Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Steps in Outbreak Investigation

Steps in Outbreak Investigation

In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:

You might also read

Related Articles

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

Sort by

Same author

Malfunctions in distributed clinical decision support: 3 cases from a multi‑component clinical decision support system.

Journal of the American Medical Informatics Association : JAMIA·2026

Same author

Large Language Model Chatbot Conversations vs Public Health Materials and Parental HPV Vaccination Intentions: A Randomized Clinical Trial.

JAMA network open·2026

Same author

Different Affordances on Facebook and SMS Text Messaging Do Not Impede Generalization of Language-Based Predictive Models.

Proceedings of the ... International AAAI Conference on Weblogs and Social Media. International AAAI Conference on Weblogs and Social Media·2026

Same author

AI assists adversarial collaboration in debate on minority salience.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

Personal variation in the palatability and side effects of liquid clindamycin among children.

Pediatric research·2026

Same author

Achievable Benchmarks of Care in Pediatric Emergency Departments.

JAMA network open·2026

Same journal

Disparities in Activation and Use of Patient Portals Among Spanish-Speaking Patients.

Applied clinical informatics·2026

Same journal

Real-World Utilization of a Hospital-Integrated Internet Hospital in Henan Province, China: A 1-Year Observational Study.

Applied clinical informatics·2026

Same journal

From Pandemic Response to Kill the Clipboard: Patient-Controlled Sharing of Health Data Using International Patient Summary (IPS) and QR codes.

Applied clinical informatics·2026

Same journal

Usage of and Satisfaction with Artificial Intelligence-Generated Draft Replies to Patient Portal Messages.

Applied clinical informatics·2026

Same journal

Automating Ambulatory Central Line Data Capture and Calculations.

Applied clinical informatics·2026

Same journal

Effectiveness of Interruptive Clinical Decision Support Alerts on Intravenous vs. Oral Acetaminophen Prescribing.

Applied clinical informatics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 15, 2026

Design of Cecal Ligation and Puncture and Intranasal Infection Dual Model of Sepsis-Induced Immunosuppression

Design of Cecal Ligation and Puncture and Intranasal Infection Dual Model of Sepsis-Induced Immunosuppression

Published on: June 15, 2019

Refining a Machine Learning Model for Predicting Infant Sepsis: A Multidisciplinary Team Supported by Human-Centered

Dean Karavite¹, Lusha Cao¹, Mary C Harris^2,3

¹Department of Biomedical and Health Informatics, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, United States.

Applied Clinical Informatics

|October 10, 2025

Summary

This summary is machine-generated.

Human-centered design (HCD) methods can improve machine learning models for clinical decisions by identifying anomalies during development and testing. Applying HCD to sepsis detection models in neonatal intensive care units led to 41 improvements.

More Related Videos

A Controlled Mouse Model for Neonatal Polymicrobial Sepsis

A Controlled Mouse Model for Neonatal Polymicrobial Sepsis

Published on: January 27, 2019

A Data-Driven Approach to Quantifying Immune States in Sepsis

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

Related Experiment Videos

Last Updated: Jan 15, 2026

Design of Cecal Ligation and Puncture and Intranasal Infection Dual Model of Sepsis-Induced Immunosuppression

Design of Cecal Ligation and Puncture and Intranasal Infection Dual Model of Sepsis-Induced Immunosuppression

Published on: June 15, 2019

A Controlled Mouse Model for Neonatal Polymicrobial Sepsis

A Controlled Mouse Model for Neonatal Polymicrobial Sepsis

Published on: January 27, 2019

A Data-Driven Approach to Quantifying Immune States in Sepsis

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

Area of Science:

Clinical Informatics
Machine Learning in Healthcare
Human-Computer Interaction

Background:

Human-centered design (HCD) is typically applied to user interfaces and visualizations in machine learning.
Its application to the core model development and testing process remains underexplored.
Clinical decision support systems benefit from robust and reliable machine learning models.

Purpose of the Study:

To demonstrate the potential of HCD methods in designing and testing machine learning models for clinical decision-making.
To investigate anomalies in a sepsis detection model for neonatal intensive care units (NICU).
To highlight the value of HCD beyond user-facing aspects of AI.

Main Methods:

Utilized interactive low-fidelity mockups with real patient data for initial anomaly detection.
Conducted qualitative analysis of interviews with 31 NICU clinicians regarding neonatal sepsis.
Employed a multidisciplinary team (neonatology, informatics, data science, HCI) for review and analysis.
Inspected patient charts, model features, and code to validate identified anomalies.

Main Results:

HCD-facilitated review identified anomalies in feature inclusion/exclusion, feature importance, and model stability.
Discovered data entry errors in electronic health records impacting model output.
Led to 41 specific changes and improvements in the sepsis prediction model.
Revealed over 41 opportunities for model enhancement through the HCD process.

Conclusions:

HCD methods can significantly enhance the development and evaluation of machine learning models, not just their display.
The integration of HCD into the model lifecycle improves accuracy, reliability, and clinical utility.
Multidisciplinary collaboration is crucial for effectively identifying and resolving machine learning model performance issues in healthcare settings.