Christina Holmes

Christina Holmes

Auto-generated profile, based on publicly available information

Christina Holmes

Queen's University, Kingston

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2025 in The Canadian Journal of Psychiatry
Verified
Journal Article
Open access
CSCallum Stephenson
Callum Stephenson
JEJazmin Eadie
Jazmin Eadie
CHChristina Holmes
Christina Holmes
KAKimia Asadpour
Kimia Asadpour
GGGilmar Gutierrez
Gilmar Gutierrez
NANazanin Alavi
Nazanin Alavi
Objectives: This study aimed to implement an artificial intelligence-assisted psychiatric triage program, assessing its impact on efficiency and resource optimization. Methods: This project recruited patients on the waitlist for psychiatric evaluation at an outpatient hospital. Participants ( n = 101) completed a digital triage module that used natural language processing and machine learning to recommend a care intensity level and a disorder-specific digital psychotherapy program. A psychiatrist also assessed the same information, and the decisions for care intensity and psychotherapy programs were compared with the artificial intelligence recommendations. Results: The overall wait time to receive care decreased by 71.43% due to this initiative. Additionally, participants received psychological care within three weeks after completing the triage module. In 71.29% of the cases, the artificial intelligence-assisted triage program and the psychiatrist suggested the same treatment intensity and psychotherapy program. Additionally, 63.29% of participants allocated to lower-intensity treatment plans by the AI-assisted triage program did not require psychiatric consultation later. Conclusions: Using artificial intelligence to expedite psychiatric triaging is a promising solution to address long wait times for mental health care. With future accuracy refinements, this could be a valuable tool to implement in hospital settings to assist care teams and improve mental health care. This could result in increased care capacity and improved workflow and decision-making. Plain Language Summary Title: Evaluation of AI and Online Psychotherapy Initiative to Improve Psychiatric Care Access and Efficiency

22 September 2025 in JMIR Preprints
Verified
Preprint
Open access
CHChristina Holmes
Christina Holmes
GNGilmar Gutierrez Nunez
Gilmar Gutierrez Nunez
CSCallum Stephenson
Callum Stephenson
EMElnaz Moghimi
Elnaz Moghimi
NMNiloufar Malakouti
Niloufar Malakouti
NANazanin Alavi
Nazanin Alavi
BACKGROUND Correctional workers (CWs), are frequently exposed to traumatic workplace events, placing them at higher risk of experiencing mental health disorders, including major depressive disorder (MDD), generalized anxiety disorder (GAD), and posttraumatic stress disorder (PTSD). Despite high prevalence of mental health challenges, CWs underutilize mental health services due to stigma, irregular work schedules, and accessibility issues. While cognitive behavioural therapy (CBT) is effective, it poses accessibility challenges. Electronic CBT (eCBT) offers a scalable, accessible alternative, but use among CWs remains underexplored. OBJECTIVE This study aimed to evaluate the efficacy of diagnosis-specific eCBT programs designed for CWs in reducing symptoms of MDD, GAD, and PTSD compared to treatment as usual (TAU). METHODS A randomized controlled trial (RCT) was conducted with 84 CWs in Ontario, assigned to either eCBT (n=40) or TAU (n=44). The eCBT program provided diagnosis-specific modules with synchronous personalized feedback from care providers over 12-weeks via the Online Psychotherapy Tool (OPTT). Symptom severity was measured at baseline, week-6, and post-treatment using validated scales for depression, anxiety, PTSD, and quality-of-life. Data analysis included paired samples t-tests, mixed linear models, and effect size calculations (Cohen's d). RESULTS The eCBT group exhibited significant reductions in symptom severity for depression, anxiety, and PTSD from baseline to post-treatment compared to TAU (p<0.01), with a moderate effect size (Cohen’s d=0.68). Symptom severity decreased by 61.37% for eCBT versus 23.29% in TAU. Mixed linear models confirmed a significant treatment-by-time interaction, favouring eCBT (p<0.01). However, no significant differences in quality-of-life improvements were observed between groups. CONCLUSIONS Diagnosis-specific eCBT programs are effective in reducing symptoms of depression, anxiety, and PTSD for CWs. The asynchronous, accessible format of eCBT addresses current key barriers. Future research should explore strategies to improve adherence and increase the accessibility of services for CWs. CLINICALTRIAL Clinicaltrials.gov (NCT04666974). INTERNATIONAL REGISTERED REPORT RR2-10.2196/30845