Optimizing Rare Disease Gait Classification through Data Balancing and Generative AI: Insights from Hereditary Cerebellar Ataxia

• Published in: Sensors (Basel, Switzerland) Vol. 24; no. 11; p. 3613
• Main Authors: Trabassi, Dante, Castiglia, Stefano Filippo, Bini, Fabiano, Marinozzi, Franco, Ajoudani, Arash, Lorenzini, Marta, Chini, Giorgia, Varrecchia, Tiwana, Ranavolo, Alberto, De Icco, Roberto, Casali, Carlo, Serrao, Mariano
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.06.2024; MDPI
• Subjects: Adult; Aged; Algorithms; Artificial Intelligence; Ataxia; Cerebellar ataxia; Cerebellar Ataxia - diagnosis; Cerebellar Ataxia - genetics; Cerebellar Ataxia - physiopathology; Classification; data augmentation; data balancing; Data collection; Datasets; Diseases; Female; Fourier transforms; Gait; Gait - physiology; gait analysis; Gait Analysis - methods; generative artificial intelligence; Humans; Kinematics; Male; Medical research; Medicine, Experimental; Middle Aged; Range of motion; Rare Diseases; Software; Walking; Italy; inertial measurement unit; rare diseases; cerebellar ataxia; data augmentation; conditional tabular generative artificial network; data balancing; synthetic minority oversampling technique; generative artificial network; generative artificial intelligence; gait analysis
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s24113613

The interpretability of gait analysis studies in people with rare diseases, such as those with primary hereditary cerebellar ataxia (pwCA), is frequently limited by the small sample sizes and unbalanced datasets. The purpose of this study was to assess the effectiveness of data balancing and generative artificial intelligence (AI) algorithms in generating synthetic data reflecting the actual gait abnormalities of pwCA. Gait data of 30 pwCA (age: 51.6 ± 12.2 years; 13 females, 17 males) and 100 healthy subjects (age: 57.1 ± 10.4; 60 females, 40 males) were collected at the lumbar level with an inertial measurement unit. Subsampling, oversampling, synthetic minority oversampling, generative adversarial networks, and conditional tabular generative adversarial networks (ctGAN) were applied to generate datasets to be input to a random forest classifier. Consistency and explainability metrics were also calculated to assess the coherence of the generated dataset with known gait abnormalities of pwCA. ctGAN significantly improved the classification performance compared with the original dataset and traditional data augmentation methods. ctGAN are effective methods for balancing tabular datasets from populations with rare diseases, owing to their ability to improve diagnostic models with consistent explainability.