Barbora Provaznikova
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Barbora Provaznikova has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
Sebastian Olbrich
7 shared publicationsGolo Kronenberg
6 shared publicationsAnna Monn
5 shared publications- Samantha Weber
Department of Adult Psychiatry and Psychotherapy, University Hospital of Psychiatry Zurich (PUK), University of Zurich, Lenggstrasse 31, Zürich CH-8032, Switzerland; Faculty of Medicine, University of Zurich, Zürich 8050, Switzerland; Institute for Implementation Science in Health Care, University of Zurich, Zurich, Switzerland
5 shared publications Erich Seifritz
4 shared publications- Tobias Welt
Institute for Regenerative Medicine-IREM, University of Zurich, 8952 Schlieren, Switzerland
3 shared publications
Latest Publications
- Open Access
- 26 October 2026
- Published by Elsevier in Clinical Neurophysiology
- Vol. 194
Predictive value of EEG/ECG biomarkers for treatment response in depression
- 26 October 2026
- Published by Elsevier in Clinical Neurophysiology
- Vol. 194
Open AccessPredictive value of EEG/ECG biomarkers for treatment response in depression
- Open Access
Predictive value of EEG/ECG Biomarkers for Treatment Response in Depression
Objective: Major depressive episodes frequently show limited response to first-line treatments, motivating the search for objective biomarkers. EEG/ECG-based support tools aggregating electrophysiological predictors may guide treatment selection. We examined whether antidepressant treatments concordant with an EEG/ECG-biomarker report were associated with higher response rates. Methods: We retrospectively analyzed adults with ICD-10 depressive disorder or bipolar depression treated with electroconvulsive therapy (ECT), repetitive transcranial magnetic stimulation (rTMS), (es)ketamine, or selective serotonin reuptake inhibitors (SSRIs) between 2022 and 2024. Resting-state EEG with simultaneous ECG generated individualized biomarker reports with modality-specific response likelihoods. Treatment chosen by clinical teams was classified as concordant or non-concordant; response was derived from routinely collected clinical scales. Results: Among 153 patients (ECT n=53, rTMS n=48, (es)ketamine n=36, SSRIs n=16), response rates were higher for concordant vs non-concordant treatments: ECT 70% vs 50%, rTMS 30% vs 13%, (es)ketamine 31% vs 10%, and SSRIs 100% vs 11%. Overall, 46% (42/92) of concordant vs. 26% (14/54) of non-concordant patients responded (absolute difference +20 percentage points; relative increase ≈77%; number needed to treat ≈5). Conclusion: Concordance with EEG/ECG biomarkers correlated with higher treatment response, warranting confirmation in prospective trials. Significance: EEG/ECG-based decision support may enhance antidepressant treatment response in everyday clinical practice.
Open AccessPredictive value of EEG/ECG Biomarkers for Treatment Response in Depression
Objective: Major depressive episodes frequently show limited response to first-line treatments, motivating the search for objective biomarkers. EEG/ECG-based support tools aggregating electrophysiological predictors may guide treatment selection. We examined whether antidepressant treatments concordant with an EEG/ECG-biomarker report were associated with higher response rates. Methods: We retrospectively analyzed adults with ICD-10 depressive disorder or bipolar depression treated with electroconvulsive therapy (ECT), repetitive transcranial magnetic stimulation (rTMS), (es)ketamine, or selective serotonin reuptake inhibitors (SSRIs) between 2022 and 2024. Resting-state EEG with simultaneous ECG generated individualized biomarker reports with modality-specific response likelihoods. Treatment chosen by clinical teams was classified as concordant or non-concordant; response was derived from routinely collected clinical scales. Results: Among 153 patients (ECT n=53, rTMS n=48, (es)ketamine n=36, SSRIs n=16), response rates were higher for concordant vs non-concordant treatments: ECT 70% vs 50%, rTMS 30% vs 13%, (es)ketamine 31% vs 10%, and SSRIs 100% vs 11%. Overall, 46% (42/92) of concordant vs. 26% (14/54) of non-concordant patients responded (absolute difference +20 percentage points; relative increase ≈77%; number needed to treat ≈5). Conclusion: Concordance with EEG/ECG biomarkers correlated with higher treatment response, warranting confirmation in prospective trials. Significance: EEG/ECG-based decision support may enhance antidepressant treatment response in everyday clinical practice.
- Open Access
- 27 February 2026
- Published by Elsevier in SSRN Electronic Journal
Can Conversational AI Reliably Assess Depressive Symptoms? A Feasibility, Acceptability and Bias-Aware Validation Study of MADRS-Chat
Background: Structured clinical interviews such as the Montgomery-Åsberg Depression Rating Scale (MADRS) are central to depression assessment but are time-intensive and inconsistently applied in routine care. Large language models (LLMs) offer new opportunities to support standardized symptom assessment through conversational interfaces, yet their clinical feasibility, validity, and potential biases remain insufficiently studied.Methods: We evaluated MADRS-Chat, an LLM-assisted text-based chatbot designed to administer the MADRS interview and generate symptom-level scores using a clinician-trained scoring model. In a prospective observational study involving psychiatric in- and outpatients, we evaluated feasibility and acceptability of a conversational chatbot and its agreement with clinician-rated MADRS scores and patient self-rated (MADRS-S) scores.Findings: MADRS-Chat was well accepted by patients and clinicians and chatbot-derived MADRS scores showed meaningful agreement with human ratings. Qualitative feedback indicated that the anonymous nature of the written interaction facilitated more open and detailed symptom disclosure. However, chatbot-administered interviews systematically yielded higher severity scores, likely reflecting interaction-induced shifts in response style. This bias was effectively addressed through lightweight post-hoc calibration.Interpretation: Our findings demonstrate that conversational AI can support structured psychiatric assessment in real-world clinical settings when used within clearly defined clinical boundaries. Moreover, text-based conversational interactions can alter symptom reporting, making explicit validation and calibration essential before deployment.
- 27 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessCan Conversational AI Reliably Assess Depressive Symptoms? A Feasibility, Acceptability and Bias-Aware Validation Study of MADRS-Chat
Background: Structured clinical interviews such as the Montgomery-Åsberg Depression Rating Scale (MADRS) are central to depression assessment but are time-intensive and inconsistently applied in routine care. Large language models (LLMs) offer new opportunities to support standardized symptom assessment through conversational interfaces, yet their clinical feasibility, validity, and potential biases remain insufficiently studied.Methods: We evaluated MADRS-Chat, an LLM-assisted text-based chatbot designed to administer the MADRS interview and generate symptom-level scores using a clinician-trained scoring model. In a prospective observational study involving psychiatric in- and outpatients, we evaluated feasibility and acceptability of a conversational chatbot and its agreement with clinician-rated MADRS scores and patient self-rated (MADRS-S) scores.Findings: MADRS-Chat was well accepted by patients and clinicians and chatbot-derived MADRS scores showed meaningful agreement with human ratings. Qualitative feedback indicated that the anonymous nature of the written interaction facilitated more open and detailed symptom disclosure. However, chatbot-administered interviews systematically yielded higher severity scores, likely reflecting interaction-induced shifts in response style. This bias was effectively addressed through lightweight post-hoc calibration.Interpretation: Our findings demonstrate that conversational AI can support structured psychiatric assessment in real-world clinical settings when used within clearly defined clinical boundaries. Moreover, text-based conversational interactions can alter symptom reporting, making explicit validation and calibration essential before deployment.
- Top Cited PapersOpen Access
Suicide- and crisis-risk detection using large language models in mental-health chatbots
Objective: Large language models (LLMs) are increasingly embedded in mental-health chatbots, yet safe deployment is limited by two unresolved challenges: (1) suicide- and crisis-risk detection lacks a definitive ground truth and is characterized by substantial clinician disagreement, and (2) most evaluations frame risk detection as an offline accuracy task rather than a real-time safety problem. This study aimed to empirically characterize these limitations and to derive design principles for uncertainty-aware, safety-oriented crisis detection in conversational artificial intelligence. Methods and Analysis: We curated a clinician-labeled dataset of 200 real-world conversation segments drawn from a deployed mental-health chatbot. Five clinical experts independently annotated each segment for suicide- and crisis-related risk. Using a single base LLM, we implemented five prompt-defined detection variants with systematically increasing sensitivity thresholds, without task-specific training or fine-tuning. Models were evaluated against clinician consensus labels to quantify false-negative and false-positive trade-offs. Latency analyses assessed feasibility for real-time, per-turn monitoring. Results: As sensitivity increased, the false-negative rate decreased monotonically from 87% to 0%, while false-positive rates rose accordingly. High - and extreme-sensitivity variants achieved near-perfect (98.9%) and perfect (100%) recall, demonstrating that near–zero–miss crisis detection from natural language is technically feasible in real time (mean latency emergency mode in which conservative risk detection operates independently from the conversational model, allowing supportive engagement to be maintained under heightened safety constraints. This layered, uncertainty-aware architecture provides a practical pathway for safer deployment of LLM-based mental-health chatbots without reliance on large training datasets or extensive model optimization. What is already known on this topic?: Mental-health chatbots based on large language models are increasingly used for psychological support, but evaluations and real-world incidents show that general-purpose LLMs are unreliable in recognizing suicide- and crisis-related risk and may respond unsafely in high-stakes situations. Suicide and crisis risk assessment lacks a stable ground truth, with substantial inter-clinician disagreement even among trained experts, indicating that automated risk detection is inherently uncertain and cannot be treated as a conventional supervised classification task. What this study adds: Demonstrates that near-zero-miss suicide- and crisis-risk detection is technically feasible using clinician-validated data and prompt-based sensitivity calibration, without the further need for fine-tuning or large task-specific training datasets. Shows that detection errors are largely driven by irreducible uncertainty rather than model failure, as misclassifications systematically align with areas of clinician disagreement, supporting the view that crisis detection is an online monitoring problem rather than a solvable classification task. Introduces an architectural safety framework for mental-health chatbots in which conservative, independent risk detection enables an operational emergency mode that prioritizes safety while maintaining empathic engagement. How this study might afect research, practice or policy: This work reframes suicide- and crisis-risk detection in conversational AI as a safety-oriented, uncertainty-aware problem rather than an accuracy-driven prediction task, challenging prevailing evaluation practices. By proposing an architectural separation between risk detection and dialogue generation, it provides a practical, scalable framework for deploying mental-health chatbots that support just-in-time safety interventions without relying on extensive clinical training data.
Top Cited PapersOpen AccessSuicide- and crisis-risk detection using large language models in mental-health chatbots
Objective: Large language models (LLMs) are increasingly embedded in mental-health chatbots, yet safe deployment is limited by two unresolved challenges: (1) suicide- and crisis-risk detection lacks a definitive ground truth and is characterized by substantial clinician disagreement, and (2) most evaluations frame risk detection as an offline accuracy task rather than a real-time safety problem. This study aimed to empirically characterize these limitations and to derive design principles for uncertainty-aware, safety-oriented crisis detection in conversational artificial intelligence. Methods and Analysis: We curated a clinician-labeled dataset of 200 real-world conversation segments drawn from a deployed mental-health chatbot. Five clinical experts independently annotated each segment for suicide- and crisis-related risk. Using a single base LLM, we implemented five prompt-defined detection variants with systematically increasing sensitivity thresholds, without task-specific training or fine-tuning. Models were evaluated against clinician consensus labels to quantify false-negative and false-positive trade-offs. Latency analyses assessed feasibility for real-time, per-turn monitoring. Results: As sensitivity increased, the false-negative rate decreased monotonically from 87% to 0%, while false-positive rates rose accordingly. High - and extreme-sensitivity variants achieved near-perfect (98.9%) and perfect (100%) recall, demonstrating that near–zero–miss crisis detection from natural language is technically feasible in real time (mean latency emergency mode in which conservative risk detection operates independently from the conversational model, allowing supportive engagement to be maintained under heightened safety constraints. This layered, uncertainty-aware architecture provides a practical pathway for safer deployment of LLM-based mental-health chatbots without reliance on large training datasets or extensive model optimization. What is already known on this topic?: Mental-health chatbots based on large language models are increasingly used for psychological support, but evaluations and real-world incidents show that general-purpose LLMs are unreliable in recognizing suicide- and crisis-related risk and may respond unsafely in high-stakes situations. Suicide and crisis risk assessment lacks a stable ground truth, with substantial inter-clinician disagreement even among trained experts, indicating that automated risk detection is inherently uncertain and cannot be treated as a conventional supervised classification task. What this study adds: Demonstrates that near-zero-miss suicide- and crisis-risk detection is technically feasible using clinician-validated data and prompt-based sensitivity calibration, without the further need for fine-tuning or large task-specific training datasets. Shows that detection errors are largely driven by irreducible uncertainty rather than model failure, as misclassifications systematically align with areas of clinician disagreement, supporting the view that crisis detection is an online monitoring problem rather than a solvable classification task. Introduces an architectural safety framework for mental-health chatbots in which conservative, independent risk detection enables an operational emergency mode that prioritizes safety while maintaining empathic engagement. How this study might afect research, practice or policy: This work reframes suicide- and crisis-risk detection in conversational AI as a safety-oriented, uncertainty-aware problem rather than an accuracy-driven prediction task, challenging prevailing evaluation practices. By proposing an architectural separation between risk detection and dialogue generation, it provides a practical, scalable framework for deploying mental-health chatbots that support just-in-time safety interventions without relying on extensive clinical training data.
- Open Access
- 8 December 2025
- Published by Elsevier in Psychiatry Research Case Reports
- Vol. 5 (1)
Remission of auditory verbal hallucinations following neuronavigated, personalized rTMS guided by EEG, MRI, and auditory evoked potentials: A case report
- 8 December 2025
- Published by Elsevier in Psychiatry Research Case Reports
- Vol. 5 (1)
Open AccessRemission of auditory verbal hallucinations following neuronavigated, personalized rTMS guided by EEG, MRI, and auditory evoked potentials: A case report
- Open Access
- 24 April 2025
- Published by Elsevier in Psychiatry Research Case Reports
- Vol. 4 (1)
Sustained remission of treatment-resistant depression following two inhalations of nitrous oxide: A case report
- 24 April 2025
- Published by Elsevier in Psychiatry Research Case Reports
- Vol. 4 (1)
Open AccessSustained remission of treatment-resistant depression following two inhalations of nitrous oxide: A case report
- Open Access
- 4 January 2025
- Published by Elsevier in Journal of Psychiatric Research
- Vol. 182, 4-12
EEG alpha activity as predictor for TBS-rTMS treatment outcome in depression
- 4 January 2025
- Published by Elsevier in Journal of Psychiatric Research
- Vol. 182, 4-12
Open AccessEEG alpha activity as predictor for TBS-rTMS treatment outcome in depression
- Open Access
Examining Nutrition Knowledge, Skills, and Eating Behaviours in People with Severe Mental Illness: A Cross-Sectional Comparison among Psychiatric Inpatients, Outpatients, and Healthy Adults
Compared to the general population, people with severe mental illness (SMI) have an increased risk of weight gain and metabolic syndrome, but also of malnutrition, in part due to unhealthy lifestyle behaviours. The aim of this cross-sectional study was to identify barriers to healthy eating, including nutrition knowledge and skills in people with SMI. For this purpose, we compared the means of anthropometric data such as body mass index, waist-to-hip ratio, and interview data on nutrition knowledge and skills, health-related variables, eating behaviours, personality, motivation, and attitudes in 65 inpatients and 67 outpatients of the Psychiatric Hospital of the University of Zurich and 64 healthy adults using ANOVA and chi-squared tests. The results showed that patients with SMI had worse nutritional status and lifestyle compared to the healthy controls, including disordered (e.g., night eating) and unhealthy (e.g., high intake of sugary foods) eating habits. However, levels of nutrition knowledge, cooking and food skills, and motivation to eat healthily were not significantly lower in the psychiatric patients than in the healthy adults and were not associated with weight change. Based on our findings, nutritional support for people with SMI is urgently needed and should include not only educational but also behavioural and long-term approaches.
Open AccessExamining Nutrition Knowledge, Skills, and Eating Behaviours in People with Severe Mental Illness: A Cross-Sectional Comparison among Psychiatric Inpatients, Outpatients, and Healthy Adults
Compared to the general population, people with severe mental illness (SMI) have an increased risk of weight gain and metabolic syndrome, but also of malnutrition, in part due to unhealthy lifestyle behaviours. The aim of this cross-sectional study was to identify barriers to healthy eating, including nutrition knowledge and skills in people with SMI. For this purpose, we compared the means of anthropometric data such as body mass index, waist-to-hip ratio, and interview data on nutrition knowledge and skills, health-related variables, eating behaviours, personality, motivation, and attitudes in 65 inpatients and 67 outpatients of the Psychiatric Hospital of the University of Zurich and 64 healthy adults using ANOVA and chi-squared tests. The results showed that patients with SMI had worse nutritional status and lifestyle compared to the healthy controls, including disordered (e.g., night eating) and unhealthy (e.g., high intake of sugary foods) eating habits. However, levels of nutrition knowledge, cooking and food skills, and motivation to eat healthily were not significantly lower in the psychiatric patients than in the healthy adults and were not associated with weight change. Based on our findings, nutritional support for people with SMI is urgently needed and should include not only educational but also behavioural and long-term approaches.