The Human Resources Strategy for Researchers
Marie Skłodowska-Curie Actions

PhD position 21 – MSCA COFUND, AI4theSciences (PSL, France) - “Finding and classifying transient patterns to predict from EEG the depth of anesthesia”

This job offer has expired

    Université PSL
    MathematicsApplied mathematics
    First Stage Researcher (R1)
    26/02/2021 23:00 - Europe/Brussels
    France › Paris
    H2020 / Marie Skłodowska-Curie Actions COFUND


“Artificial intelligence for the Sciences” (AI4theSciences) is an innovative, interdisciplinary and intersectoral PhD programme, led by Université Paris Sciences et Lettres (PSL) and co-funded by the European Commission. Supported by the European innovation and research programme Horizon 2020-Marie Sklodowska-Curie Actions, AI4theSciences is uniquely shaped to train a new generation of researchers at the highest academic level in their main discipline (Physics, Engineering, Biology, Human and Social Sciences) and master the latest technologies in Artificial Intelligence and Machine Learning which apply in their own field.

26 doctoral students will join the PSL university's doctoral schools in 2 academic cohorts to carry out work on subjects suggested and defined by PSL's scientific community. The 2020 call will offer up to 15 PhD positions on 24 PhD research projects. The candidates will be recruited through HR processes of high standard, based on transparency, equal opportunities and excellence.


Description of the PhD subject: “Finding and classifying transient patterns to predict from EEG the depth of anesthesia”


Context - Motivation

The objective of this project is to find and classify transient patterns to predict from EEG the depth of anesthesia. The EEGs will be provided by Pr. Dan Longrois' group, recorded routinely in his department at Henri Mourier hospital and will be analyzed and classified by D. Holcman's group (at ENS-PSL in his data modeling group). This research will be done in partnership with the two groups to define the main axes.


The reasons for the EEG will be

  1. checked 10 minutes after the start of the anesthesia and reveal the patient's fragility for different types of hypnotics.
  2. sought in real time a few minutes before the patient plunges into a too deep state associated with possible post-anesthetic complications.


We will develop an analysis of the EEG signal using the Wilson wavelet to extract the predictive transient patterns and dynamics of the power bands, but also the first time of onset of suppression in various frequency bands (such as alpha). We evaluate the most predictive parameters. We will build a multidimensional map of these parameters, which will define high-dimensional manifolds (> 2). We will develop a control procedure to re-evaluate the doses of anesthesia. We will then use classification methods such as SVM, Gaussian, Random forest to characterize the predictive value of each parameter for the depth of anesthesia that we characterize by the statistical combinations of the parameters extracted. We will develop predictive algorithms that we will apply to two patient cohorts (children and adults). The potential result will be a new method of analysis and algorithms that can be used in hospital settings.


Scientific Objectives, Methodology & Expected results

In this study, we first propose to predict the appearance of IsoElectric Suppression (IES) from the EEG and to take into account many artefacts (and to develop a new method of re-calibration of artefacts based on the conservation of energy by frequency bands). We will develop tools to filter the signal in real time from using Wilson wavelets and also look at transient events in the alpha 8-14Hz frequency band and look for these variations and partial suppressions in real time. This method is divided into several steps which will be summarized by a decision algorithm based on the temporal variation and the statistics of the partial removals of the alpha band.

Background: The ElectroEncephaloGram (EEG) can contain various frequency ranges, but also transient patterns such as isoelectric suppression (IES) which consist of periods of isoelectric activity that can last from a few seconds to several minutes [Amzica, Altwegg-Boussac]. These suppressions appear in several pathological states such as epileptic encephalopathies [Ohtahara], drug intoxications [DeRubeis], cephalic [Young] or cerebral diseases. They are also associated with postoperative sleep disorder [Nelson], the emergence of delirium [Fritz], and increased mortality in critically ill patients sedated [Watson] during anesthesia. Suppressions may also occur when anesthetic concentrations ncrease [Purdon]. Avoiding SEIs associated with anesthetic drugs is a recommendation during anesthesia, but there is no robust method to anticipate and prevent these SEIs [Brown].

EEG monitoring tracks intraoperative brain activity during general anesthesia (GA) and can measure the depth of anesthesia (DoA), defined as the degree of central nervous system depression produced by anesthetics. Commercial DoA monitors such as the Bspectral Index System (BIS) monitor (Covidien, USA) convert the EEG signal to a sensitization percentage between 0 (cortical silence) and 100 (awake patient) [Hajat]. Monitoring of DoA can prevent accidental loss of consciousness or overdoses of anesthetics. It is used to decrease the concentration of anesthetic and postoperative complications [Luginbuhl, Musialowicz]. DoA can detect burst suppressions [Chemali] or interpret the EEG signal to track loss of consciousness [Engemann] as it appears. An anesthetic such as propofol is an intravenous anesthetic agent commonly used to abolish consciousness during surgery. The ideal GA is achieved when the patient remains in this state of alpha-delta hypnosis for the duration of the surgery. Nevertheless, some patients develop SEI, due to an increase in anesthetic doses [purdon2015] which could decrease the cerebral metabolic oxygen rate (CMRO) [ching2012, lewis2013].


  • Step 1: Segmentation of the EEG signal: For anesthesia, the analysis will start from the moment the patient falls asleep due to the general anesthesia. Before describing the detection of alpha-S, we recall that the detection of IES is done by looking for regions of the signal with an amplitude of less than 8μV and lasting more than one second
  • Step 2: Detection grounds: We will develop algorithm to detect the first time of appearance of the IES and slope of the proportion of alpha-S: We will estimate the time t_αS (resp. T_IES) of appearance of the first alpha-S (resp. IES) in the EEG signal. We will use these times statistics to predict the sensitivity to anesthesia in real time.
  • Step 3: Average behavior of the alpha-S statistic for the two populations: We will compare the variables described in the previous section (duration, frequency of occurrence and mean amplitude of alpha-S and the alphja band) and study their mean distribution within groups of patients(anesthesia) with and without IESfor children.and seniors> 60 years old.
  • Step 4: Univariate and multivariate classification: To classify the patients we will use the variables described above and we will introduce non-EEG variables including age, height and weight as well as the maximum variation in Mean Arterial Pressure (ΔPAM) during induction, impact of the latter on postoperative complications. We will use different multivariate classification methods in order to demonstrate that the new variables that we have found are excellent predictors of IES.

The PhD candidate will visit the hospital and interact with Pr. Dan Longrois. The Phd candidate will register in mathematics, working at the intersection of signal processing, Intelligent-classification and Data modelling and predictive medicine. New method with a direct application to anaesthesia prediction could result in patents.


International mobility

Possibility to interact with the group of Pr. S. Jaffard for wavelet analysis and with Pr. S.Eglen for Deep learning (U. of Cambridge, UK)


Thesis supervision

David Holcman and Dan Longrois



Created in 2012, Université PSL is aiming at developing interdisciplinary training programmes and science projects of excellence within its members. Its 140 laboratories and 2,900 researchers carry out high-level disciplinary research, both fundamental and applied, fostering a strong interdisciplinary approach. The scope of Université PSL covers all areas of knowledge and creation (Sciences, Humanities and Social Science, Engineering, the Arts). Its eleven component schools gather 17,000 students and have won more than 200 ERC. PSL has been ranked 36th in the 2020 Shanghai ranking (ARWU).

More Information


  • Opportunity to conduct academic research in a top 100 university in the world.
  • High-quality doctoral training rewarded by a PhD degree, prepared within Ecole Normale Supérieure - PSL and delivered by PSL.
  • Access to cutting-edge infrastructures for research & innovation.
  • Appointment for a period of 36 months (job contract delivered by the involved component school of PSL) based on a salary of 3100 € gross employer (including employer tax) per month or approximately a 2228 € gross salary per month.
  • Job contract under the French labour legislation in force, respecting health and safety, and social security: 35 hours per week contract, 25 days of annual leave per year (“congés annuels”). Eventual complementary activities may be accepted or proposed by the co-supervisors (maximum of 64h/year for teaching, 32 day/year for specific missions).
  • Short stay(s) or secondment in France or abroad are expected.
  • An international environment supported by the adherence to the European Charter & Code.
  • Access to AI training package, with a strong interdisciplinary focus, together with a Career development Plan

Eligibility criteria

  • Applicants must have a Master’s degree (or be in the process of obtaining one) or have a University degree equivalent to a European Master’s (5-year duration) to be eligible at the time of the deadline of the relative call.
  • There is no nationality or age criteria, but applicants must not have resided or carried out their main activity (work, studies, etc.) in France for more than 12 months in the 3 years immediately before the deadline of the call (MSCA Mobility rule).
  • Applicants must declare to be available to start the programme on schedule.

For submitting your online application, go to: https://www.psl.eu/recherche/grands-projets-de-recherche/projets-europee...


The online application should contain the following documents:

  • English translated transcripts from the Master’s degree (or equivalent 5-year degree). A copy of the Master’s degree or a certificate of achievement will be required later on for the final registration.
  • International curriculum vitae and a cover letter explaining the reasons that lead him/her to prepare a PhD, why he/she applies to this offer and his/her professional project (guidelines will be given to the applicants in order to help him/her in the writing of his/her letter).
  • Two academic reference letters.
  • A statement duly signed on the mobility rules, availability, and conflicts of interest.


The applicants can only apply to one PhD project among the available ones. Multiple applications of one candidate will automatically make all his/her applications ineligible.

Selection process

The applications will be analysed by the Management Team for eligibility and completeness. Afterwards, the applications will be reviewed by the Selection Committee. In the pre-selection round (March-April 2021), applicants will be rated using a scoring system based on 3 criteria (academic excellence, experience, motivation, and qualities). A shortlist of qualified applicants will be interviewed during the selection round (June 2021) to further assess their qualifications and skills according to the predefined selection criteria.

All information regarding the applications (criteria, composition of the Selection Committee, requirements) can be found on the website of the programme, in greater detail.


The selection and recruitment processes of the PhD student will be in accordance with the European Charter for Researchers and Code of Conduct of the Recruitment of Researchers. The recruitment process will be open, transparent, impartial, equitable, and merit based. There will be no discrimination based on race, gender, sexual orientation, religion of belief, disability, or age.

Additional comments

The Group of Applied maths and Computational biology is a research unit at the Ecole Normale Supérieure (ENS - PSL).


The Ecole Normale Supérieure - PSL is a leading multidisciplinary institution that focuses on training through research. The ENS - PSL defines and applies scientific and technological research policies, from a multidisciplinary and international perspective and counts close relationships with prestigious partners, in France and abroad. It encompasses fourteen teaching and research departments, spanning the main humanities, sciences, and disciplines. The ENS - PSL currently has a staff of almost 800 lecturers, ENS - PSL, CNRS or associated researchers, and post-doc researchers. Within its Departments, the ENS - PSL includes 40 research units identified as ENS - PSL, INSERM or INRIA, encompassing ENS - PSL and CNRS agents as well as 300 foreign researchers and 650 doctoral students. The ENS - PSL respects the principles of the European Charter and Code for Researchers and is engaged in the HRS4R certification.

Web site for additional job details

Required Research Experiences

    1 - 4

Offer Requirements

    Engineering: Master Degree or equivalent
    ENGLISH: Excellent


  • Typical profile: Engineer and/or Master of Science.
  • Knowledge in data analysis, signal processing, classification method.

Work location(s)
1 position(s) available at
IBENS, Ecole Normale Supérieure - PSL
46, rue d Ulm

EURAXESS offer ID: 579042


The responsibility for the jobs published on this website, including the job description, lies entirely with the publishing institutions. The application is handled uniquely by the employer, who is also fully responsible for the recruitment and selection processes.


Please contact support@euraxess.org if you wish to download all jobs in XML.