were identified for the families of Paenibacillaceae and Flavobacteriaceaea, for the genus Fenollaria, and the species Flintibacter butyricus, Christensenella timonensis, and Eisenbergiella massiliensis among others. The phyla Proteobacteria, Tenericutes and the family Peptostreptococcaceae were more abundant in TR, whereas the phylum Actinobacteria was enriched in R patients. Moreover, a number of bacteria only characterized the microbiota of TR patients, and many others were only detected in R. Our results confirm that dysbiosis is a hallmark of MDD and suggest that microbiota of TR patients significantly differs from responders to antidepressants. This finding further supports the relevance of an altered composition of the gut microbiota in the etiopathogenesis of MDD, suggesting a role in response to antidepressants.

show abstract

“…Overall, our model evaluations provide a more reliable and conservative measure of ML performance compared with prior studies (Bhak et al, 2019; Guilloux et al, 2015; Khodayari‐Rostamabad, Reilly, Hasey, Debruin, & Maccrimmon, 2010; Yi et al, 2012; Yu et al, 2016). Specifically, previously published studies perform feature selection, often through DEG analysis, and training of the ML classifier based on the set of preselected features, on the same dataset (Bhak et al, 2019; Yi et al, 2012).…”

Section: Discussionmentioning

confidence: 70%

“…Yu, Xue, Redei, and Bagheri (2016) applied an SVM approach to classify MDD cases and controls based on expression data of preselected blood RNA markers, measured using quantitative real-time polymerase chain reaction. Recently, a study by Bhak et al (2019) utilized a multi-omics approach. A random forest classifier was applied on blood transcriptomic and methylomic data, combined, to distinguish between MDD cases, suicide attempters, and controls.…”

Section: Introductionmentioning

confidence: 99%

Machine learning and bioinformatic analysis of brain and blood mRNA profiles in major depressive disorder: A case–control study

Ramamurthy

Bennani

et al. 2021

American J of Med Genetics Pt B

View full text Add to dashboard Cite

This study analyzed gene expression messenger RNA data, from cases with major depressive disorder (MDD) and controls, using supervised machine learning (ML). We built on the methodology of prior studies to obtain more generalizable/reproducible results. First, we obtained a classifier trained on gene expression data from the dorsolateral prefrontal cortex of post‐mortem MDD cases (n = 126) and controls (n = 103). An average area‐under‐the‐receiver‐operating‐characteristics‐curve (AUC) from 10‐fold cross‐validation of 0.72 was noted, compared to an average AUC of 0.55 for a baseline classifier (p = .0048). The classifier achieved an AUC of 0.76 on a previously unused testing‐set. We also performed external validation using DLPFC gene expression values from an independent cohort of matched MDD cases (n = 29) and controls (n = 29), obtained from Affymetrix microarray (vs. Illumina microarray for the original cohort) (AUC: 0.62). We highlighted gene sets differentially expressed in MDD that were enriched for genes identified by the ML algorithm. Next, we assessed the ML classification performance in blood‐based microarray gene expression data from MDD cases (n = 1,581) and controls (n = 369). We observed a mean AUC of 0.64 on 10‐fold cross‐validation, which was significantly above baseline (p = .0020). Similar performance was observed on the testing‐set (AUC: 0.61). Finally, we analyzed the classification performance in covariates subgroups. We identified an interesting interaction between smoking and recall performance in MDD case prediction (58% accurate predictions in cases who are smokers vs. 43% accurate predictions in cases who are non‐smokers). Overall, our results suggest that ML in combination with gene expression data and covariates could further our understanding of the pathophysiology in MDD.

show abstract

Depression and suicide risk prediction models using blood-derived multi-omics data

Cited by 51 publications

References 37 publications

Potential Biomarkers for Diagnosing Major Depressive Disorder Patients with Suicidal Ideation

Potential Biomarkers for Diagnosing Major Depressive Disorder Patients with Suicidal Ideation

Exploring the Role of Gut Microbiota in Major Depressive Disorder and in Treatment Resistance to Antidepressants

Machine learning and bioinformatic analysis of brain and blood mRNA profiles in major depressive disorder: A case–control study

Contact Info

Product

Resources

About