Predicting pediatric anxiety from the temporal pole using neural responses to emotional faces

AbstractA prominent cognitive aspect of anxiety is dysregulation of emotional interpretation of facial expressions, associated with neural activity from the amygdala and prefrontal cortex. We report machine learning analysis of fMRI results supporting a key role for a third area, the temporal pole (TP) for childhood anxiety in this context. This finding is based on differential fMRI responses to emotional faces (angry versus fearful faces) in children with one or more of generalized anxiety, separation anxiety, and social phobia (n = 22) compared with matched controls (n = 23). In our machine learning (Adaptive Boosting) model, the right TP distinguished anxious from control children (accuracy = 81%). Involvement of the TP as significant for neurocognitive aspects of pediatric anxiety is a novel finding worthy of further investigation.

Download Full-text

fMRI-Based Machine Learning Analysis of Neural Substrates of Pediatric Anxiety: Temporal Pole and Emotional Face-Responses.

10.21203/rs.3.rs-120600/v1 ◽

2020 ◽

Author(s):

Jeffrey Sawalha ◽

Muhammad Yousefnezhad ◽

Alessandro Selvitella ◽

Bo Cao ◽

Andrew Greenshaw ◽

...

Keyword(s):

Machine Learning ◽

Separation Anxiety ◽

Childhood Anxiety ◽

Fearful Faces ◽

Pediatric Anxiety ◽

Machine Learning Model ◽

Temporal Pole ◽

The Right ◽

Emotional Face ◽

Learning Analysis

Abstract A prominent cognitive aspect of anxiety is dysregulation of emotional interpretation of facial expressions, associated with neural activity from the amygdala and prefrontal cortex. We report machine learning analysis of fMRI results supporting a key role for a third area, the temporal pole (TP) for childhood anxiety in this context. This finding is based on differential fMRI responses to emotional faces (e.g. angry versus fearful faces) in children with one or more of generalized anxiety, separation anxiety, and social phobia (n = 22) compared with matched controls (n = 23). In our machine learning model, the right TP distinguished anxious from control children (accuracy = 81%). Involvement of the TP as significant for neurocognitive aspects of pediatric anxiety is a novel finding worthy of further investigation.

Download Full-text

Neural Responses to Consciously and Unconsciously Perceived Emotional Faces: A Spinal fMRI Study

Brain Sciences ◽

10.3390/brainsci8080156 ◽

2018 ◽

Vol 8 (8) ◽

pp. 156 ◽

Cited By ~ 1

Author(s):

Alyssia Wilson ◽

Tiffany Kolesar ◽

Jennifer Kornelsen ◽

Stephen Smith

Keyword(s):

Spinal Cord ◽

Cervical Spinal Cord ◽

Spin Echo ◽

Single Shot ◽

Neural Responses ◽

Emotional Modulation ◽

Potential Threat ◽

Emotional Faces ◽

Fearful Faces ◽

Spinal Fmri

Emotional stimuli modulate activity in brain areas related to attention, perception, and movement. Similar increases in neural activity have been detected in the spinal cord, suggesting that this understudied component of the central nervous system is an important part of our emotional responses. To date, previous studies of emotion-dependent spinal cord activity have utilized long presentations of complex emotional scenes. The current study differs from this research by (1) examining whether emotional faces will lead to enhanced spinal cord activity and (2) testing whether these stimuli require conscious perception to influence neural responses. Fifteen healthy undergraduate participants completed six spinal functional magnetic resonance imaging (fMRI) runs in which three one-minute blocks of fearful, angry, or neutral faces were interleaved with 40-s rest periods. In half of the runs, the faces were clearly visible while in the other half, the faces were displayed for only 17 ms. Spinal fMRI consisted of half-Fourier acquisition single-shot turbo spin-echo (HASTE) sequences targeting the cervical spinal cord. The results indicated that consciously perceived faces expressing anger elicited significantly more activity than fearful or neutral faces in ventral (motoric) regions of the cervical spinal cord. When stimuli were presented below the threshold of conscious awareness, neutral faces elicited significantly more activity than angry or fearful faces. Together, these data suggest that the emotional modulation of spinal cord activity is most impactful when the stimuli are consciously perceived and imply a potential threat toward the observer.

Download Full-text

Brain Responsivity to Emotional Faces Differs in Alcoholic Men and Women

10.1101/496166 ◽

2019 ◽

Cited By ~ 1

Author(s):

Marlene Oscar-Berman ◽

Susan Mosher Ruiz ◽

Ksenija Marinkovic ◽

Mary M. Valmas ◽

Gordon J. Harris ◽

...

Keyword(s):

Gender Differences ◽

Emotional Processing ◽

Gender Effects ◽

Anterior Cingulate ◽

Reverse Direction ◽

Neural Responses ◽

Neuropsychological Dysfunction ◽

Emotional Faces ◽

The Right ◽

Emotional Face

AbstractInclusion of women in alcoholism research has shown that gender differences contribute to unique profiles of cognitive, emotional, and neuropsychological dysfunction. We employed functional magnetic resonance imaging (fMRI) of abstinent long-term alcoholics (21 women [ALCw] and 21 men [ALCm]) and demographically-similar nonalcoholic controls (21 women [NCw] and 21 men [NCm]) to explore how gender and alcoholism interact to influence emotional processing and memory. Participants completed a delayed match-to-sample emotional face memory fMRI task. While the results corroborated reports implicating amygdalar, superior temporal, and cerebellar involvement in emotional processing overall, the alcoholic participants showed hypoactivation of the left intraparietal sulcus to encoding the identity of the emotional face stimuli. The nonalcoholic participants demonstrated more reliable gender differences in neural responses to encoding the identity of the emotional faces than did the alcoholic group, and widespread neural responses to these stimuli were more pronounced in the NCw than in the NCm. By comparison, gender differences among ALC participants were either smaller or in the opposite direction (higher brain activation in ALCm than ALCw). Specifically, Group by Gender interaction effects indicated stronger responses to emotional faces by ALCm than ALCw in the left superior frontal gyrus and the right inferior frontal sulcus, while NCw had stronger responses than NCm. However, this pattern was inconsistent throughout the brain, with results suggesting the reverse direction of gender effects in the hippocampus and anterior cingulate cortex. Together, these findings demonstrated that gender plays a significant role in the profile of functional brain abnormalities observed in alcoholism.

Download Full-text

Case of Asperger's Syndrome and Lesion of the Right Amygdala: Deficits in Implicit and Explicit Fearful Face Recognition

Frontiers in Psychology ◽

10.3389/fpsyg.2021.677549 ◽

2021 ◽

Vol 12 ◽

Author(s):

Katja Koelkebeck ◽

Jochen Bauer ◽

Thomas Suslow ◽

Patricia Ohrmann

Keyword(s):

Emotion Recognition ◽

Male Patient ◽

Recognition Task ◽

Facial Emotion ◽

Implicit Processing ◽

Emotional Faces ◽

Amygdala Activation ◽

Fearful Faces ◽

The Right ◽

Implicit And Explicit

Introduction: Studies of brain-damaged patients revealed that amygdala lesions cause deficits in the processing and recognition of emotional faces. Patients with autism spectrum disorders (ASD) have similar deficits also related to dysfunctions of the limbic system including the amygdala.Methods: We investigated a male patient who had been diagnosed with Asperger's syndrome. He also presented with a lesion of the right mesial temporal cortex, including the amygdala. We used functional magnetic resonance imaging (fMRI) to investigate neuronal processing during a passive viewing task of implicit and explicit emotional faces. Clinical assessment included a facial emotion recognition task.Results: There was no amygdala activation on both sides during the presentation of masked emotional faces compared to the no-face control condition. Presentation of unmasked happy and angry faces activated the left amygdala compared to the no-face control condition. There was no amygdala activation in response to unmasked fearful faces on both sides. In the facial emotion recognition task, the patient biased positive and neutral expressions as negative.Conclusions: This case report describes a male patient with right amygdala damage and an ASD. He displayed a non-response of the amygdala to fearful faces and tended to misinterpret fearful expressions. Moreover, a non-reactivity of both amygdalae to emotional facial expressions at an implicit processing level was revealed. It is discussed whether the deficient implicit processing of facial emotional information and abnormalities in fear processing could contribute and aggravate the patient's impairments in social behavior and interaction.

Download Full-text

Abnormal Early Gamma Responses to Emotional Faces Differentiate Unipolar from Bipolar Disorder Patients

BioMed Research International ◽

10.1155/2014/906104 ◽

2014 ◽

Vol 2014 ◽

pp. 1-9 ◽

Cited By ~ 4

Author(s):

T. Y. Liu ◽

Y. S. Chen ◽

T. P. Su ◽

J. C. Hsieh ◽

L. F. Chen

Keyword(s):

Bipolar Disorder ◽

Early Stage ◽

Bipolar Disorders ◽

Gamma Oscillations ◽

Gamma Activity ◽

Depression Symptoms ◽

Emotional Faces ◽

Temporal Pole ◽

The Right ◽

Normal Controls

This study investigates the cortical abnormalities of early emotion perception in patients with major depressive disorder (MDD) and bipolar disorder (BD) using gamma oscillations. Twenty-three MDD patients, twenty-five BD patients, and twenty-four normal controls were enrolled and their event-related magnetoencephalographic responses were recorded during implicit emotional tasks. Our results demonstrated abnormal gamma activity within 100 ms in the emotion-related regions (amygdala, orbitofrontal (OFC) cortex, anterior insula (AI), and superior temporal pole) in the MDD patients, suggesting that these patients may have dysfunctions or negativity biases in perceptual binding of emotional features at very early stage. Decreased left superior medial frontal cortex (smFC) responses to happy faces in the MDD patients were correlated with their serious level of depression symptoms, indicating that decreased smFC activity perhaps underlies irregular positive emotion processing in depressed patients. In the BD patients, we showed abnormal activation in visual regions (inferior/middle occipital and middle temporal cortices) which responded to emotional faces within 100 ms, supporting that the BD patients may hyperactively respond to emotional features in perceptual binding. The discriminant function of gamma activation in the left smFC, right medial OFC, right AI/inferior OFC, and the right precentral cortex accurately classified 89.6% of patients as unipolar/bipolar disorders.

Download Full-text

A Machine Learning Application for Raising WASH Awareness in the Times of COVID-19 Pandemic (Preprint)

10.2196/preprints.25320 ◽

2020 ◽

Cited By ~ 1

Author(s):

Rohan Pandey ◽

Vaibhav Gautam ◽

Ridam Pal ◽

Harsh Bandhey ◽

Lovedeep Singh Dhingra ◽

...

Keyword(s):

Machine Learning ◽

Natural Language Processing ◽

Natural Language ◽

Machine Translation ◽

Language Processing ◽

User Feedback ◽

Who Guidelines ◽

The Times ◽

The Right ◽

Local Languages

BACKGROUND The COVID-19 pandemic has uncovered the potential of digital misinformation in shaping the health of nations. The deluge of unverified information that spreads faster than the epidemic itself is an unprecedented phenomenon that has put millions of lives in danger. Mitigating this ‘Infodemic’ requires strong health messaging systems that are engaging, vernacular, scalable, effective and continuously learn the new patterns of misinformation. OBJECTIVE We created WashKaro, a multi-pronged intervention for mitigating misinformation through conversational AI, machine translation and natural language processing. WashKaro provides the right information matched against WHO guidelines through AI, and delivers it in the right format in local languages. METHODS We theorize (i) an NLP based AI engine that could continuously incorporate user feedback to improve relevance of information, (ii) bite sized audio in the local language to improve penetrance in a country with skewed gender literacy ratios, and (iii) conversational but interactive AI engagement with users towards an increased health awareness in the community. RESULTS A total of 5026 people who downloaded the app during the study window, among those 1545 were active users. Our study shows that 3.4 times more females engaged with the App in Hindi as compared to males, the relevance of AI-filtered news content doubled within 45 days of continuous machine learning, and the prudence of integrated AI chatbot “Satya” increased thus proving the usefulness of an mHealth platform to mitigate health misinformation. CONCLUSIONS We conclude that a multi-pronged machine learning application delivering vernacular bite-sized audios and conversational AI is an effective approach to mitigate health misinformation. CLINICALTRIAL Not Applicable

Download Full-text

Machine Learning Approach for Predicting Lane-Change Maneuvers using the SHRP2 Naturalistic Driving Study Data

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/03611981211003581 ◽

2021 ◽

pp. 036119812110035

Author(s):

Anik Das ◽

Mohamed M. Ahmed

Keyword(s):

Machine Learning ◽

Prediction Accuracy ◽

Machine Learning Algorithms ◽

Support Vector ◽

Lane Change ◽

Adaptive Boosting ◽

Extreme Gradient Boosting ◽

Naturalistic Driving Study ◽

Naturalistic Driving ◽

Change Prediction

Accurate lane-change prediction information in real time is essential to safely operate Autonomous Vehicles (AVs) on the roadways, especially at the early stage of AVs deployment, where there will be an interaction between AVs and human-driven vehicles. This study proposed reliable lane-change prediction models considering features from vehicle kinematics, machine vision, driver, and roadway geometric characteristics using the trajectory-level SHRP2 Naturalistic Driving Study and Roadway Information Database. Several machine learning algorithms were trained, validated, tested, and comparatively analyzed including, Classification And Regression Trees (CART), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Support Vector Machine (SVM), K Nearest Neighbor (KNN), and Naïve Bayes (NB) based on six different sets of features. In each feature set, relevant features were extracted through a wrapper-based algorithm named Boruta. The results showed that the XGBoost model outperformed all other models in relation to its highest overall prediction accuracy (97%) and F1-score (95.5%) considering all features. However, the highest overall prediction accuracy of 97.3% and F1-score of 95.9% were observed in the XGBoost model based on vehicle kinematics features. Moreover, it was found that XGBoost was the only model that achieved a reliable and balanced prediction performance across all six feature sets. Furthermore, a simplified XGBoost model was developed for each feature set considering the practical implementation of the model. The proposed prediction model could help in trajectory planning for AVs and could be used to develop more reliable advanced driver assistance systems (ADAS) in a cooperative connected and automated vehicle environment.

Download Full-text

Machine Learning-Based Prediction of Air Quality

Applied Sciences ◽

10.3390/app10249151 ◽

2020 ◽

Vol 10 (24) ◽

pp. 9151

Author(s):

Yun-Chia Liang ◽

Yona Maimury ◽

Angela Hsiang-Ling Chen ◽

Josue Rodolfo Cuevas Juarez

Keyword(s):

Machine Learning ◽

Air Quality ◽

Random Forest ◽

Prediction Models ◽

Superior Performance ◽

Support Vector ◽

Economic Activities ◽

Adaptive Boosting ◽

Series Of Experiments ◽

Artificial Neural Network Ann

Air, an essential natural resource, has been compromised in terms of quality by economic activities. Considerable research has been devoted to predicting instances of poor air quality, but most studies are limited by insufficient longitudinal data, making it difficult to account for seasonal and other factors. Several prediction models have been developed using an 11-year dataset collected by Taiwan’s Environmental Protection Administration (EPA). Machine learning methods, including adaptive boosting (AdaBoost), artificial neural network (ANN), random forest, stacking ensemble, and support vector machine (SVM), produce promising results for air quality index (AQI) level predictions. A series of experiments, using datasets for three different regions to obtain the best prediction performance from the stacking ensemble, AdaBoost, and random forest, found the stacking ensemble delivers consistently superior performance for R2 and RMSE, while AdaBoost provides best results for MAE.

Download Full-text