{
  "abstract": "The number and magnitude of Highly Pathogenic Avian Influenza (HPAI) outbreaks have increased globally in recent years, placing substantial burdens on public health and causing significant economic losses to the poultry industry. Identifying spatial hotspots and key environmental drivers of HPAI is essential for improving surveillance efficiency and enabling targeted prevention strategies. This study aimed to identify spatial hotspots and cold spots of HPAI in Canada and determine the most influential predictors of HPAI occurrence at both national and local levels. Subdivision-level data were compiled from multiple sources, including reported HPAI cases in wild birds, waterfowl population density, poultry premises, weather and air quality indicators, vegetation cover, elevation, gross primary production, water bodies, and wildfire occurrence. Spatial cluster analyses using Getis-Ord Gi* and Anselin Moran's I were conducted to detect hotspots and cold spots and generate risk maps. Generalized Additive Models (GAM), XGBoost, and Random Forest Regression (RFR) were compared using R-squared score, root mean square error, and mean absolute error, and Shapley Additive exPlanations were applied to the machine learning models to quantify predictor importance. Consistent HPAI hotspots were identified in southwestern British Columbia, central and southern Alberta, southern Ontario, and the Atlantic provinces, while cold spots were observed in several central and northern regions. Hotspots of HPAI in domestic birds coincided with hotspots in wild birds, indicating that poultry and bird farms located in these areas are at higher risk of infection. GAM achieved the highest cross-validation accuracy, with XGBoost slightly outperforming RFR. Across all models, waterfowl population density, poultry premises, vegetation metrics including gross primary production, and air quality emerged as the most influential predictors. These findings provide actionable insights to support risk-based HPAI surveillance, targeted biosecurity interventions, and improved resource allocation in Canada.",
  "abstract_shown": true,
  "affiliations": [
    "Artificial Intelligence & Mathematical Modeling Lab (AIMMLab), Dalla Lana School of Public Health, University of Toronto, 155 College St, Room 500, Toronto, ON M5T 3M7, Canada.",
    "Global South Artificial Intelligence for Pandemic and Epidemic Preparedness and Response Network (AI4PEP), Toronto, ON, Canada.",
    "Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, ON, Canada.",
    "Department of Mathematics, York University, Toronto, ON M3J 1P3, Canada.",
    "Department of Food and Drugs, University of Parma, 43125 Parma, Italy.",
    "Canada Animal Health Surveillance System (CAHSS), Animal Health Canada, Elora, ON N0B 1S0, Canada.",
    "Institute of Health Policy, Management and Evaluation (IHPME), University of Toronto, Toronto, ON, Canada.",
    "Department of Mathematics, University of Toronto, Bahen Centre for Information Technology, Room 6291, 40 St. George Street, Toronto, ON M5S 2E4, Canada.",
    "Munk School of Global Affairs & Public Policy, University of Toronto, Toronto, ON, Canada."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0,
        1,
        2,
        3
      ],
      "name": "Zahra Movahedi Nia"
    },
    {
      "affs": [
        4
      ],
      "name": "Nicola Luigi Bragazzi"
    },
    {
      "affs": [
        5
      ],
      "name": "Murray Gillies"
    },
    {
      "affs": [
        5
      ],
      "name": "Emma Gardner"
    },
    {
      "affs": [
        0,
        1,
        2,
        6,
        7,
        8
      ],
      "name": "Jude Dzevela Kong"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/aj8vztsgh3ct4.bib",
  "cited_by": 0,
  "doi": "10.1016/j.onehlt.2026.101630",
  "fulltext_url": "https://europepmc.org/articles/PMC13742085",
  "id": "aj8vztsgh3ct4",
  "issns": [
    "2352-7714"
  ],
  "landing_url": "https://europepmc.org/article/MED/42997465",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Research Paper"
    ],
    [
      "openalex",
      "2713|Influenza Virus Research Studies"
    ]
  ],
  "openalex": "W7223246407",
  "pdf_url": "https://europepmc.org/articles/PMC13742085?pdf=render",
  "pmcid": "PMC13742085",
  "pmid": "42997465",
  "published": "2026-10-22",
  "publisher": "Elsevier",
  "ris": "https://research.draconitic.com/paper/aj8vztsgh3ct4.ris",
  "sources": [
    {
      "first_seen": "2026-11-09T15:20:41Z",
      "native_id": "MED:42997465",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42997465"
    },
    {
      "first_seen": "2026-11-10T12:22:59Z",
      "native_id": "PMC13742085",
      "source": "pmc",
      "url": "https://doi.org/10.1016/j.onehlt.2026.101630"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2713|Influenza Virus Research Studies",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Highly pathogenic avian influenza in Canada: Spatial analysis of ecological hot and cold spots and environmental drivers.",
  "title_text": "Highly pathogenic avian influenza in Canada: Spatial analysis of ecological hot and cold spots and environmental drivers.",
  "type": "peer-reviewed",
  "updated_at": "2026-11-10T12:22:59Z",
  "url": "https://research.draconitic.com/paper/aj8vztsgh3ct4",
  "venue": "One health (Amsterdam, Netherlands)",
  "versions": []
}