Breath analysis in detecting epilepsy
Bibliographic record
Abstract
Abstract The aim of this proof of concept study is to investigate if an electronic nose (eNose) is able to make a distinction between breath profiles of diagnosed epilepsy patients and epilepsy-free control subjects. An eNose is a non-invasive device, with a working mechanism that is based on the presence of volatile organic compounds (VOCs) in exhaled breath. These VOCs interact with the sensors of the eNose, and the eNose has to be trained to distinguish between breath patterns from patients with a specific disease and control subjects without that disease. During the measurement participants were asked to breathe through the eNose for five minutes via a disposable mouthpiece. Seventy-four epilepsy patients and 110 control subjects were measured to train the eNose and create a classification model. To assess the effects of anti-epileptic drugs (AEDs) usage on the classification, additional test groups were measured: seven patients who (temporarily) did not use AEDs and 11 patients without epilepsy who used AEDs. The results show that an eNose is able to make a distinction between epilepsy and control subjects with a sensitivity of 76%, a specificity of 67%, and an accuracy of 71%. The results of the two additional groups of subjects show that the created model classifies one out of seven epilepsy patients without AEDs and six out of 13 patients without epilepsy but with AEDs correctly. In this proof of concept study, the Aeonose TM is able to differentiate between epilepsy patients and control subjects. However, the number of false positives and false negatives is still high, which suggests that this first model is still mainly based on the usage of various AEDs.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".