Journal Articles

Permanent URI for this collectionhttps://mro.massey.ac.nz/handle/10179/7915

Browse

Filters

2022 - 20243

Settings

Has files: YesSubject: search.filters.subject.source attribution

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Source attribution of campylobacteriosis in Australia, 2017-2019.
    (John Wiley and Sons, Inc., 2023-12-01) McLure A; Smith JJ; Firestone SM; Kirk MD; French N; Fearnley E; Wallace R; Valcanis M; Bulach D; Moffatt CRM; Selvey LA; Jennison A; Cribb DM; Glass K
    Campylobacter jejuni and Campylobacter coli infections are the leading cause of foodborne gastroenteritis in high-income countries. Campylobacter colonizes a variety of warm-blooded hosts that are reservoirs for human campylobacteriosis. The proportions of Australian cases attributable to different animal reservoirs are unknown but can be estimated by comparing the frequency of different sequence types in cases and reservoirs. Campylobacter isolates were obtained from notified human cases and raw meat and offal from the major livestock in Australia between 2017 and 2019. Isolates were typed using multi-locus sequence genotyping. We used Bayesian source attribution models including the asymmetric island model, the modified Hald model, and their generalizations. Some models included an "unsampled" source to estimate the proportion of cases attributable to wild, feral, or domestic animal reservoirs not sampled in our study. Model fits were compared using the Watanabe-Akaike information criterion. We included 612 food and 710 human case isolates. The best fitting models attributed >80% of Campylobacter cases to chickens, with a greater proportion of C. coli (>84%) than C. jejuni (>77%). The best fitting model that included an unsampled source attributed 14% (95% credible interval [CrI]: 0.3%-32%) to the unsampled source and only 2% to ruminants (95% CrI: 0.3%-12%) and 2% to pigs (95% CrI: 0.2%-11%) The best fitting model that did not include an unsampled source attributed 12% to ruminants (95% CrI: 1.3%-33%) and 6% to pigs (95% CrI: 1.1%-19%). Chickens were the leading source of human Campylobacter infections in Australia in 2017-2019 and should remain the focus of interventions to reduce burden.
  • Thumbnail Image
    Item
    Lost in the Forest: Encoding categorical variables and the absent levels problem
    (Springer Nature, 2024-04-10) Smith HL; Biggs PJ; French NP; Smith ANH; Marshall JC; Gama J
    Levels of a predictor variable that are absent when a classification tree is grown can not be subject to an explicit splitting rule. This is an issue if these absent levels are present in a new observation for prediction. To date, there remains no satisfactory solution for absent levels in random forest models. Unlike missing data, absent levels are fully observed and known. Ordinal encoding of predictors allows absent levels to be integrated and used for prediction. Using a case study on source attribution of Campylobacter species using whole genome sequencing (WGS) data as predictors, we examine how target-agnostic versus target-based encoding of predictor variables with absent levels affects the accuracy of random forest models. We show that a target-based encoding approach using class probabilities, with absent levels designated the highest rank, is systematically biased, and that this bias is resolved by encoding absent levels according to the a priori hypothesis of equal class probability. We present a novel method of ordinal encoding predictors via principal coordinates analysis (PCO) which capitalizes on the similarity between pairs of predictor levels. Absent levels are encoded according to their similarity to each of the other levels in the training data. We show that the PCO-encoding method performs at least as well as the target-based approach and is not biased.
  • Thumbnail Image
    Item
    Lost in the Forest
    (Cold Spring Harbor Laboratory, 2022) Smith HL; Biggs PJ; French NP; Smith ANH; Marshall JC
    To date, there remains no satisfactory solution for absent levels in random forest models. Absent levels are levels of a predictor variable encountered during prediction for which no explicit rule exists. Imposing an order on nominal predictors allows absent levels to be integrated and used for prediction. The ordering of predictors has traditionally been via class probabilities with absent levels designated the lowest order. Using a combination of simulated data and pathogen source-attribution models using whole-genome sequencing data, we examine how the method of ordering predictors with absent levels can (i) systematically bias a model, and (ii) affect the out-of-bag error rate. We show that the traditional approach is systematically biased and underestimates out-of-bag error rates, and that this bias is resolved by ordering absent levels according to the a priori hypothesis of equal class probability. We present a novel method of ordering predictors via principal coordinates analysis (PCO) which capitalizes on the similarity between pairs of predictor levels. Absent levels are designated an order according to their similarity to each of the other levels in the training data. We show that the PCO method performs at least as well as the traditional approach of ordering and is not biased.