Interpretability Versus Accuracy: A Comparison of Machine Learning Models Built Using Different Algorithms, Performance Measures, and Features to Predict E. coli Levels in Agricultural Water

A rapid approach with machine learning for quantifying the relative burden of antimicrobial resistance in natural aquatic environments

The massive use and discharge of antibiotics have led to increasing concerns about antimicrobial resistance (AMR) in natural aquatic environments. Since the dose-response mechanisms of pathogens with AMR have not yet been fully understood, and the antibiotic resistance genes and bacteria-related data collection via field sampling and laboratory testing is time-consuming and expensive, designing a rapid approach to quantify the burden of AMR in the natural aquatic environment has become a challenge. To cope with such a challenge, a new approach involving an integrated machine-learning framework was developed by investigating the associations between the relative burden of AMR and easily accessible variables (i.e., relevant environmental variables and adjacent land-use patterns). The results, based on a real-world case analysis, demonstrate that the quantification speed has been reduced from 3-7 days, which is typical for traditional measurement procedures with field sampling and laboratory testing, to approximately 0.5 hours using the new approach. Moreover, all five metrics for AMR relative burden quantification exceed the threshold level of 85%, with F1-score surpassing 0.92. Compared to logistic regression, decision trees, and basic random forest, the adaptive random forest model within the framework significantly improves quantification accuracy without sacrificing model interpretability. Two environmental variables, dissolved oxygen and resistivity, along with the proportion of green areas were identified as three key feature variables for the rapid quantification. This study contributes to the enrichment of burden analyses and management practices for rapid quantification of the relative burden of AMR without dose-response information.

Using machine learning models to estimate Escherichia coli concentration in an irrigation pond from water quality and drone-based RGB imagery data

The rapid and efficient quantification of Escherichia coli concentrations is crucial for monitoring water quality. Remote sensing techniques and machine learning algorithms have been used to detect E. coli in water and estimate its concentrations. The application of these approaches, however, is challenged by limited sample availability and unbalanced water quality datasets. In this study, we estimated the E. coli concentration in an irrigation pond in Maryland, USA, during the summer season using demosaiced natural color (red, green, and blue: RGB) imagery in the visible and infrared spectral ranges, and a set of 14 water quality parameters. We did this by deploying four machine learning models - Random Forest (RF), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGB), and K-nearest Neighbor (KNN) - under three data utilization scenarios: water quality parameters only, combined water quality and small unmanned aircraft system (sUAS)-based RGB data, and RGB data only. To select the training and test datasets, we applied two data-splitting methods: ordinary and quantile data splitting. These methods provided a constant splitting ratio in each decile of the E. coli concentration distribution. Quantile data splitting resulted in better model performance metrics and smaller differences between the metrics for both the training and testing datasets. When trained with quantile data splitting after hyperparameter optimization, models RF, GBM, and XGB had R2 values above 0.847 for the training dataset and above 0.689 for the test dataset. The combination of water quality and RGB imagery data resulted in a higher R2 value (>0.896) for the test dataset. Shapley additive explanations (SHAP) of the relative importance of variables revealed that the visible blue spectrum intensity and water temperature were the most influential parameters in the RF model. Demosaiced RGB imagery served as a useful predictor of E. coli concentration in the studied irrigation pond.

Machine learning for municipal sludge recycling by thermochemical conversion towards sustainability

The sustainable disposal of high-moisture municipal sludge (MS) has received increasing attention. Thermochemical conversion technologies can be used to recycle MS into liquid/gas bio-fuel and value-added solid products. In this review, we compared energy recovery potential of common thermochemical technologies (i.e., incineration, pyrolysis, hydrothermal conversion) for MS disposal via statistical methods, which indicated that hydrothermal conversion had a great potential in achieving energy recovery from MS. The application of machine learning (ML) in MS recycling was discussed to decipher complex relationships among MS components, process parameters and physicochemical reactions. Comprehensive ML models should be developed considering successive reaction processes of thermochemical conversion in future studies. Furthermore, challenges and prospects were proposed to improve effectiveness of ML for energizing thermochemical conversion of MS regarding data collection and preprocessing, model optimization and interpretability. This review sheds light on mechanism exploration of MS thermochemical recycling by ML, and provide practical guidance for MS recycling.

Application and Potential of Artificial Intelligence in Heart Failure: Past, Present, and Future

The prevalence of heart failure (HF) is increasing, necessitating accurate diagnosis and tailored treatment. The accumulation of clinical information from patients with HF generates big data, which poses challenges for traditional analytical methods. To address this, big data approaches and artificial intelligence (AI) have been developed that can effectively predict future observations and outcomes, enabling precise diagnoses and personalized treatments of patients with HF. Machine learning (ML) is a subfield of AI that allows computers to analyze data, find patterns, and make predictions without explicit instructions. ML can be supervised, unsupervised, or semi-supervised. Deep learning is a branch of ML that uses artificial neural networks with multiple layers to find complex patterns. These AI technologies have shown significant potential in various aspects of HF research, including diagnosis, outcome prediction, classification of HF phenotypes, and optimization of treatment strategies. In addition, integrating multiple data sources, such as electrocardiography, electronic health records, and imaging data, can enhance the diagnostic accuracy of AI algorithms. Currently, wearable devices and remote monitoring aided by AI enable the earlier detection of HF and improved patient care. This review focuses on the rationale behind utilizing AI in HF and explores its various applications.

Predicting microbial water quality in on-site water reuse systems with online sensors

Widespread implementation of on-site water reuse is hindered by the limited availability of monitoring approaches that ensure microbial quality during operation. In this study, we developed a methodology for monitoring microbial water quality in on-site water reuse systems using inexpensive and commercially available online sensors. An extensive dataset containing sensor and microbial water quality data for six of the most critical types of disruptions in membrane bioreactors with chlorination was collected. We then tested the ability of three typological machine learning algorithms - logistic regression, support-vector machine, and random forest - to predict the microbial water quality as "safe" or "unsafe" for reuse. The main criteria for model optimization was to ensure a low false positive rate (FPR) - the percentage of safe predictions when the actual condition is unsafe - which is essential to protect users health. This resulted in enforcing a fixed FPR ≤ 2%. Maximizing the true positive rate (TPR) - the percentage of safe predictions when the actual condition is safe - was given second priority. Our results show that logistic-regression-based models using only two out of the six sensors (free chlorine and oxidation-reduction potential) achieved the highest TPR. Including sensor slopes as engineered features allowed to reach similar TPRs using only one sensor instead of two. Analysis of the occurrence of false predictions showed that these were mostly early alarms, a characteristic that could be regarded as an asset in alarm management. In conclusion, the simplest algorithm in combination with only one or two sensors performed best at predicting the microbial water quality. This result provides useful insights for water quality modeling or for applications where small datasets are a common challenge and a general advantage might be gained by using simpler models that reduce the risk of overfitting, allow better interpretability, and require less computational power.

Applications of artificial intelligence and machine learning in heart failure

Machine learning (ML) is a sub-field of artificial intelligence that uses computer algorithms to extract patterns from raw data, acquire knowledge without human input, and apply this knowledge for various tasks. Traditional statistical methods that classify or regress data have limited capacity to handle large datasets that have a low signal-to-noise ratio. In contrast to traditional models, ML relies on fewer assumptions, can handle larger and more complex datasets, and does not require predictors or interactions to be pre-specified, allowing for novel relationships to be detected. In this review, we discuss the rationale for the use and applications of ML in heart failure, including disease classification, early diagnosis, early detection of decompensation, risk stratification, optimal titration of medical therapy, effective patient selection for devices, and clinical trial recruitment. We discuss how ML can be used to expedite implementation and close healthcare gaps in learning healthcare systems. We review the limitations of ML, including opaque logic and unreliable model performance in the setting of data errors or data shift. Whilst ML has great potential to improve clinical care and research in HF, the applications must be externally validated in prospective studies for broad uptake to occur.

Correlation value determined to increase Salmonella prediction success of deep neural network for agricultural waters

The use of computer-based tools has been becoming popular in the field of produce safety. Various algorithms have been applied to predict the population and presence of indicator microorganisms and pathogens in agricultural water sources. The purpose of this study is to improve the Salmonella prediction success of deep feed-forward neural network (DFNN) in agricultural surface waters with a determined correlation value based on selected features. Datasets were collected from six agricultural ponds in Central Florida. The most successful physicochemical and environmental features were selected by the gain ratio for the prediction of generic Escherichia coli population with machine learning algorithms (decision tree, random forest, support vector machine). Salmonella prediction success of DFNN was evaluated with dataset including selected environmental and physicochemical features combined with predicted E. coli populations with and without correlation value. The performance of correlation value was evaluated with all possible mathematical dataset combinations (nCr) of six ponds. The higher accuracy performances (%) were achieved through DFNN analyses with correlation value between 88.89 and 98.41 compared to values with no correlation value from 83.68 to 96.99 for all dataset combinations. The findings emphasize the success of determined correlation value for the prediction of Salmonella presence in agricultural surface waters.

Interpretable tree-based ensemble model for predicting beach water quality

Tree-based machine learning models based on environmental features offer low-cost and timely solutions for predicting microbial fecal contamination in beach water to inform the public of the health risk. However, many of these models are black boxes that are difficult for humans to understand, which may cause severe consequences such as unexplained decisions and failure in accountability. To develop interpretable predictive models for beach water quality, we evaluate five tree-based models, namely classification tree, random forest, CatBoost, XGBoost, and LightGBM, and employ a state-of-the-art explanation method SHAP to explain the models. When tested on the Escherichia coli (E. coli) concentration data collected from three beach sites along Lake Erie shores, LightGBM, followed by XGBoost, achieves the highest averaged precision and recall scores. For all three sites, both models suggest lake turbidity as the most important predictor, and elucidate the crucial role of accurate local data of wave height and rainfall in the model development. Local SHAP values further reveal the robustness of the importance of lake turbidity as its SHAP value increases nearly monotonically with its value and is minimally affected by other environmental factors. Moreover, we found an intriguing interaction between lake turbidity and day-of-year. This work suggests that the combination of LightGBM and SHAP has a promising potential to develop interpretable models for predicting microbial water quality in freshwater lakes.

Precision Irrigation Management Using Machine Learning and Digital Farming Solutions

Freshwater is essential for irrigation and the supply of nutrients for plant growth, in order to compensate for the inadequacies of rainfall. Agricultural activities utilize around 70% of the available freshwater. This underscores the importance of responsible management, using smart agricultural water technologies. The focus of this paper is to investigate research regarding the integration of different machine learning models that can provide optimal irrigation decision management. This article reviews the research trend and applicability of machine learning techniques, as well as the deployment of developed machine learning models for use by farmers toward sustainable irrigation management. It further discusses how digital farming solutions, such as mobile and web frameworks, can enable the management of smart irrigation processes, with the aim of reducing the stress faced by farmers and researchers due to the opportunity for remote monitoring and control. The challenges, as well as the future direction of research, are also discussed.

Prediction of E. coli Concentrations in Agricultural Pond Waters: Application and Comparison of Machine Learning Algorithms

The microbial quality of irrigation water is an important issue as the use of contaminated waters has been linked to several foodborne outbreaks. To expedite microbial water quality determinations, many researchers estimate concentrations of the microbial contamination indicator Escherichia coli (E. coli) from the concentrations of physiochemical water quality parameters. However, these relationships are often non-linear and exhibit changes above or below certain threshold values. Machine learning (ML) algorithms have been shown to make accurate predictions in datasets with complex relationships. The purpose of this work was to evaluate several ML models for the prediction of E. coli in agricultural pond waters. Two ponds in Maryland were monitored from 2016 to 2018 during the irrigation season. E. coli concentrations along with 12 other water quality parameters were measured in water samples. The resulting datasets were used to predict E. coli using stochastic gradient boosting (SGB) machines, random forest (RF), support vector machines (SVM), and k-nearest neighbor (kNN) algorithms. The RF model provided the lowest RMSE value for predicted E. coli concentrations in both ponds in individual years and over consecutive years in almost all cases. For individual years, the RMSE of the predicted E. coli concentrations (log10 CFU 100 ml-1) ranged from 0.244 to 0.346 and 0.304 to 0.418 for Pond 1 and 2, respectively. For the 3-year datasets, these values were 0.334 and 0.381 for Pond 1 and 2, respectively. In most cases there was no significant difference (P > 0.05) between the RMSE of RF and other ML models when these RMSE were treated as statistics derived from 10-fold cross-validation performed with five repeats. Important E. coli predictors were turbidity, dissolved organic matter content, specific conductance, chlorophyll concentration, and temperature. Model predictive performance did not significantly differ when 5 predictors were used vs. 8 or 12, indicating that more tedious and costly measurements provide no substantial improvement in the predictive accuracy of the evaluated algorithms.