Tools / models
This section encompasses all scientific publications on tools / models generated by the project.
Deep learning methods to predict amyotrophic lateral sclerosis disease progression
#Journal
Corrado Pancotti, Giovanni Birolo, Cesare Rollo, Tiziana Sanavia, Barbara Di Camillo, Umberto Manera, Adriano Chiò & Piero Fariselli
Amyotrophic lateral sclerosis (ALS) is a complex disease that weakens muscles by attacking nerve cells. Because ALS patients face shortened lifespans, understanding the disease’s progression quickly is crucial for improving treatments. Scientists are turning to computer models to forecast how ALS develops over time.
One major data source aiding this research is the PRO-ACT repository. In 2015, a competition challenged developers to create programs predicting ALS progression using this data.
Our study dives into this challenge, applying advanced Deep Learning techniques.
Our findings suggest that Deep Learning could offer a fresh approach to forecasting ALS progression, offering hope for more effective treatment strategies.
Learning prognostic models using a mixture of biclustering and triclustering: Predicting the need for non-invasive ventilation in Amyotrophic Lateral Sclerosis
#Peer-reviewed #Journal
Diogo F. Soares, Rui Henriques, Marta Gromicho, Mamede de Carvalho, Sara C. Madeira
This paper wants to improve the best features in methods used for predicting outcomes and deciding when patients with Amyotrophic Lateral Sclerosis (ALS) need non-invasive breathing assistance. It achieves this by studying clear patterns of how the disease progresses. The discoveries made can also be useful for understanding other aspects of ALS and similar diseases.
Artificial intelligence and statistical methods for stratification and prediction of progression in amyotrophic lateral sclerosis: A systematic review
#Peer-reviewed #Journal
Erica Tavazzi, Enrico Longato, Martina Vettoretti, Helena Aidos, Isotta Trescato, Chiara Roversi, Andreia S Martins, Eduardo N Castanho, Ruben Branco, Diogo F Soares, Alessandro Guazzo, Giovanni Birolo, Daniele Pala, Pietro Bosoni, Adriano Chiò, Umberto Manera, Mamede de Carvalho, Bruno Miranda, Marta Gromicho, Inês Alves, Riccardo Bellazzi, Arianna Dagliati, Piero Fariselli, Sara C Madeira, Barbara Di Camillo
This systematic review examines artificial intelligence’s methodological landscape in ALS, focusing on patient stratification and disease progression prediction.
Out of 1604 reports, we identified 15 studies on patient stratification, 28 on ALS progression prediction, and 6 on both. We highlighted a general agreement in terms of input variable selection for both stratification and prediction of ALS progression, and in terms of prediction targets. A striking lack of validated models emerged, as well as a general difficulty in reproducing many published studies, mainly due to the absence of the corresponding parameter lists. While deep learning seems promising for prediction applications, its superiority with respect to traditional methods has not been established; there is, instead, ample room for its application in the subfield of patient stratification. Finally, an open question remains on the role of new environmental and behavioural variables collected via novel, real-time sensors.
Baseline Machine Learning Approaches To Predict Amyotrophic Lateral Sclerosis Disease Progression
#Workshop
Trescato I., Guazzo A., Longato E., Hazizaj E., Roversi C., Tavazzi E., Vettoretti M., Di Camillo B.
The main goal of this study was to compare different methods for predicting the occurrence and timing of specific events in ALS, including the need for non-invasive ventilation, percutaneous endoscopic gastrostomy, and death. The study took place during the CLEF Challenge 2022, and the organizers provided two versions of datasets: the first comprised information collected only at the first visit after ALS diagnosis, while the second included all information collected during a 6-month follow-up starting from the first visit. Notably, regardless of the outcome predicted, the models including dynamic features improved model performance, highlighting the significance of the first 6 months of data for accurate predictions in fast-progressing diseases like ALS.
iDPP@CLEF 2023: The Intelligent Disease Progression Prediction Challenge
#Conference
Helena Aidos, Roberto Bergamaschi, Paola Cavalla, Adriano Chiò, Arianna Dagliati, Barbara Di Camillo, Mamede Alves de Carvalho, Nicola Ferro, Piero Fariselli, Jose Manuel García Dominguez, Sara C. Madeira & Eleonora Tavazzi
Amyotrophic Lateral Sclerosis (ALS) and Multiple Sclerosis (MS) are chronic diseases characterized by progressive or alternate impairment of neurological functions (motor, sensory, visual, cognitive). The goal of iDPP@CLEF Open Evaluation Challenge 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. iDPP@CLEF will continue in CLEF 2023, focusing on the prediction of MS progression and exploring whether pollution and environmental data can improve the prediction of ALS progression.