- Registration closes: April 22, 2022
- Runs submission deadline: May 6, 2022
- Evaluation results out: May 20, 2022
- Participant and position paper submission deadline: May 27, 2022
- Notification of acceptance for participant and position papers: June 13, 2022
- Camera-ready participant papers submission: July 1, 2022
- iDPP CLEF Workshop: September 5-8, 2022 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.
In particular, we offer the following activities:
Pilot Task 1 –
Ranking Risk of Impairment
It focuses on ranking of patients based on the risk of impairment in specific domains. More in detail, we will use the ALSFRS-R scale to monitor speech, swallowing, handwriting, dressing/hygiene, walking and respiratory ability in time and will ask participants to rank patients based on time to event risk of experiencing impairment in each specific domain.
Pilot Task 2 –
Predicting Time of Impairment
It refines Task 1 asking participants to predict when specific impairments will occur (i.e. in the correct time-window). In this regard, we assess model calibration in terms of the ability of the proposed algorithms to estimate a probability of an event close to the true probability within a specified time-window.
Position Papers Task 3 –
Explainability of AI algorithms
We call for proposals of different visualization frameworks able to show the multivariate nature of the data and the model predictions in an explainable, possibly interactive, way.
Information on the Datasets
The iDPP@CLEF 2022 challenge will share three valuable datasets which are used in the tasks above described for both training and testing algorithms to predict the progression of ALS and/or to showcase approaches for the explainability of such algorithms.
These datasets come from two clinical institutions, one in Lisbon (Portugal), and the other in Turin (Italy) and contain data about real patients, fully anonymized. These datasets are highly curated. They are produced from an ontology developed by the BRAINTEASER project which ensures the consistency of the data represented. Moreover, several checks have been performed to ensure that all the instances are clean, contain proper values in the expected ranges, and do not have contradictions.
Dataset A: is intended for the prediction of NIV – Non-invasive ventilation (or the competing event Death) and consists of 1,804 patients and 6,002 visits (ALSFRS-R questionnaires, Spirometry, etc.).
Dataset B: is intended for the prediction of PEG – Percutaneous Endoscopic Gastrostomy (or the competing event Death) and consists of 2,145 patients and 7,180 visits (ALSFRS-R questionnaires, Spirometry, etc.).
Dataset C: is intended for the prediction of Death and consists of 2,250 patients and 7,536 visits (ALSFRS-R questionnaires, Spirometry, etc.).
All the datasets are split into a training and test set according to a (approximately) 80%-20% ratio.