Pandemic vaccination campaigns must account for vaccine skepticism as an obstacle to overcome. Using machine learning to identify behavioral and psychological patterns in public survey datasets can provide valuable insights and inform vaccination campaigns based on empirical evidence. However, we argue that the adoption of local and global explanation methodologies can provide additional support to health practitioners by suggesting personalized communication strategies and revealing potential demographic, social, or structural barriers to vaccination requiring systemic changes. In this paper, we first implement a chain classification model for the adoption of the vaccine during the H1N1 influenza outbreak taking seasonal vaccination information into account, and then compare it with a binary classifier for vaccination to better understand the overall patterns in the data. Following that, we derive and compare global explanations using post-hoc methodologies and interpretable-by-design models. Our findings indicate that socio-demographic factors play a distinct role in the H1N1 vaccination as compared to the general vaccination. Nevertheless, medical recommendation and health insurance remain significant factors for both vaccinations. Then, we concentrated on the subpopulation of individuals who did not receive an H1N1 vaccination despite being at risk of developing severe symptoms. In an effort to assist practitioners in providing effective recommendations to patients, we present rules and counterfactuals for the selected instances based on local explanations. Finally, we raise concerns regarding gender and racial disparities in healthcare access by analysing the interaction effects of sensitive attributes on the model’s output.

Explaining Socio-demographic and Behavioral Patterns of Vaccination against the Swine Flu (H1N1) Pandemic

Punzi, Clara
;
Gezici, Gizem;Pellungrini, Roberto;Giannotti, Fosca
2023

Abstract

Pandemic vaccination campaigns must account for vaccine skepticism as an obstacle to overcome. Using machine learning to identify behavioral and psychological patterns in public survey datasets can provide valuable insights and inform vaccination campaigns based on empirical evidence. However, we argue that the adoption of local and global explanation methodologies can provide additional support to health practitioners by suggesting personalized communication strategies and revealing potential demographic, social, or structural barriers to vaccination requiring systemic changes. In this paper, we first implement a chain classification model for the adoption of the vaccine during the H1N1 influenza outbreak taking seasonal vaccination information into account, and then compare it with a binary classifier for vaccination to better understand the overall patterns in the data. Following that, we derive and compare global explanations using post-hoc methodologies and interpretable-by-design models. Our findings indicate that socio-demographic factors play a distinct role in the H1N1 vaccination as compared to the general vaccination. Nevertheless, medical recommendation and health insurance remain significant factors for both vaccinations. Then, we concentrated on the subpopulation of individuals who did not receive an H1N1 vaccination despite being at risk of developing severe symptoms. In an effort to assist practitioners in providing effective recommendations to patients, we present rules and counterfactuals for the selected instances based on local explanations. Finally, we raise concerns regarding gender and racial disparities in healthcare access by analysing the interaction effects of sensitive attributes on the model’s output.
2023
Settore INF/01 - Informatica
The 1st World Conference on eXplainable Artificial Intelligence (xAI 2023)
Lisboa, Portugal
July 26-28 2023
Explainable Artificial Intelligence First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part III
Springer Science and Business Media Deutschland GmbH
9783031440663
Chain classification; Explainable AI; Protected Groups; Vaccination Patterns; Vaccine hesitancy;
   Science and technology for the explanation of AI decision making
   XAI
   European Commission
   Horizon 2020 Framework Programme
   834756

   SoBigData++: European Integrated Infrastructure for Social Mining and Big Data Analytics
   SoBigData-PlusPlus
   European Commission
   Horizon 2020 Framework Programme
   871042

   SoBigData.it - Strengthening the Italian RI for Social Mining and Big Data Analytics
   SoBigData.it
   MUR
   NextGenerationEU - National Recovery and Resilience Plan, PNRR
   Prot. IR000001 3 - Notice n. 3264 of 12/28/2021
File in questo prodotto:
File Dimensione Formato  
978-3-031-44067-0_31.pdf

accesso aperto

Tipologia: Published version
Licenza: Creative Commons
Dimensione 1.42 MB
Formato Adobe PDF
1.42 MB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11384/134782
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
  • OpenAlex 0
social impact