Statistical Machine Learning Models Research Articles

Choice of refractive surgery types for myopia assisted by machine learning based on doctors’ surgical selection data

In recent years, corneal refractive surgery has been widely used in clinics as an effective means to restore vision and improve the quality of life. When choosing myopia-refractive surgery, it is necessary to comprehensively consider the differences in equipment and technology as well as the specificity of individual patients, which heavily depend on the experience of ophthalmologists. In our study, we took advantage of machine learning to learn about the experience of ophthalmologists in decision-making and assist them in the choice of corneal refractive surgery in a new case. Our study was based on the clinical data of 7,081 patients who underwent corneal refractive surgery between 2000 and 2017 at the Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences. Due to the long data period, there were data losses and errors in this dataset. First, we cleaned the data and deleted the samples of key data loss. Then, patients were divided into three groups according to the type of surgery, after which we used SMOTE technology to eliminate imbalance between groups. Six statistical machine learning models, including NBM, RF, AdaBoost, XGBoost, BP neural network, and DBN were selected, and a ten-fold cross-validation and grid search were used to determine the optimal hyperparameters for better performance. When tested on the dataset, the multi-class RF model showed the best performance, with agreement with ophthalmologist decisions as high as 0.8775 and Macro F1 as high as 0.8019. Furthermore, the results of the feature importance analysis based on the SHAP technique were consistent with an ophthalmologist’s practical experience. Our research will assist ophthalmologists in choosing appropriate types of refractive surgery and will have beneficial clinical effects.

Statistical Machine Learning Model for Distributed Energy Planning in Industrial Park

With the advancement of industrial modernization, industrial parks have become the main body of new energy production and consumption. However, due to the large demand for energy in industrial agglomeration, the way of energy utilization is changing to sustainable. The direct connection of distributed energy resources in industrial parks, including photovoltaic power generation systems, has an important impact on its planning and operation. Furthermore, weather scenarios can have an impact on distributed photovoltaic generation, and the uncertainty in photovoltaic power output will, in turn, affect the uncertainty in industrial park planning. Therefore, this paper aims to address the issues of inaccurate prediction of distributed electricity generation during the planning period and the non-uniform distribution of energy resources such as electricity, heating, and cooling. This is achieved through the application of statistical machine learning. The paper intends to incorporate the ideas of statistical machine learning into the model for industrial park distributed energy random opportunity-constrained planning, aiming to resolve the problems of non-uniform distribution of distributed energy sources within the park, along with uncertainty in their outputs and high overall investment costs. The model takes the planning, construction and operating costs of the industrial park as the objective function, uses the lost load cost to ensure the safety of the industrial park, and uses the Chebyshev inequality probability to limit the output characteristics of distributed energy equipment. In terms of operation, the planning period is subdivided into heating period, cooling period and transition period, and the balance of electricity, heat and cold is considered. Finally, an actual example of an industrial park is used to verify the effectiveness of this method. Experimental validation shows that this approach can ensure safety requirements in industrial parks during the heating season, cooling season, and transitional periods by flexibly adjusting the confidence threshold. Simultaneously, it delivers significant economic benefits.

RootInteractive tool for multidimensional statistical analysis, machine learning and analytical model validation

The ALICE experiment [1] at CERN’s LHC is specifically designed for investigating heavy ion collisions. The upgraded ALICE accommodates a tenfold increase in Pb–Pb luminosity and a two-order-of-magnitude surge in minimum bias events. To address the challenges of high detector occupancy and event pile-ups, advanced multidimensional data analysis techniques, including machine learning (ML), are indispensable. Despite ML’s popularity, the complexity of its models presents interpretation challenges, and oversimplification in analysis often leads to inaccuracies. Our objective was to develop RootInteractive, a tool for multidimensional statistical analysis. This tool simplifies data analysis across dimensions, visualizes functions with uncertainties, and validates assumptions and approximations. In RootInteractive, it is crucial to easily define the functional composition of analytical parametric and non-parametric functions, exploit symmetries, and define multidimensional "invariant" functions and corresponding alarms. RootInteractive [2] adopts a declarative programming paradigm, ensuring userfriendliness for experts, students, and educators. It facilitates interactive visualization, n-dimensional histogramming/projection, and information extraction on both Python/C++ server and Javascript client. The tool supports client/server applications in Jupyter or standalone client-side applications. Through data compression, datasets with O(107) entries and O(25) attributes can be interactively analyzed in a browser with O(0.500-1 GB) size. Representative downsampling and reweighting/pre-aggregation enable the effective analysis of one year of ALICE data for various purposes.

Towards Smart EV Charging: Assessing the Flexibility Provision Potential of Electric Vehicle Charging Stations for Cost-Effective Grid Responsiveness

In the dynamic shift towards a sustainable global energy landscape, electric vehicle (EV) charging stations emerge as crucial components, fostering clean mobility while holding untapped potential for grid support. This study investigates the flexibility potential of charging stations, aiming to provide ancillary services to the grid. The methodology, encompassing diverse factors from parking scenarios to technical regulations, serves a dual purpose: probabilistically forecasting the station’s engagement in services and assessing its capacity to mitigate grid events. Building on prior research in frequency maintenance and voltage stability, the methodology creates a comprehensive framework, challenging the synthesis of this knowledge with the dynamic nature of EV charging patterns. Leveraging a two-year dataset from a specific charging station, the research builds upon previous statistical analyses conducted in a prior study. In this continuation, the study employs a variety of statistical analyses and machine learning models, including XGBoost, to explore time-based, energy-based, and behavior-based perspectives. Results showcase increased charging sessions and energy consumption, emphasizing the growing role of EVs in the energy landscape. The study presents simulation algorithms for ancillary service potential, revealing the impact of a EV charging management proposal on daily power consumption, client satisfaction, net profit, and pricing dynamics. The intricate interplay between charging stations, electric grid providers, and users underscores the need for strategic considerations to optimize economic viability and user satisfaction in the evolving electric vehicle charging landscape. As the electric mobility era unfolds, this study provides a crucial approach for forecasting capabilities and estimating economic gains, contributing to the sustainable integration of electric vehicles into the global energy ecosystem.

Enhancing sewage flow prediction using an integrated improved SSA-CNN-Transformer-BiLSTM model

<p>Accurate prediction of sewage flow is crucial for optimizing sewage treatment processes, cutting down energy consumption, and reducing pollution incidents. Current prediction models, including traditional statistical models and machine learning models, have limited performance when handling nonlinear and high-noise data. Although deep learning models excel in time series prediction, they still face challenges such as computational complexity, overfitting, and poor performance in practical applications. Accordingly, this study proposed a combined prediction model based on an improved sparrow search algorithm (SSA), convolutional neural network (CNN), transformer, and bidirectional long short-term memory network (BiLSTM) for sewage flow prediction. Specifically, the CNN part was responsible for extracting local features from the time series, the Transformer part captured global dependencies using the attention mechanism, and the BiLSTM part performed deep temporal processing of the features. The improved SSA algorithm optimized the model's hyperparameters to improve prediction accuracy and generalization capability. The proposed model was validated on a sewage flow dataset from an actual sewage treatment plant. Experimental results showed that the introduced Transformer mechanism significantly enhanced the ability to handle long time series data, and an improved SSA algorithm effectively optimized the hyperparameter selection, improving the model's prediction accuracy and training efficiency. After introducing an improved SSA, CNN, and Transformer modules, the prediction model's $ {R^{\text{2}}} $ increased by 0.18744, $ RMSE $ (root mean square error) decreased by 114.93, and $ MAE $ (mean absolute error) decreased by 86.67. The difference between the predicted peak/trough flow and monitored peak/trough flow was within 3.6% and the predicted peak/trough flow appearance time was within 2.5 minutes away from the monitored peak/trough flow time. By employing a multi-model fusion approach, this study achieved efficient and accurate sewage flow prediction, highlighting the potential and application prospects of the model in the field of sewage treatment.</p>

Classification of chronic ankle instability using machine learning technique based on ankle kinematics during heel rise in delivery workers.

Ankle injuries in delivery workers (DWs) are often caused by trips, and high recurrence rates of ankle sprains are related to chronic ankle instability (CAI). Heel rise requires joint angles and moments similar to those of the terminal stance phase of walking that the foot supinates. Thus, our study aimed to develop, determine, and compare the predictive performance of statistical machine learning models to classify DWs with and without CAI using ankle kinematics during heel rise. In total, 203 DWs were screened for eligibility. Seven predictors were included in our study (age, work duration, body mass index, calcaneal stance position angle [CSPA] in the initial and terminal positions during heel rise, calcaneal movement during heel rise [CMHR], and plantar flexion angle during heel rise). Six machine learning algorithms, including logistic regression, decision tree, AdaBoost, Extreme Gradient boosting machines, random forest, and support vector machine, were trained. The random forest model (area under the curve [AUC], 0.967 [excellent]; F1, 0.889; accuracy, 0.925) confirmed the best predictive performance in the test datasets among the six machine learning models. For Shapley Additive Explanations, old age, low CMHR, high CSPA in the initial position, high PFA, long work duration, low CSPA in the terminal position, and high body mass index were the most important predictors of CAI in the random forest model. Ankle kinematics during heel rise can be considered in the classification of DWs with and without CAI.

Statistical Machine Learning for Power Flow Analysis Considering the Influence of Weather Factors on Photovoltaic Power Generation.

It is generally accepted that the impact of weather variation is gradually increasing in modern distribution networks with the integration of high-proportion photovoltaic (PV) power generation and weather-sensitive loads. This article analyzes power flow using a novel stochastic weather generator (SWG) based on statistical machine learning (SML). The proposed SML model, which incorporates generative adversarial networks (GANs), probability theory, and information theory, enables the generation and evaluation of simulated hourly weather data throughout the year. The GAN model captures various weather variation characteristics, including weather uncertainties, diurnal variations, and seasonal patterns. Compared to shallow learning models, the proposed deep learning model exhibits significant advantages in stochastic weather simulation. The simulated data generated by the proposed model closely resemble real data in terms of time-series regularity, integrity, and stochasticity. The SWG is applied to model PV power generation and weather-sensitive loads. Then, we actively conduct a power flow analysis (PFA) on a real distribution network in Guangdong, China, using simulated data for an entire year. The results provide evidence that the GAN-based SWG surpasses the shallow machine learning approach in terms of accuracy. The proposed model ensures accurate analysis of weather-related power flow and provides valuable insights for the analysis, planning, and design of distribution networks.

Land Use Change Modelling Using Logistic Regression, Random Forest and Additive Logistic Regression in Kubu Raya Regency, West Kalimantan

Kubu Raya Regency is a regency in the province of West Kalimantan which has a wetland ecosystem including a high-density swamp or peatland ecosystem along with an extensive area of mangroves. The function of wetland ecosystems is essential for fauna, as a source of livelihood for the surrounding community and as storage reservoir for carbon stocks. Most of the land in Kubu Raya Regency is peatland. As a consequence, peat has long been used for agriculture and as a source of livelihood for the community. Along with the vast area of peat, the regency also has a potential high risk of peat fires. This study aims to predict land use changes in Kubu Raya Regency using three statistical machine learning models, specifically Logistic Regression (LR), Random Forest (RF) and Additive Logistic Regression (ALR). Land cover map data were acquired from the Ministry of Environment and Forestry and subsequently reclassified into six types of land cover at a resolution of 100 m. The land cover data were employed to classify land use or land cover class for the Kubu Raya regency, for the years 2009, 2015 and 2020. Based on model performance, RF provides greater accuracy and F1 score as opposed to LR and ALR. The outcome of this study is expected to provide knowledge and recommendations that may aid in developing future sustainable development planning and management for Kubu Raya Regency.

Utilizing a novel high-resolution malaria dataset for climate-informed predictions with a deep learning transformer model

Climatic factors influence malaria transmission via the effect on the Anopheles vector and Plasmodium parasite. Modelling and understanding the complex effects that climate has on malaria incidence can enable important early warning capabilities. Deep learning applications across fields are proving valuable, however the field of epidemiological forecasting is still in its infancy with a lack of applied deep learning studies for malaria in southern Africa which leverage quality datasets. Using a novel high resolution malaria incidence dataset containing 23 years of daily data from 1998 to 2021, a statistical model and XGBOOST machine learning model were compared to a deep learning Transformer model by assessing the accuracy of their numerical predictions. A novel loss function, used to account for the variable nature of the data yielded performance around + 20% compared to the standard MSE loss. When numerical predictions were converted to alert thresholds to mimic use in a real-world setting, the Transformer’s performance of 80% according to AUROC was 20–40% higher than the statistical and XGBOOST models and it had the highest overall accuracy of 98%. The Transformer performed consistently with increased accuracy as more climate variables were used, indicating further potential for this prediction framework to predict malaria incidence at a daily level using climate data for southern Africa.

An intercomparison of weather normalization of PM2.5 concentration using traditional statistical methods, machine learning, and chemistry transport models

Traditional statistical methods (TSM) and machine learning (ML) methods have been widely used to separate the effects of emissions and meteorology on air pollutant concentrations, while their performance compared to the chemistry transport model has been less fully investigated. Using the Community Multiscale Air Quality Model (CMAQ) as a reference, a series of experiments was conducted to comprehensively investigate the performance of TSM (e.g., multiple linear regression and Kolmogorov–Zurbenko filter) and ML (e.g., random forest and extreme gradient boosting) approaches in quantifying the effects of emissions and meteorology on the trends of fine particulate matter (PM2.5) during 2013−2017. Model performance evaluation metrics suggested that the TSM and ML methods can explain the variations of PM2.5 with the highest performance from ML. The trends of PM2.5 showed insignificant differences (p > 0.05) for both the emission-related (PM2.5EMI\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${{\\rm{PM}}}_{2.5}^{{\\rm{EMI}}}$$\\end{document}) and meteorology-related components between TSM, ML, and CMAQ modeling results. PM2.5EMI\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${{\\rm{PM}}}_{2.5}^{{\\rm{EMI}}}$$\\end{document} estimated from ML showed the least difference to that from CMAQ. Considering the medium computing resources and low model biases, the ML method is recommended for weather normalization of PM2.5. Sensitivity analysis further suggested that the ML model with optimized hyperparameters and the exclusion of temporal variables in weather normalization can further produce reasonable results in emission-related trends of PM2.5.

Effective Utilization of Data for Predicting COVID-19 Dynamics: An Exploration through Machine Learning Models

This study is centered around the COVID-19 pandemic which has posed a global health concern for over three years. It emphasizes the importance of effectively utilizing epidemic simulation models for informed decision-making concerning epidemic control. The challenge lies in appropriately choosing, adapting, and interpreting these models. The research constructs three statistical machine learning models to predict the spread of COVID-19 in specific regions and evaluates their performance using real COVID-19 incidence data. The paper presents short-term (3, 7, 14, 21, and 30 days) forecasts of COVID-19 morbidity and mortality for Germany, Japan, South Korea, and Ukraine. The precision of each model was scrutinized based on the type of input data used. Recommendations are provided on how various data sources can enhance the interpretation quality of machine learning models predicting infectious disease dynamics. The initial findings suggest the need for the comprehensive utilization of all available data, favoring cumulative data during holiday-rich periods and daily data otherwise. To minimize the absolute error, databases should be compiled using daily morbidity and mortality rates.

Interpolation, Satellite-Based Machine Learning, or Meteorological Simulation? A Comparison Analysis for Spatio-temporal Mapping of Mesoscale Urban Air Temperature

AbstractFine-resolution spatio-temporal maps of near-surface urban air temperature (Ta) provide crucial data inputs for sustainable urban decision-making, personal heat exposure, and climate-relevant epidemiological studies. The recent availability of IoT weather station data allows for high-resolution urban Ta mapping using approaches such as interpolation techniques or machine learning (ML). This study is aimed at executing these approaches and traditional numerical modeling within a practical and operational framework and evaluate their practicality and efficiency in cases where data availability, computational constraints, or specialized expertise pose challenges. We employ Netatmo crowd-sourced weather station data and three geospatial mapping approaches: (1) Ordinary Kriging, (2) statistical ML model (using predictors primarily derived from Earth Observation Data), and (3) weather research and forecasting model (WRF) to predict/map daily Ta at nearly 1-km spatial resolution in Warsaw (Poland) for June–September and compare the predictions against observations from 5 meteorological reference stations. The results reveal that ML can serve as a viable alternative approach to traditional kriging and numerical simulation, characterized by reduced complexity and higher computational speeds within the domain of urban meteorological studies (overall RMSE = 1.06 °C and R2 = 0.94, compared to ground-based meteorological stations). The results have implications for identifying the urban regions vulnerable to overheating and evidence-based urban management in response to climate change. Due to the open-sourced nature of the applied predictors and input parsimony, the ML method can be easily replicated for other EU cities.

Classification of mathematical test questions using machine learning on datasets of learning management system questions.

Every student has a varied level of mathematical proficiency. Therefore, it is important to provide them with questions accordingly. Owing to advances in technology and artificial intelligence, the Learning Management System (LMS) has become a popular application to conduct online learning for students. The LMS can store multiple pieces of information on students through an online database, enabling it to recommend appropriate questions for each student based on an analysis of their previous responses to questions. Particularly, the LMS manages learners and provides an online platform that can evaluate their skills. Questions need to be classified according to their difficulty level so that the LMS can recommend them to learners appropriately and thereby increase their learning efficiency. In this study, we classified large-scale mathematical test items provided by ABLE Tech, which supports LMS-based online mathematical education platforms, using various machine learning techniques according to the difficulty levels of the questions. First, through t-test analysis, we identified the significant correlation variables according to the difficulty level. The t-test results showed that answer rate, type of question, and solution time were positively correlated with the difficulty of the question. Second, items were classified according to their difficulty level using various machine learning models, such as logistic regression (LR), random forest (RF), and extreme gradient boosting (xgboost). Accuracy, precision, recall, F1 score, the area under the curve of the receiver operating curve (AUC-ROC), Cohen's Kappa and Matthew's correlation coefficient (MCC) scores were used as the evaluation metrics. The correct answer rate, question type, and time for solving a question correlated significantly with the difficulty level. The machine learning-based xgboost model outperformed the statistical machine learning models, with a 85.7% accuracy, and 85.8% F1 score. These results can be used as an auxiliary tool in recommending suitable mathematical questions to various learners based on their difficulty level.

A fundamental diagram based hybrid framework for traffic flow estimation and prediction by combining a Markovian model with deep learning

Accurate traffic congestion estimation and prediction are critical building blocks for smart trip planning and rerouting decisions in transportation systems. Over the decades, there have been many studies focusing on traffic congestion estimation and prediction with different statistical approaches (e.g., Markov chain) and machine learning models (e.g., clustering, Bayesian networks, and artificial neural networks). However, there is a lack of a unified framework to address the mechanisms of different models and integrate the advantages of different methods through combinations. This paper introduces the FD-Markov-LSTM model, a hybrid interpretable approach that combines the fundamental diagram (FD), Markov chain, and long short-term memory (LSTM). The aim is to estimate and predict traffic states by integrating statistical data in both congested and uncongested scenarios. The FD-Markov-LSTM model leverages the FD to identify hierarchical traffic states and utilizes the Markov process to capture the probabilistic transitions between these states. We employ the LSTM model to further capture the residual time series produced by the Markov chain model (assuming a memoryless property) to enhance the estimation and prediction performance. The proposed model's accuracy in estimating and predicting traffic flow is evaluated using empirical data from three case studies conducted in Beijing and Los Angeles. The results highlight a significant improvement in accuracy compared to classical benchmark models such as the Markov model, ARIMA model, k-Nearest Neighbor model, Random Forest model, and LSTM. Specifically, the FD-Markov-LSTM model achieves reductions of over 39% in mean absolute error, 35% in root mean squared error, and 7.4% in mean absolute percentage error. These results clearly demonstrate that the FD-Markov-LSTM model outperforms the benchmark models, enabling more precise predictions of traffic flow.

Predicting the Performance of PEM Fuel Cells by Determining Dehydration or Flooding in the Cell Using Machine Learning Models

Modern industries encourages the use of hydrogen as an energy carrier to decarbonize the electricity grid, Polymeric Electrolyte membrane fuel cell which uses hydrogen as a fuel to produce electricity, is an efficient and reliable ‘power to gas’ technology. However, a key issue obstructing the advancement of PEMFCs is the unpredictability of their performance and failure events caused by flooding and dehydration. The accurate prediction of these two events is required to avoid any catastrophic failure in the cell. A typical approach used to predict failure modes relies on modeling failure-induced performance losses and monitoring the voltage of a cell. Data-driven machine learning models must be developed to address these challenges. Herein, we present a machine learning model for the prediction of the failure modes of operating cells. The model predicted the relative humidity of a cell by considering the cell voltage and current density as the input parameters. Advanced regression techniques, such as support vector machine, decision tree regression, random forest regression and artificial neural network, were used to improve the predictions. Features related to the model were derived from cell polarization data. The model’s results were validated with real-time test data obtained from the cell. The statistical machine learning models accurately provided information on the flooding- and dehydration-induced failure events.

Enhancing understanding of real-world listening experiences: Insights from ecological momentary assessments with assistive listening technologies

Comprehending the daily listening experiences of people who use assistive listening technologies is difficult due to individual differences and the variety of listening environments they encounter. Consequently, a lack of comprehensive insight into real-world experiences often leads to misconstrued interpretations of research outcomes and future technological directions. Addressing this issue, the National Acoustic Laboratories (NAL) in Sydney, Australia, has been actively investigating the applications of ecological momentary assessments (EMA) since 2010. By employing EMA, NAL aims to comprehend the impact of assistive listening technologies in real-world conditions. To achieve this, we invested data from four distinct studies, encompassing more than 3000 survey entries. Utilizing an EMA app specifically developed by NAL, participants reported various challenges they faced in their listening experiences. These challenges include difficulties in understanding conversation when listening to a single speaker or in multitasking scenarios, as well as frustration with the loudness and annoyance of background noise. The analysis of this extensive dataset involved a combination of conventional statistical methods and advanced machine learning models. By employing these techniques, key insights were extracted from the data, offering valuable guidance for the design of future research conducted in real-world settings.

Statistical Techniques vs. Machine Learning Models: A Comparative Analysis for Exchange Rate Forecasting in Fragile Five Countries

Statistical Techniques vs. Machine Learning Models: A Comparative Analysis for Exchange Rate Forecasting in Fragile Five Countries

A deep learning prediction model of DenseNet-LSTM for concrete gravity dam deformation based on feature selection

Dam deformation can comprehensively reflect the operational status of the dam. Thus, it is significant to build a dam deformation prediction model with high accuracy for the operation of concrete gravity dams. The concrete gravity dam is a complex and dynamic system. Based on the current prediction methods, such as the statistical models or machine learning (ML) models, it is a challenge to capture the complicated relationships between deformation and various features, as well as the features and time. As a result, we have proposed a deep learning model called DenseNet-LSTM, which combines the densely connected convolutional Network (DenseNet) and long short-term memory (LSTM) network. Meanwhile, correlation analysis and random forest (RF) are also adopted to evaluate and select deformation features. In the case study, the deformation monitoring data of multiple points at different elevations in the same section of a typical concrete gravity dam in southwestern China are selected to verify the model. For all the monitoring points, the correlation coefficient of the proposed model is more than 0.99. The result shows that the DenseNet-LSTM model can reveal the dynamic evolution process of deformation of the concrete gravity dam. Compared with the CNN-LSTM, LSTM, and ML-based models, the accuracy of the proposed model is higher and its generalization ability is better, which provides new methods for dam safety monitoring.

Radiomics Correlation to CD68+ Tumor-Associated Macrophages in Clear Cell Renal Cell Carcinoma

Introduction: Renal cell carcinoma (RCC) is the ninth most common cancer worldwide, with clear cell RCC (ccRCC) being the most frequent histological subtype. The tumor immune microenvironment (TIME) of ccRCC is an important factor to guide treatment, but current assessments are tissue-based, which can be time-consuming and resource-intensive. In this study, we used radiomics extracted from clinically performed computed tomography (CT) as a noninvasive surrogate for CD68 tumor-associated macrophages (TAMs), a significant component of ccRCC TIME. Methods: TAM population was measured by CD68+/PanCK+ ratio and tumor-TAM clustering was measured by normalized K function calculated from multiplex immunofluorescence (mIF). A total of 1,076 regions on mIF slides from 78 patients were included. Radiomic features were extracted from multiphase CT of the ccRCC tumor. Statistical machine learning models, including random forest, Adaptive Boosting, and ElasticNet, were used to predict TAM population and tumor-TAM clustering. Results: The best models achieved an area under the ROC curve of 0.81 (95% CI: [0.69, 0.92]) for TAM population and 0.77 (95% CI: [0.66, 0.88]) for tumor-TAM clustering, respectively. Conclusion: Our study demonstrates the potential of using CT radiomics-derived imaging markers as a surrogate for assessment of TAM in ccRCC for real-time treatment response monitoring and patient selection for targeted therapies and immunotherapies.

Machine Learning for Improved Detection of Pathogenic E. coli in Hydroponic Irrigation Water Using Impedimetric Aptasensors: A Comparative Study.

Reuse of alternative water sources for irrigation (e.g., untreated surface water) is a sustainable approach that has the potential to reduce water gaps, while increasing food production. However, when growing fresh produce, this practice increases the risk of bacterial contamination. Thus, rapid and accurate identification of pathogenic organisms such as Shiga-toxin producing Escherichia coli (STEC) is crucial for resource management when using alternative water(s). Although many biosensors exist for monitoring pathogens in food systems, there is an urgent need for data analysis methodologies that can be applied to accurately predict bacteria concentrations in complex matrices such as untreated surface water. In this work, we applied an impedimetric electrochemical aptasensor based on gold interdigitated electrodes for measuring E. coliO157:H7 in surface water for hydroponic lettuce irrigation. We developed a statistical machine-learning (SML) framework for assessing different existing SML methods to predict the E. coliO157:H7 concentration. In this study, three classes of statistical models were evaluated for optimizing prediction accuracy. The SML framework developed here facilitates selection of the most appropriate analytical approach for a given application. In the case of E. coliO157:H7 prediction in untreated surface water, selection of the optimum SML technique led to a reduction of test set RMSE by at least 20% when compared with the classic analytical technique. The statistical framework and code (open source) include a portfolio of SML models, an approach which can be used by other researchers using electrochemical biosensors to measure pathogens in hydroponic irrigation water for rapid decision support.