Objective
Predicting suicide is notoriously difficult and complex, but a serious public health issue. An innovative approach utilizing machine learning (ML) that incorporates features of psychological mechanisms and decision‐making characteristics related to suicidality could create an improved model for identifying suicide risk in patients with major depressive disorder (MDD).
Method
Forty‐four patients with MDD and past suicide attempts (MDD_SA, N = 44); 48 patients with MDD but without past suicide attempts (MDD_NS, N = 48–42 of whom with suicide ideation [MDD_SI, N = 42]), and healthy controls (HCs, N = 51) completed seven psychometric assessments including the Three‐dimensional Psychological Pain Scale (TDPPS), and one behavioral assessment, the Balloon Analogue Risk Task (BART). Descriptive statistics, group comparisons, logistic regressions, and ML were used to explore and compare the groups and generate predictors of suicidal acts.
Results
MDD_SA and MDD_NS differed in TDPPS total score, pain arousal and avoidance subscale scores, suicidal ideation scores, and relevant decision‐making indicators in BART. Logistic regression tests linked suicide attempts to psychological pain avoidance and a risk decision‐making indicator. The resultant key ML model distinguished MDD_SA/MDD_NS with 88.2% accuracy. The model could also distinguish MDD_SA/MDD_SI with 81.25% accuracy. The ML model using hopelessness could classify MDD_SI/HC with 94.4% accuracy.
Conclusion
ML analyses showed that motivation to avoid intolerable psychological pain, coupled with impaired decision‐making bias toward under‐valuing life's worth are highly predictive of suicide attempts. Analyses also demonstrated that suicidal ideation and attempts differed in potential mechanisms, as suicidal ideation was more related to hopelessness. ML algorithms show useful promises as a predictive instrument.
Background
In the last decade, suicidality has been increasingly theorized as a distinct phenomenon from major depressive disorder (MDD), with unique psychological and neural mechanisms, rather than being mostly a severe symptom of MDD. Although decision‐making biases have been widely reported in suicide attempters with MDD, little is known regarding what components of these biases can be distinguished from depressiveness itself.
Methods
Ninety‐three patients with current MDD (40 with suicide attempts [SA group] and 53 without suicide attempts [NS group]) and 65 healthy controls (HCs) completed psychometric assessments and the balloon analog risk task (BART). To analyze and compare decision‐making components among the three groups, we applied a five‐parameter Bayesian computational modeling.
Results
Psychological assessments showed that the SA group had greater suicidal ideation and psychological pain avoidance than the NS group. Computational modeling showed that both MDD groups had higher risk preference and lower ability to learn and adapt from within‐task observations than HCs, without differences between the SA and NS patient groups. The SA group also had higher loss aversion than the NS and HC groups, which had similar loss aversion.
Conclusions
Our BART and computational modeling findings suggest that psychological pain avoidance and loss aversion may be important suicide risk factor that are distinguishable from depression illness itself.
Background
Obsessive-compulsive personality disorder (OCPD) is a high-prevalence personality disorder characterized by subtle but stable interpersonal dysfunction. There have been only limited studies addressing the behavioral patterns and cognitive features of OCPD in interpersonal contexts. The purpose of this study was to investigate how behaviors differ between OCPD individuals and healthy controls (HCs) in the context of guilt-related interpersonal responses.
Method
A total of 113 participants were recruited, including 46 who were identified as having OCPD and 67 HCs. Guilt-related interpersonal responses were manipulated and measured with two social interactive tasks: the Guilt Aversion Task, to assess how anticipatory guilt motivates cooperation; and the Guilt Compensation Task, to assess how experienced guilt induces compensation behaviors. The guilt aversion model and Fehr–Schmidt inequity aversion model were adopted to analyze decision-making in the Guilt Aversion Task and the Guilt Compensation Task, respectively.
Results
Computational model-based results demonstrated that, compared with HCs, the OCPD group exhibited less guilt aversion when making cooperative decisions as well as less guilt-induced compensation after harming others.
Conclusion
Our findings indicate that individuals with OCPD tend to be less affected by guilt than HCs. These impairments in guilt-related responses may prevent adjustments in behaviors toward compliance with social norms and thus result in interpersonal dysfunctions.
Background: The human striatum is a heterogeneous structure involved in diverse functional domains that related to distinct striatum subregions. Striatal dysfunction was thought to be a fundamental element in schizophrenia. However, the connectivity pattern of striatum solely based on functional or structural characteristics leads to inconsistent findings in healthy adult and also schizophrenia. This study aims to develop an integrated striatal model and reveal the altered functional connectivity pattern of the striatum in schizophrenia.Methods: Two data-driven approaches, task-dependent meta-analytic connectivity modeling (MACM) and task-independent resting-state functional connectivity (RSFC), were used for seven anatomical connectivity-based striatum subregions to provide an integrated striatal model. Then, RSFC analyses of seven striatal subregions were applied to 45 first-episode schizophrenia (FES) and 27 healthy controls to examine the difference, based on the integrated model, of functional connectivity pattern of striatal subregions.Results: MACM and RSFC results showed that striatum subregions were associated with discrete cortical regions and involved in distinct cognitive processes. Besides, RSFC results overlapped with MACM findings but showed broader distributions. Importantly, significantly reduced functional connectivity was identified between limbic subregion and thalamus, medial prefrontal cortex, anterior cingulate cortex, and insula and also between executive subregions and thalamus, supplementary motor area, and insula in FES.Conclusions: Combing functional and structural connectivity information, this study provides the integrated model of corticostriatal subcircuits and confirms the abnormal functional connectivity of limbic and executive striatum subregions with different networks and thalamus, supporting the important role of the corticostriatal-thalamic loop in the pathophysiology of schizophrenia.
The subgenual anterior cingulate cortex (sgACC) appears to play a central role in the pathophysiology of major depressive disorder (MDD). To wit, its functional interactive profile with the left dorsal lateral prefrontal cortex (DLPFC) has been shown to be related to treatment outcomes with transcranial magnetic stimulation (TMS) treatment outcomes. Nevertheless, previous research on sgACC functional connectivity (FC) in MDD has yielded inconsistent results, partly due to small sample sizes and limited statistical power of prior work. Here, leveraging a large multi-site sample (1660 MDD patients vs. 1341 healthy controls) from Phase II of the Depression Imaging REsearch ConsorTium (DIRECT), we systematically delineated case-control difference maps of sgACC FC and examined their clinical relevance to previously identified TMS targets. We also investigated case-control FC difference maps of left DLPFC sub-fields. In MDD patients we found significantly increased FC between sgACC and thalamus and reduced FC to a broad array of brain regions, including somatosensory area, occipital lobe, medial and lateral temporal lobe, and insular cortex, when global signal regression (GSR) was not implemented. Intriguingly, we found enhanced left DLPFC-sgACC FC in MDD patients when GSR was performed. We leveraged an prior independent sample to explore the possible relationship between the case-control differences regarding sgACC's FC profiles and the treatment out comes of TMS. In sites in which open TMS treatment was administered, case-control differences in sgACC FC, with GSR, were related to clinical improvement. Next we tested whether the position of peak of the FC maps (previously identified TMS target) could be altered in MDD patients as compred with healthy controls (HC)s. We found the optimized TMS target differed in MDD patients. Several DLPFC sub-fields yielded case-control differences in whole-brain FC maps. In summary, we reliably delineated MDD-related abnormalities of sgACC FC profiles in a large sample. GSR was essential in applying case-control difference maps to identify optimized TMS targets. Our results highlight the functional heterogeneity of the left DLPFC and of precise TMS targets therein.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.