Research Interests

Network-Augmented Machine Learning (NAMU)

Suicidal ideation is a complex phenomenon shaped by interactions among depressive symptoms. Traditional prediction models often treat symptoms as independent, overlooking the meaningful relationships between them. My research introduces the Network-Augmented Machine Learning Utility (NAMU), which integrates network-derived features—such as symptom centrality and edge strength—into machine learning models to enhance interpretability.

Using PHQ-9 data from a nationally representative U.S. sample (NHANES; N = 46,373), we transformed eight depressive symptoms into 37 network-based features and identified a compact set of six features that yielded strong predictive performance (PR AUC: 90.34%). These features illuminated how specific symptoms and their interconnections contribute to suicide risk.

Following a recent poster presentation of this work, I am now extending NAMU to diverse clinical populations, including bipolar spectrum disorders, and testing its cross-cultural generalizability using Korean national data (KNHANES). This research highlights how machine learning, when grounded in symptom networks, can improve early identification and support culturally tailored mental health interventions.

Representative Research

• Kim, H., Yocum, A. K., McInnis, M. G., & Sperry, S. H. Enhancing suicidal ideation prediction and interpretability with Network-Augmented Machine Learning Utility (NAMU), Poster presented at the 35th Albert J. Silverman Conference, Ann Arbor, Michigan, USA.

A copy of the recently presented poster can be found here: [pdf]

Underlying Mechanisms of Affective Disorders

Repetitive negative thinking, such as rumination and worry, is a common and detrimental pattern of thought. These thoughts can exacerbate cognitive, physical, and interpersonal problems, increasing the risk of affective disorders like depressive disorder, bipolar disorder, and anxiety disorder. Individuals experiencing these conditions often struggle to break free from repetitive negative thoughts. However, the mechanisms that sustain this pattern remain unclear. The Contrast Avoidance Model offers insight into this issue. The model suggests that some individuals are particularly uncomfortable with sharp downturns in their emotions, known as Negative Emotional Contrasts. These individuals engage in repetitive negative thinking as a strategy to avoid abrupt emotional shifts. Additionally, the model posits that repetitive negative thoughts can lead to Positive Emotional Contrasts if outcomes turn out better than expected. My work aims to 1) empirically test the validity of the Contrast Avoidance Model, 2) examine the model's applicability to other affective disorders, such as bipolar spectrum disorders, and 3) design and validate psychological interventions targeting the mechanism of contrast avoidance.

Representative Research

• Kim, H., McInnis, M. G., & Sperry, S. H. (2024). An initial test of the Contrast Avoidance Model in bipolar spectrum disorders. Journal of Psychiatric Research.

• Kim, H., & Newman, M. G. (2023). Worry and Rumination Enhance Positive Emotional Contrast Based on the Framework of the Contrast Avoidance Model. Journal of Anxiety Disorders.

• Kim, H., & Newman, M. G. (2022). Avoidance of negative emotional contrast from worry and rumination: An application of the contrast avoidance model. Journal of Behavioral and Cognitive Therapy.

• Newman, M. G., Schwob, J. T., Rackoff, G. N., Van Doren, N., Shin, K. E., & Kim, H. (2022). The naturalistic reinforcement of worry from positive and negative emotional contrast: Results from a momentary assessment study within social interactions. Journal of Anxiety Disorders.

• Newman, M. G., Rackoff, G. N., Zhu, Y., & Kim, H. (2022). A transdiagnostic evaluation of contrast avoidance across generalized anxiety disorder, major depressive disorder, and social anxiety disorder. Journal of Anxiety Disorders.

• Kim, H. & Newman, M. G. (2019). The paradox of relaxation-induced anxiety and mediation effects of contrast avoidance in generalized anxiety disorder and major depressive disorder. Journal of Affective Disorders.

• Newman, M. G., Cho S., & Kim H. (2017). Worry and generalized anxiety disorder: A review. Reference module in Neuroscience and Biobehavioral Psychology.

Idiographic Patterns in Affective Disorders

Understanding the unique differences in affective disorders enables healthcare professionals to customize their diagnostic and therapeutic strategies. For instance, recognizing how certain disorders manifest distinct symptoms across various demographic groups and throughout the course of illness can improve diagnostic accuracy and treatment effectiveness. Additionally, by identifying idiographic patterns in symptom progression, healthcare providers can allocate resources to at-risk populations at the right time, potentially preventing the further advancement of these disorders. My research focuses on three main objectives: 1) identifying individual variations in the presentation and interrelation of affective disorder symptoms, 2) identifying differential time-varying patterns in the progression of mental disorder symptoms, and 3) developing and validating personalized healthcare treatments based on individual characteristics, incorporating these findings.

Representative Research

• Kim. H. (2024). Sex differences in age-varying trends of depressive symptoms, substance use, and their associations among South Korean adults: A Time-Varying Effect Modeling (TVEM) analysis of a nationwide sample. Journal of Affective Disorders. 

• Kim. H., McInnis, M. G., & Sperry. S. H. (2024). Longitudinal dynamics between anxiety and depression in bipolar spectrum disorders. Journal of Psychopathology and Clinical Science, 133(2), 129-139.

• Jo, D., & Kim, H. (2023). Network analysis of depressive symptoms in South Korean adults: Similarities and differences between women and men. Current Psychology, 1-12.

• Kim, H., & Duval, E. R. (2022). Social anxiety and depression symptoms are differentially related in men and women. Current Psychology. 1-12.

• Kim, H., Rackoff, G. (Co-first author), Fitzsimmons-Craft, E., Shin, K., Zainal, N., Schwob, T., Eisenberg, D., Wilfley, D., Taylor, C., & Newman, M. (2022). College mental health before and during the COVID-19 pandemic: Results from a nationwide survey. Cognitive Therapy and Research.

Interpersonal Problems in Affective Disorders

Affective disorders frequently result in challenges in interpersonal relationships. Studies indicate that individuals with these disorders are prone to higher levels of withdrawal, isolation, alienation, and loneliness compared to those without such issues. They may also be more inclined to resort to substances like alcohol and drugs as a coping mechanism for interpersonal stress. In certain cases, such as social anxiety disorder, symptoms can manifest as intense fear and avoidance of social situations. My research is focused on three primary objectives: 1) identifying factors that contribute to interpersonal difficulties in individuals with affective disorders, 2) exploring temporal dynamics of emotion dysregulation processes in mental disorders with interpersonal deficits such as social anxiety disorder, and 3) identifying subtypes of affective disorders based on the disposition of interpersonal problems. 

Representative Research

• Kim, H., & Duval, E. R. (2022). Social anxiety and depression symptoms are differentially related in men and women. Current Psychology.

• Chun, Y., Woo, S., Kim, H., Kang, C., & Yang, E. (2009). The relationships between children's interpersonal types and parental factors. The Korean Journal of School Psychology, 6(2), 103-122.

Current Research Projects

• Analyzing data examining the effects of close interpersonal relationships on the longitudinal course of bipolar spectrum disorders (Collaborator: Frances Adiukwu, M.D.)

• Analyzing data comparing the efficacy of different attention bias modification modalities for social anxiety (PI: Elizabeth R. Duval, Ph.D., Michigan Medicine).

• Collaborating with Sojung Kim, Ph.D. (Yeungnam University) on an ecological momentary assessment study examining interpersonal deficits of individuals with social anxiety and their alcohol use problems.

Methodologies for Affective Disorder Research

In experimental research focusing on affective disorders, it is crucial to use stimuli that can reliably and effectively provoke a specific target emotion, without being affected by external factors such as researcher biases. Moreover, when evaluating different emotion regulation processes, such as worry and rumination, it is vital to employ inductions that are methodologically consistent. As a result, my research primarily revolves around the creation and validation of potent emotion induction stimuli.

Representative Research

• Kim, H., & Newman, M. G. (2024). Development and validation of novel worry and rumination induction methods, Research Square.

• Kim, H., Lu, X., Costa, M., Kandemir, B., Adams, R. B., Li, J., Wang, J. Z., & Newman, M.G. (2018). Development and validation of Image Stimuli for Emotion Elicitation (ISEE), Psychiatry Research.

• Kandemir, B., Kim, H., Newman, M.G., Adams, R.B., Li, J., & Wang, J.Z. Demographic differences and biases in affect evoked by visual features. (2023). In Wang, J. Z., & Adams, R. B. (Eds.), Modeling visual aesthetics, emotion, and artistic style. New York, NY: Springer.