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

Data mining issues for improved birth outcomes

L Goodwin1, J Prather, K Schlitz

  • 1Duke University Durham, NC 27710, USA. linda.goodwin@duke.edu

Biomedical Sciences Instrumentation
|January 1, 1997
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

The prevalence of hazardous and harmful drinking in the UK Police Service, and their co-occurrence with job strain and mental health problems.

Epidemiology and psychiatric sciences·2021
Same author

[Medical therapy of obesity in France in 2021].

La Revue de medecine interne·2021
Same author

Hospital admissions for non-communicable disease in the UK military and associations with alcohol use and mental health: a data linkage study.

BMC public health·2020
Same author

Drinking motivations in UK serving and ex-serving military personnel.

Occupational medicine (Oxford, England)·2020
Same author

A systematic review of asylum-seeking women's views and experiences of UK maternity care.

Midwifery·2019
Same author

Hazardous alcohol consumption among spouses or partners of military service personnel: a systematic review of the literature.

Journal of the Royal Army Medical Corps·2018

Data mining in healthcare faces challenges like poor data quality and missing values. Research on Duke University

Area of Science:

  • Health Informatics
  • Data Mining
  • Clinical Data Analysis

Background:

  • Data mining for health outcomes is hindered by data quality issues such as redundancy, inconsistency, and missing values.
  • Temporal and repeated measures in clinical data present unique analytical challenges.
  • Effective data mining requires addressing theoretical and technical problems, including uncertainty management.

Purpose of the Study:

  • To report on ongoing data mining research using a large perinatal clinical database.
  • To identify and address key challenges in applying data mining techniques to patient data.

Main Methods:

  • Utilizing Duke University's perinatal database, containing nearly a decade of clinical patient data.
  • Analyzing a dataset with 71,753 patient records and 4-5000 variables per patient.

Related Experiment Videos

  • Investigating methods to overcome data quality and consistency issues in large-scale health datasets.

    • Main Results:

    • Preliminary results from the ongoing data mining research are presented.
    • The study highlights the complexity of managing and analyzing extensive clinical datasets.
    • Challenges in data preprocessing and technique selection for perinatal data are discussed.

    Conclusions:

    • Addressing data quality and consistency is crucial for successful health outcome prediction.
    • Further research is needed to refine data mining techniques for complex clinical data.
    • The Duke University perinatal database serves as a valuable resource for advancing health informatics.