Suicide risk stratification among major depressed patients based on a machine learning approach and whole-brain functional connectivity

Chen, Shengli; Zhang, Xiaojing; Lin, Shiu‐Ru; Zhang, Yingli; Xu, Ziyun; Li, Yanqing; Xu, Manxi; Hou, Gangqiang; Qiu, Yingwei

doi:10.1016/j.jad.2022.11.022

Cited by 5 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNN resulted the most accurate prediction model. Chen et al, [ 55 ] 36 MDD with low-risk (19/17); 126 MDD with high-risk (86/40) MDD Unmedicated SVM (LOOCV) rsMRI Low vs High suicide risk Acc: 0.85 AUC: 0.87 Sens: 0.86 Spec: 0.78 intra-network dysconnectivity in the sensorimotor network and inter-network dysconnectivity between the default and dorsal attention network characterized high-risk patients Chen et al, [ 47 ] 32 BD with suicidal ideation (21/11); 18 BD without suicidal ideation (9/9) BD Not specified SVM (LOOCV, 1000 permutation) 12 features from 1 H-MRS (biochemical metabolite ratios in the bilateral prefrontal white matter and hippocampus) Suicide ideation Acc: 0.88 AUC: 0.90 Sens: 0.94 Spec: 0.78 The most relevant features were NAA/Cr ratios in the bilateral WM, mI/Cr ratios in the bilateral WM, and NAA/Cr ratios and Cho/Cr ratios in the left hippocampus Zhong et al, [ 80 ] 30 BD II with suicide attempts (23/7); 38 BD II without suicide attempts (21/17); 35 HC (19/16) BD II Unmedicated SVM (10-folds CV) Dynamic functional network connectivity based on rsMRI Suicide attempts Acc: 0.75 AUC: 0.83 Sens: 0.70 Spec: 0.79 Decreased dynamic functional connectivity variability between the left putamen and the right postcentral gyrus was found in non-suicidal compared to suicidal BD II and HC. Xu et al, [ 60 ] 51 MDD with suicidal attempts (39/12); 74 MDD with suicidal ideation (49/25); 48 MDD without ideation/attempts (28/20); 38 HC (25/13) MDD Not specified SVM (LOOCV) Dynamic functional network connectivity based on rsMRI (>200 features) Suicide attempts and ideation MDD suicide attemps vs NS Acc: 0.80 AUC: 0.88 Sens: 0.88 Spec: 0.…”

Section: Resultsmentioning

confidence: 99%

“…Moreover, 14 studies predicted suicide ideation alone [ 45 – 55 ] or in combination with suicide attempts [ 56 – 60 ]. Finally, other studies predicted self-harm [ 61 – 64 ], suicide risk [ 38 , 55 , 65 – 70 ], the number of suicide attempts [ 71 ], and the presence of a familiar history of suicide [ 72 ].…”

Section: Resultsmentioning

confidence: 99%

“…Ten studies employed brain imaging data to predict suicide: seven studies used resting-state MRI (rsMRI) [ 54 , 55 , 60 , 68 , 69 , 79 , 80 ], two used both rsMRI and structural MRI [ 58 , 81 ], three used diffusion tensor imaging (DTI) [ 49 , 59 , 82 ], and one structural MRI in combination with clinical and demographic data [ 53 ], and one single study employed measures from spectroscopy [ 47 ]. Eight studies (13.6%) analyzed the text obtained from interviews and EHR using natural language processing (NLP).…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Machine learning and the prediction of suicide in psychiatric populations: a systematic review

Pigoni,

Delvecchio,

Turtulici

et al. 2024

Transl Psychiatry

View full text Add to dashboard Cite

Machine learning (ML) has emerged as a promising tool to enhance suicidal prediction. However, as many large-sample studies mixed psychiatric and non-psychiatric populations, a formal psychiatric diagnosis emerged as a strong predictor of suicidal risk, overshadowing more subtle risk factors specific to distinct populations. To overcome this limitation, we conducted a systematic review of ML studies evaluating suicidal behaviors exclusively in psychiatric clinical populations. A systematic literature search was performed from inception through November 17, 2022 on PubMed, EMBASE, and Scopus following the PRISMA guidelines. Original research using ML techniques to assess the risk of suicide or predict suicide attempts in the psychiatric population were included. An assessment for bias risk was performed using the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) guidelines. About 1032 studies were retrieved, and 81 satisfied the inclusion criteria and were included for qualitative synthesis. Clinical and demographic features were the most frequently employed and random forest, support vector machine, and convolutional neural network performed better in terms of accuracy than other algorithms when directly compared. Despite heterogeneity in procedures, most studies reported an accuracy of 70% or greater based on features such as previous attempts, severity of the disorder, and pharmacological treatments. Although the evidence reported is promising, ML algorithms for suicidal prediction still present limitations, including the lack of neurobiological and imaging data and the lack of external validation samples. Overcoming these issues may lead to the development of models to adopt in clinical practice. Further research is warranted to boost a field that holds the potential to critically impact suicide mortality.

show abstract