Related Experiment Video
Updated: Oct 19, 2025
06:19
Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
1.2K
Incorporating metadata in HIV transmission network reconstruction: A machine learning feasibility assessment
Sepideh Mazrouee1, Susan J Little1, Joel O Wertheim1
1Department of Medicine, Division of Infectious Diseases and Global Public Health, University of California San Diego, San Diego, California, United States.
Plos Computational Biology
|September 22, 2021
Summary
Machine learning enhances HIV transmission tracking by integrating patient metadata with genetic data. This approach expands epidemiological insights beyond individuals with available viral sequences, improving HIV surveillance.
Area of Science:
- Epidemiology
- Computational Biology
- Infectious Disease Modeling
Background:
- HIV molecular epidemiology relies on genetic sequencing to estimate transmission patterns.
- Current methods exclude individuals with Human Immunodeficiency Virus (HIV) not accessing consistent care, limiting transmission tracking.
- Patient metadata offers potential for expanding transmission network reconstruction.
Purpose of the Study:
- To investigate the utility of machine learning algorithms in reconstructing HIV transmission networks using patient metadata.
- To determine if non-genetic features can predict genetic relatedness and identify transmission clusters.
- To expand HIV transmission estimation beyond individuals with available viral genotypes.
Main Methods:
- Supervised classification algorithms (Random Forest, Decision Tree, Support Vector Machine) were applied to the San Diego PIRC cohort dataset.
- Models were trained to differentiate genetically related and unrelated individuals using metadata and genotypes.
- Algorithms were extended to identify clusters of similar viral sequences based on combined data.
Main Results:
- Random Forest and Decision Tree models achieved over 80% accuracy, precision, recall, and F1-score using a subset of meta-features.
- These models demonstrated approximately 80% sensitivity and specificity, with AUCs of 97% and 94% respectively.
- Support Vector Machine significantly improved accuracy in assigning viral sequences to clusters compared to random classification.
Conclusions:
- Patient metadata contains crucial information for understanding HIV transmission dynamics within clusters.
- Machine learning approaches integrating metadata and genetic data can expand the reconstruction of HIV transmission networks.
- Novel computational methods are essential for leveraging non-genetic information to enhance HIV epidemiological surveillance.
More Related Videos
Related Concept Videos
01:18Steps in Outbreak Investigation
258
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:
258
01:25Statistical Methods for Analyzing Epidemiological Data
619
Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
619