A Comprehensive Research Profile and Commentary
Introduction
This paper provides a comprehensive analysis of the research career, scholarly contributions, and academic trajectory of Dr. Kadir Uludag, a postdoctoral researcher whose work bridges computational psychiatry, clinical psychology, and sleep neuroscience. Drawing upon his published works, research metrics, and professional activities, this commentary examines the breadth and depth of his contributions to psychiatric research, with particular attention to his methodological innovations in machine learning applications, his substantive findings in tardive dyskinesia and schizophrenia, and his emerging focus on large-scale biobank data analysis.
Dr. Uludag’s career represents an increasingly important model in contemporary psychiatric research: the integration of computational methods with clinical expertise to address complex questions in mental health. His trajectory from clinical training in Turkey to doctoral studies in China, followed by postdoctoral appointments at two of China’s premier medical institutions, reflects both the globalization of psychiatric research and the particular opportunities afforded by China’s substantial investments in neuroscience and mental health research infrastructure.
Research Contributions
Tardive Dyskinesia: Prediction, Mechanisms, and Treatment
Dr. Uludag’s most sustained and impactful research programme addresses tardive dyskinesia (TD), a potentially irreversible movement disorder caused by long-term antipsychotic treatment that represents one of the most clinically significant adverse effects in schizophrenia management. His contributions to this field span prevalence characterization, risk factor identification, biomarker investigation, and machine learning-based prediction.
His study on prevalence, clinical correlates, and risk factors of TD in Chinese patients with schizophrenia, published in the *Asian Journal of Psychiatry*, provided essential epidemiological characterization of TD burden in this population. While TD prevalence has been extensively studied in Western cohorts, data from Chinese populations remain comparatively limited despite China’s large schizophrenia patient population and distinctive antipsychotic prescribing patterns. This work addressed a significant knowledge gap and provided baseline data against which preventive interventions can be evaluated.
The investigation of superoxide dismutase (SOD) levels and genetic polymorphisms in TD development, published in *Oxidative Medicine and Cellular Longevity*, advanced mechanistic understanding of TD pathophysiology. The oxidative stress hypothesis of TD posits that antipsychotic-induced dopamine receptor blockade leads to increased dopamine turnover and reactive oxygen species generation, ultimately resulting in neuronal damage in motor pathways. By examining SOD—a critical antioxidant enzyme—alongside its genetic determinants, this work provided evidence linking oxidative stress vulnerability to TD risk, with potential implications for antioxidant-based preventive strategies.
His machine learning-based prediction models for TD, published in *Schizophrenia Research*, represent perhaps his most methodologically innovative contribution to this field. By applying supervised learning algorithms to clinical, demographic, and biological variables, Dr. Uludag developed models capable of identifying patients at elevated TD risk prior to symptom onset. Such predictive tools hold considerable clinical value, potentially enabling targeted monitoring, earlier intervention, or selection of lower-risk antipsychotic regimens for vulnerable patients. The publication venue, one of the premier journals in schizophrenia research, indicates recognition of this work’s significance by the field.
The comprehensive review of brain imaging studies in TD, published in *Future Neurology*, synthesized neuroimaging findings to characterize the structural and functional brain correlates of this condition. This review likely identified common patterns across studies—potentially including basal ganglia volume alterations, white matter integrity disruption, or functional connectivity abnormalities—while highlighting methodological limitations and directions for future research.
Taken together, Dr. Uludag’s TD research programme demonstrates progressive elaboration from descriptive epidemiology through mechanistic investigation to predictive modelling, culminating in integrative review. This trajectory reflects mature scientific development and positions him as an emerging authority in TD research.
Machine Learning Applications in Psychiatry
Beyond his TD-specific work, Dr. Uludag has contributed to the broader methodological literature on machine learning applications in psychiatric research. His book chapter on hyperparameters and tuning methods for random forest using Python’s scikit-learn in psychology studies, published by IGI Global, provides practical guidance for researchers seeking to implement these methods. Random forest algorithms are particularly well-suited to psychiatric applications given their ability to handle mixed variable types, capture non-linear relationships, and provide variable importance measures—characteristics that address common challenges in psychiatric data analysis.
His investigation of machine learning-driven prediction of decisional uncertainty in medical students following the 2023 Kahramanmaras earthquakes, published in *Health Psychology Research*, demonstrated the applicability of these methods to disaster mental health contexts. Earthquakes represent acute psychological stressors with potential lasting mental health consequences; understanding factors that predict cognitive processing difficulties, such as decisional uncertainty, can inform targeted psychological support delivery. This work also reflects Dr. Uludag’s engagement with Turkey’s mental health challenges alongside his China-based research.
The study on coronary blindness—desensitization after excessive coronavirus information exposure—published in *Health Policy and Technology*, applied computational thinking to a phenomenon of broad public health significance during the COVID-19 pandemic. By characterizing how repeated exposure to health threat information can paradoxically reduce appropriate concern and preventive behaviour, this work contributed to understanding of risk communication effectiveness and information environment design.
Heroin Dependence: Genetic and Clinical Correlates
Dr. Uludag’s research on heroin dependence represents a distinct but complementary research line. His investigation of concurrent substance use and genetic variation in heroin dependence, published in *Clinical Social Work and Health Intervention*, and his work using genetic parameters to predict somatization in females with heroin dependence, published in *Heroin Dose and Related Clinical Disorders*, examined biological and clinical heterogeneity within heroin-dependent populations.
These studies contribute to the growing recognition that substance use disorders are phenotypically and genetically heterogeneous conditions requiring personalized treatment approaches. The focus on sex-specific predictors of somatization—the tendency to experience and communicate psychological distress through physical symptoms—addresses an important dimension of clinical variation with implications for treatment matching and outcome prediction.
### Vitamin D, Platelet Parameters, and Psychiatric Relevance
Dr. Uludag’s study on vitamin D status and its relationship with platelet parameters in young adults, published in *Current Medicinal Chemistry*, extends his research into biochemical correlates of health with potential psychiatric implications. Vitamin D deficiency has been associated with various psychiatric conditions, including depression and schizophrenia, while platelet parameters may reflect inflammatory processes relevant to psychiatric pathophysiology. Although this study appears primarily focused on general health parameters, the findings may inform understanding of biological pathways linking nutritional status, inflammation, and mental health.
Dr. Uludag’s co-authored publications reflect collaborative engagement across multiple research groups and topics. Notable contributions include work on MnSOD activity and cognitive impairment in unmedicated first-episode schizophrenia (*Antioxidants*), which extended his oxidative stress research into cognitive domains; investigation of the NLRP3 inflammasome in post-spinal cord injury anxiety and depression (*ACS Chemical Neuroscience*), connecting neuroinflammation to psychiatric outcomes; and studies on somatic symptom burden, PTSD, and dissociation involving large samples (*Journal of Psychosomatic Research*).
His involvement in global burden of disease research examining non-optimal temperature effects on children’s health (*Translational Pediatrics*) indicates participation in large-scale collaborative projects with public health implications. Work on virtual dietitian applications for precision nutrition (*IEEE/HNICEM*) and AI integration in lesson planning demonstrates technological interests extending beyond core psychiatric applications.
The series of publications on complex PTSD, dissociation, and self-compassion in cross-cultural samples, appearing in *Social Psychiatry and Psychiatric Epidemiology* and *Journal of Psychiatric Research*, reflects engagement with trauma-related disorders from a cross-cultural perspective. These studies, examining the validity of Western-derived diagnostic constructs in South Asian populations, contribute to the growing recognition that psychiatric classification systems require cultural validation and adaptation.
## Editorial Contributions and Peer Review
Dr. Uludag’s editorial activities are remarkable in both volume and scope. Service on the editorial boards of *PLOS ONE*, *Health Policy and Technology*, and *Discover Psychology* positions him within the editorial leadership of respected journals. His role as Section Editor for Qualitative Research at the *Indian Journal of Psychological Medicine* (2025–2027) indicates recognized expertise in qualitative methodologies despite his primary identification with quantitative and computational approaches.
Book Chapters and Dissemination Activities
Dr. Uludag’s 29 Scopus-indexed book chapters demonstrate commitment to knowledge dissemination across formats. Topics span practical guides for implementing machine learning methods (random forest hyperparameters, Nilearn brain imaging analysis), integrative reviews (methamphetamine-induced psychosis and schizophrenia comparison), and forward-looking perspectives on AI applications (ChatGPT emotional understanding, AI in sleep and weight research).
The chapter on Alzheimer’s disease for *The Palgrave Encyclopedia of Disability* (Springer Nature) and the chapter on nose-to-brain nanoformulation delivery for depression indicate breadth extending into neurodegeneration and nanomedicine. These contributions, while perhaps not carrying the same weight as original research publications in peer-reviewed journals, serve valuable educational functions and may reach audiences distinct from those accessing journal literature.
references:
Antipsychotic-based machine learning models may help prediction of tardive dyskinesia in patients with schizophrenia
https://pubmed.ncbi.nlm.nih.gov/36621324/
Tardive dyskinesia development, superoxide dismutase levels, and relevant genetic polymorphisms
