Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Using data preprocessing and single layer perceptron to analyze laboratory data

J J Forsström1, K Irjala, G Selén

  • 1Department of Medicine, University of Turku, Finland.

Scandinavian Journal of Clinical and Laboratory Investigation. Supplementum
|January 1, 1995
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Ti <sub></sub>C <sub></sub> MXenes with fully saturated and thermally stable Cl terminations.

Nanoscale advances·2022
Same author

The effects of microstructure, Nb content and secondary Ruddlesden-Popper phase on thermoelectric properties in perovskite CaMn<sub>1-</sub> Nb <sub></sub> O<sub>3</sub> (<i>x</i> = 0-0.10) thin films.

RSC advances·2022
Same author

EuGMS Task and Finish group on Fall-Risk-Increasing Drugs (FRIDs): Position on Knowledge Dissemination, Management, and Future Research.

European geriatric medicine·2021
Same author

Perceptions of Professional Responsibility When Caring for Older People in Home Care in Sweden.

Journal of community health nursing·2020
Same author

Theoretical study of phase stability, crystal and electronic structure of MeMgN<sub>2</sub> (Me = Ti, Zr, Hf) compounds.

Journal of materials science·2020
Same author

Anatomy and resilience of the global production ecosystem.

Nature·2019
Same journal

Standardization of tumor markers - priorities identified through external quality assessment.

Scandinavian journal of clinical and laboratory investigation. Supplementum·2016
Same journal

Next generation sequencing in cancer: opportunities and challenges for precision cancer medicine.

Scandinavian journal of clinical and laboratory investigation. Supplementum·2016
Same journal

microRNAs as cancer biomarkers.

Scandinavian journal of clinical and laboratory investigation. Supplementum·2016
Same journal

Biomarkers along the continuum of care in lung cancer.

Scandinavian journal of clinical and laboratory investigation. Supplementum·2016
Same journal

Precision medicine: what's all the fuss about?

Scandinavian journal of clinical and laboratory investigation. Supplementum·2016
Same journal

Serum thyroglobulin in the monitoring of differentiated thyroid cancer.

Scandinavian journal of clinical and laboratory investigation. Supplementum·2016
See all related articles

DiagaiD software uses machine learning to link clinical data, aiding diagnoses like appendicitis and myocardial infarction. This tool transforms lab values into logical insights for better clinical decision support.

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Medicine
  • Clinical Decision Support Systems

Background:

  • Hospitals generate vast amounts of clinical data daily, with essential patient information stored in computer files.
  • Existing laboratory reference values offer limited insight into the diagnostic weight of abnormal test results in specific clinical contexts.
  • There is a need for tools that can intelligently link patient databases with clinical knowledge to support healthcare professionals.

Purpose of the Study:

  • To introduce DiagaiD, a software package designed to bridge patient databases and clinicians using machine learning.
  • To demonstrate DiagaiD's capability in transforming numerical clinical data into clinically relevant logical values for decision support.
  • To evaluate DiagaiD's performance in diagnosing acute appendicitis and myocardial infarction using small datasets.

Related Experiment Videos

Main Methods:

  • Development of the DiagaiD software package utilizing neural network-based machine learning techniques.
  • Implementation of data transformation methods combined with a single-layer perceptron to build nonlinear models from preclassified cases.
  • Application of the DiagaiD scheme to two small datasets for the diagnosis of acute appendicitis and myocardial infarction.

Main Results:

  • The DiagaiD software demonstrated its ability to learn clinically relevant transformations from numerical to logical values.
  • Performance evaluation in diagnosing acute appendicitis and myocardial infarction showed promising results.
  • Comparison with logistic regression and backpropagation neural networks indicated slightly better performance for the neuro-fuzzy tool, though not statistically significant.

Conclusions:

  • DiagaiD offers a novel approach to clinical decision support by leveraging machine learning on existing patient data.
  • The software can effectively translate complex clinical data into actionable insights for clinicians.
  • Further validation with larger datasets is warranted to confirm the statistical significance of the observed performance improvements.