Dual Mechanisms of Control in Comorbid Major Depression and Anxiety Disorders: Machine Learning-Based Prediction of Symptom Severity

Jiao Jiangli; Wang Tian

doi:10.16719/j.cnki.1671-6981.20260506

PDF(1670 KB)

Journal of Psychological Science ›› 2026, Vol. 49 ›› Issue (5) : 1087-1097. DOI: 10.16719/j.cnki.1671-6981.20260506

General Psychology，Experimental Psychology & Ergonomics

Dual Mechanisms of Control in Comorbid Major Depression and Anxiety Disorders: Machine Learning-Based Prediction of Symptom Severity

Jiao Jiangli ¹^,²^,^** ,
Wang Tian ²

Author information +

History +

Abstract

Major depressive disorder (MDD) and anxiety disorders (AD) exhibit high rates of comorbidity, presenting a significant challenge for clinical diagnosis and treatment. Traditional diagnostic frameworks often conceptualize these conditions as distinct entities, potentially overlooking the complex, interactive nature of their symptomatology and the shared cognitive mechanisms that may underlie both. Cognitive control, the ability to regulate thoughts and actions in accordance with internal goals, is a core deficit transdiagnostically associated with both MDD and AD. The contemporary dual-mechanisms of control theory posits two distinct modes: proactive control and reactive control. Understanding the profile of these control modes in comorbid MDD and AD (MDD-AD) could provide crucial insights into the disorder's mechanisms and inform more precise assessment tools. This study aimed to (1) investigate the specific characteristics of proactive and reactive cognitive control in individuals with MDD-AD compared to those with single diagnoses and healthy controls, and (2) construct and validate a machine learning-based model capable of predicting overall symptom severity using behavioral indices from a cognitive control paradigm.

The study design involved four groups of participants: 50 individuals in the MDD-AD group, 50 in the MDD-only group (MDD-o), 51 in the AD-only group (AD-o), and 50 in the healthy control group (HC). Participants were screened using the Zung Self-Rating Depression Scale (SDS) and Zung Self-Rating Anxiety Scale (SAS). Through the AX-CPT task, the reaction times, accuracy, and the relative strength of proactive and reactive control modes (Proactive Behavioral Index, PBI) were assessed. Additionally, a Random Forest (RF) regression model was used to predict symptom severity based on reaction times and accuracy, evaluating the applicability of the model across different groups.

The results showed that the MDD-AD group had significantly longer reaction times compared to other groups in the AX-CPT task, and significantly lower accuracy on BX trials compared to the HC group. Specifically, the reaction times in AX trials were 646 ms for the MDD-AD group, compared to 401 ms for the HC group (p <.001). In BX trials, MDD-AD participants exhibited significantly lower accuracy (.85) compared to the HC group (.99, p <.001). The Proactive Behavioral Index (PBI) indicated that MDD-AD participants showed significantly lower proactive control (PBI_RT =.10) compared to HC participants (PBI_RT =.20, p <.001). Moreover, MDD-AD participants exhibited compensatory enhancement of reactive control in the accuracy-based PBI, with PBI_ACC values of -.18, which was significantly lower than that of the AD-o group (-.40, p <.05), and higher than the MDD-o group (.22, p <.001). These findings suggest that in MDD-AD, proactive control is impaired while reactive control is enhanced.

Machine learning analysis demonstrated that the RF regression model, particularly the comprehensive diagnostic model, outperformed single-diagnosis models in predicting symptom severity. The comprehensive diagnostic model achieved a mean absolute error (MAE) of 5.23, with an R² of.78, indicating strong predictive accuracy. SHAP (SHapley Additive exPlanations) analysis revealed that reaction times in AY and BX trials were key features in predicting symptom severity. The model's feature importance ranking was stable, with the most significant features being the behavioral performance in these trials ( ρ =.89).

In conclusion, individuals with MDD-AD exhibit a distinct cognitive control mode characterized by reduced proactive control and compensatory enhancement of reactive control. The machine learning-based prediction model, utilizing the AX-CPT task, effectively predicts symptom severity and provides theoretical support for the precise assessment and intervention of comorbid disorders. Future research may further integrate multimodal data and expand sample sizes to validate the generalizability of the dual cognitive control model in other psychiatric conditions and explore its underlying neural mechanisms.

Key words

comorbid major depression and anxiety disorders (MDD-AD) / proactive control / reactive control / machine learning

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Jiao Jiangli , Wang Tian. Dual Mechanisms of Control in Comorbid Major Depression and Anxiety Disorders: Machine Learning-Based Prediction of Symptom Severity[J]. Journal of Psychological Science. 2026, 49(5): 1087-1097 https://doi.org/10.16719/j.cnki.1671-6981.20260506

References

List( Publishing order | Descend order by publishing year | Descend order by cited within ) Chart analysis

[1]	宋永宁, 俞晨曦, 夏榕. (2021). 自闭谱系障碍: 一种主动性的社会认知控制缺陷. 心理科学, 44(3), 745-753. Cited in this article [1]

[2]	田雪, 邱江. (2015). 抑郁症的脑功能整合异常--来自有效连接的证据. 心理科学, 38(6), 1334-1339. Cited in this article [1]

[3]	徐雷, 唐丹丹, 陈安涛. (2012). 主动性和反应性认知控制的权衡机制及影响因素. 心理科学进展, 20(7), 1012-1022. Cited in this article [1]

[4]	张森森, 丁凤琴, 李宁, 靖治. (2025). 焦虑与抑郁的共病: 基于交叉滞后路径模型和网络分析的纵向研究. 心理科学, 48(3), 732-742. Cited in this article [1]

[5]	Braver, T. S. (2012). The variable nature of cognitive control: A dual mechanisms framework. Trends in Cognitive Sciences, 16(2), 106-113. Cited in this article [2]

[6]

Braver, T.,

, Gray,

J. R.

, & Burgess,

G. C.

(2008). Explaining the many varieties of working memory variation:Dual mechanisms of cognitive control. In A. Conway, C. Jarrold, M. Kane, A. Miyake, & J. Towse (Eds.), Variation in working memory (pp. 76-106). Oxford University Press.

Cited in this article [1]

[7]	Braver, T. S., Kizhner, A., Tang, R. X., Freund, M. C., & Etzel, J. A. (2021). The dual mechanisms of cognitive control project. Journal of Cognitive Neuroscience, 33(9), 1990-2015. Cited in this article [1]

[8]	Braver, T. S., Paxton, J. L., Locke, H. S., & Barch, D. M. (2009). Flexible neural mechanisms of cognitive control within human prefrontal cortex. Proceedings of the National Academy of Sciences of the United States of America, 106(18), 7351-7356. Cited in this article [2]

[9]	Chau, A. K. C., Minihan, S., Okayama, S., & Schweizer, S. (2025). The relationship between cognitive and affective control and symptoms of depression and anxiety across the lifespan: A 3-wave longitudinal study. Comprehensive Psychiatry, 137, Article 152564. Cited in this article [1]

[10]	Chen, Z. Y., Tang, Y. C., Liu, X. R., Li, W., Hu, Y. Y., Hu, B. W., … Feng, T. Y. (2024). Edge-centric connectome-genetic markers of bridging factor to comorbidity between depression and anxiety. Nature Communications, 15(1), Article 10560. Cited in this article [1]

[11]

Cui,

X. B.

, Ding,

Q. W.

, Yu,

S. T.

, Zhang,

S. Y.

, & Li,

X. B.

(2024). The deficit in cognitive reappraisal capacity in individuals with anxiety or depressive disorders: Meta-analyses of behavioral and neuroimaging studies. Clinical Psychology Review, 114, Article 102480.

Cited in this article [1]

[12]	Dunstan, D. A., & Scott, N. (2019). Clarification of the cut-off score for Zung' s self-rating depression scale. BMC Psychiatry, 19(1), Article 177. Cited in this article [1]

[13]	Dunstan, D. A., & Scott, N. (2020). Norms for Zung' s self-rating anxiety scale. BMC Psychiatry, 20(1), Article 90. Cited in this article [1]

[14]	Eysenck, M. W., Moser, J. S., Derakshan, N., Hepsomali, P., & Allen, P. (2023). A neurocognitive account of attentional control theory: How does trait anxiety affect the brain' s attentional networks? Cognition and Emotion, 37(2), 220-237. Cited in this article [1]

[15]	Faul, F., Erdfelder, E., Lang, A. G., & Buchner, A. (2007). Gpower 3: A flexible statistical power analysis program for the social, behavioral, and biomedical sciences. Behavior Research Methods*, 39(2), 175-191. Cited in this article [1]

[16]	Grahek, I., Everaert, J., Krebs, R. M., & Koster, E. H. W. (2018). Cognitive control in depression: Toward clinical models informed by cognitive neuroscience. Clinical Psychological Science, 6(4), 464-480. Cited in this article [1]

[17]	Grahek, I., Shenhav, A., Musslick, S., Krebs, R. M., & Koster, E. H. W. (2019). Motivation and cognitive control in depression. Neuroscience and Biobehavioral Reviews, 102, 371-381. Cited in this article [1]

[18]

Groen,

R. N.

, Ryan,

, Wigman,

J. T. W.

, Riese,

, Penninx,

B. W. J. H.

, Giltay,

E. J.

, Wichers,

, & Hartman,

C. A.

(2020). Comorbidity between depression and anxiety: Assessing the role of bridge mental states in dynamic psychological networks. BMC Medicine, 18(1), Article 308.

Cited in this article [1]

[19]	Heeren, A., Jones, P. J., & McNally, R. J. (2018). Mapping network connectivity among symptoms of social anxiety and comorbid depression in people with social anxiety disorder. Journal of Affective Disorders, 228, 75-82. Cited in this article [1]

[20]

Jenkins,

L. M.

, Stange,

J. P.

, Bessette,

K. L.

, Chang,

Y. S.

, Corwin,

S. D.

, Skerrett,

K. A.

, Zubleta,

J. K.

, Crane, N.,

,. Pine,

D. S.

, & Langenecker,

S. A.

(2018). Differential engagement of cognitive control regions and subgenual cingulate based upon presence or absence of comorbid anxiety with depression. Journal of Affective Disorders, 241, 371-380.

Cited in this article [1]

[21]	Kerns, J. G., Cohen, J. D., MacDonald, A. W., Cho, R. Y., Stenger, V. A., & Carter, C. S. (2004). Anterior cingulate conflict monitoring and adjustments in control. Science, 303(5660), 1023-1026. Cited in this article [1]

[22]	Li, C., & Managi, S. (2025). Impacts of community attachment and community livability on environmental activity according to XGBoost and SHAP. Cities, 156, Article 105559. Cited in this article [1]

[23]	Liu, Y. C., Liu, Z. H., Luo, X., & Zhao, H. J. T. (2022). Diagnosis of Parkinson' s disease based on SHAP value feature selection. Biocybernetics and Biomedical Engineering, 42(3), 856-869. Cited in this article [1]

[24]	Masuyama, A. (2025). The impact of induced stress on reactive and proactive control in depression. PeerJ, 13, Article e18821. Cited in this article [4]

[25]	Masuyama, A., & Mochizuki, S. (2020). Induced sad mood affects context processing in cognitive control in mildly depressive undergraduates. Current Psychology, 39(4), 1476-1484. Cited in this article [2]

[26]	Miyake, A., Friedman, N. P., Emerson, M. J., Witzki, A. H., Howerter, A., & Wager, T. D. (2000). The unity and diversity of executive functions and their contributions to complex “frontal lobe” tasks: A latent variable analysis. Cognitive Psychology, 41(1), 49-100. Cited in this article [1]

[27]	Owen, C. A., Dick, G., & Whigham, P. A. (2024). Using decomposed error for reproducing implicit understanding of algorithms. Evolutionary Computation, 32(1), 49-68. Cited in this article [1]

[28]	Richter, T., Fishbain, B., Fruchter, E., Richter-Levin, G., & Okon-Singer, H. (2021). Machine learning-based diagnosis support system for differentiating between clinical anxiety and depression disorders. Journal of Psychiatric Research, 141, 199-205. Cited in this article [2]

[29]	Richter, T., Stahi, S., Mirovsky, G., Hel-Or, H., & Okon-Singer, H. (2024). Disorder-specific versus transdiagnostic cognitive mechanisms in anxiety and depression: Machine-learning-based prediction of symptom severity. Journal of Affective Disorders, 354, 473-482. Cited in this article [3]

[30]	Sallum, L. F., Alves, C. L., de O. Toutain, T. G. L., Porto, J. A. M., Thielemann, C., & Rodrigues, F. A. (2024). Revealing patterns in major depressive disorder with machine learning and networks. Chaos, Solitons and Fractals, 194, Article 116163. Cited in this article [1]

[31]	Sawah, M. S., Elmannai, H., El-Bary, A. A., Lotfy, K., & Sheta, O. E. (2025). Distributed denial of service (DDoS) classification based on random forest model with backward elimination algorithm and grid search algorithm. Scientific Reports, 15(1), Article 19063. Cited in this article [1]

[32]	Thunberg, P., Reingardt, M., Rode, J., & Msghina, M. (2024). Categorical and dimensional aspects of stimulant medication effects in adult patients with ADHD and healthy controls. Frontiers in Pharmacology, 15, Article 1412178. Cited in this article [1]

[33]	Vanderhasselt, M. A., De Raedt, R., De Paepe, A., Aarts, K., Otte, G., Van Dorpe, J., & Pourtois, G. (2014). Abnormal proactive and reactive cognitive control during conflict processing in major depression. Journal of Abnormal Psychology, 123(1), 68-80. Cited in this article [1]

[34]	Walker, J. C., Parker, A. J., Patel, K. R., Dougherty, L. R., & Wiggins, J. L. (2025). Dimensional foundations toward a novel nosology addressing comorbidity: Preadolescent syndrome profiles. Journal of Affective Disorders, 382, 282-289. Cited in this article [1]

[35]	Wang, T., Yang, L., Yang, L., Liu, B. P., & Jia, C. X. (2024). The relationship between psychological pain and suicidality in patients with major depressive disorder: A meta-analysis. Journal of Affective Disorders, 346, 115-121. Cited in this article [1]

[36]

Wen,

, Tang,

, Wang,

X. H.

, Tong,

Y. Y.

, Zhu,

D. X.

, Wang,

, Ding,

, Su,

P. Y.

, & Wang,

G. F.

(2025). Predictive analysis of bullying victimization trajectory in a Chinese early adolescent cohort based on machine learning. Journal of Affective Disorders, 371, 205-214.

Cited in this article [1]

[37]

Xie,

W. Q.

, Wang,

, Lin,

Z. X.

, Luo,

X. D.

, Chen,

W. Q.

, Xu,

M. Z.

, Liang,

L. Z.

, Liu,

X. F.

, Wang,

Y. Z.

, Lou,

, & Cheng,

M. M.

(2022). Multimodal fusion diagnosis of depression and anxiety based on CNN-LSTM model. Computerized Medical Imaging and Graphics, 102, Article 102128.

Cited in this article [1]

[38]	Xu, M. S., Li, Z. A., Qi, S. Q., Fan, L. X., Zhou, X. L., & Yang, D. (2020). Social exclusion modulates dual mechanisms of cognitive control: Evidence from ERPs. Human Brain Mapping, 41(10), 2669-2685. Cited in this article [4]

[39]	Yang, Y. C., Miskovich, T. A., & Larson, C. L. (2018). State anxiety impairs proactive but enhances reactive control. Frontiers in Psychology, 9, Article 2570. Cited in this article [3]

[40]	Zhang, S. S., Ding, F. Q., & Chen, J. T. (2024). Comorbidity of anxiety and depression disorder among clinical referral patients: A longitudinal study based on network analysis. Current Psychology, 43(23), 20655-20667. Cited in this article [1]

[41]

Zhao,

R. N.

, Xu,

, Shi,

G. Y.

, Li,

, Shao,

S. Y.

, Shangguan,

F. F.

, & Cui,

L. X.

(2024). Connection of social anxiety to impaired pattern of cognitive control and underlying motivational deficiencies: Evidence from event-related potentials. Psychophysiology, 61(9), Article e14598.

Cited in this article [1]

[42]	Zheng, K. L., Liu, Z. X., Miao, Z. M., Xiong, G. Q., Yang, H. H., Zhong, M. T., & Yi, J. Y. (2024). Impaired cognitive flexibility in major depressive disorder: Evidences from spatial-temporal ERPs analysis. Journal of Affective Disorders, 365, 406-416. Cited in this article [1]

[43]	Zhou, E. Q., Wang, W., Ma, S. M., Xie, X. H., Kang, L. J., Xu, S. X., Deng, Z., Gong, Q., Nie, Z., Yao, L., Bu, L., Wang, F., & Liu, Z. C. (2024). Prediction of anxious depression using multimodal neuroimaging and machine learning. NeuroImage, 285, Article 120499. Cited in this article [1]

[44]	Zhou, X. B., Lin, Z. H., Yang, W. Q., Xiang, M. J., Zhou, B., & Zou, Z. L. (2023). The differences of event-related potential components in patients with comorbid depression and anxiety, depression, or anxiety alone. Journal of Affective Disorders, 340, 516-522. Cited in this article [2]