Article

Evaluating Few-Shot Prompting for Spectrogram-Based Lung Sound Classification Using a Multimodal Language Model

2025-07-28

Abstract excerpt

<h4>Introduction</h4> Traditional deep learning models for lung sound analysis require large, labeled datasets; multimodal LLMs may offer a flexible, prompt-based alternative. This study aimed to evaluate the utility of a general-purpose multimodal LLM, GPT-4o, for lung sound classification from mel-spectrograms and assess whether a few-shot prompt approach improves performance over zero-shot prompting. <h4>Metho...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: ceb66fb8-48d6-5b98-b8c3-41398148c42e
DOI: 10.1101/2025.07.27.25332255

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Evaluating Few-Shot Prompting for Spectrogram-Based Lung Sound Classification Using a Multimodal Language ModelDOI 10.1101/2025.07.27.25332255Read

A Comparative Investigation of Zero-shot Prompting and Fine-tuning for Clinical Note SummarizationSemantic proximity Read

Minimal-Preprocessing Paradigm for Robust COVID-19 Detection from Cough Audio Using Deep LearningSemantic proximity Read

Bridging Acoustic and Semantic Spaces for Interpretable Voice Scoring via Zero-Shot Semantic ExpansionSemantic proximity Read

Empirical Review of LLM-driven Classification of Multidimensional Sleep Health Mentions from Free-Text Clinical NotesSemantic proximity Read

Advances and Challenges in Respiratory Sound Analysis: A Technique Review Based on the ICBHI2017 DatabaseSemantic proximity Read

Automated Detection of Poor-Quality Digital Heart Sound Recordings Using Noise InjectionSemantic proximity Read

Construction and validation of an automatic segmentation method for respiratory sound time labelsSemantic proximity Read

Deep Learning for Heart Sound Analysis: A Literature ReviewSemantic proximity Read

RED-RHD (Rice Early Detection – Rheumatic Heart Disease): AI-Based Adaptive Multi-Regional System for Early Detection and Murmur Classification of Rheumatic Heart DiseaseSemantic proximity Read

<i>Can you hear me now</i>? Clinical applications of audio recordingsSemantic proximity Read

3D Mel-Spectrogram–Based Deep Learning for Automated Multiclass Diagnosis of Pathological VoicesSemantic proximity Read

Fine-Tuning LLaMA2 for Summarizing Discharge Notes: Evaluating the Role of Highlighted InformationSemantic proximity Read