This study explores the feasibility of employing eXplainable Artificial Intelligence (XAI) methodologies for the analysis of cough patterns in respiratory diseases. A cohort of 20 adult patients, all presenting persistent cough as a symptom of respiratory disease, was monitored for 24 hours using a smartphone. The audio signals underwent frequency domain transformation to yield 1-second spectrograms, subsequently processed by a CNN to detect cough events. Quantitative analysis of spectrogram regions relevant for cough detection highlighted by occlusion maps, revealed significant differences between patient groups. Notably, distinctions were observed between the Chronic Obstructive Pulmonary Disease (COPD) patient group and groups with other respiratory pathologies, both chronic and non-chronic. In conclusion, interpretability analysis methods applied to neural networks offer insights into cough-related distinctions among patients with varying respiratory conditions.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC53108.2024.10781781 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Hemispheric asymmetries in the control of upper limb movements.
Handb Clin Neurol
March 2025
Department of Psychology, University of Campania 'Luigi Vanvitelli', Caserta, Italy. Electronic address:
This chapter deals with the unique human abilities of using tools, imitating others' gestures, drawing, and building complex items. Herein, after a brief overview of clinical manifestations and assessment of disorders of tool use and imitation (upper limb apraxia) and of the impairments in drawing and assembling multipart objects (constructional apraxia), brain asymmetries are discussed mainly starting from the neuropsychologic studies on patients with focal brain lesions, although both upper limb apraxia and constructional apraxia are often observed during the course of neurodegenerative diseases. Although no room is allowed here for a full discussion of brain-behavior relationships, relevant functional neuroimaging findings in healthy individuals are considered.
View Article and Find Full Text PDFBrain Network Alterations in Fragile X Syndrome.
Neurosci Biobehav Rev
March 2025
Neuroscience and Mental Health, The Hospital for Sick Children, Canada; Institute of Biomedical Engineering, University of Toronto, Toronto, Canada; Division of Neurosurgery, The Hospital for Sick Children, Canada.
Fragile X syndrome (FXS), caused by FMR1 gene mutations, leads to widespread brain alterations significantly impacting cognition and behaviour. Recent advances have provided a deeper understanding of the neural substrates of FXS. This review provides a comprehensive overview of the current knowledge of neuronal network alterations in FXS.
View Article and Find Full Text PDFAbnormal resting-state neural activities of language and non-language cognitive function impairments in stroke patients with aphasia: A cross-sectional study.
Clin Neurol Neurosurg
March 2025
Department of Rehabilitation Medicine, Beijing Tiantan Hospital, Capital Medical University, Beijing 100070, China. Electronic address:
Objective: Language impairments may mask non-language cognitive deficits in post-stroke aphasia (PSA) patients. Moreover, the underlying neural mechanisms of both language and non-language cognitive impairment remain unclear. This study aimed to investigate the activities and functional abnormalities of local and remote brain regions and their relationship with cognitive function in PSA patients, to provide more effective tips in future clinical therapy.
View Article and Find Full Text PDFPocketDTA: A pocket-based multimodal deep learning model for drug-target affinity prediction.
Comput Biol Chem
March 2025
Scientific Research Management Department, Shanghai University, Shanghai, 200444, China. Electronic address:
Drug-target affinity prediction is a fundamental task in the field of drug discovery. Extracting and integrating structural information from proteins effectively is crucial to enhance the accuracy and generalization of prediction, which remains a substantial challenge. This paper proposes a pocket-based multimodal deep learning model named PocketDTA for drug-target affinity prediction, based on the principle of "structure determines function".
View Article and Find Full Text PDFDevelopmental timing of adversity and neural network organization: An fNIRS study of the impact of refugee displacement.
Dev Cogn Neurosci
March 2025
University of Toronto, Toronto, ON, Canada; Haskins Laboratories, New Haven, CT, USA.
This study investigated the neurodevelopmental impacts of displacement on resettled Syrian refugee children in Canada, focusing on how the timing and duration of adversity experienced during displacement influence neural network organization. Using graph theoretical approaches within a network neuroscience framework, we examined how the developmental timing of displacement (age of displacement, duration of displacement) related to functional integration, segregation, and small-worldness. Syrian refugee children (n = 61, M=14 Range = 8-18), completed a resting state scan using functional Near Infrared Spectroscopy (fNIRS) neuroimaging.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!