MOMohsen Omrani

Mohsen Omrani

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mohsen Omrani has a total of 165 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Developing and implementing a web-based psychotherapy program to address anxiety and depression among patients receiving oncological and palliative care: An open-label, mixed-methods randomized controlled pilot trial (Preprint)

    by Jazmin Eadie, Gina Layzell, Callum Stephenson, Nadia Gregnitha, Shadé Miller, Payam Khalafi, Israa Sinan, Danielle Kain, Maggie McDougall, Julia Davies, et al.

    BACKGROUND Cancer is a prevalent disease that commonly leads to comorbid mental health conditions that are often undertreated due to barriers to traditional psychotherapy. Online cognitive behavioural therapy (e-CBT) could be an effective way to reduce these barriers since it demonstrates efficacy in reducing depression and anxiety symptoms, but its effectiveness is understudied in oncological and palliative populations. OBJECTIVE This study aimed to develop a web-based psychotherapy clinic for individuals receiving oncological and palliative care to examine whether this program is an effective psychotherapy to address this population's needs. METHODS Sixty participants diagnosed with depressive disorder and/or anxiety disorder in the context of oncological and/or palliative care conditions were recruited in Kingston, Canada. Participants were randomly assigned to either 8 weeks of a Mindfulness-Enhanced e-CBT (MECBT) program plus treatment as usual (TAU; n=32) or TAU alone (n=28). Participants in the MECBT condition completed weekly pre-designed modules, homework, and were sent personalized feedback. Additionally, a survey was sent out to all MECBT participants to conduct a thematic analysis of their experiences with the program. RESULTS Both conditions demonstrated reductions in anxiety and depression symptoms over time, and a statistically significant difference in depression scores occurred when comparing treatments. Six main themes were identified during the thematic analysis. CONCLUSIONS Findings support the effectiveness of MECBT in reducing depression severity. Qualitative benefits included providing structure, flexibility, and accessibility. Constructive feedback included problems with time restraints, the need for continuity of care, technical challenges, and the need for human contact. CLINICALTRIAL NCT04666974 INTERNATIONAL REGISTERED REPORT RR2-10.2196/30735

  • Open Access

    Clinician Perceptions of AI in Care: Cross-Sectional Survey

    by Callum Stephenson, Jazmin Eadie, Mohsen Omrani, Nazanin Alavi

    Background: AI is increasingly being explored as a tool to enhance efficiency, access, and diagnostic accuracy in mental health care. However, the perspectives of clinicians, who are central to the delivery and oversight of care, on the use of AI remain underexamined. Objective: This study aimed to explore clinicians’ perceptions of AI in clinical care, including perceived benefits, risks, barriers to implementation, and training needs. Methods: A cross-sectional survey was distributed (via email and social media) from August 2024 to November 2024 to mental health professionals in the United States. The survey aimed to capture attitudes toward AI integration, perceived utility, and adoption-related challenges and facilitators in mental health care. Quantitative data were analyzed using descriptive statistics, whereas open-ended responses were analyzed thematically to identify key insights. Results: Respondents (N=62) were mostly (43/62, 69.4%) not currently using AI in practice. The most frequently endorsed benefits included reduction in time spent in coding and billing (32/60, 53.3%), automated intake (23/61, 37.7%), and improved documentation (23/61, 37.7%) by mental health professionals. However, most expressed discomfort with using AI in patient care, and concerns were raised about inaccurate outputs (47/61, 77%), algorithmic bias (41/61, 67.2%), reduced accessibility (31/61, 50.8%), and job stability (22/61, 36.1%). Barriers to adoption included clinician resistance (46/61, 75.4%), lack of validation (41/61, 67.2%), and challenges with technical integration (26/61, 42.6%). Most respondents (54/61, 88.5%) believed that specialized training in AI ethics and applications was moderately, very, or extremely important for clinicians. Open-ended responses reinforced concerns about dehumanization, cultural insensitivity, ethical accountability, and insufficient technological literacy. Conclusions: Mental health professionals in this sample viewed AI as a potentially useful adjunct to care but not a replacement. Ethical concerns, limited trust, and a strong emphasis on the human dimensions of therapy suggest that implementation must proceed with caution. Clinician-informed strategies, ethical frameworks, and targeted training are essential to support the responsible and effective integration of AI into mental health practice.

  • Open Access

    Structured large language model extraction of clinical factors from electronic health record text supports scalable psychiatric severity prediction

    by Callum Stephenson, Alessandra Camassa, Margot Wagner, Amirhossein H Shirazi, Nazanin Alavi, Mohsen Omrani

    Background: Mental health systems face escalating demand that exceeds clinician capacity, making accurate severity-based triage a critical bottleneck. Severity assessment guides treatment intensity, resource allocation, and risk management, yet most clinically relevant information remains embedded in unstructured electronic health record (EHR) narratives, limiting its utility for scalable decision support. Objectives: This study evaluates whether a single large language model (LLM) can autonomously extract clinical factors from psychiatric EHR narratives, derive predictive weights from those factors, and use the resulting structured representation to predict clinician-implied severity at scale. Methods: From a Mayo Clinic repository of more than 2.7 million encounters, 15,000 de-identified psychiatric notes were sampled into a 5,000-patient discovery cohort and a 10,000-patient replication cohort. The same LLM (Llama 3 8B Instruct) extracted 17 background clinical factors and 3 treatment-action factors from each note. Severity reference labels were derived from the treatment-action factors using pre-specified clinical criteria. The LLM independently derived two factor-weight dictionaries from the discovery cohort: one capturing risk-oriented predictors of severe presentations and one capturing protective predictors. Five weighting conditions were then evaluated against the severity labels: the two LLM-derived dictionaries, two controls (LLM-derived variables with randomized weights; clinically irrelevant variables with arbitrary weights), and an unweighted zero-shot baseline. Performance was assessed across 928 valid iterations in the replication cohort. Results: LLM-derived structured conditions significantly outperformed all controls and the baseline, with statistically equivalent performance between the two structured conditions. Improvements in precision and recall were balanced, indicating gains in discriminative capacity rather than threshold shifts. The variables and weights the LLM derived as predictors of severe presentations aligned closely with established clinical determinants of psychiatric severity. Conclusion: A single LLM can derive clinically meaningful factor weights from unstructured EHR narratives and use them to predict psychiatric severity at scale, supporting a viable path toward interpretable, scalable triage in resource-constrained mental health systems.

  • Open Access

    Clinician perceptions of artificial intelligence in care: A mixed methods study (Preprint)

    by Callum Stephenson, Jazmin Eadie, Mohsen Omrani, Nazanin Alavi

    BACKGROUND AI is increasingly being explored as a tool to enhance efficiency, access, and diagnostic accuracy in mental health care. However, the perspectives on the use of AI from clinicians, who are central to the delivery and oversight of care, remain underexamined. OBJECTIVE This study aimed to explore clinicians' perceptions of AI in clinical care, including perceived benefits, risks, barriers to implementation, and training needs. METHODS A cross-sectional mixed-methods survey was distributed from August to November 2024 to mental health professionals in the US. Quantitative data were analyzed using descriptive statistics, while open-ended responses were analyzed thematically to identify key insights. RESULTS Respondents (n=62) were mostly not currently using AI in practice. The most frequently endorsed benefits included reductions in clinical workload, improved efficiency, and enhanced data analysis. However, a majority expressed discomfort using AI in patient care, and concerns were raised about inaccurate outputs, algorithmic bias, privacy, and weakened therapeutic rapport. Barriers to adoption included clinician resistance, lack of validation, and challenges with technical integration. Most respondents believed that specialized training in AI ethics and applications is important for clinicians. Qualitative findings reinforced concerns about dehumanization, cultural insensitivity, ethical accountability, and insufficient technological literacy. CONCLUSIONS Mental health professionals view AI as a potentially useful adjunct, but not a replacement, in care. Ethical concerns, limited trust, and a strong emphasis on the human dimensions of therapy suggest that implementation must proceed with caution. Clinician-informed strategies, ethical frameworks, and targeted training are essential to support the responsible and effective integration of AI into mental health practice.

  • Open Access

    Diverse ancestral brainstem noradrenergic neuron activity across species and biological factors

    by Michael A. Kelberman, Ellen Rodberg, Brandon R. Munn, Ehsan Arabzadeh, Chloe J. Bair-Marshall, Craig W. Berridge, Esther Berrocoso, Vincent Breton-Provencher, Daniel J. Chandler, Alicia Che, et al.

    The brainstem cell group, locus coeruleus (LC), is present across vertebrates and influences cardiorespiratory, metabolic, immune, and cognitive functions by activating in two putatively distinct firing patterns. Yet, the degree to which the LC firing rates and patterns are homogenous across species has never been assessed due to inherently limited sample sizes. To remedy this, we pooled cross-species data from 20 laboratories to show that firing rates differ across species and are modulated by sex, age, and type of in vitro or in vivo preparation. Contrary to the prevailing dual-mode firing pattern schema, we observed patterns spread across a low-dimensional manifold, with subregions enriched for specific biological factors and neurodegenerative disease models. Our findings show considerable diversity in an ancestral vertebrate neuromodulatory system.


  • Open Access

    Incorporating a Stepped Care Approach Into Internet-Based Cognitive Behavioral Therapy for Depression: Randomized Controlled Trial

    by Jasleen Kaur Jagayat, Anchan Kumar, Yijia Shao, Amrita Pannu, Charmy Patel, Amirhossein Shirazi, Mohsen Omrani, Nazanin Alavi

    Background: Depression is a hidden burden, yet it is a leading cause of disability worldwide. Despite the adverse effects of depression, fewer than one-third of patients receive care. Internet-based cognitive behavioral therapy (i-CBT) is an effective treatment for depression, and combining i-CBT with supervised care could make the therapy scalable and effective. A stepped care model is a framework for beginning treatment with an effective and low-intensity intervention while adapting care based on the patient’s needs. Objective: This study investigated the efficacy of a stepped care i-CBT model for depression based on changes in self-reported depressive symptoms. Methods: In this single-blinded, randomized controlled trial, participants were allocated to either the i-CBT–only group (28/56, 50%) or the i-CBT with stepped care group (28/56, 50%). Both groups received a 13-week i-CBT program tailored for depression. The i-CBT program was provided through a secure, online mental health clinic called the Online Psychotherapy Tool. Participants read through the sessions and completed the assignments related to each session. Participants in the stepped care group received additional interventions from their care provider based on standard questionnaire scores (ie, Patient Health Questionnaire–9 [PHQ-9], Quick Inventory of Depressive Symptomatology [QIDS], and Quality of Life Enjoyment and Satisfaction Questionnaire–Short Form) and their assignment responses. From lowest to highest intensity, the additional interventions included SMS text messages, phone calls, video calls, or a video call with a psychiatrist. Results: For this study, 56 participants were recruited to complete an i-CBT program (n=28, 50%; mean age 37.9; SD 13.08 y; 7/28, 27% were men) or an i-CBT with stepped care program (n=28, 50%; mean age 40.6; SD 14.28 y; 11/28, 42% were men). The results of this study indicate that the i-CBT program was effective in significantly reducing depressive symptoms, as measured by the PHQ-9 (F4,80=9.95; P<.001) and QIDS (F2,28=5.73; P=.008); however, there were no significant differences in the reduction of depressive symptoms between the 2 groups (PHQ-9: F4,80=0.43; P=.78; QIDS: F2,28=3.05; P=.06). The stepped care group was not significantly better in reducing depressive symptoms than the i-CBT group (PHQ-9, P=.79; QIDS, P=.06). Although there were no significant differences observed between the number of participants who completed the program between the groups (χ21=2.6; P=.10), participants in the stepped care group, on average, participated in more sessions than those who prematurely terminated participation in the i-CBT group (t55=−2; P=.03; 95% CI –4.83 to –0.002). Conclusions: Implementing a stepped care approach in i-CBT is an effective treatment for depression, and the stepped care model can assist patients to complete more sessions in their treatment. Trial Registration: Clinicaltrials.gov NCT04747873; https://clinicaltrials.gov/study/NCT04747873


  • Open Access

    Efficacy of an Electronic Cognitive Behavioral Therapy Program Delivered via the Online Psychotherapy Tool for Depression and Anxiety Related to the COVID-19 Pandemic: Pre-Post Pilot Study

    by Elnaz Moghimi, Callum Stephenson, Anika Agarwal, Niloofar Nikjoo, Niloufar Malakouti, Gina Layzell, Anne O'RIordan, Jasleen Jagayat, Amirhossein Shirazi, Gilmar Gutierrez, et al.

    Background: Lockdowns and social distancing resulting from the COVID-19 pandemic have worsened the population’s mental health and made it more difficult for individuals to receive care. Electronic cognitive behavioral therapy (e-CBT) is a cost-effective and evidence-based treatment for anxiety and depression and can be accessed remotely. Objective: The objective of the study was to investigate the efficacy of online psychotherapy tailored to depression and anxiety symptoms during the pandemic. Methods: The pilot study used a pre-post design to evaluate the efficacy of a 9-week e-CBT program designed for individuals with depression and anxiety affected by the pandemic. Participants were adults (N=59) diagnosed with major depressive disorder and generalized anxiety disorder, whose mental health symptoms initiated or worsened during the COVID-19 pandemic. The online psychotherapy program focused on teaching coping, mindfulness, and problem-solving skills. Symptoms of anxiety and depression, resilience, and quality of life were assessed. Results: Participants demonstrated significant improvements in symptoms of anxiety (P=.02) and depression (P=.03) after the intervention. Similar trends were observed in the intention-to-treat analysis. No significant differences were observed in resilience and quality-of-life measures. The sample comprised mostly females, making it challenging to discern the benefits of the intervention in males. Although a pre-post design is less rigorous than a controlled trial, this design was selected to observe changes in scores during a critical period. Conclusions: e-CBT for COVID-19 is an effective and accessible treatment option. Improvements in clinical symptoms of anxiety and depression can be observed in individuals whose mental health is affected by the COVID-19 pandemic. Trial Registration: ClinicalTrials.gov NCT04476667; https://clinicaltrials.gov/study/NCT04476667 International Registered Report Identifier (IRRID): RR2-10.2196/24913


  • Open Access

    Using Natural Language Processing as a Scalable Mental Status Evaluation Technique

    by Margot Wagner, Jasleen Jagayat, Anchan Kumar, Amir Shirazi, Nazanin Alavi, Mohsen Omrani

    Mental health is in a state of crisis with demand for mental health services significantly surpassing available care. As such, building scalable and objective measurement tools for mental health evaluation is of primary concern. Given the usage of spoken language in diagnostics and treatment, it stands out as potential methodology. Here a model is built for mental health status evaluation using natural language processing. Specifically, a RoBERTa-based model is fine-tuned on text from psychotherapy sessions to predict mental health status with prediction accuracy on par with clinical evaluations at 74%.


  • Open Access

    Comparing the Efficacy of an Electronically Delivered Cognitive Behavioral Therapy Program to a Mental Health Check-In Program for Generalized Anxiety Disorder: Protocol for a Randomized Trial

    by Callum Stephenson, Anchan Kumar, Niloufar Malakouti, Niloofar Nikjoo, Jasleen Jagayat, Tessa Gizzarelli, Charmy Patel, Gilmar Gutierrez, Amirhossein Shirazi, Megan Yang, et al.

    Background: Generalized anxiety disorder (GAD) is a prevalent anxiety disorder, with cognitive behavioral therapy (CBT) being the gold standard treatment. However, it is inaccessible and costly to many, as the mental health industry is overwhelmed by the demand for treatment. This means effective, accessible, and time-saving strategies must be developed to combat these problems. Web-based interventions for mental health disorders are an innovative and promising way to address these barriers. While electronically delivered CBT (e-CBT) has already proved productive and scalable for treating anxiety, other less resource-intensive interventions can be innovated. Checking up on mental health face-to-face has been shown to provide similar benefits to patients with anxiety disorders previously, but more research is needed to evaluate the efficacy of web-based delivery of this intervention. Objective: This study will compare the efficacy of e-CBT and a web-based mental health check-in program to treat GAD. These programs will both be delivered through a secure, web-based care delivery platform. Methods: We will randomly allocate participants (N=100) who are 18 years or older with a confirmed diagnosis of GAD to either an e-CBT program or a mental health check-in program over 12 weeks to address their anxiety symptoms. Participants in the e-CBT arm will complete predesigned modules and homework assignments while receiving personalized feedback and asynchronous interaction with a therapist through the platform. Participants in the mental health check-in arm will be contacted weekly through the web-based platform’s written chat feature (messaging system). Therapists will ask the participants a series of predesigned questions that revolve around a different theme each week to prompt conversation. Using clinically validated questionnaires, the efficacy of the e-CBT arm will be compared to the mental health check-in arm. These questionnaires will be completed at baseline, week 6, and week 12. Results: The study received ethics approval in April 2021, and participant recruitment began in May 2021. Participant recruitment has been conducted through targeted advertisements and physician referrals. Complete data collection and analysis are expected to conclude by August 2023. Linear and binomial regression (continuous and categorical outcomes, respectively) will be conducted. Conclusions: To the research team’s knowledge, this will be the first study to date comparing the efficacy of e-CBT with a web-based mental health check-in program to treat GAD. The findings from this study can help progress the development of more scalable, accessible, and efficacious mental health treatments. Trial Registration: ClinicalTrials.gov NCT04754438; https://classic.clinicaltrials.gov/ct2/show/NCT04754438 International Registered Report Identifier (IRRID): DERR1-10.2196/48899


  • Open Access

    Incorporating a Stepped Care Approach Into Internet-Based Cognitive Behavioral Therapy for Depression: Randomized Controlled Trial (Preprint)

    by Jasleen Kaur Jagayat, Anchan Kumar, Yijia Shao, Amrita Pannu, Charmy Patel, Amirhossein Shirazi, Mohsen Omrani, Nazanin Alavi

    BACKGROUND Depression is a hidden burden, yet it is a leading cause of disability worldwide. Despite the adverse effects of depression, fewer than one-third of patients receive care. Internet-based cognitive behavioral therapy (i-CBT) is an effective treatment for depression, and combining i-CBT with supervised care could make the therapy scalable and effective. A stepped care model is a framework for beginning treatment with an effective and low-intensity intervention while adapting care based on the patient’s needs. OBJECTIVE This study investigated the efficacy of a stepped care i-CBT model for depression based on changes in self-reported depressive symptoms. METHODS In this single-blinded, randomized controlled trial, participants were allocated to either the i-CBT–only group (28/56, 50%) or the i-CBT with stepped care group (28/56, 50%). Both groups received a 13-week i-CBT program tailored for depression. The i-CBT program was provided through a secure, online mental health clinic called the Online Psychotherapy Tool. Participants read through the sessions and completed the assignments related to each session. Participants in the stepped care group received additional interventions from their care provider based on standard questionnaire scores (ie, Patient Health Questionnaire–9 [PHQ-9], Quick Inventory of Depressive Symptomatology [QIDS], and Quality of Life Enjoyment and Satisfaction Questionnaire–Short Form) and their assignment responses. From lowest to highest intensity, the additional interventions included SMS text messages, phone calls, video calls, or a video call with a psychiatrist. RESULTS For this study, 56 participants were recruited to complete an i-CBT program (n=28, 50%; mean age 37.9; SD 13.08 y; 7/28, 27% were men) or an i-CBT with stepped care program (n=28, 50%; mean age 40.6; SD 14.28 y; 11/28, 42% were men). The results of this study indicate that the i-CBT program was effective in significantly reducing depressive symptoms, as measured by the PHQ-9 (F4,80=9.95; P<.001) and QIDS (F2,28=5.73; P=.008); however, there were no significant differences in the reduction of depressive symptoms between the 2 groups (PHQ-9: F4,80=0.43; P=.78; QIDS: F2,28=3.05; P=.06). The stepped care group was not significantly better in reducing depressive symptoms than the i-CBT group (PHQ-9, P=.79; QIDS, P=.06). Although there were no significant differences observed between the number of participants who completed the program between the groups (χ21=2.6; P=.10), participants in the stepped care group, on average, participated in more sessions than those who prematurely terminated participation in the i-CBT group (t55=−2; P=.03; 95% CI –4.83 to –0.002). CONCLUSIONS Implementing a stepped care approach in i-CBT is an effective treatment for depression, and the stepped care model can assist patients to complete more sessions in their treatment. CLINICALTRIAL Clinicaltrials.gov NCT04747873; https://clinicaltrials.gov/study/NCT04747873