MétaCan
Menu
Back to cohort
Record W2343041920 · doi:10.1136/bmjresp-2016-000136

Wheezes, crackles and rhonchi: simplifying description of lung sounds increases the agreement on their classification: a study of 12 physicians' classification of lung sounds from video recordings

2016· article· en· W2343041920 on OpenAlexaff
Hasse Melbye, Luis García‐Marcos, Paul L.P. Brand, Mark L. Everard, Kostas Ν. Priftis, Hans Pasterkamp

Bibliographic record

VenueBMJ Open Respiratory Research · 2016
Typearticle
Languageen
FieldMedicine
TopicPhonocardiography and Auscultation Techniques
Canadian institutionsUniversity of Manitoba
FundersEuropean Respiratory Society
KeywordsCracklesMedicineLungSpeech recognitionRespiratory soundsNatural language processingPathologyAudiologyArtificial intelligencePattern recognition (psychology)Internal medicineComputer science

Abstract

fetched live from OpenAlex

BACKGROUND: The European Respiratory Society (ERS) lung sounds repository contains 20 audiovisual recordings of children and adults. The present study aimed at determining the interobserver variation in the classification of sounds into detailed and broader categories of crackles and wheezes. METHODS: Recordings from 10 children and 10 adults were classified into 10 predefined sounds by 12 observers, 6 paediatricians and 6 doctors for adult patients. Multirater kappa (Fleiss' κ) was calculated for each of the 10 adventitious sounds and for combined categories of sounds. RESULTS: The majority of observers agreed on the presence of at least one adventitious sound in 17 cases. Poor to fair agreement (κ<0.40) was usually found for the detailed descriptions of the adventitious sounds, whereas moderate to good agreement was reached for the combined categories of crackles (κ=0.62) and wheezes (κ=0.59). The paediatricians did not reach better agreement on the child cases than the family physicians and specialists in adult medicine. CONCLUSIONS: Descriptions of auscultation findings in broader terms were more reliably shared between observers compared to more detailed descriptions.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.035
metaresearch head score (Gemma)0.122
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.035
Threshold uncertainty score0.183

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0350.122
Meta-epidemiology (narrow)0.0000.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0010.002
Scholarly communication0.0010.001
Open science0.0010.003
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.267
GPT teacher head0.446
Teacher spread0.178 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations77
Published2016
Admission routes1
Has abstractyes

Explore more

Same venueBMJ Open Respiratory ResearchSame topicPhonocardiography and Auscultation TechniquesFrench-language works237,207