top of page
IMG_1650_edited.jpg

Key Publications

First Author Academic Papers

ORCID: 0000-0003-4111-8286

Machine learning potential for identifying and forecasting complex environmental drivers of Vibrio vulnificus infections in the USA

Environmental Health Perspectives,

January 2025

This paper used the unique opportunity offered by the USA Vibrio epidemiological surveillance database, and machine learning (in the form of random forest classifiers) to forecast V. vulnificus infections and characterise complex non-linear environmental drivers. The highest-performing model had an Area Under the Curve score of 0.984 and a sensitivity of 0.971. This study accentuates the potential of machine learning and robust surveillance for forecasting environmentally-associated marine infections.

https://doi.org/10.1289/EHP15593

Identifying gene-level mechanisms of successful dispersal of Vibrio parahaemolyticus during El Niño events

Microbial Genomics,

November 2024

This paper focuses on the role of wider climate cycles, particularly the El Niño Southern Oscillation, on Vibrio dynamics, and tested the potential of state-of-the-art methodologies (in time series analysis and machine learning) to characterise this. It quantifies the previously-hypothesized lagged impact of strong El Niño events on Vibrio populations, and explored gene-level dispersal mechanisms related to plankton attachment that underline such associations.

https://doi.org/10.1099/mgen.0.001317

A machine learning approach to identify eco-evolutionary drivers of Vibrio parahaemolyticus ST3 expansion

JMIR Bioinformatics and Biotechnology, 

November 2024

This paper characterises the extent to which eco-evolutionary drivers were involved in VpST3 expansion process, using genomic data from clinical and environmental VpST3 sequences collected globally over the period of expansion. A range of ecological and evolutionary drivers are tested for their potential in predicting VpST3 expansion 
dynamics within a machine learning approach.

https://doi.org/10.2196/62747

Evolutionary dynamics of the successful expansion of pandemic Vibrio parahaemolyticus ST3 in Latin America

Nature Communications, September 2024

This paper uncovers the emergence of the pandemic clone (VpST3) into Latin America, identifying the mechanisms of VpST3 expansion into a distinct marine climate, as the first detection outside its endemic region of tropical Asia. This paper identified signatures of successful adaptation to local environmental conditions that contribute to the emergence and establishment of a variant into new, geographic regions with distinct climates.

https://doi.org/10.1038/s41467-024-52159-y

Forecasting climate-associated non-tuberculous mycobacteria (NTM) infections in the UK using international surveillance data and machine learning

PLOS Global Public Health, 

August 2024

This paper assessed the burden of NTM infections in the UK under projected climate change, by examining the relationship between climate variables and available NTM surveillance data internationally, and training a machine learning model with these associations to provide forecasts for the UK.

https://doi.org/10.1371/journal.pgph.0003262 

An integrated eco-evolutionary framework to predict population-level responses of climate-sensitive pathogens 

Current Opinion in Biotechnology,

February 2023

This review proposes a framework to support such analysis, by combining genomic evolutionary analysis with climate time-series data in a novel spatiotemporal dataframe for use within machine learning applications, to understand past and future evolutionary pathogen responses to climate change.

https://doi.org/10.1016/j.copbio.2023.102898

Cholera Risk: A Machine Learning Approach Applied to Essential Climate Variables

International Journal of Environment and Public Health, 

December 2020

In this study we provide a novel exploration of the potential of a machine learning approach to forecast environmental cholera risk in coastal India, utilising atmospheric, terrestrial and oceanic satellite-derived essential climate variables. 89.5% of coastal cholera outbreaks are correctly identified using the model.

https://doi.org/10.3390/ijerph17249378

Amy Marie Campbell

amymariecampbell.co.uk

©2023 by Amy Marie Campbell

bottom of page