2026-10-13T03:02:16Z
https://api.figshare.com/v2/oai
oai:figshare.com:article/33973550
2026-09-23T13:48:42Z
category_1
category_4
category_146
category_7
category_16
category_272
category_39
category_734
category_69
portal_63
item_type_3
month_year_09_2026
Multivariable
Investigation of Physicochemical Drivers
Influencing Opportunistic Pathogens in Drinking Water
Hyeok Kim (9383640)
Juliana Marks (25097690)
Hyun-Suk Oh (1406938)
Rabin Bhattarai (20394408)
Thanh H. Nguyen (771355)
Biophysics
Biochemistry
Space Science
Medicine
Physiology
Environmental Sciences not elsewhere classified
Ecology
Biological Sciences not elsewhere classified
Inorganic Chemistry
support vector regression
shapley additive explanations
optimized using cross
interpret predictor contributions
extreme gradient boosting
combined data sets
best test performance
whereas differing ph
temperature ranges altered
g ., ph
rf model achieved
legionella spp .,
higher legionella spp
sup >–</ sup
2 </ sup
temperature ), ops
legionella spp
water temperature
ph values
rf ),
mycobacterium spp
k </
</ sub
strong association
relative importance
random forest
premise plumbing
predict qpcr
physicochemical parameters
op occurrence
multivariable investigation
influential predictors
explore relationships
environmental conditions
derived cell
across individual
>< sub
80 ).
Opportunistic pathogens (OPs) in
drinking water distribution systems
(DWDS) and premise plumbing pose health risks. Effective management
requires understanding the associations between physicochemical parameters
and OP occurrence. This study applied machine learning (ML) models
to explore relationships between physicochemical parameters (e.g.,
pH, temperature), OPs (Legionella spp., Pseudomonas spp., and Mycobacterium spp.), and the free-living amoeba Vermamoeba vermiformis. eXtreme Gradient Boosting, Random Forest (RF), and Support Vector
Regression were optimized using cross-validation to predict qPCR-derived
cell-equivalent (CE) concentrations, and Shapley Additive exPlanations
(SHAP) were used to interpret predictor contributions. For Legionella spp., the RF model achieved the best test
performance (R<sup>2</sup> = 0.80). SHAP analysis identified pH, free
chlorine, and water temperature as the most influential predictors
of Legionella spp. CE concentrations.
Lower free chlorine concentrations and pH values above the p<i>K</i><sub>a</sub> of OCl<sup>–</sup> were associated
with higher Legionella spp. CE concentrations. V. vermiformis and Mycobacterium spp. showed a strong association in the ML models, consistent with
previously reported biological interactions. Across individual and
combined data sets, free chlorine consistently influenced model outputs,
whereas differing pH and temperature ranges altered their relative
importance. Overall, ML provided a framework for identifying associations
between environmental conditions and OP occurrence in DWDS and premise
plumbing.
2026-09-23T00:00:00Z
Dataset
Dataset
10.1021/acsestwater.6c00639.s002
https://figshare.com/articles/dataset/Multivariable_Investigation_of_Physicochemical_Drivers_Influencing_Opportunistic_Pathogens_in_Drinking_Water/33973550
CC BY-NC 4.0