Machine learning-assisted environmental surveillance of Legionella: A retrospective observational study in Friuli-Venezia Giulia region of Italy in the period 2002–2019

Brunello, Andrea; Civilini, M.; Martin, Stefano De; Felice, Antonella; Franchi, Marinella; Iacumin, Lucilla; Saccomanno, Nicola; Vitacolonna, Nicola

doi:10.1016/j.imu.2021.100803

Cited by 9 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recent Italian outbreaks and the increment of Lp infections incidence in Italy and in other countries have demonstrated that a correct and fast characterization of isolates is important and necessary (Szewzyk et al, 2000 ; Faccini et al, 2020 ; Brunello et al, 2022 ). The diagnostic techniques used by clinical and environmental laboratories often lead to an absence or mis-classification of isolates, and as a consequence to the underestimation of the risk of infection, as documented by epidemiological data (Rota et al, 2021a ).…”

Section: Discussionmentioning

confidence: 99%

Use of Fourier-Transform Infrared Spectroscopy With IR Biotyper® System for Legionella pneumophila Serogroups Identification

et al. 2022

View full text Add to dashboard Cite

Legionella spp. are Gram-negative bacteria that inhabit freshwater environments representing a serious risk for human health. Legionella pneumophila (Lp) is the species most frequently responsible for a severe pneumonia known as Legionnaires' disease. Lp consists of 15 serogroups (Sgs), usually identified by monoclonal or polyclonal antibodies. With regard to Lp serogrouping, it is well known that phenotyping methods do not have a sufficiently high discriminating power, while genotypic methods although very effective, are expensive and laborious. Recently, mass spectrometry and infrared spectroscopy have proved to be rapid and successful approaches for the microbial identification and typing. Different biomolecules (e.g., lipopolysaccharides) adsorb infrared radiation originating from a specific microbial fingerprint. The development of a classification system based on the intra-species identification features allows a rapid and reliable typing of strains for diagnostic and epidemiological purposes. The aim of the study was the evaluation of Fourier Transform Infrared Spectroscopy using the IR Biotyper® system (Bruker Daltonik, Germany) for the identification of Lp at the serogroup (Sg) level for diagnostic purposes as well as in outbreak events. A large dataset of Lp isolates (n = 133) and ATCC reference strains representing the 15 Lp serogroups were included. The discriminatory power of the instrument's classifier, was tested by Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). All isolates were classified as follows: 12/133 (9.0%) as Lp Sg1 and 115/133 (86.5%) as Lp Sg 2–15 (including both ATCC and environmental Lp serogroup). Moreover, a mis-classification for 2/133 (1.5%) isolates of Lp Sg 2–15 that returned as Lp Sg1 was observed, and 4/133 (3.0%) isolates were not classified. An accuracy of 95.49% and an error rate of 4.51% were calculated. IR Biotyper® is able provide a quick and cost-effective reliable Lp classification with advantages compared with agglutination tests that show ambiguous and unspecific results. Further studies including a larger number of isolates could be useful to implement the classifier obtaining a robust and reliable tool for the routine Lp serogrouping. IR Biotyper® could be a powerful and easy-to-use tool to identify Lp Sgs, especially during cluster/outbreak investigations, to trace the source of the infection and promptly adopt preventive and control strategies.

show abstract

Section: Discussionmentioning

confidence: 99%

Use of Fourier-Transform Infrared Spectroscopy With IR Biotyper® System for Legionella pneumophila Serogroups Identification

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The NARA-based simulator achieves a high fidelity in mimicking water tank temperature with an accuracy exceeding 97%. A recent study integrated both unsupervised and supervised ML to correlate the spread of Legionella with environmental variables in retirement homes, health-related facilities, tourism-related buildings, and swimming-pools s from 2002 to 2019 in Italy (Brunello et al, 2022). That study used an unsupervised ML algorithm to identify the spatiotemporal distribution of atypical Legionella…”

Section: Surveilling and Mitigating Opportunistic Pathogensmentioning

confidence: 99%

Machine Learning to Access and Ensure Safe Drinking Water Supply: A Systematic Review

Feng,

Zhang,

Chen

et al. 2024

Preprint

View full text Add to dashboard Cite

Drinking water is essential to public health and socioeconomic growth. Therefore, assessing and ensuring drinking water supply is a critical task in modern society. Conventional approaches to analyzing and controlling drinking water quality are labor-intensive and costly with a low throughput. Machine learning (ML) is an alternative, promising technique to assess and ensuring safe drinking water supply. Existing reviews have summarized the applications of ML in safe drinking water supply from different aspects. However, a state-of-the-art, comprehensive review is missing that focuses on applying ML to monitor, simulate, predict, and control drinking water quality, especially in municipal engineered water systems. This review, therefore, critically compiles the applications of ML in assessing and ensuring water quality in engineered water systems. To be comprehensive, we also cover the applications of ML in other drinking-water-related settings such as water sources and water purification processes. We explain the basic mechanics and workflows of ML, focusing on the applications of ML to access and control key factors or etiologies in drinking water from the physical, chemical, and microbiological aspects. Those factors or etiologies affect water quality and public health, such as water pipeline failures, disinfectant by-products, heavy metals, opportunistic pathogens, biofilms, and antimicrobial resistance genes. We then illustrate the distribution of ML models across research topics in safe drinking water supply. Finally, we discuss the challenges and outlooks for the applications of machine learning in safe drinking water supply. This is the first review summarizing the feasibility and applications of ML in assessing and ensuring water quality in municipal engineered water systems as well as other related water environments.

show abstract

“…The NARA-based simulator achieves a high fidelity in mimicking water tank temperatures with an accuracy exceeding 97%. Another study integrated both unsupervised and supervised ML techniques to correlate the spread of Legionella with environmental variables in retirement homes, health-related facilities, tourism-related buildings, and swimming-pool environments in Italy (Brunello et al, 2022). That study used an unsupervised learning algorithm to identify the spatiotemporal distribution of atypical Legionella through an ordinal regression model.…”

Section: Legionellamentioning

confidence: 99%

Machine Learning to Access and Ensure Safe Drinking Water Supply: A Systematic Review

Feng,

Chen,

et al. 2024

Preprint

View full text Add to dashboard Cite

Drinking water is essential to public health and socioeconomic growth. Therefore, assessing and ensuring drinking water supply is a critical task in modern society. Conventional approaches to analyzing and controlling drinking water quality are labor-intensive and costly with a low throughput. Machine learning (ML) is an alternative, promising technique for assessing and ensuring safe drinking water supply. Existing reviews have summarized the applications of ML in safe drinking water supply from different aspects. However, a state-of-the-art, comprehensive review is missing that focuses on applying ML to monitor, simulate, predict, and control drinking water quality, especially in engineered water systems. This review, therefore, critically compiles the applications of ML in assessing and ensuring water quality in engineered water systems. To be comprehensive, we also cover the applications of ML in other drinking-water-related settings such as water sources and water purification processes. We explain the basic mechanics and workflows of ML and focus on the applications of ML to access and control key factors or etiologies in drinking water from the physical, chemical, and microbiological aspects. Those factors or etiologies affect water quality and public health, such as water pipeline failures, disinfectant by-products, heavy metals, opportunistic pathogens, biofilms, and antimicrobial resistance genes. We then present a macroscopic illustration to display the distribution of ML models across research topics in safe drinking water supply. Neural-network-based and regression-based models are the top two models frequently used in the field of drinking water supply. We finally discuss the challenges and outlooks for the applications of machine learning in safe drinking water supply. Filling the gap between the water research and the AI research communities and using AI to solve the global drinking water crisis should be the main focus of future research. This is the first review summarizing the feasibility and applications of ML in assessing and ensuring water quality in municipal engineered water systems as well as related water environments.

show abstract

Machine learning-assisted environmental surveillance of Legionella: A retrospective observational study in Friuli-Venezia Giulia region of Italy in the period 2002–2019

Cited by 9 publications

References 36 publications

Use of Fourier-Transform Infrared Spectroscopy With IR Biotyper® System for Legionella pneumophila Serogroups Identification

Use of Fourier-Transform Infrared Spectroscopy With IR Biotyper® System for Legionella pneumophila Serogroups Identification

Machine Learning to Access and Ensure Safe Drinking Water Supply: A Systematic Review

Machine Learning to Access and Ensure Safe Drinking Water Supply: A Systematic Review

Contact Info

Product

Resources

About