Dataset Information

Tracking Major Sources of Water Contamination Using Machine Learning.

ABSTRACT: Current microbial source tracking techniques that rely on grab samples analyzed by individual endpoint assays are inadequate to explain microbial sources across space and time. Modeling and predicting host sources of microbial contamination could add a useful tool for watershed management. In this study, we tested and evaluated machine learning models to predict the major sources of microbial contamination in a watershed. We examined the relationship between microbial sources, land cover, weather, and hydrologic variables in a watershed in Northern California, United States. Six models, including K-nearest neighbors (KNN), Naïve Bayes, Support vector machine (SVM), simple neural network (NN), Random Forest, and XGBoost, were built to predict major microbial sources using land cover, weather and hydrologic variables. The results showed that these models successfully predicted microbial sources classified into two categories (human and non-human), with the average accuracy ranging from 69% (Naïve Bayes) to 88% (XGBoost). The area under curve (AUC) of the receiver operating characteristic (ROC) illustrated XGBoost had the best performance (average AUC = 0.88), followed by Random Forest (average AUC = 0.84), and KNN (average AUC = 0.74). The importance index obtained from Random Forest indicated that precipitation and temperature were the two most important factors to predict the dominant microbial source. These results suggest that machine learning models, particularly XGBoost, can predict the dominant sources of microbial contamination based on the relationship of microbial contaminants with daily weather and land cover, providing a powerful tool to understand microbial sources in water.

SUBMITTER: Wu J

PROVIDER: S-EPMC7854693 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Tracking Major Sources of Water Contamination Using Machine Learning.

Wu Jianyong J Song Conghe C Dubinsky Eric A EA Stewart Jill R JR

Frontiers in microbiology 20210120

Current microbial source tracking techniques that rely on grab samples analyzed by individual endpoint assays are inadequate to explain microbial sources across space and time. Modeling and predicting host sources of microbial contamination could add a useful tool for watershed management. In this study, we tested and evaluated machine learning models to predict the major sources of microbial contamination in a watershed. We examined the relationship between microbial sources, land cover, weathe ...[more]

PMID: 33552026

Similar Datasets

Project description:BACKGROUND:Antimicrobial resistance (AMR) has been a worldwide public health concern. Current widespread AMR pollution has posed a big challenge in accurately disentangling source-sink relationship, which has been further confounded by point and non-point sources, as well as endogenous and exogenous cross-reactivity under complicated environmental conditions. Because of insufficient capability in identifying source-sink relationship within a quantitative framework, traditional antibiotic resistance gene (ARG) signatures-based source-tracking methods would hardly be a practical solution. RESULTS:By combining broad-spectrum ARG profiling with machine-learning classification SourceTracker, here we present a novel way to address the question in the era of high-throughput sequencing. Its potential in extensive application was firstly validated by 656 global-scale samples covering diverse environmental types (e.g., human/animal gut, wastewater, soil, ocean) and broad geographical regions (e.g., China, USA, Europe, Peru). Its potential and limitations in source prediction as well as effect of parameter adjustment were then rigorously evaluated by artificial configurations with representative source proportions. When applying SourceTracker in region-specific analysis, excellent performance was achieved by ARG profiles in two sample types with obvious different source compositions, i.e., influent and effluent of wastewater treatment plant. Two environmental metagenomic datasets of anthropogenic interference gradient further supported its potential in practical application. To complement general-profile-based source tracking in distinguishing continuous gradient pollution, a few generalist and specialist indicator ARGs across ecotypes were identified in this study. CONCLUSION:We demonstrated for the first time that the developed source-tracking platform when coupling with proper experiment design and efficient metagenomic analysis tools will have significant implications for assessing AMR pollution. Following predicted source contribution status, risk ranking of different sources in ARG dissemination will be possible, thereby paving the way for establishing priority in mitigating ARG spread and designing effective control strategies.

Project description:Areas of concern (AOCs) around the Great Lakes are characterized by historic and ongoing problems with microbial water quality, leading to beneficial use impairments (BUIs) such as beach postings and closures. In this study, we assessed river and beach sites within the Rouge River watershed, associated stormwater outfalls, and at Rouge Beach. The concentrations of Escherichia coli as well as human- and gull-specific qPCR microbial source tracking (MST) markers were assessed at all sites. A preliminary comparison of digital PCR (dPCR) methodologies for both MST markers was conducted regarding sensitivity and specificity. Within the watershed, the outfalls were found to be a prominent source of human fecal contamination, with two outfalls particularly affected by sewage cross-connections. However, the occurrence of human fecal contamination along Rouge Beach and in the lower portions of the watershed was largely dependent on rain events. Gull fecal contamination was the predominant source of contamination at the beach, particularly during dry weather. The multiplex human/gull dPCR methodology used in this study tended to be more sensitive than the individual quantitative PCR (qPCR) assays, with only a slight decrease in specificity. Both dPCR and qPCR methodologies identified the same predominance of human and gull markers in stormwater and beach locations, respectively; however, the dPCR multiplex assay was more sensitive and capable of detecting fecal contamination that was undetected by qPCR assays. These results demonstrate the dPCR assay used in this study could be a viable tool for MST studies to increase the ability to identify low levels of fecal contamination.IMPORTANCE Fecal contamination of recreational water poses a persistent and ongoing problem, particularly in areas of concern around the Great Lakes. The identification of the source(s) of fecal contamination is essential for safeguarding public health as well as guiding remediation efforts; however, fecal contamination may frequently be present at low levels and remain undetectable by certain methodologies. In this study, we utilized microbial source tracking techniques using both quantitative and digital PCR assays to identify sources of contamination. Our results indicated high levels of human fecal contamination within stormwater outfalls, while lower levels were observed throughout the watershed. Additionally, high levels of gull fecal contamination were detected at Rouge Beach, particularly during drier sampling events. Furthermore, our results indicated an increased sensitivity of the digital PCR assay to detect both human and gull contamination, suggesting it could be a viable tool for future microbial source tracking studies.

Project description:BackgroundIdentifying active lesions in magnetic resonance imaging (MRI) is crucial for the diagnosis and treatment planning of multiple sclerosis (MS). Active lesions on MRI are identified following the administration of Gadolinium-based contrast agents (GBCAs). However, recent studies have reported that repeated administration of GBCA results in the accumulation of Gd in tissues. In addition, GBCA administration increases health care costs. Thus, reducing or eliminating GBCA administration for active lesion detection is important for improved patient safety and reduced healthcare costs. Current state-of-the-art methods for identifying active lesions in brain MRI without GBCA administration utilize data-intensive deep learning methods.ObjectiveTo implement nonlinear dimensionality reduction (NLDR) methods, locally linear embedding (LLE) and isometric feature mapping (Isomap), which are less data-intensive, for automatically identifying active lesions on brain MRI in MS patients, without the administration of contrast agents.Materials and methodsFluid-attenuated inversion recovery (FLAIR), T2-weighted, proton density-weighted, and pre- and post-contrast T1-weighted images were included in the multiparametric MRI dataset used in this study. Subtracted pre- and post-contrast T1-weighted images were labeled by experts as active lesions (ground truth). Unsupervised methods, LLE and Isomap, were used to reconstruct multiparametric brain MR images into a single embedded image. Active lesions were identified on the embedded images and compared with ground truth lesions. The performance of NLDR methods was evaluated by calculating the Dice similarity (DS) index between the observed and identified active lesions in embedded images.ResultsLLE and Isomap, were applied to 40 MS patients, achieving median DS scores of 0.74 ± 0.1 and 0.78 ± 0.09, respectively, outperforming current state-of-the-art methods.ConclusionsNLDR methods, Isomap and LLE, are viable options for the identification of active MS lesions on non-contrast images, and potentially could be used as a clinical decision tool.

Project description:Background Carotid endarterectomy (CEA) is a major vascular operation for stroke prevention that carries significant perioperative risks; however, outcome prediction tools remain limited. The authors developed machine learning algorithms to predict outcomes following CEA. Methods and Results The National Surgical Quality Improvement Program targeted vascular database was used to identify patients who underwent CEA between 2011 and 2021. Input features included 36 preoperative demographic/clinical variables. The primary outcome was 30-day major adverse cardiovascular events (composite of stroke, myocardial infarction, or death). The data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, 6 machine learning models were trained using preoperative features. The primary metric for evaluating model performance was area under the receiver operating characteristic curve. Model robustness was evaluated with calibration plot and Brier score. Overall, 38 853 patients underwent CEA during the study period. Thirty-day major adverse cardiovascular events occurred in 1683 (4.3%) patients. The best performing prediction model was XGBoost, achieving an area under the receiver operating characteristic curve of 0.91 (95% CI, 0.90-0.92). In comparison, logistic regression had an area under the receiver operating characteristic curve of 0.62 (95% CI, 0.60-0.64), and existing tools in the literature demonstrate area under the receiver operating characteristic curve values ranging from 0.58 to 0.74. The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.02. The strongest predictive feature in our algorithm was carotid symptom status. Conclusions The machine learning models accurately predicted 30-day outcomes following CEA using preoperative data and performed better than existing tools. They have potential for important utility in guiding risk-mitigation strategies to improve outcomes for patients being considered for CEA.

Dataset Information

Tracking Major Sources of Water Contamination Using Machine Learning.

Publications

Tracking Major Sources of Water Contamination Using Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets