Gradient Boosting Machine Model Research Articles

Radiomics-based machine learning for automated detection of Pneumothorax in CT scans.

The increasing complexity of diagnostic imaging often leads to misinterpretations and diagnostic errors, particularly in critical conditions such as pneumothorax. This study addresses the pressing need for improved diagnostic accuracy in CT scans by developing an intelligent model that leverages radiomics features and machine learning techniques. By enhancing the detection of pneumothorax, this research aims to mitigate diagnostic errors and accelerate the process of image interpretation, ultimately improving patient outcomes. Data used in this study was extracted from the medical records of 175 patients with suspected pneumothorax. The collected images were preprocessed in Matlab software. Radiomics features were extracted from each image and finally, the machine learning models were implemented on these features. The used machine learning algorithms are Gradient Tree Boosting (GBM), eXtreme Gradient Boosting (XGBoost), and Light GBM. To evaluate the performance of models, various evaluation criteria such as precision, accuracy, specificity, sensitivity, F1 score, Area Under the Receiver Operating Characteristic (ROC) Curve (AUC), and misclassification were calculated. According to the calculated evaluation criteria, in terms of accuracy, the Gradient Boosting Machine (GBM) model achieved the highest performance with an accuracy of 98.97%, followed closely by the XGBoost model at 98.29%. For precision, the GBM model outperformed the other models, recording a precision value of 99.55%. Regarding sensitivity, all three models-GBM, XGBoost, and LightGBM (LGBM)-demonstrated strong performance, with sensitivity values of 99%, 99%, and 100%, respectively, indicating minimal variation among them. The artificial intelligence models used in this study have significant potential to enhance patient care by supporting radiologists and other clinicians in the diagnosis of pneumothorax. These models can facilitate the prioritization of positive cases, expedite evaluations, and ultimately improve patient outcomes.

Deciphering the nonlinear and synergistic role of building energy variables in shaping carbon emissions: A LightGBM- SHAP framework in office buildings

As the global demand for sustainable buildings continues to rise, accurately assessing and managing carbon emissions during the operational phase of buildings has become an urgent challenge. This study employs machine learning and Explainable Artificial Intelligence (XAI) to explore the impact and synergistic effects of energy variables on carbon emissions in office building operations. Initially, energy consumption data from 28 office buildings in China were collected to construct a dataset comprising 24 energy indicators across four dimensions. The Lightweight Gradient Boosting Machine (LightGBM) and Extreme Gradient Boosting (XGBoost) models were used to predict building carbon emission, PV carbon offset, and net carbon emission based on different energy parameters. The SHapley Additive exPlanations (SHAP) method was utilized to interpret the model results from both global and local perspectives. The study results indicate that: (1) The LightGBM model, optimized with GridSearchCV, shows better stability and reliability in predicting carbon emissions. (2) SHAP bar plots和SHAP beeswarm plots reveal that the WWR in the ES dimension and the PVArea in the EP dimension are the most critical variables affecting building carbon emission and PV carbon offset. (3) SHAP dependence plots show that the contributions of energy variables are not independent, with differentiated synergistic effects among variables in emission reduction. (4) SHAP force plots consider interactions among multiple variables, identifying key variable ranges to minimize building carbon emission and maximize PV carbon offset.

Predictive modeling of preoperative acute heart failure in older adults with hypertension: a dual perspective of SHAP values and interaction analysis

BackgroundIn older adults with hypertension, hip fractures accompanied by preoperative acute heart failure significantly elevate surgical risks and adverse outcomes, necessitating timely identification and management to improve patient outcomes.Research objectiveThis study aims to enhance the early recognition of acute heart failure in older hypertensive adults prior to hip fracture surgery by developing a predictive model using logistic regression (LR) and machine learning methods, optimizing preoperative assessment and management.MethodsEmploying a retrospective study design, we analyzed hypertensive older adults who underwent hip fracture surgery at Hebei Medical University Third Hospital from January 2018 to December 2022. Predictive models were constructed using LASSO regression and multivariable logistic regression, evaluated via nomogram charts. Five additional machine learning methods were utilized, with variable importance assessed using SHAP values and the impact of key variables evaluated through multivariate correlation analysis and interaction effects.ResultsThe study included 1,370 patients. LASSO regression selected 18 key variables, including sex, age, coronary heart disease, pulmonary infection, ventricular arrhythmias, acute myocardial infarction, and anemia. The logistic regression model demonstrated robust performance with an AUC of 0.753. Although other models outperformed it in sensitivity and F1 score, logistic regression’s discriminative ability was significant for clinical decision-making. The Gradient Boosting Machine model, notable for a sensitivity of 95.2%, indicated substantial capability in identifying patients at risk, crucial for reducing missed diagnoses.ConclusionWe developed and compared efficacy of predictive models using logistic regression and machine learning, interpreting them with SHAP values and analyzing key variable interactions. This offers a scientific basis for assessing preoperative heart failure risk in older adults with hypertension and hip fractures, providing significant guidance for individualized treatment strategies and underscoring the value of applying machine learning in clinical settings.

Flood impact assessment in remote areas using machine learning, SAR, and GIS: a case study of Ngabang District, Indonesia

ABSTRACT Flooding in remote regions presents significant challenges due to data scarcity, complicating impact assessment and mitigation efforts. This research delineates an integrated methodology for quantifying flood impacts in such contexts. By leveraging machine-learning algorithms, Sentinel-1 synthetic aperture radar (SAR) imagery was combined with digital elevation model data and river proximity metrics to predict and accurately demarcate flood extents. Geographic information systems overlay techniques were then employed for spatial analysis of the floods’ impacts on population and infrastructural assets. The methodology was applied in a case study in Ngabang District, Indonesia, demonstrating its utility. Analysis using decision tree, random forest (RF), and gradient boosting machine models provided critical insights into flood prediction factors. The RF model was chosen as the best, successfully identified flood-prone regions, achieving an accuracy of 0.94 and a Kappa of 0.87 on the testing data, demonstrating its robustness. The flood map showed significant impacts, affecting 373.81 hectares, 10,706 people, 1,500 buildings, and 15 km of roads. This study highlights the importance of proximity, elevation, SAR imagery, and iterative model improvements in flood prediction, offering valuable insights for flood management and mitigation efforts in data-scarce regions.

Preoperative prediction of post hepatectomy liver failure after surgery for hepatocellular carcinoma on CT-scan by machine learning and radiomics analyses.

No instruments are available to predict preoperatively the risk of posthepatectomy liver failure (PHLF) in HCC patients. The aim was to predict the occurrence of PHLF preoperatively by radiomics and clinical data through machine-learning algorithms. Clinical data and 3-phases CT scans were retrospectively collected among 13 Italian centres between 2008 and 2022. Radiomics features were extracted in the non-tumoral liver area. Data were split between training(70%) and test(30%) sets. An oversampling was run(ADASYN) in the training set. Random-Forest(RF), extreme gradient boosting (XGB) and support vector machine (SVM) models were fitted to predict PHLF. Final evaluation of the metrics was run in the test set. The best models were included in an averaging ensemble model (AEM). Five-hundred consecutive preoperative CT scans were collected with the relative clinical data. Of them, 17 (3.4%) experienced a PHLF. Two-hundred sixteen radiomics features per patient were extracted. PCA selected 19 dimensions explaining >75% of the variance. Associated clinical variables were: size, macrovascular invasion, cirrhosis, major resection and MELD score. Data were split in training cohort (70%, n=351) and a test cohort (30%, n=149). The RF model obtained an AUC=89.1%(Spec.=70.1%, Sens.=100%, accuracy=71.1%, PPV=10.4%, NPV=100%). The XGB model showed an AUC=89.4%(Spec.=100%, Sens.=20.0%, Accuracy=97.3%, PPV=20%, NPV=97.3%). The AEM combined the XGB and RF model, obtaining an AUC=90.1%(Spec.=89.5%, Sens.=80.0%, accuracy=89.2%, PPV=21.0%, NPV=99.2%). The AEM obtained the best results in terms of discrimination and true positive identification. This could lead to better define patients fit or unfit for liver resection.

Leveraging Data Science Technology for Advancing Credit Risk Assessment

The evaluation of credit risk (CR) has become prominent in recent years, particularly among banks, as default rates are on the rise and economic insecurity remains persistent. Traditional credit scoring techniques oftentimes are inadequate and provide little means for risk estimation, necessitating the development of new models using data science methodologies. In this study, a novel Intelligent Dwarf Mongoose tuned Light Gradient Boosting Machine (IDM-LGBM) model that boosts the accuracy of CR and improves forecasting performance, is introduced. The Light Gradient Boosting Machine model's hyperparameters were optimized using the Intelligent Dwarf Mongoose technique, improving the model's predictive strength. The CR dataset was gathered from the Kaggle platform. The data is then pre-processed using Z-score normalization. To evaluate the efficiency of the suggested IDM-LGBM technique, which has been implemented employing a Python platform. Results show that the IDM-LGBM model performed significantly better than conventional methods in terms of recall (98.1%), accuracy (97.2%), F1-score (97.4%), and precision (96.5%). Subsequent studies could concentrate on addressing real-time data streams and enhancing models to respond to the changing credit environment.

Predictive performance of machine learning models for kidney complications following coronary interventions: a systematic review and meta-analysis.

Acute kidney injury (AKI) and contrast-induced nephropathy (CIN) are common complications following percutaneous coronary intervention (PCI) or coronary angiography (CAG), presenting significant clinical challenges. Machine learning (ML) models offer promise for improving patient outcomes through early detection and intervention strategies. A comprehensive literature search following PRISMA guidelines was conducted in PubMed, Scopus, and Embase from inception to June 11, 2024. Study characteristics, ML models, performance metrics (AUC, accuracy, sensitivity, specificity, precision), and risk-of-bias assessment using the PROBAST tool were extracted. Statistical analysis used a random-effects model to pool AUC values, with heterogeneity assessed via the I2 statistic. From 431 initial studies, 14 met the inclusion criteria. Gradient Boosting Machine (GBM) and Support Vector Machine (SVM) models showed the highest pooled AUCs of 0.87 (95% CI: 0.82-0.92) and 0.85 (95% CI: 0.80-0.90), respectively, with low heterogeneity (I2 < 30%). Random Forest (RF) had a similar AUC of 0.85 (95% CI: 0.78-0.92) but significant heterogeneity (I2 > 90%). Multilayer perceptron (MLP) and XGBoost models had moderate pooled AUCs of 0.79 (95% CI: 0.74-0.84) with high heterogeneity. RF showed strong accuracy (0.83, 95% CI: 0.70-0.96), while SVM had balanced sensitivity (0.69, 95% CI: 0.63-0.75) and specificity (0.73, 95% CI: 0.60-0.86). Age, serum creatinine, left ventricular ejection fraction, and hemoglobin consistently influenced model efficacy. GBM and SVM models, with robust AUCs and low heterogeneity, are effective in predicting AKI and CIN post-PCI/CAG. RF, MLP, and XGBoost, despite competitive AUCs, showed considerable heterogeneity, emphasizing the need for further validation.

Enhancing wind erosion risk assessment through remote sensing techniques.

Preventing wind erosion and dust storms has always been a major concern in arid and semi-arid areas because of their negative effects on the environment. This study aims to utilize remote sensing and machine learning techniques to model, monitor, and predict the risk of wind erosion in Northeast Iran. Through an examination of relevant studies, a comprehensive review was conducted, leading to the identification of eight remote sensing indicators that exhibited the highest correlation with field data. These indicators were subsequently employed to model the risk of wind erosion in the study area. Various methods including Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting Machine (GBM), and Generalized Linear Models (GLM) were employed to carry out the modeling process. The final method utilized a weighted average of the model, and the SDM statistical package was used to combine different approaches to decrease uncertainty when modeling and monitoring wind erosion in the area. The modeling results indicated that in 2008, the RF model performed the best (AUC = 0.92, TSS = 0.82, and Kappa = 0.96), while in 2023, the GBM model showed superior performance (AUC = 0.95, TSS = 0.79, and Kappa = 0.95). Therefore, the utilization of an ensemble model emerged as an effective approach to reduce uncertainty during the modeling process. By employing the ensemble model, the outcomes obtained accurately depicted an elevated intensity of wind erosion in the northeastern regions of the study area by 2023. Furthermore, considering the climatic scenarios and projected land use changes, it is anticipated that wind erosion intensity will experience a 23% increase in the central and southern parts of the study area by 2038. By taking into account the reliable results of the ensemble model, which offers reduced uncertainty, it becomes feasible to implement effective planning, optimal management, and appropriate measures to mitigate the progression of wind erosion.

Machine learning identification of risk factors for ischaemic stroke in patients with heart failure with reduced ejection fraction but without atrial fibrillation: A report from WARCEF trial

Abstract Background The prediction of ischaemic stroke in patients with heart failure with reduced ejection fraction (HFrEF) but without atrial fibrillation (AF) remains challenging and risk stratification based clinical factors alone has limited discrimination. Our aim was to evaluate the performance of machine learning (ML) to identify risk factors for ischaemic stroke in such HFrEF patients. Methods We performed a post-hoc analysis of the WARCEF trial, only including patients without prior history of AF, and censoring those who developed incident AF during follow-up. We evaluated the performance of 9 ML models to identify risk factors for incident stroke, using metrics including area under the curve (AUC), precision, specificity, and decision curve analysis. The importance of each feature in constructing the model was quantified using SHapley Additive exPlanations (SHAP) values. Results We included 2,213 patients with HFrEF but without AF (mean age 59±12 years; 79% male). Of these, 74 (3.3%) had an ischaemic stroke during mean follow-up of 3.5±1.8 years. Out of the 29 patient-demographics variables, 12 were selected for the ML training. All ML models demonstrated high AUC values, outperforming the CHA2DS2-VASc score (Figure 1). The logistic regression model exhibited a slight deviation from this trend. The XGBoost model achieved an AUC of 0.86 (95% confidence interval [CI]: 0.72-0.99), while the Random Forest model showed an AUC of 0.85 (95% CI: 0.74-0.96). Similarly, the Support Vector Machine and Light Gradient Boosting Machine models recorded AUCs of 0.85 (95% CI: 0.72-0.97) and 0.83 (95% CI: 0.70-0.96), respectively. Each of these models attained precision and specificity scores of 1.0, indicating high performance. These models consistently provided significant net clinical benefits. Key risk factors for stroke identified across these models were creatinine clearance and blood urea nitrogen. The use of warfarin appears to be protective. Conclusions Machine-learning models can identify risk factors for ischaemic stroke in patients with HFrEF but without AF. Worsening renal failure was predictive of an incident stroke, while warfarin use was protective against stroke (Figure 2).Figure 1Figure 2

Interpreting the Epidemiological Characteristics of HIV-1 in Heterosexually Transmitted Population Based on Molecular Transmission Network in Kunming, Yunnan: A Retrospective Cohort Study.

Heterosexuals have become the most prevalent group of HIV-1 in Kunming, Yunnan Province. Utilizing the principle of genetic similarity between their gene sequences, we built a molecular transmission network by gathering data from earlier molecular epidemiological studies. This allowed us to analyze the epidemiological features of this group and offer fresh concepts and approaches for the prevention and management of HIV-1 epidemics. Cytoscope was used to visualize and characterize the network following the processing of the sample gene sequences by BioEdit and HyPhy. The number of possible links and the size of the clusters were investigated as influencing factors using a zero-inflated Poisson model and a logistic regression model, respectively. A scikit-learn-based prediction model was developed to account for the dynamic changes in the HIV-1 molecular network. Six noteworthy modular clusters with network scores ranging from 4 to 9 were found from 150 clusters using Molecular Complex Detection analysis at a standard genetic distance threshold of 0.01. The size of the number of possible links and the network's clustering rate were significantly impacted by sampling time, marital status, and CD4+ T lymphocytes (all p < 0.05). The gradient boosting machine (GBM) model had the highest area under the curve value, 0.884 ± 0.051, according to scikit-learn. Though not all cluster subtypes grew equally, the network clusters were relatively specific and aggregated. The largest local transmission-risk group for HIV-1CRF08_BC is now the heterosexual transmission population. The most suitable model for constructing the HIV-1 molecular network dynamics prediction model was found to be the GBM model.

Inertial measurement unit technology for gait detection: a comprehensive evaluation of gait traits in two Italian horse breeds.

The shift of the horse breeding sector from agricultural to leisure and sports purposes led to a decrease in local breeds' population size due to the loss of their original breeding purposes. Most of the Italian breeds must adapt to modern market demands, and gait traits are suitable phenotypes to help this process. Inertial measurement unit (IMU) technology can be used to objectively assess them. This work aims to investigate on IMU recorded data (i) the influence of environmental factors and biometric measurements, (ii) their repeatability, (iii) the correlation with judge evaluations, and (iv) their predictive value. The Equisense Motion S® was used to collect phenotypes on 135 horses, Bardigiano (101) and Murgese (34) and the data analysis was conducted using R (v.4.1.2). Analysis of variance (ANOVA) was employed to assess the effects of biometric measurements and environmental and animal factors on the traits. Variations in several traits depending on the breed were identified, highlighting different abilities among Bardigiano and Murgese horses. Repeatability of horse performance was assessed on a subset of horses, with regularity and elevation at walk being the traits with the highest repeatability (0.63 and 0.72). The positive correlation between judge evaluations and sensor data indicates judges' ability to evaluate overall gait quality. Three different algorithms were employed to predict the judges score from the IMU measurements: Support Vector Machine (SVM), Gradient Boosting Machine (GBM), and K-Nearest Neighbors (KNN). A high variability was observed in the accuracy of the SVM model, ranging from 55 to 100% while the other two models showed higher consistency, with accuracy ranging from 74 to 100% for the GBM and from 64 to 88% for the KNN. Overall, the GBM model exhibits the highest accuracy and the lowest error. In conclusion, integrating IMU technology into horse performance evaluation offers valuable insights, with implications for breeding and training.

Derivation of Analytical Equations for the Fundamental Period of Framed Structures Using Machine Learning and SHAP Values

The fundamental period is one of the most important parameters for the design of new structures as well as for estimating the capacity of existing ones. Thus, to estimate it, various design codes and researchers have adopted several approximate analytical equations based on a number of key structural parameters. To this end, the present study introduces a novel methodology for deriving the analytical equations for the fundamental period of reinforced concrete structures. The methodology is based on machine learning explainability techniques, specifically the so-called SHapley Additive exPlanations values. These values are commonly employed as an explainability tool. However, in the proposed novel approach they are employed as a basis to fit analytical curves, which allows the resulting equations to be constructed sequentially and in an informed manner while controlling the balance between accuracy and complexity. An extended dataset consisting of 4026 data points is employed, on which a Gradient Boosting Machine model is fitted. The model achieves excellent accuracy, with a coefficient of determination R2≈0.99, while the equations derived from the proposed formulation achieve an R2≈0.95 and Mean Absolute Error ≈0.12. This demonstrates the potential applicability of the proposed methodology in a wide array of similar engineering challenges.

Utility of Certain AI Models in Climate-Induced Disasters

To address the current challenge of climate change at the local and global levels, this article discusses a few important water resources engineering topics, such as estimating the energy dissipation of flowing waters over hilly areas through the provision of regulated stepped channels, predicting the removal of silt deposition in the irrigation canal, and predicting groundwater level. Artificial intelligence (AI) in water resource engineering is now one of the most active study topics. As a result, multiple AI tools such as Random Forest (RF), Random Tree (RT), M5P (M5 model trees), M5Rules, Feed-Forward Neural Networks (FFNNs), Gradient Boosting Machine (GBM), Adaptive Boosting (AdaBoost), and Support Vector Machines kernel-based model (SVM-Pearson VII Universal Kernel, Radial Basis Function) are tested in the present study using various combinations of datasets. However, in various circumstances, including predicting energy dissipation of stepped channels and silt deposition in rivers, AI techniques outperformed the traditional approach in the literature. Out of all the models, the GBM model performed better than other AI tools in both the field of energy dissipation of stepped channels with a coefficient of determination (R2) of 0.998, root mean square error (RMSE) of 0.00182, and mean absolute error (MAE) of 0.0016 and sediment trapping efficiency of vortex tube ejector with an R2 of 0.997, RMSE of 0.769, and MAE of 0.531 during testing. On the other hand, the AI technique could not adequately understand the diversity in groundwater level datasets using field data from various stations. According to the current study, the AI tool works well in some fields of water resource engineering, but it has difficulty in other domains in capturing the diversity of datasets.

A robust LightGBM model for concrete tensile strength forecast to aid in resilience-based structure strategies

The tensile strength (TS) of concrete is a factor in the design of civil engineering structures. Traditional methods for assessing concrete TS have notable limitations, leading to the emergence of non-destructive testing (NDT) as an innovative alternative. This study introduces a novel, optimized approach for accurate, non-destructive TS prediction by integrating Gradio, Bayesian optimization (BO), and Shapley additive explanations (SHAP). The input parameters for the model were ultrasonic pulse velocity (UPV) and electrical resistivity (ER). Using a comprehensive dataset of 3460 datapoints, a light gradient-boosting machine (LightGBM) model was developed. Through extensive hyperparameter tuning facilitated by BO, the model achieved a robust prediction accuracy of approximately 98 %. The novel application of SHAP in this study provided deep insights into model behavior, confirming UPV as the most critical variable for TS prediction. The deployment of the model using Gradio further enhances its accessibility and usability. This combined methodology not only advances the application of machine learning (ML) in civil engineering but also offers a powerful, globally applicable tool for accurately forecasting concrete TS. This supports resilience-based management strategies, essential for the sustainable development of infrastructure. The study's novel integration of BO for optimization and SHAP for interpretability marks a significant step forward in the precise prediction of TS, offering practical benefits for both researchers and industry professionals.

Development and Validation of a Nocturnal Hypoglycaemia Risk Model for Patients With Type 2 Diabetes Mellitus.

To develop and test different machine learning algorithms for predicting nocturnal hypoglycaemia in patients with type 2 diabetes mellitus. A retrospective study. We collected data from dynamic blood glucose monitoring of patients with T2DM admitted to the Department of Endocrinology and Metabolism at a hospital in Shanghai, China, from November 2020 to January 2022. Patients undergone the continuous glucose monitoring (CGM) for ≥ 24 h were included in this study. Logistic regression, random forest and light gradient boosting machine algorithms were employed, and the models were validated and compared using AUC, accuracy, specificity, recall rate, precision, F1 score and the Kolmogorov-Smirnov test. A total of 4015 continuous glucose-monitoring data points from 440 patients were included, and 28 variables were selected to build the risk prediction model. The 440 patients had an average age of 62.7 years. Approximately 48.2% of the patients were female and 51.8% were male. Nocturnal hypoglycaemia appeared in 573 (14.30%) of 4015 continuous glucose monitoring data. The light gradient boosting machine model demonstrated the highest predictive performances: AUC (0.869), specificity (0.802), accuracy (0.801), precision (0.409), recall rate (0.797), F1 score (0.255) and Kolmogorov (0.603). The selected predictive factors included time below the target glucose range, duration of diabetes, insulin use before bed and dynamic blood glucose monitoring parameters from the previous day. No Patient or Public Contribution.

Neural decoding and feature selection methods for closed-loop control of avoidance behavior

Objective.Many psychiatric disorders involve excessive avoidant or defensive behavior, such as avoidance in anxiety and trauma disorders or defensive rituals in obsessive-compulsive disorders. Developing algorithms to predict these behaviors from local field potentials (LFPs) could serve as the foundational technology for closed-loop control of such disorders. A significant challenge is identifying the LFP features that encode these defensive behaviors.Approach.We analyzed LFP signals from the infralimbic cortex and basolateral amygdala of rats undergoing tone-shock conditioning and extinction, standard for investigating defensive behaviors. We utilized a comprehensive set of neuro-markers across spectral, temporal, and connectivity domains, employing SHapley Additive exPlanations for feature importance evaluation within Light Gradient-Boosting Machine models. Our goal was to decode three commonly studied avoidance/defensive behaviors: freezing, bar-press suppression, and motion (accelerometry), examining the impact of different features on decoding performance.Main results.Band power and band power ratio between channels emerged as optimal features across sessions. High-gamma (80-150 Hz) power, power ratios, and inter-regional correlations were more informative than other bands that are more classically linked to defensive behaviors. Focusing on highly informative features enhanced performance. Across 4 recording sessions with 16 subjects, we achieved an average coefficient of determination of 0.5357 and 0.3476, and Pearson correlation coefficients of 0.7579 and 0.6092 for accelerometry jerk and bar press rate, respectively. Utilizing only the most informative features revealed differential encoding between accelerometry and bar press rate, with the former primarily through local spectral power and the latter via inter-regional connectivity. Our methodology demonstrated remarkably low training/inference time and memory usage, requiring<310 ms for training,<0.051 ms for inference, and 16.6 kB of memory, using a single core of AMD Ryzen Threadripper PRO 5995WX CPU.Significance.Our results demonstrate the feasibility of accurately decoding defensive behaviors with minimal latency, using LFP features from neural circuits strongly linked to these behaviors. This methodology holds promise for real-time decoding to identify physiological targets in closed-loop psychiatric neuromodulation.

Polynomial-SHAP analysis of liver disease markers for capturing of complex feature interactions in machine learning models

Liver disease diagnosis is pivotal for effective patient management, and machine learning techniques have shown promise in this domain. In this study, we investigate the impact of Polynomial-SHapley Additive exPlanations analysis on enhancing the performance and interpretability of machine learning models for liver disease classification. Our results demonstrate significant improvements in accuracy, precision, recall, F1_score, and Matthews correlation coefficient across various algorithms when polynomial- SHapley Additive exPlanations analysis is applied. Specifically, the Light Gradient Boosting Machine model achieves exceptional performance with 100 % accuracy in both scenarios. Furthermore, by comparing the results obtained with and without the approach, we observe substantial differences in the performance, highlighting the importance of incorporating Polynomial-SHapley Additive exPlanations analysis for improved model performance. The Polynomial features and SHapley Additive exPlanations values also enhance the interpretability of machine learning models by capturing complex feature interactions, enabling users to gain deeper insights into the underlying mechanisms driving the diagnosis. Moreover, data rebalancing using Synthetic Minority Over-sampling Technique and parameter tuning were employed to optimize the performance of the models. These findings underscore the significance of employing this analytical approach in machine-learning-based diagnostic systems for liver diseases, offering superior performance and enhanced interpretability for informed decision-making in clinical practice.

Boosting efficiency in a clinical literature surveillance system with LightGBM.

Given the suboptimal performance of Boolean searching to identify methodologically sound and clinically relevant studies in large bibliographic databases, exploring machine learning (ML) to efficiently classify studies is warranted. To boost the efficiency of a literature surveillance program, we used a large internationally recognized dataset of articles tagged for methodological rigor and applied an automated ML approach to train and test binary classification models to predict the probability of clinical research articles being of high methodologic quality. We trained over 12,000 models on a dataset of titles and abstracts of 97,805 articles indexed in PubMed from 2012-2018 which were manually appraised for rigor by highly trained research associates and rated for clinical relevancy by practicing clinicians. As the dataset is unbalanced, with more articles that do not meet the criteria for rigor, we used the unbalanced dataset and over- and under-sampled datasets. Models that maintained sensitivity for high rigor at 99% and maximized specificity were selected and tested in a retrospective set of 30,424 articles from 2020 and validated prospectively in a blinded study of 5253 articles. The final selected algorithm, combining a LightGBM (gradient boosting machine) model trained in each dataset, maintained high sensitivity and achieved 57% specificity in the retrospective validation test and 53% in the prospective study. The number of articles needed to read to find one that met appraisal criteria was 3.68 (95% CI 3.52 to 3.85) in the prospective study, compared with 4.63 (95% CI 4.50 to 4.77) when relying only on Boolean searching. Gradient-boosting ML models reduced the work required to classify high quality clinical research studies by 45%, improving the efficiency of literature surveillance and subsequent dissemination to clinicians and other evidence users.

Personalized Prediction of Long-Term Renal Function Prognosis Following Nephrectomy Using Interpretable Machine Learning Algorithms: Case-Control Study.

Acute kidney injury (AKI) is a common adverse outcome following nephrectomy. The progression from AKI to acute kidney disease (AKD) and subsequently to chronic kidney disease (CKD) remains a concern; yet, the predictive mechanisms for these transitions are not fully understood. Interpretable machine learning (ML) models offer insights into how clinical features influence long-term renal function outcomes after nephrectomy, providing a more precise framework for identifying patients at risk and supporting improved clinical decision-making processes. This study aimed to (1) evaluate postnephrectomy rates of AKI, AKD, and CKD, analyzing long-term renal outcomes along different trajectories; (2) interpret AKD and CKD models using Shapley Additive Explanations values and Local Interpretable Model-Agnostic Explanations algorithm; and (3) develop a web-based tool for estimating AKD or CKD risk after nephrectomy. We conducted a retrospective cohort study involving patients who underwent nephrectomy between July 2012 and June 2019. Patient data were randomly split into training, validation, and test sets, maintaining a ratio of 76.5:8.5:15. Eight ML algorithms were used to construct predictive models for postoperative AKD and CKD. The performance of the best-performing models was assessed using various metrics. We used various Shapley Additive Explanations plots and Local Interpretable Model-Agnostic Explanations bar plots to interpret the model and generated directed acyclic graphs to explore the potential causal relationships between features. Additionally, we developed a web-based prediction tool using the top 10 features for AKD prediction and the top 5 features for CKD prediction. The study cohort comprised 1559 patients. Incidence rates for AKI, AKD, and CKD were 21.7% (n=330), 15.3% (n=238), and 10.6% (n=165), respectively. Among the evaluated ML models, the Light Gradient-Boosting Machine (LightGBM) model demonstrated superior performance, with an area under the receiver operating characteristic curve of 0.97 for AKD prediction and 0.96 for CKD prediction. Performance metrics and plots highlighted the model's competence in discrimination, calibration, and clinical applicability. Operative duration, hemoglobin, blood loss, urine protein, and hematocrit were identified as the top 5 features associated with predicted AKD. Baseline estimated glomerular filtration rate, pathology, trajectories of renal function, age, and total bilirubin were the top 5 features associated with predicted CKD. Additionally, we developed a web application using the LightGBM model to estimate AKD and CKD risks. An interpretable ML model effectively elucidated its decision-making process in identifying patients at risk of AKD and CKD following nephrectomy by enumerating critical features. The web-based calculator, found on the LightGBM model, can assist in formulating more personalized and evidence-based clinical strategies.

Improving soil moisture prediction with deep learning and machine learning models

Reliable soil moisture (SM) data is critical for effective water resources management, yet its accurate measurement and prediction remain challenging. This study was conducted to develop a deep learning regression network for sub-hourly SM prediction and compare its performance with traditional machine learning models, including the eXtreme gradient boosting (XGB), light gradient-boosting (LGB), cat boosting (CB), random forest (RF), k-nearest neighbors (kNN), and long short-term memory (LSTM) models. Sub-hourly SM, electrical conductivity (EC), soil temperature (ST), and weather parameters were collected during research experiments conducted for two years (2020–2021 and 2021–2022) at the Tropical Research and Education Center (TREC), University of Florida. A network of SM sensors and a weather station were installed at the experimental site with 24 plots of green beans and sweet corn under full and three deficit irrigation treatments with three replications. Model performance metrics such as coefficient of determination (r2) and global performance indicator (GPI) were used to evaluate the performance of the models. Results showed that all MLs and DL models performed more than satisfactorily in simulating SM of green beans and sweet corn plots. The testing average r2 and GPI of MLs were 0.83 and 0.02 (green beans) and 0.85 and 0.02 (sweet corn). However, XGB and LGB models outperformed the remaining ML and DL models. The testing r2 and GPI of XGB were 0.86 and 0.014 for green beans, whereas 0.88 and 0.015 for sweet corn. The r2 and GPI values for the LGB were 0.85 and 0.014 for green beans, while 0.88 and 0.015 for sweet corn. Even though DL model took longer and resources to be trained, its performance was not as accurate as that of XGB and LGB models. However, the performance of DL was better than the LSTM model. The r2 and RMSE of the LSTM model were 0.68 and 0.02cm 3 cm-3 for green beans and 0.75 and 0.02cm 3 cm-3 for sweet corn, respectively. Whereas the r2 and RMSE of DL were 0.84 and 0.015cm 3 cm-3 (green beans) and 0.85 and 0.02 cm 3 cm-3 (sweet corn). The ML and DL models performed better in simulating SM of sweet corn plots than green beans. Overall, these results confirmed that the ML and DL models could be alternative tools for SM prediction for agricultural fields, with potential applications for irrigation scheduling and water resources management.