2024-07-24-mahdi24a.md

title	abstract	year	volume	publisher	series	software	layout	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	genre	issued	pdf	extras
Tuning In: Comparative Analysis of Audio Classifier Performance in Clinical Settings with Limited Data	This study assesses deep learning models for audio classification in a clinical setting with the constraint of small datasets reflecting the prospective collection of real-world data. We analyze CNNs, including DenseNet and ConvNeXt, alongside transformer models like ViT, and SWIN, and compare them against pretrained audio models such as AST, YAMNet and VGGish. Our method highlights the benefits of pretraining on large datasets before fine-tuning on specific clinical data. We prospectively collected two first-of-its-kind patient audio datasets from stroke patients. We investigated various preprocessing techniques, finding that RGB and grayscale spectrogram transformations affect model performance differently based on the priors they learn from pretraining. Our findings indicate CNNs can match or exceed transformer models in small dataset contexts, with DenseNet-Contrastive and AST models showing notable performance. This study highlights the significance of incremental marginal gains through model selection, pretraining, and preprocessing in sound classification; this offers valuable insights for clinical diagnostics that rely on audio classification.	2024	248	PMLR	Proceedings of Machine Learning Research	https://github.com/UofTNeurology	inproceedings	2640-3498	mahdi24a	0	Tuning In: Comparative Analysis of Audio Classifier Performance in Clinical Settings with Limited Data	446	460	446-460	446	false	Mahdi, Hamza and Nashnoush, Eptehal and Saab, Rami and Balachandar, Arjun and Dagli, Rishit and Perri, Lucas and Khosravani, Houman	given family Hamza Mahdi given family Eptehal Nashnoush given family Rami Saab given family Arjun Balachandar given family Rishit Dagli given family Lucas Perri given family Houman Khosravani	2024-07-24		Proceedings of the fifth Conference on Health, Inference, and Learning	inproceedings	date-parts 2024 7 24	https://raw.githubusercontent.com/mlresearch/v248/main/assets/mahdi24a/mahdi24a.pdf