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

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

doi:10.1038/s41398-019-0595-2

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

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

Department of Biomedical Sciences

Research output: Contribution to journal › Article › peer-review

15 Citations (Scopus)

Abstract

More than 300 million people worldwide experience depression; annually, ~800,000 people die by suicide. Unfortunately, conventional interview-based diagnosis is insufficient to accurately predict a psychiatric status. We developed machine learning models to predict depression and suicide risk using blood methylome and transcriptome data from 56 suicide attempters (SAs), 39 patients with major depressive disorder (MDD), and 87 healthy controls. Our random forest classifiers showed accuracies of 92.6% in distinguishing SAs from MDD patients, 87.3% in distinguishing MDD patients from controls, and 86.7% in distinguishing SAs from controls. We also developed regression models for predicting psychiatric scales with R² values of 0.961 and 0.943 for Hamilton Rating Scale for Depression–17 and Scale for Suicide Ideation, respectively. Multi-omics data were used to construct psychiatric status prediction models for improved mental health treatment.

Original language	English
Article number	262
Journal	Translational psychiatry
Volume	9
Issue number	1
DOIs	https://doi.org/10.1038/s41398-019-0595-2
Publication status	Published - 2019 Dec 1

ASJC Scopus subject areas

Psychiatry and Mental health
Cellular and Molecular Neuroscience
Biological Psychiatry

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1038/s41398-019-0595-2

Cite this

Bhak, Y., Jeong, H. O., Cho, Y. S., Jeon, S., Cho, J., Gim, J. A., Jeon, Y., Blazyte, A., Park, S. G., Kim, H. M., Shin, E. S., Paik, J. W., Lee, H. W., Kang, W., Kim, A., Kim, Y., Kim, B. C., Ham, B. J., Bhak, J., & Lee, S. (2019). Depression and suicide risk prediction models using blood-derived multi-omics data. Translational psychiatry, 9(1), [262]. https://doi.org/10.1038/s41398-019-0595-2

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; Blazyte, 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.

In: Translational psychiatry, Vol. 9, No. 1, 262, 01.12.2019.

Research output: Contribution to journal › Article › peer-review

Bhak, Youngjune ; Jeong, Hyoung oh ; Cho, Yun Sung ; Jeon, Sungwon ; Cho, Juok ; Gim, Jeong An ; Jeon, Yeonsu ; Blazyte, 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. / Depression and suicide risk prediction models using blood-derived multi-omics data. In: Translational psychiatry. 2019 ; Vol. 9, No. 1.

@article{eabdd52438bd4cbe9fd3acdc7e06b3a9,

title = "Depression and suicide risk prediction models using blood-derived multi-omics data",

abstract = "More than 300 million people worldwide experience depression; annually, ~800,000 people die by suicide. Unfortunately, conventional interview-based diagnosis is insufficient to accurately predict a psychiatric status. We developed machine learning models to predict depression and suicide risk using blood methylome and transcriptome data from 56 suicide attempters (SAs), 39 patients with major depressive disorder (MDD), and 87 healthy controls. Our random forest classifiers showed accuracies of 92.6% in distinguishing SAs from MDD patients, 87.3% in distinguishing MDD patients from controls, and 86.7% in distinguishing SAs from controls. We also developed regression models for predicting psychiatric scales with R2 values of 0.961 and 0.943 for Hamilton Rating Scale for Depression–17 and Scale for Suicide Ideation, respectively. Multi-omics data were used to construct psychiatric status prediction models for improved mental health treatment.",

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

note = "Funding Information: We thank Prof. Yoon-Kyung Cho for supporting this project. We also thank Korea University Anam Hospital members for helping source blood and information of participants. Korea Institute of Science and Technology Information (KISTI) provided us with the Korea Research Environment Open NETwork (KREONET). This work was supported by the Civil-Military Dual-Use Technology Development Program (14-BR-SS-03) through the Agency for Defense Development; U-K BRAND Research Fund (1.190007.01) of UNIST; Research Project Funded by Ulsan City Research Fund (1.190033.01) of UNIST; the Next-Generation Information Computing Development Program through the National Research Foundation of Korea funded by the Ministry of Science and ICT (NRF-2016M3C4A7952635). Publisher Copyright: {\textcopyright} 2019, The Author(s).",

year = "2019",

month = dec,

day = "1",

doi = "10.1038/s41398-019-0595-2",

language = "English",

volume = "9",

journal = "Translational Psychiatry",

issn = "2158-3188",

publisher = "Nature Publishing Group",

number = "1",

}

TY - JOUR

T1 - Depression and suicide risk prediction models using blood-derived multi-omics data

AU - Bhak, Youngjune

AU - Jeong, Hyoung oh

AU - Cho, Yun Sung

AU - Jeon, Sungwon

AU - Cho, Juok

AU - Gim, Jeong An

AU - Jeon, Yeonsu

AU - Blazyte, Asta

AU - Park, Seung Gu

AU - Kim, Hak Min

AU - Shin, Eun Seok

AU - Paik, Jong Woo

AU - Lee, Hae Woo

AU - Kang, Wooyoung

AU - Kim, Aram

AU - Kim, Yumi

AU - Kim, Byung Chul

AU - Ham, Byung Joo

AU - Bhak, Jong

AU - Lee, Semin

N1 - Funding Information: We thank Prof. Yoon-Kyung Cho for supporting this project. We also thank Korea University Anam Hospital members for helping source blood and information of participants. Korea Institute of Science and Technology Information (KISTI) provided us with the Korea Research Environment Open NETwork (KREONET). This work was supported by the Civil-Military Dual-Use Technology Development Program (14-BR-SS-03) through the Agency for Defense Development; U-K BRAND Research Fund (1.190007.01) of UNIST; Research Project Funded by Ulsan City Research Fund (1.190033.01) of UNIST; the Next-Generation Information Computing Development Program through the National Research Foundation of Korea funded by the Ministry of Science and ICT (NRF-2016M3C4A7952635). Publisher Copyright: © 2019, The Author(s).

PY - 2019/12/1

Y1 - 2019/12/1

N2 - More than 300 million people worldwide experience depression; annually, ~800,000 people die by suicide. Unfortunately, conventional interview-based diagnosis is insufficient to accurately predict a psychiatric status. We developed machine learning models to predict depression and suicide risk using blood methylome and transcriptome data from 56 suicide attempters (SAs), 39 patients with major depressive disorder (MDD), and 87 healthy controls. Our random forest classifiers showed accuracies of 92.6% in distinguishing SAs from MDD patients, 87.3% in distinguishing MDD patients from controls, and 86.7% in distinguishing SAs from controls. We also developed regression models for predicting psychiatric scales with R2 values of 0.961 and 0.943 for Hamilton Rating Scale for Depression–17 and Scale for Suicide Ideation, respectively. Multi-omics data were used to construct psychiatric status prediction models for improved mental health treatment.

AB - More than 300 million people worldwide experience depression; annually, ~800,000 people die by suicide. Unfortunately, conventional interview-based diagnosis is insufficient to accurately predict a psychiatric status. We developed machine learning models to predict depression and suicide risk using blood methylome and transcriptome data from 56 suicide attempters (SAs), 39 patients with major depressive disorder (MDD), and 87 healthy controls. Our random forest classifiers showed accuracies of 92.6% in distinguishing SAs from MDD patients, 87.3% in distinguishing MDD patients from controls, and 86.7% in distinguishing SAs from controls. We also developed regression models for predicting psychiatric scales with R2 values of 0.961 and 0.943 for Hamilton Rating Scale for Depression–17 and Scale for Suicide Ideation, respectively. Multi-omics data were used to construct psychiatric status prediction models for improved mental health treatment.

UR - http://www.scopus.com/inward/record.url?scp=85073559326&partnerID=8YFLogxK

U2 - 10.1038/s41398-019-0595-2

DO - 10.1038/s41398-019-0595-2

M3 - Article

C2 - 31624227

AN - SCOPUS:85073559326

VL - 9

JO - Translational Psychiatry

JF - Translational Psychiatry

SN - 2158-3188

IS - 1

M1 - 262

ER -

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

Abstract

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this