Machine learning models for diagnosis and risk prediction in eating disorders, depression, and alcohol use disorder.

This study uses machine learning models to uncover diagnostic and risk prediction markers for eating disorders (EDs), major depressive disorder (MDD), and alcohol use disorder (AUD). Utilizing case-control samples (ages 18-25 years) and a longitudinal population-based sample (n=1,851), the models, incorporating diverse data domains, achieved high accuracy in classifying EDs, MDD, and AUD from healthy controls. The area under the receiver operating characteristic curves (AUC-ROC [95% CI]) reached 0.92 [0.86-0.97] for AN and 0.91 [0.85-0.96] for BN, without relying on body mass index as a predictor. The classification accuracies for MDD (0.91 [0.88-0.94]) and AUD (0.80 [0.74-0.85]) were also high. Each data domain emerged as accurate classifiers individually, with personality distinguishing AN, BN, and their controls with AUC-ROCs ranging from 0.77 to 0.89. The models demonstrated high transdiagnostic potential, as those trained for EDs were also accurate in classifying AUD and MDD from healthy controls, and vice versa (AUC-ROCs, 0.75-0.93). Shared predictors, such as neuroticism, hopelessness, and symptoms of attention-deficit/hyperactivity disorder, were identified as reliable classifiers. For risk prediction in the longitudinal population sample, the models exhibited moderate performance (AUC-ROCs, 0.64-0.71), highlighting the potential of combining multi-domain data for precise diagnostic and risk prediction applications in psychiatry.

Differing impact of the COVID-19 pandemic on youth mental health: combined population and clinical study.

BACKGROUND: Identifying youths most at risk to COVID-19-related mental illness is essential for the development of effective targeted interventions. AIMS: To compare trajectories of mental health throughout the pandemic in youth with and without prior mental illness and identify those most at risk of COVID-19-related mental illness. METHOD: Data were collected from individuals aged 18-26 years (N = 669) from two existing cohorts: IMAGEN, a population-based cohort; and ESTRA/STRATIFY, clinical cohorts of individuals with pre-existing diagnoses of mental disorders. Repeated COVID-19 surveys and standardised mental health assessments were used to compare trajectories of mental health symptoms from before the pandemic through to the second lockdown. RESULTS: Mental health trajectories differed significantly between cohorts. In the population cohort, depression and eating disorder symptoms increased by 33.9% (95% CI 31.78-36.57) and 15.6% (95% CI 15.39-15.68) during the pandemic, respectively. By contrast, these remained high over time in the clinical cohort. Conversely, trajectories of alcohol misuse were similar in both cohorts, decreasing continuously (a 15.2% decrease) during the pandemic. Pre-pandemic symptom severity predicted the observed mental health trajectories in the population cohort. Surprisingly, being relatively healthy predicted increases in depression and eating disorder symptoms and in body mass index. By contrast, those initially at higher risk for depression or eating disorders reported a lasting decrease. CONCLUSIONS: Healthier young people may be at greater risk of developing depressive or eating disorder symptoms during the COVID-19 pandemic. Targeted mental health interventions considering prior diagnostic risk may be warranted to help young people cope with the challenges of psychosocial stress and reduce the associated healthcare burden.

Towards smart glasses for facial expression recognition using OMG and machine learning.

This study aimed to evaluate the use of novel optomyography (OMG) based smart glasses, OCOsense, for the monitoring and recognition of facial expressions. Experiments were conducted on data gathered from 27 young adult participants, who performed facial expressions varying in intensity, duration, and head movement. The facial expressions included smiling, frowning, raising the eyebrows, and squeezing the eyes. The statistical analysis demonstrated that: (i) OCO sensors based on the principles of OMG can capture distinct variations in cheek and brow movements with a high degree of accuracy and specificity; (ii) Head movement does not have a significant impact on how well these facial expressions are detected. The collected data were also used to train a machine learning model to recognise the four facial expressions and when the face enters a neutral state. We evaluated this model in conditions intended to simulate real-world use, including variations in expression intensity, head movement and glasses position relative to the face. The model demonstrated an overall accuracy of 93% (0.90 f1-score)-evaluated using a leave-one-subject-out cross-validation technique.

Optomyography-based sensing of facial expression derived arousal and valence in adults with depression.

Background: Continuous assessment of affective behaviors could improve the diagnosis, assessment and monitoring of chronic mental health and neurological conditions such as depression. However, there are no technologies well suited to this, limiting potential clinical applications. Aim: To test if we could replicate previous evidence of hypo reactivity to emotional salient material using an entirely new sensing technique called optomyography which is well suited to remote monitoring. Methods: Thirty-eight depressed and 37 controls (≥18, ≤40 years) who met a research diagnosis of depression and an age-matched non-depressed control group. Changes in facial muscle activity over the brow (corrugator supercilli) and cheek (zygomaticus major) were measured whilst volunteers watched videos varying in emotional salience. Results: Across all participants, videos rated as subjectively positive were associated with activation of muscles in the cheek relative to videos rated as neutral or negative. Videos rated as subjectively negative were associated with brow activation relative to videos judged as neutral or positive. Self-reported arousal was associated with a step increase in facial muscle activation across the brow and cheek. Group differences were significantly reduced activation in facial muscles during videos considered subjectively negative or rated as high arousal in depressed volunteers compared with controls. Conclusion: We demonstrate for the first time that it is possible to detect facial expression hypo-reactivity in adults with depression in response to emotional content using glasses-based optomyography sensing. It is hoped these results may encourage the use of optomyography-based sensing to track facial expressions in the real-world, outside of a specialized testing environment.

A shared neural basis underlying psychiatric comorbidity.

Recent studies proposed a general psychopathology factor underlying common comorbidities among psychiatric disorders. However, its neurobiological mechanisms and generalizability remain elusive. In this study, we used a large longitudinal neuroimaging cohort from adolescence to young adulthood (IMAGEN) to define a neuropsychopathological (NP) factor across externalizing and internalizing symptoms using multitask connectomes. We demonstrate that this NP factor might represent a unified, genetically determined, delayed development of the prefrontal cortex that further leads to poor executive function. We also show this NP factor to be reproducible in multiple developmental periods, from preadolescence to early adulthood, and generalizable to the resting-state connectome and clinical samples (the ADHD-200 Sample and the Stratify Project). In conclusion, we identify a reproducible and general neural basis underlying symptoms of multiple mental health disorders, bridging multidimensional evidence from behavioral, neuroimaging and genetic substrates. These findings may help to develop new therapeutic interventions for psychiatric comorbidities.

Facial EMG sensing for monitoring affect using a wearable device.

Using a novel wearable surface electromyography (sEMG), we investigated induced affective states by measuring the activation of facial muscles traditionally associated with positive (left/right orbicularis and left/right zygomaticus) and negative expressions (the corrugator muscle). In a sample of 38 participants that watched 25 affective videos in a virtual reality environment, we found that each of the three variables examined-subjective valence, subjective arousal, and objective valence measured via the validated video types (positive, neutral, and negative)-sEMG amplitude varied significantly depending on video content. sEMG aptitude from "positive muscles" increased when participants were exposed to positively valenced stimuli compared with stimuli that was negatively valenced. In contrast, activation of "negative muscles" was elevated following exposure to negatively valenced stimuli compared with positively valenced stimuli. High arousal videos increased muscle activations compared to low arousal videos in all the measured muscles except the corrugator muscle. In line with previous research, the relationship between sEMG amplitude as a function of subjective valence was V-shaped.

Default mode network connectivity and attention-deficit/hyperactivity disorder in adolescence: Associations with delay aversion and temporal discounting, but not mind wandering.

BACKGROUND: Attention-deficit/hyperactivity disorder (ADHD) has been associated with reduced resting state connectivity in the core subsystem of the default mode network (DMN; medial prefrontal cortex - posterior cingulate cortex). However, the neuropsychological consequences of this hypoconnectivity remain to be determined. Building on recent theoretical models of DMN function, we tested the association between DMN hypo-connectivity and three neuropsychological processes previously implicated in ADHD: (i) excessive task-unrelated spontaneous thought (i.e., mind-wandering); (ii) sub-optimal decision-making due to exaggerated temporal discounting; and (iii) delay aversion - a heightened emotional response to the imposition or experience of delay. METHODS: Twenty male adolescents with a clinical diagnosis of ADHD and 18 typically developing adolescents (all aged 11-16 years) underwent a resting-state fMRI scan to assess DMN connectivity. An experimental paradigm was used to assess temporal discounting and self-report questionnaires were used to measure mind wandering and delay aversion. RESULTS: ADHD was significantly associated with DMN hypo-connectivity specifically in the core subsystem, elevated levels of mind-wandering, delay aversion, and temporal discounting. Mediation analysis suggested that DMN hypoconnectivity mediated the link between ADHD and delay aversion. CONCLUSION: The results provide initial evidence that disturbances in the DMN may impair ability to regulate delay-related negative affect in adolescents with ADHD.

Brain Functional Connectivity Correlates of Response in the 7.5% CO2 Inhalational Model of Generalized Anxiety Disorder: A Pilot Study.

BACKGROUND: The 7.5% CO2 inhalational model can be used to explore potential treatments for generalized anxiety disorder. However, it is unknown how inter-individual variability in the functional architecture of negative affective valence systems might relate to anxiogenic response in this model. METHODS: A total of 13 healthy volunteers underwent functional magnetic resonance imaging during a passive emotional face perception task. We explored task-evoked functional connectivity in the potential threat system through generalized psychophysiological interaction analysis. Within 7 days, these participants underwent prolonged 7.5% CO2 inhalation, and results from the generalized psychophysiological interaction analysis were correlated with CO2 outcome measures. RESULTS: Functional connectivity between ventromedial prefrontal cortex and right amygdala positively correlated with heart rate and subjective anxiety, while connectivity between midcingulate cortex and left amygdala negatively correlated with anxiety during CO2 challenge. CONCLUSIONS: Response to CO2 challenge correlated with task-evoked functional connectivity in the potential threat system. Further studies should assess whether this translates into clinical populations.

Reduced Default Mode Connectivity in Adolescents With Conduct Disorder.

OBJECTIVE: Conduct disorder (CD) is characterized by impulsive, aggressive, and antisocial behaviors that might be related to deficits in empathy and moral reasoning. The brain's default mode network (DMN) has been implicated in self-referential cognitive processes of this kind. METHOD: This study examined connectivity between key nodes of the DMN in 29 adolescent boys with CD and 29 age- and sex-matched typically developing adolescent boys. The authors ensured that group differences in DMN connectivity were not explained by comorbidity with other disorders by systematically controlling for the effects of substance use disorders (SUDs), attention-deficit/hyperactivity disorder (ADHD) symptoms, psychopathic traits, and other common mental health problems. RESULTS: Only after adjusting for co-occurring ADHD symptoms, the group with CD showed hypoconnectivity between core DMN regions compared with typically developing controls. ADHD symptoms were associated with DMN hyperconnectivity. There was no effect of psychopathic traits on DMN connectivity in the group with CD, and the key results were unchanged when controlling for SUDs and other common mental health problems. CONCLUSION: Future research should directly investigate the possibility that the aberrant DMN connectivity observed in the present study contributes to CD-related deficits in empathy and moral reasoning and examine self-referential cognitive processes in CD more generally.