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

Predictive Models for Primary Health Care: assessing PCATool with Machine Learning in Rio de Janeiro, Brazil.

Luiz Alexandre Chisini1,2, Otávio Pereira D'Avila1, Mauro Cardoso Ribeiro1

  • 1Universidade Federal de Pelotas. R. Gonçalves Chaves 457, Centro. 96015-560 Pelotas RS Brasil. alexandrechisini@gmail.com.

Ciencia & Saude Coletiva
|July 1, 2026
PubMed
Summary

Related Concept Videos

Primary Healthcare Services01:30

Primary Healthcare Services

Primary care promotes wellness and prevents disease. This care includes health promotion, education, protection (such as immunizations), early disease screening, and environmental considerations. Settings providing this type of healthcare include physician offices, public health clinics, school nursing, and community health nursing.
In 1978, international leaders convened in Alma-Ata, Kazakhstan, for what would be a pivotal event in global health. The Alma-Ata Declaration was the first to call...

You might also read

Related Articles

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

Sort by
Same author

Digital Health coordinated by an enhanced Primary Health Care (PHC) System.

Ciencia & saude coletiva·2026
Same author

Can the Net Promoter Score predict the Primary Care Assessment Tool? A transfer learning approach.

Ciencia & saude coletiva·2026
Same authorSame journal

Electronic system for clinical information management for dental schools: digital integration of teaching and service.

Ciencia & saude coletiva·2026
Same author

Spin and Methodological Quality of Systematic Reviews and Meta-Analyses Comparing Single- and Multiple-Visit Endodontic Treatment: A Meta-Research Study.

Australian endodontic journal : the journal of the Australian Society of Endodontology Inc·2026
Same author

Eighteen years of TelessaúdeRS in Brazilian Primary Health Care: main actions and achieved results.

Ciencia & saude coletiva·2026
Same author

Primary Health Care in IBGE's Household Surveys: Limits and Possibilities.

Ciencia & saude coletiva·2026
Same journal

ERRATUM.

Ciencia & saude coletiva·2026
Same journal

Digital innovation in the regulation of specialized consultations and exams in Manaus, Brazil: challenges and impacts.

Ciencia & saude coletiva·2026
Same journal

Implementation of eConsults in the Brazilian Unified Health System: proposal of an evaluative model.

Ciencia & saude coletiva·2026
Same journal

Primary Health Care teams and facilities map: a tool for planning and management.

Ciencia & saude coletiva·2026
Same journal

Teleconsultation in primary care: conceptual model and implementation in favela territories.

Ciencia & saude coletiva·2026
See all related articles
This summary is machine-generated.

Machine learning models can predict Patient-Centered Assessment Tool (PCATool) scores. Random Forest Classifier and Extreme Gradient Boosting showed strong performance in adults and children, respectively, with continuity of care being a key predictor.

Area of Science:

  • Health Informatics
  • Machine Learning in Healthcare
  • Patient Experience Measurement

Background:

  • The Patient-Centered Assessment Tool (PCATool) measures healthcare quality.
  • Predictive modeling can optimize healthcare assessments.
  • Evaluating machine learning for PCATool score prediction is crucial.

Purpose of the Study:

  • To assess machine learning algorithms' predictive accuracy for PCATool scores.
  • To compare model performance using adult and child datasets over a decade.
  • To identify key predictors of PCATool scores.

Main Methods:

  • Utilized two datasets (2014, 2024) from Rio de Janeiro, including 4,417 adults and 4,072 children.
  • Employed Random Forest Classifier (RFC) and Extreme Gradient Boosting (EGB).

Related Experiment Videos

  • Divided 2014 data into training (80%) and test sets; 2024 data used for external validation. Shapley value analysis identified influential predictors.

    • Main Results:

    • RFC achieved AUC=0.68 for general and essential scores in adults (test set).
    • EGB showed best performance for children's general scores (AUC=0.65, test set).
    • Continuity of care with the same doctor was the most significant predictor across models.

    Conclusions:

    • Machine learning models demonstrate potential for predicting PCATool scores.
    • RFC and EGB are effective algorithms for adult and child populations, respectively.
    • Continuity of care is a vital factor in patient-centered care assessment.