PhD position - Multimodal Methods for Depression Detection F/M

I apply
Update on 28/10/2024
  • Contract type:  Fixed-Term contract

  • Work time:  Full time

  • Location Martigny

Role Summary

We are seeking a PhD student to develop multi-modal, gender- and culture-aware deep learning techniques for analyzing and classifying various depression disorders using clinical interviews.  
Funded by the Swiss NSF, the project is a collaboration between the Idiap Research Institute in Switzerland, the Department of Computer Science of the Mathematics Research Center (CIMAT), in Mexico and the  Department of Epidemiological and Psychosocial Research from the National Institute of Psychiatry Ramón de la Fuente Muñiz (INPRFM) in Mexico.
Worldwide, mental disorders significantly affect individuals' disability-adjusted life years. Timely detection and treatment are critical challenges for healthcare institutions in ensuring access to appropriate care options. The primary goal of the project is to develop AI-based solutions to assist experts in the diagnosis of depression disorders, including symptom identification, risk factor assessment, disease progression predictions, and online psychometric tools.
The approaches to be developed aim to learn embedding vectors by modelling relationships across different modalities of data (speech, video, text, experts' knowledge) while maintaining transparency and interpretability, which is especially crucial in health-related applications. A significant challenge arises when integrating multi-modal information, as each data source differs in nature. Additionally, the models will be designed to be culturally and gender-aware, ensuring that these factors are considered in the learning process. Defining how to model long-distance semantics and prosodic abnormalities using these diverse sources of information will be among the core challenges to be addressed.
At Idiap, the project will build on our recent work that has shown that Graph Convolutional Networks are plausible solutions for training a depression detection model from transcribed clinical interviews. All work will be conducted in close collaboration with our partners in Mexico, CIMAT and the INPRFM. The INPRFM will serve as our clinical partner, providing access to clinical data and offering feedback on the psychological aspects involved in the development of the proposed solutions, ensuring their reliability. Meanwhile, CIMAT will be our technical partner, contributing to the development of AI and deep learning methodologies that will play a critical role in achieving the project's overall objectives. The successful candidate will spend around half a year of their study seconded to Mexico, with a counterpart in Mexico also spending half a year at Idiap.

 

Duties include

  • Conduct research as outlined in the project’s objectives under the supervision of Dr. Esaú VILLATORO-TELLO & Dr. Jean-Marc ODOBEZ
  • Collaborate with international partners and other Doctoral Candidates within the project
  • Participate in project meetings and boards
  • When appropriate, assume leading role as Idiap contact point or work package leader
  • Help supervise PhD students and interns in collaboration with supervisors
  •  Participate in various Idiap activities and projects as requested by supervisor(s) or Idiap management
 

 

Your Profile

●        The ideal Ph.D student should have a master  (or equivalent) degree in engineering, computer science, physics or mathematics.

●        Ideal candidates should have a good background in mathematics, programming ( Python, scripting languages), and machine learning, including deep learning.

●        Knowledge in Speech and Signal Processing, Natural Language Processing, or prior experience in modern medical data analysis is a plus.

●        Interest in the target domain and collaboration.

●        The SNSF SPIRIT program is especially concerned with gender and identity inclusivity; we will emphasise this through the hiring process. In this sense, we particularly encourage applications from female candidates.

●        The student will be enrolled at a doctoral school at EPFL and located at Idiap 

 

Additionnal information

The deadline for applications is 31.01.2025

 The position is available from early 2025, fully funded for four years.

 

Required language

Fluency in English. Spanish - Desirable. French is a plus.

About Idiap

Idiap is a research institute of national importance that engages in fundamental research, education and technology transfer in artificial intelligence, machine learning and signal processing. Idiap offers competitive salaries and conditions in a young, high-quality, dynamic, and multicultural environment. Idiap is located in the town of Martigny in Valais, a scenic region in the south of Switzerland, surrounded by the highest mountains of Europe, and offering exceptional quality of life, exciting recreational activities, including hiking, climbing and skiing, as well as varied cultural activities. English is the official working language.

 

At Idiap we place great emphasis on diversity and we know diversity fosters creativity and innovation. We are committed to equality of opportunity, to being fair and inclusive, and to being a place where we all belong. Employment at Idiap is based solely on a person's merit and qualifications. Idiap does not discriminate against any employee or applicant because of race, color, religion, gender, sexual orientation, gender identity/expression, national origin, disability, age, marital status, pregnancy, or any other basis protected by law.

Réf: f613298c-51b2-456a-83c8-617fc537687b

Apply

PhD position - Multimodal Methods for Depression Detection F/M

Fixed-Term contract
Full time
Martigny

This information is used to process your application. The legal basis is that of measures prior to the conclusion of a possible employment contract. Unless you take action, this information will be kept for no more than 2 years.

* Required fields

Share job

Our last jobs