Baseline Characteristics of Participants in a Digital Stethoscope Validation Study

64 participants with various respiratory conditions had their lung sounds recorded and classified using a novel digital stethoscope (Skeeper SM-300®) and conventional methods. The dataset likely contains baseline participant characteristics and classification results from a single-center, prospective, investigator-blinded investigation. The data was published by Sue In Choi under a CC-BY-4.0 license and last updated in May 2026.

Use Cases

• Validate digital stethoscope performance based on comparison with conventional auscultation results.
• Train machine learning models for lung sound classification based on expert-labeled categories like crackle and wheezing.
• Assess patient comfort and acceptability of novel remote healthcare devices based on survey responses.
• Analyze diagnostic accuracy for different breathing sounds (e.g., deep vs. tidal) based on specialist agreement metrics.

Strengths

• Includes data from 64 participants across multiple respiratory condition groups.
• Provides statistically significant agreement metrics (к-values ranging from 0.8043 to 0.8337) between raters and methods.
• Explicitly evaluates non-inferiority, diagnostic accuracy, and patient comfort.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is from a single-center study, which may limit generalizability.

Provenance

Source

figshare

Collection Method

Single-center, prospective, single-arm, investigator-blinded clinical investigation.

Freshness

Last updated 2026-05-13 17:40:32; freshness should be verified.