iDPP CLEF Workshop – 21st September 2023

Agenda

Session 1, 11:30-13:00 EEST​ (90 mins)

Welcome and Introduction (5 mins)

Overview of the Lab (20 mins, including questions)

 
 
Overview of iDPP@CLEF 2023: The Intelligent Disease Progression Prediction Challenge
 
Guglielmo Faggioli, Alessandro Guazzo, Stefano Marchesin, Laura Menotti, Isotta Trescato, Helena Aidos, Roberto Bergamaschi, Giovanni Birolo, Paola Cavalla, Adriano Chiò, Arianna Dagliati, Mamede de Carvalho, Giorgio Maria Di Nunzio, Piero Fariselli, Jose Manuel García Dominguez, Marta Gromicho, Enrico Longato, Sara C. Madeira, Umberto Manera, Gianmaria Silvello, Eleonora Tavazzi, Erica Tavazzi, Martina Vettoretti, Barbara Di Camillo, Nicola Ferro
 

Paper

h

Slides

Participant Presentations (15 mins, including questions)

 
 
Maximum Likelihood Estimation with Deep Learning for Multiple Sclerosis Progression Prediction
 
Tsvetan Asamov, Petar Ivanov, Anna Aksenova, Dimitar Taskov, Svetla Boytcheva
 

Paper

h

Slides

Repository

m
Investigating the Impact of Environmental Data on ALS Prognosis with Survival Analysis
 
Ruben Branco, Diogo F. Soares, Andreia S. Martins, Joana Barros Valente, Eduardo N. Castanho, Sara C. Madeira, Helena Aidos
 

Paper

h

Slides

Repository

m
Predicting and Explaining Risk of Disease Worsening Using Temporal Features in Multiple Sclerosis
 
Tommaso Mario Buonocore, Pietro Bosoni, Giovanna Nicora, Mahin Vazifehdan, Riccardo Bellazzi, Enea Parimbelli, Arianna Dagliati
 

Paper

h

Slides

Repository

m
Time-to-Event Interpretable Machine Learning for Multiple Sclerosis Worsening Prediction: Results from iDPP@CLEF 2023
 
Angela Lombardi, Maria Luigia Natalia De Bonis, Giuseppe Fasano, Alessia Sportelli, Tommaso Colafiglio, Domenico Lofù, Paolo Sorino, Fedelucio Narducci, Eugenio Di Sciascio, Tommaso Di Noia

Paper

h

Slides

Repository

m

Lunch Break, 13:00-14:00 EEST

Session 2, 14:00-15:30 EEST (90 mins)

Participant Presentations (15 mins, including questions)

 
 
Baseline Machine Learning Approaches To Predict Multiple Sclerosis Disease Progression
 
Alessandro Guazzo, Isotta Trescato, Enrico Longato, Erica Tavazzi, Martina Vettoretti, Barbara Di Camillo
 

Paper

h

Slides

Repository

m
HULAT@IDDP CLEF 2023: Intelligent Prediction of Disease Progression in Multiple Sclerosis Patients
 
Alberto Ramos, Paloma Martínez, Israel González-Carrasco

Paper

h

Slides

Repository

m
Survival Analysis for Multiple Sclerosis: Predicting Risk of Disease Worsening
 
Ruben Branco, Joana Barros Valente, Andreia S. Martins, Diogo F. Soares, Eduardo N. Castanho, Sara C. Madeira, Helena Aidos
 

Paper

h

Slides

Repository

m
Predicting Risk of Multiple Sclerosis Worsening
 
Marek Hanzl, Lukáš Picek
 

Paper

h

Slides

Repository

m
Air Pollution Profiling through Patient Stratification: Study of ALS Staging Systems Usefulness in Facilitating Data-driven Disease Subtyping and Discovery of Hazardous Ambient Air Pollutants
 
Mohamed Chiheb Karray

Paper

h

Slides

Repository

m
Multiple Sclerosis Survival Prediction Results from DSM-COMPBIO UNITO
 
Ivan Rossi, Giovanni Birolo, Piero Fariselli

Paper

h

Slides

Repository

m

Discussion and closing (5 mins)

 
 

Motivation

Amyotrophic Lateral Sclerosis (ALS) and Multiple Sclerosis (MS) are chronic diseases characterized by progressive or alternate impairment of neurological functions (motor, sensory, visual, cognitive). Patients have to manage alternated periods in hospital with care at home, experiencing a constant uncertainty regarding the timing of the disease acute phases and facing a considerable psychological and economic burden that also involves their caregivers. Clinicians, on the other hand, need tools able to support them in all the phases of the patient treatment, suggest personalized therapeutic decisions, indicate urgently needed interventions.

Important dates

  • Registration closes: April 28, 2023
  • Runs submission deadline: May 10, 2023
  • Evaluation results out: May 26, 2023
  • Participant and position paper submission deadline: June 5, 2023
  • Notification of acceptance for participant and position papers: June 23, 2023
  • Camera-ready participant papers submission: July 7, 2023
  • iDPP CLEF Workshop: September 18-21, 2023 during the CLEF Conference

The goal of iDPP@CLEF is to design and develop an evaluation infrastructure for AI algorithms able to:

Better describe disease mechanisms.

Stratify patients according to their phenotype assessed all over the disease evolution.

Predict disease progression in a probabilistic, time dependent fashion.

Tasks

Overall iDPP is targeting two kinds of activities: (a) tasks on disease progression prediction; (b) position papers on the impact of the exposure to pollutants on the prediction algorithms. Overall, this mix will provide participants with the opportunity to make some hands-on experience with these data and provide feedback about the task design as well as to brainstorm on how to evaluate this kind of algorithms and, in particular, assess their explainability. 
In this iteration of iDPP@CLEF we will focus on MS for the prediction tasks and on ALS for the position papers task.

In particular, we offer the following activities:

Task 1 –

Predicting Risk of Disease Worsening (Multiple Sclerosis):

it will focus on ranking subjects based on the risk of worsening, setting the problem as a survival analysis task. More specifically the risk of worsening predicted
by the algorithm should reflect how early a patient experience the event “worsening”. Worsening is defined based on the Expanded Disability Status Scale (EDSS), accordingly to clinical standards. In particular we will consider two different definitions in subtasks 1a and 1b, respectively.

• Subtask 1a: the patient crosses the threshold EDSS ≥ 3 at least twice within one year interval;
• Subtask 1b: the second definition of worsening depends on the first recorded value accordingly to current clinical protocols. If Baseline EDSS < 1, worsening event occurs when an increase of EDSS by 1.5 points is first observed; if 1 ≤ Baseline EDSS < 5.5, worsening event occurs when an increase of EDSS by 1 point is first observed; if baseline EDSS ≥ 5.5, worsening event occurs when an increase of EDSS by 0.5 points is first observed.

In both cases the occurrence of the worsening event and the time of occurrence will be pre-computed by the challenge organizers

Task 2 –

Predicting Probability of Worsening (Multiple Sclerosis):

it will refine Task 1 asking participants to explicitly assign a probability of worsening at different time windows (e.g., between years 4 and 6, 6 and 8, 8 and 10 etc.). Worsening will be defined in two different ways in subtasks 2a and 2b as for Task 1.

Position Papers Task 3 –

Impact of Exposition to Pollutants (Amyotrophic Lateral Sclerosis):

we will evaluate proposals of different approaches to assess if exposure to different pollutants is a useful variable to predict time to Percutaneous Endoscopic Gastrostomy (PEG), Non-Invasive Ventilation (NIV) and death in ALS patients.

Information on the Datasets

We will provide retrospective, fully anonymized MS and ALS clinical data including demographic and clinical characteristics, coming from clinical institutions in Italy, Portugal, and Spain.

For Task 1 and Task 2 we will release a brand new dataset with MS data consisting of about 1,800 patients.

For Position Paper Task 3 we will re-use the ALS dataset developed in iDPP@CLEF 2022, consisting of about 2,250 patients, and will extend it with environmental and pollution data.

Organizers

  • Helena Aidos, University of Lisbon, Portugal
  • Roberto Bergamaschi, University of Pavia, Italy
  • Paola Cavalla, “Città della Salute e della Scienza”, Turin, Italy
  • Adriano Chio’, University of Turin, Italy
  • Arianna Dagliati, University of Pavia, Italy
  • Barbara Di Camillo, University of Padua, Italy
  • Mamede Alves de Carvalho, University of Lisbon, Portugal
  • Nicola Ferro, University of Padua, Italy
  • Piero Fariselli, University of Turin, Italy
  • Jose Manuel García Dominguez, Gregorio Marañon Hospital in Madrid, Spain
  • Sara C. Madeira, University of Lisbon, Italy
  • Eleonora Tavazzi, IRCCS Foundation C. Mondino in Pavia, Italy
Skip to content