SAND: The Challenge on Speech Analysis for Neurodegenerative Disease Assessment
Authors: Giovanna Sannino, Ivanoe De Falco, Nadia Brancati, Laura Verde, Maria Frucci, Daniel Riccio, Vincenzo Bevilacqua, Antonio Di Marino, Lucia Aruta, Valentina Virginia Iuzzolino, Gianmaria Senerchia, Myriam Spisto, Raffaele Dubbioso
Organizations: National Research Council of Italy (CNR), Institute for High-Performance Computing and Networking (ICAR), Naples, 80131, Italy · Department of Mathematics and Physics, University of Campania “Luigi Vanvitelli”, Caserta, 81100, Italy · Department of Electrical Engineering and Information Technologies, University of Naples “Federico II”, Naples, 80125, Italy · Department of Neurosciences, Reproductive Sciences and Odontostomatology, University of Naples “Federico II”, Naples, 80131, Italy · Department of Advanced Biomedical Sciences, University of Naples “Federico II”, Naples, 80131, Italy · Department of Psychology, University of Campania “Luigi Vanvitelli”, Caserta, 81100, Italy
Recent advances in Artificial Intelligence (AI) and the exploration of noninvasive, objective biomarkers, such as speech signals, have encouraged the development of algorithms to support the early diagnosis of neurodegenerative diseases, including Amyotrophic Lateral Sclerosis (ALS). Voice changes in subjects suffering from ALS typically manifest as progressive dysarthria, which is a prominent neurodegenerative symptom because it affects patients as the disease progresses. Since voice signals are complex data, the development and use of advanced AI techniques are fundamental to extracting distinctive patterns from them. Validating AI algorithms for ALS diagnosis and monitoring using voice signals is challenging, particularly due to the lack of annotated reference datasets. In this work, we present the outcome of a collaboration between a multidisciplinary team of clinicians and Machine Learning experts to create both a clinically annotated validation dataset and the "Speech Analysis for Neurodegenerative Diseases" (SAND) challenge based on it. Specifically, by analyzing voice disorders, the SAND challenge provides an opportunity to develop, test, and evaluate AI models for the automatic early identification and prediction of ALS disease progression.
Figures & tables
Figure 1: Stylized illustration of the Vox4Health acquisition setup. The smartphone is placed at approximately 20 cm from the subject’s mouth with an angle of about 45 ∘ . Audio is recorded via the Vox4Health m-health application and stored as 8 kHz, 16-bit WAV files.
Class
Severity Level
Distribution (%)
Class 1
ALS – Severe
2.23%
Class 2
ALS – Moderate
9.55%
Class 3
ALS – Mild
20.95%
Class 4
ALS – No Dysarthria
27.94%
Class 5
Healthy
39.33%
Table 1: Class distribution for Task 1.
Class
Severity Level
Distribution (%)
Class 1
ALS – Severe
13.64%
Class 2
ALS – Moderate
21.97%
Class 3
ALS – Mild
28.79%
Class 4
ALS – No Dysarthria
35.60%
Table 2: Class distribution for Task 2.
Figure 2: Number of teams registered for the SAND Challenge for each continent.
Figure 3: Number of Teams registered for the SAND Challenge for each country.
Figure 4: Number of Teams Participating for each country in a) Task 1, and b) Task 2.
Dept. of Information Systems and Cybersecurity The University of Texas at San Antonio San Antonio, TX, USA · School of Engineering Medicine Texas A&M University Houston, TX, USA