Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.

Ranking Information Extracted from Uncertainty Quantification of the Prediction of a Deep Learning Model on Medical Time Series Data

Open access
Stoean, Ruxandra, Stoean, Catalin, Atencia, Miguel, Rodríguez-Labrada, Roberto, Joya, Gonzalo · 2020 · Mathematics

Abstract

Uncertainty quantification in deep learning models is especially important for the medical applications of this complex and successful type of neural architectures. One popular technique is Monte Carlo dropout that gives a sample output for a record, which can be measured statistically in terms of average probability and variance for each diagnostic class of the problem. The current paper puts forward a convolutional–long short-term memory network model with a Monte Carlo dropout layer for obtaining information regarding the model uncertainty for saccadic records of all patients. These are next used in assessing the uncertainty of the learning model at the higher level of sets of multiple records (i.e., registers) that are gathered for one patient case by the examining physician towards an accurate diagnosis. Means and standard deviations are additionally calculated for the Monte Carlo uncertainty estimates of groups of predictions. These serve as a new collection where a random forest model can perform both classification and ranking of variable importance. The approach is validated on a real-world problem of classifying electrooculography time series for an early detection of spinocerebellar ataxia 2 and reaches an accuracy of 88.59% in distinguishing between the three classes of patients.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/math8071078

Cites

30 of 30 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Representation of all saccades from a register in class control (C029), one presymptomatic (P022) and sick (S021).
Figure 1 Representation of all saccades from a register in class control (C029), one presymptomatic (P022) and sick (S021).CC-BY · From the PDF
Figure 2 Overview of the proposed methodology.
Figure 2 Overview of the proposed methodology.CC-BY · From the PDF
Figure 3 Box plots with probabilities and variances for classes C, P and S reached by the Monte Carlo dropout (MCD) runs for the presymptomatic register P022. Each row corresponds to the saccades that were classified as control ( top ), presymptomatic ( middle ) and sick ( bottom ).
Figure 3 Box plots with probabilities and variances for classes C, P and S reached by the Monte Carlo dropout (MCD) runs for the presymptomatic register P022. Each row corresponds to the saccades that were classified as control ( top ), presymptomatic ( middle ) and sick ( bottom ).CC-BY · From the PDF
Figure 4 Example of the classification probabilities and variances from the 100 MCD runs for some saccades from class control (3 saccades in register C029, rows 1-3), from class presymptomatic (2 samples from register P022, rows 4-5) and from class sick (1 saccade from register S021, last row).
Figure 4 Example of the classification probabilities and variances from the 100 MCD runs for some saccades from class control (3 saccades in register C029, rows 1-3), from class presymptomatic (2 samples from register P022, rows 4-5) and from class sick (1 saccade from register S021, last row).CC-BY · From the PDF
Figure 5 The label prediction with probabilities and variances for each saccade of the example registers as accumulated from the 100 MCD runs.
Figure 5 The label prediction with probabilities and variances for each saccade of the example registers as accumulated from the 100 MCD runs.CC-BY · From the PDF
Figure 6 Confusion matrices for Random Forest (RF) with and without variances (on the top row) and the corresponding application of DT (on the bottom row).
Figure 6 Confusion matrices for Random Forest (RF) with and without variances (on the top row) and the corresponding application of DT (on the bottom row).CC-BY · From the PDF
Figure 7 Importance of the features as derived from Gini impurity.
Figure 7 Importance of the features as derived from Gini impurity.CC-BY · From the PDF
Figure 8 Importance of the features for each class in turn.
Figure 8 Importance of the features for each class in turn.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

1 retracted

Show all 30 references

Cited by

Metadata

Authors
Stoean, R., Stoean, C., Atencia, M., Rodríguez-Labrada, R., & Joya, G.
Affiliations
  • Romanian Institute of Science and Technology (RO)
  • Romanian Institute of Science and Technology, 400022 Cluj-Napoca, Romania
  • Universidad de Málaga (ES)
  • Cuban Neuroscience Center, 11600 Havana, Cuba
Venue
Mathematics
Publisher
MDPI AG
Published
2020-07-02
Volume
8
Issue
7
Pages
1078
ISSN
2227-7390 (ISSN-L)
OpenAlex
W3038849371
Cited by
16
References
30
Citations by year
2026: 1 · 2024: 3 · 2023: 3 · 2022: 1 · 2021: 6 · 2020: 2
FWCI
1.18
Type
journal article
Language
en
Open access
Locations
  • Mathematics (publishedVersion, cc-by)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Greater South Information System
Funders
  • Ministerio de Ciencia e Innovación (TIN2017-88728-C2-1-R)
  • University of Málaga-Andalucía-Tech through the Plan Propio de Investigación y Transferencia (Project DIATAX: 345 Integración de nuevas tecnologías para el diagnóstico temprano de las Ataxias Hereditarias)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
Keywords
uncertainty quantification, Monte Carlo dropout, convolutional LSTM, electrooculography, saccades, spinocerebellar ataxia type 2, early diagnosis, random forest, variable importance ranking

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.