PhD Position in Multimodal AI for ICU Clinical Decision Support 100%, Zurich, fixed-term The Biomedical Data Science Lab (BMDS Lab) at the Department of Health Sciences and Technology, ETH Zurich, is seeking a highly motivated PhD candidate to join our interdisciplinary research team working at the intersection of data science, clinical simulation, and critical care research. Project background Intensive care units are among the most cognitively demanding environments in medicine. Clinicians must rapidly integrate streams of patient data, coordinate with teams, monitor alarms, and document interventions, all under extreme time pressure. Yet how clinicians actually allocate attention, reason verbally, and make decisions remains poorly understood. This PhD project addresses that gap. Sitting at the intersection of clinical simulation, multimodal AI, and human factors research, the successful candidate will design high-fidelity ICU simulation scenarios, capture a unique synchronized dataset of gaze, speech, and documentation behaviour from practising ICU clinicians, and evaluate how these cognitive markers can improve AI-assisted clinical decision support systems (CDSS). This 4-year position is fully funded by the ETH Foundation. Job description As a PhD student, you will be an integral part of our interdisciplinary research team spanning biomedical data science, clinical simulation, and human factors. You will take an active role in shaping and executing a novel research programme at the frontier of multimodal AI and ICU clinical cognition. Under the guidance of Prof. Jutzeler, a dedicated postdoctoral researcher, and collaborators, you will have access to unique clinical datasets, wearable sensing technology, and state-of-the-art simulation facilities. Design, script, and iteratively refine high-fidelity ICU simulation scenarios in collaboration with clinical experts, ensuring authenticity and cognitive challenge across participant experience levels Configure and operate wearable smart glasses and synchronised multimodal recording systems capturing eye-tracking, audio, video, and digital documentation Recruit and conduct simulation sessions with ICU clinicians across Switzerland, managing data collection, participant coordination, and protocol adherence Preprocess, annotate, and manage a rich multimodal dataset, applying both qualitative and quantitative analytical methods to model clinician attention, verbal reasoning, and documentation behaviour Develop and evaluate machine learning models, including unimodal, fusion, and attention-based transformer architectures, to assess the added value of cognitive data streams for clinical decision support Conduct systematic literature reviews across the fields of ICU decision-making, multimodal AI, eye-tracking, and clinical simulation Document and disseminate research findings through peer-reviewed publications and presentations at national and international conferences Contribute to the supervision of Master's students and selected teaching activities within the BMDS lab Profile Qualifications: Master's degree in Computer Science, Biomedical Engineering, Data Science, Cognitive Science, or a related field Strong Python programming skills and experience with PyTorch or TensorFlow Interest in multimodal data, time-series analysis, or NLP Excellent English; German or French is an asset for participant interactions Capacity for self-directed work within an interdisciplinary team Excellent written and oral communication skills in English and German Ability to work independently and collaboratively in a team environment Highly organized with excellent communication and interpersonal skills Preferred Qualifications: Experience with eye-tracking or wearable sensor technology Background in clinical simulation, usability evaluation, or human factors Familiarity with speech processing, speaker diarization, or ASR Knowledge of explainable AI methods (SHAP, LIME, attention visualisation) Exposure to clinical environments or health informatics Workplace We offer A fully funded position with a competitive Swiss doctoral salary Access to a unique 90,000+ case clinical dataset and state-of-the-art simulation facilities Opportunities to engage in cutting-edge research with the potential for high impact Opportunities for professional development Opportunities to engage with different communities bridging data science and medicine research leading to high-impact publications You will be part of a highly motivated, friendly and collaborative team chevron_right Working, teaching and research at ETH Zurich We value diversity and sustainability In line with our values, ETH Zurich encourages an inclusive culture. We promote equality of opportunity, value diversity and nurture a working and learning environment in which the rights and dignity of all our staff and students are respected. Visit our Equal Opportunities and Diversity website to find out how we ensure a fair and open environment that allows everyone to grow and flourish. Sustainability is a core value for us – we are consistently working towards a climate-neutral future. Curious? So are we. We look forward to receiving your online application with the following documents: CV MSc and BSc diploma Task-based statements: For each of the following tasks, provide a short description (maximum 1 page per task) of how you would approach the problem, including methods, tools, or analysis strategies you would use. Task 1: Temporal Modeling of Clinician Behavior: You have access to time-stamped data capturing where a clinician looked, what they said, and what they documented during a clinical task. How would you preprocess and model this data to identify meaningful behavioral patterns. Task 2: Evaluating the Added Value of a New Data Modality: You are extending a structured clinical baseline model with an additional behavioral data stream. How would you evaluate whether this new modality genuinely improves predictive performance? For further information, please contact Prof. Catherine Jutzeler at Catherine.Jutzeler@hest.ethz.ch and Dr. Liliana Paredes (lparedes@ethz.ch), and visit our website. We evaluate applications on a rolling basis. Shortlisted candidates will be invited for an online interview within two to three weeks. Please note that we exclusively accept applications submitted through our online application portal. Applications via email or postal services will not be considered. About ETH Zürich ETH Zurich is one of the world’s leading universities specialising in science and technology. We are renowned for our excellent education, cutting-edge fundamental research and direct transfer of new knowledge into society. Over 30,000 people from more than 120 countries find our university to be a place that promotes independent thinking and an environment that inspires excellence. Located in the heart of Europe, yet forging connections all over the world, we work together to develop solutions for the global challenges of today and tomorrow. Wenn Sie sich auf diese Stelle bewerben, erwähnen Sie bitte dass Sie sie auf Universitoxy gesehen haben.

PhD Position in Multimodal AI for ICU Clinical Decision Support

100%, Zurich, fixed-term

The Biomedical Data Science Lab (BMDS Lab) at the Department of Health Sciences and Technology, ETH Zurich, is seeking a highly motivated PhD candidate to join our interdisciplinary research team working at the intersection of data science, clinical simulation, and critical care research.

Project background

Intensive care units are among the most cognitively demanding environments in medicine. Clinicians must rapidly integrate streams of patient data, coordinate with teams, monitor alarms, and document interventions, all under extreme time pressure. Yet how clinicians actually allocate attention, reason verbally, and make decisions remains poorly understood. This PhD project addresses that gap. Sitting at the intersection of clinical simulation, multimodal AI, and human factors research, the successful candidate will design high-fidelity ICU simulation scenarios, capture a unique synchronized dataset of gaze, speech, and documentation behaviour from practising ICU clinicians, and evaluate how these cognitive markers can improve AI-assisted clinical decision support systems (CDSS).

This 4-year position is fully funded by the ETH Foundation.

Job description

As a PhD student, you will be an integral part of our interdisciplinary research team spanning biomedical data science, clinical simulation, and human factors. You will take an active role in shaping and executing a novel research programme at the frontier of multimodal AI and ICU clinical cognition. Under the guidance of Prof. Jutzeler, a dedicated postdoctoral researcher, and collaborators, you will have access to unique clinical datasets, wearable sensing technology, and state-of-the-art simulation facilities.

Design, script, and iteratively refine high-fidelity ICU simulation scenarios in collaboration with clinical experts, ensuring authenticity and cognitive challenge across participant experience levels
Configure and operate wearable smart glasses and synchronised multimodal recording systems capturing eye-tracking, audio, video, and digital documentation
Recruit and conduct simulation sessions with ICU clinicians across Switzerland, managing data collection, participant coordination, and protocol adherence
Preprocess, annotate, and manage a rich multimodal dataset, applying both qualitative and quantitative analytical methods to model clinician attention, verbal reasoning, and documentation behaviour
Develop and evaluate machine learning models, including unimodal, fusion, and attention-based transformer architectures, to assess the added value of cognitive data streams for clinical decision support
Conduct systematic literature reviews across the fields of ICU decision-making, multimodal AI, eye-tracking, and clinical simulation
Document and disseminate research findings through peer-reviewed publications and presentations at national and international conferences
Contribute to the supervision of Master's students and selected teaching activities within the BMDS lab

Profile

Qualifications:

Master's degree in Computer Science, Biomedical Engineering, Data Science, Cognitive Science, or a related field
Strong Python programming skills and experience with PyTorch or TensorFlow
Interest in multimodal data, time-series analysis, or NLP
Excellent English; German or French is an asset for participant interactions
Capacity for self-directed work within an interdisciplinary team
Excellent written and oral communication skills in English and German
Ability to work independently and collaboratively in a team environment
Highly organized with excellent communication and interpersonal skills

Preferred Qualifications:

Experience with eye-tracking or wearable sensor technology
Background in clinical simulation, usability evaluation, or human factors
Familiarity with speech processing, speaker diarization, or ASR
Knowledge of explainable AI methods (SHAP, LIME, attention visualisation)
Exposure to clinical environments or health informatics

Workplace

We offer

A fully funded position with a competitive Swiss doctoral salary
Access to a unique 90,000+ case clinical dataset and state-of-the-art simulation facilities
Opportunities to engage in cutting-edge research with the potential for high impact
Opportunities for professional development
Opportunities to engage with different communities bridging data science and medicine research leading to high-impact publications
You will be part of a highly motivated, friendly and collaborative team

chevron_right Working, teaching and research at ETH Zurich

We value diversity and sustainability

In line with our values, ETH Zurich encourages an inclusive culture. We promote equality of opportunity, value diversity and nurture a working and learning environment in which the rights and dignity of all our staff and students are respected. Visit our Equal Opportunities and Diversity website to find out how we ensure a fair and open environment that allows everyone to grow and flourish. Sustainability is a core value for us – we are consistently working towards a climate-neutral future.

Curious? So are we.

We look forward to receiving your online application with the following documents:

CV
MSc and BSc diploma
Task-based statements: For each of the following tasks, provide a short description (maximum 1 page per task) of how you would approach the problem, including methods, tools, or analysis strategies you would use.
- Task 1: Temporal Modeling of Clinician Behavior: You have access to time-stamped data capturing where a clinician looked, what they said, and what they documented during a clinical task. How would you preprocess and model this data to identify meaningful behavioral patterns.
- Task 2: Evaluating the Added Value of a New Data Modality: You are extending a structured clinical baseline model with an additional behavioral data stream. How would you evaluate whether this new modality genuinely improves predictive performance?

For further information, please contact Prof. Catherine Jutzeler at Catherine.Jutzeler@hest.ethz.ch and Dr. Liliana Paredes (lparedes@ethz.ch), and visit our website.

We evaluate applications on a rolling basis. Shortlisted candidates will be invited for an online interview within two to three weeks. Please note that we exclusively accept applications submitted through our online application portal. Applications via email or postal services will not be considered.

About ETH Zürich

ETH Zurich is one of the world’s leading universities specialising in science and technology. We are renowned for our excellent education, cutting-edge fundamental research and direct transfer of new knowledge into society. Over 30,000 people from more than 120 countries find our university to be a place that promotes independent thinking and an environment that inspires excellence. Located in the heart of Europe, yet forging connections all over the world, we work together to develop solutions for the global challenges of today and tomorrow.

Wenn Sie sich auf diese Stelle bewerben, erwähnen Sie bitte dass Sie sie auf Universitoxy gesehen haben.

Bewerbung

Mehr