Using decision fusion methods to improve outbreak detection in disease surveillance

Gaëtan Texier (1, 2) , Rodrigue Allodji (2) , Loty Diop (3) , Jean-Baptiste Meynard (2, 4) , Liliane Pellegrin (1, 2) , Herve Chaudet (1, 2)

1 VITROME - Vecteurs - Infections tropicales et méditerranéennes
2 CESPA - Centre d'épidémiologie et de santé publique des armées [Marseille]
3 IFPRI - International Food Policy Research Institute [Washington]
4 SESSTIM - U1252 INSERM - Aix Marseille Univ - UMR 259 IRD - Sciences Economiques et Sociales de la Santé & Traitement de l'Information Médicale

Background When outbreak detection algorithms (ODAs) are considered individually, the task of outbreak detection can be seen as a classification problem and the ODA as a sensor providing a binary decision (outbreak yes or no) for each day of surveillance. When they are considered jointly (in cases where several ODAs analyze the same surveillance signal), the outbreak detection problem should be treated as a decision fusion (DF) problem of multiple sensors. Methods This study evaluated the benefit for a decisions support system of using DF methods (fusing multiple ODA decisions) compared to using a single method of outbreak detection. For each day, we merged the decisions of six ODAs using 5 DF methods (two voting methods, logistic regression, CART and Bayesian network - BN). Classical metrics of accuracy, prediction and timelines were used during the evaluation steps. Results In our results, we observed the greatest gain (77%) in positive predictive value compared to the best ODA if we used DF methods with a learning step (BN, logistic regression, and CART). Conclusions To identify disease outbreaks in systems using several ODAs to analyze surveillance data, we recommend using a DF method based on a Bayesian network. This method is at least equivalent to the best of the algorithms considered, regardless of the situation faced by the system. For those less familiar with this kind of technique, we propose that logistic regression be used when a training dataset is available.

Domains: Life Sciences [q-bio]; Microbiology and Parasitology; Bacteriology; Life Sciences [q-bio]; Microbiology and Parasitology; Virology; Life Sciences [q-bio]; Microbiology and Parasitology; Parasitology; Life Sciences [q-bio]; Human health and pathology; Cardiology and cardiovascular system; Life Sciences [q-bio]; Human health and pathology; Emerging diseases; Life Sciences [q-bio]; Human health and pathology; Infectious diseases

Gaëtan Texier, Rodrigue Allodji, Loty Diop, Jean-Baptiste Meynard, Liliane Pellegrin, et al.. Using decision fusion methods to improve outbreak detection in disease surveillance. BMC Medical Informatics and Decision Making, 2019, 19 (1), ⟨10.1186/s12911-019-0774-3⟩. ⟨hal-02263741⟩