Publications by authors named "Mattia Cf Prosperi"

2 Publications

  • Page 1 of 1

Phylodynamic applications in 21 century global infectious disease research.

Glob Health Res Policy 2017 8;2:13. Epub 2017 May 8.

Department of Epidemiology, University of Florida, Gainesville, FL USA.

Background: Phylodynamics, the study of the interaction between epidemiological and pathogen evolutionary processes within and among populations, was originally defined in the context of rapidly evolving viruses and used to characterize transmission dynamics. The concept of phylodynamics has evolved since the early 21 century, extending its reach to slower-evolving pathogens, including bacteria and fungi, and to the identification of influential factors in disease spread and pathogen population dynamics.

Results: The phylodynamic approach has now become a fundamental building block for the development of comparative phylogenetic tools capable of incorporating epidemiological surveillance data with molecular sequences into a single statistical framework. These innovative tools have greatly enhanced scientific investigations of the temporal and geographical origins, evolutionary history, and ecological risk factors associated with the growth and spread of viruses such as human immunodeficiency virus (HIV), Zika, and dengue and bacteria such as Methicillin-resistant .

Conclusions: Capitalizing on an extensive review of the literature, we discuss the evolution of the field of infectious disease epidemiology and recent accomplishments, highlighting the advancements in phylodynamics, as well as the challenges and limitations currently facing researchers studying emerging pathogen epidemics across the globe.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1186/s41256-017-0034-yDOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5683535PMC
May 2017

Predicting phenotypes of asthma and eczema with machine learning.

BMC Med Genomics 2014 8;7 Suppl 1:S7. Epub 2014 May 8.

Background: There is increasing recognition that asthma and eczema are heterogeneous diseases. We investigated the predictive ability of a spectrum of machine learning methods to disambiguate clinical sub-groups of asthma, wheeze and eczema, using a large heterogeneous set of attributes in an unselected population. The aim was to identify to what extent such heterogeneous information can be combined to reveal specific clinical manifestations.

Methods: The study population comprised a cross-sectional sample of adults, and included representatives of the general population enriched by subjects with asthma. Linear and non-linear machine learning methods, from logistic regression to random forests, were fit on a large attribute set including demographic, clinical and laboratory features, genetic profiles and environmental exposures. Outcome of interest were asthma, wheeze and eczema encoded by different operational definitions. Model validation was performed via bootstrapping.

Results: The study population included 554 adults, 42% male, 38% previous or current smokers. Proportion of asthma, wheeze, and eczema diagnoses was 16.7%, 12.3%, and 21.7%, respectively. Models were fit on 223 non-genetic variables plus 215 single nucleotide polymorphisms. In general, non-linear models achieved higher sensitivity and specificity than other methods, especially for asthma and wheeze, less for eczema, with areas under receiver operating characteristic curve of 84%, 76% and 64%, respectively. Our findings confirm that allergen sensitisation and lung function characterise asthma better in combination than separately. The predictive ability of genetic markers alone is limited. For eczema, new predictors such as bio-impedance were discovered.

Conclusions: More usefully-complex modelling is the key to a better understanding of disease mechanisms and personalised healthcare: further advances are likely with the incorporation of more factors/attributes and longitudinal measures.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1186/1755-8794-7-S1-S7DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4101570PMC
March 2015