Machine Learning-based Prediction Model Research Articles

Machine learning-based prediction model of lower extremity deep vein thrombosis after stroke.

This study aimed to apply machine learning (ML) techniques to develop and validate a risk prediction model for post-stroke lower extremity deep vein thrombosis (DVT) based on patients' limb function, activities of daily living (ADL), clinical laboratory indicators, and DVT preventive measures. We retrospectively analyzed 620 stroke patients. Eight ML models-logistic regression (LR), support vector machine (SVM), random forest (RF), decision tree (DT), neural network (NN), extreme gradient boosting (XGBoost), Bayesian (NB), and K-nearest neighbor (KNN)-were used to build the model. These models were extensively evaluated using ROC curves, AUC, PR curves, PRAUC, accuracy, sensitivity, specificity, and clinical decision curves (DCA). Shapley's additive explanation (SHAP) was used to determine feature importance. Finally, based on the optimal ML algorithm, different functional feature set models were compared with the Padua scale to select the best feature set model. Our results indicated that the RF algorithm demonstrated superior performance in various evaluation metrics, including AUC (0.74/0.73), PRAUC (0.58/0.58), accuracy (0.75/0.77), and sensitivity (0.78/0.80) in both the training set and test set. DCA analysis revealed that the RF model had the highest clinical net benefit. SHAP analysis showed that D-dimer had the most significant influence on DVT, followed by age, Brunnstrom stage (lower limb), prothrombin time (PT), and mobility ability. The RF algorithm can predict post-stroke DVT to guide clinical practice.

Strategic data augmentation with CTGAN for smart manufacturing: Enhancing ML predictions of paper breaks in pulp-and-paper production

This article addresses the significant challenge posed by the rare occurrence of paper breaks in the pulp-and-paper industry, which, despite their infrequency during production, have considerable economic consequences. We analyze operational data from a paper manufacturing machine, focusing on the rare instances of paper breaks (124 out of 18,398 cases) identified through a quality assurance protocol. This scarcity presents a challenge for machine learning-based predictive models. To overcome this, we introduce a novel data augmentation strategy using Conditional Generative Adversarial Networks (CTGAN) and Synthetic Minority Oversampling Technique (SMOTE), aimed at generating synthetic data that not only reflects the real operational data’s distribution but also improves the predictive models’ performance metrics. We assess the impact of this data augmentation on three machine learning algorithms—Decision Trees (DT), Random Forest (RF), and Logistic Regression (LR)—both before and after augmentation. The use of a CTGAN-enhanced dataset led to notable enhancements in predictive maintenance metrics. Specifically, the ability of the models to detect machine breaks (Class 1) increased significantly: over 30% for Decision Trees, 20% for Random Forest, and nearly 90% for Logistic Regression. This methodological progress offers valuable contributions to the fields of industrial quality control and maintenance scheduling by improving the prediction of rare events in manufacturing processes.

Early recurrence as a pivotal event in nasopharyngeal carcinoma: identifying predictors and key molecular signals for survivors

PurposeThe duration of response to treatment is a significant prognostic indicator, with early recurrence (ER) often predicting poorer survival outcomes in nasopharyngeal carcinoma (NPC) survivors. This study seeks to elucidate the factors contributing to the onset of ER following radiotherapy in NPC survivors.MethodsThis investigation encompassed 2,789 newly diagnosed NPC patients who underwent radical intensity-modulated radiotherapy. Ordinal logistic regression analysis was employed to evaluate the independent predictors of earlier recurrence. A machine learning-based prediction model of NPC recurrence patterns was developed. Tumorous RNA-sequencing (in-house cohort: N = 192) and biological tipping point analysis were utilized to infer potential molecular mechanisms associated with ER.ResultsOur results demonstrated that ER within 24 months post-initial treatment was the optimal time frame for identifying early malignant progression in NPC survivors. The ER cohort (150 of 2,789, 5.38%) exhibited a notably short median overall survival of 48.6 months. Multivariate analyses revealed that male gender, T4 stage, local or regional residual disease, detectable pre- and post-radiotherapy EBV DNA, and the absence of induction chemotherapy were significant predictors of earlier recurrence. The machine learning-based predictive model further underscored the importance of tumor-related factors in NPC recurrence. Moreover, ER emerged as a pivotal stage in NPC progression, with 15 critical transition signals identified potentially associated with the negative modulation of the immune response.ConclusionsOur comprehensive analysis of NPC recurrence patterns has unveiled insights into the key factors driving ER and provided novel insights into potential early warning biomarkers and the mechanisms underlying NPC progression.

A data-driven approach for predicting cash flow performance of public owners in building projects: insights from Turkish cases

PurposeThe cash flow from government agencies to contractors, called progress payment, is a critical step in public projects. The delays in progress payments significantly affect the project performance of contractors and lead to conflicts between two parties in the Turkish construction industry. Although some previous studies focused on the issues in internal cash flows (e.g. inflows and outflows) of construction companies, the context of cash flows from public agencies to contractors in public projects is still unclear. Therefore, the primary objective of this study is to develop and test diverse machine learning-based predictive models on the progress payment performance of Turkish public agencies and improve the predictive performance of these models with two different optimization algorithms (e.g. first-order and second-order). In addition, this study explored the attributes that make the most significant contribution to predicting the payment performance of Turkish public agencies.Design/methodology/approachIn total, project information of 2,319 building projects tendered by the Turkish public agencies was collected. Six different machine learning algorithms were developed and two different optimization methods were applied to achieve the best machine learning (ML) model for Turkish public agencies' cash flow performance in this study. The current research tested the effectiveness of each optimization algorithm for each ML model developed. In addition, the effect size achieved in the ML models was evaluated and ranked for each attribute, so that it is possible to observe which attributes make significant contributions to predicting the cash flow performance of Turkish public agencies.FindingsThe results show that the attributes “inflation rate” (F5; 11.2%), “consumer price index” (F6; 10.55%) and “total project duration” (T1; 10.9%) are the most significant factors affecting the progress payment performance of government agencies. While decision tree (DT) shows the best performance among ML models before optimization process, the prediction performance of models support vector machine (SVM) and genetic algorithm (GA) has been significantly improved by Broyden–Fletcher–Goldfarb–Shanno (BFGS)-based Quasi-Newton optimization algorithm by 14.3% and 18.65%, respectively, based on accuracy, AUROC (Area Under the Receiver Operating Characteristics) and F1 values.Practical implicationsThe most effective ML model can be used and integrated into proactive systems in real Turkish public construction projects, which provides management of cash flow issues from public agencies to contractors and reduces conflicts between two parties.Originality/valueThe development and comparison of various predictive ML models on the progress payment performance of Turkish public owners in construction projects will be the first empirical attempt in the body of knowledge. This study has been carried out by using a high number of project information with diverse 27 attributes, which distinguishes this study in the body of knowledge. For the optimization process, a new hyper parameter tuning strategy, the Bayesian technique, was adopted for two different optimization methods. Thus, it is available to find the best predictive model to be integrated into real proactive systems in forecasting the cash flow performance of Turkish public agencies in public works projects. This study will also make novel contributions to the body of knowledge in understanding the key parameters that have a negative impact on the payment progress of public agencies.

An integrated machine learning model enhances delayed graft function prediction in pediatric renal transplantation from deceased donors

BackgroundKidney transplantation is the optimal renal replacement therapy for children with end-stage renal disease; however, delayed graft function (DGF), a common post-operative complication, may negatively impact the long-term outcomes of both the graft and the pediatric recipient. However, there is limited research on DGF in pediatric kidney transplant recipients. This study aims to develop a predictive model for the risk of DGF occurrence after pediatric kidney transplantation by integrating donor and recipient characteristics and utilizing machine learning algorithms, ultimately providing guidance for clinical decision-making.MethodsThis single-center retrospective cohort study includes all recipients under 18 years of age who underwent single-donor kidney transplantation at our hospital between 2016 and 2023, along with their corresponding donors. Demographic, clinical, and laboratory examination data were collected from both donors and recipients. Univariate logistic regression models and differential analysis were employed to identify features associated with DGF. Subsequently, a risk score for predicting DGF occurrence (DGF-RS) was constructed based on machine learning combinations. Model performance was evaluated using the receiver operating characteristic curves, decision curve analysis (DCA), and other methods.ResultsThe study included a total of 140 pediatric kidney transplant recipients, among whom 37 (26.4%) developed DGF. Univariate analysis revealed that high-density lipoprotein cholesterol (HDLC), donor after circulatory death (DCD), warm ischemia time (WIT), cold ischemia time (CIT), gender match, and donor creatinine were significantly associated with DGF (P < 0.05). Based on these six features, the random forest model (mtry = 5, 75%p) exhibited the best predictive performance among 97 machine learning models, with the area under the curve values reaching 0.983, 1, and 0.905 for the entire cohort, training set, and validation set, respectively. This model significantly outperformed single indicators. The DCA curve confirmed the clinical utility of this model.ConclusionsIn this study, we developed a machine learning-based predictive model for DGF following pediatric kidney transplantation, termed DGF-RS, which integrates both donor and recipient characteristics. The model demonstrated excellent predictive accuracy and provides essential guidance for clinical decision-making. These findings contribute to our understanding of the pathogenesis of DGF.

Conventional machine learning-based prediction models did not outperform the International IgA Nephropathy Prediction Tool.

Immunoglobulin A nephropathy (IgAN) is a major cause of end-stage kidney disease (ESKD). The International IgA Nephropathy Prediction Tool (IIgAN-PT) predicts IgAN prognosis, but improvement in the prediction performance using machine learning (ML)-based methods is needed. We analyzed 4,425 biopsy-confirmed patients with IgAN and ≥6 months of follow-up from nine tertiary university hospitals in Korea. The study population was divided into development and validation cohorts. Using the collected 87 clinicodemographic and pathological variables, ML-based prediction models for ESKD or estimated glomerular filtration rate were constructed: 1) the conventional CatBoost model, 2) the optimized CatBoost model with Cox proportional hazards, 3) the deep Cox proportional hazards model, and 4) the deep Cox mixture model. The area under the curve (AUC) and calibration plots were used to investigate the discriminative and calibration performance of the models, which were then compared with those of the IIgAN-PT full model. The full model showed excellent performance (AUC [95% confidence interval] for 5-year outcome, 0.896 [0.8530.940]), with acceptable calibration results. The ML-based models showed good performance in predicting adverse kidney outcomes and revealed acceptable discrimination performance in the external validation (AUC [95% confidence interval] for the 5-year outcome: 1) 0.829 [0.791-0.866]; 2) 0.847 [0.804-0.890]; 3) 0.823 [0.784-0.862]; and 4) 0.832 [0.794-0.870]), although they underestimated the external validation cohort risks. With the validation data, the overall performance of the IIgAN-PT was non-inferior to that of the ML-based model. Conclusions: Our ML-based models showed good performance in predicting adverse kidney outcomes in patients with IgAN but they did not outperform the IIgAN-PT.

Machine learning models for mortality prediction in critically ill patients with acute pancreatitis-associated acute kidney injury.

The occurrence of acute kidney injury (AKI) was associated with an increased mortality rate among acute pancreatitis (AP) patients, indicating the importance of accurately predicting the mortality rate of critically ill patients with acute pancreatitis-associated acute kidney injury (AP-AKI) at an early stage. This study aimed to develop and validate machine learning-based predictive models for in-hospital mortality rate in critically ill patients with AP-AKI by comparing their performance with the traditional logistic regression (LR) model. This study used data from three clinical databases. The predictors were identified by the Recursive Feature Elimination algorithm. The LR and two machine learning models-random forest (RF) and eXtreme Gradient Boosting (XGBoost)-were developed using 10-fold cross-validation to predict in-hospital mortality rate in AP-AKI patients. A total of 1089 patients from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) and eICU Collaborative Research Database (eICU-CRD) were included in the training set and 176 patients from Xiangya Hospital were included in the external validation set. The in-hospital mortality rates of the training and external validation sets were 13.77% and 54.55%, respectively. Compared with the area under the curve (AUC) values of the LR model and the RF model, the AUC value of the XGBoost model {0.941 [95% confidence interval (CI) 0.931-0.952]} was significantly higher (both P<.001) and the XGBoost model had the smallest Brier score of 0.039 in the training set. In the external validation set, the performance of the XGBoost model was acceptable, with an AUC value of 0.724 (95% CI 0.648-0.800). However, it did not differ significantly from the LR and RF models. The XGBoost model was superior to the LR and RF models in terms of both the discrimination and calibration in the training set. Whether the findings can be generalized needs to be further validated.

Predicting superagers: a machine learning approach utilizing gut microbiome features.

Cognitive decline is often considered an inevitable aspect of aging; however, recent research has identified a subset of older adults known as "superagers" who maintain cognitive abilities comparable to those of younger individuals. Investigating the neurobiological characteristics associated with superior cognitive function in superagers is essential for understanding "successful aging." Evidence suggests that the gut microbiome plays a key role in brain function, forming a bidirectional communication network known as the microbiome-gut-brain axis. Alterations in the gut microbiome have been linked to cognitive aging markers such as oxidative stress and inflammation. This study aims to investigate the unique patterns of the gut microbiome in superagers and to develop machine learning-based predictive models to differentiate superagers from typical agers. We recruited 161 cognitively unimpaired, community-dwelling volunteers aged 60 years or from dementia prevention centers in Seoul, South Korea. After applying inclusion and exclusion criteria, 115 participants were included in the study. Following the removal of microbiome data outliers, 102 participants, comprising 57 superagers and 45 typical agers, were finally analyzed. Superagers were defined based on memory performance at or above average normative values of middle-aged adults. Gut microbiome data were collected from stool samples, and microbial DNA was extracted and sequenced. Relative abundances of bacterial genera were used as features for model development. We employed the LightGBM algorithm to build predictive models and utilized SHAP analysis for feature importance and interpretability. The predictive model achieved an AUC of 0.832 and accuracy of 0.764 in the training dataset, and an AUC of 0.861 and accuracy of 0.762 in the test dataset. Significant microbiome features for distinguishing superagers included Alistipes, PAC001137_g, PAC001138_g, Leuconostoc, and PAC001115_g. SHAP analysis revealed that higher abundances of certain genera, such as PAC001138_g and PAC001115_g, positively influenced the likelihood of being classified as superagers. Our findings demonstrate the machine learning-based predictive models using gut-microbiome features can differentiate superagers from typical agers with a reasonable performance.

Physics-Based vs Data-Driven 24-Hour Probabilistic Forecasts of Precipitation for Northern Tropical Africa

Abstract Numerical weather prediction (NWP) models struggle to skillfully predict tropical precipitation occurrence and amount, calling for alternative approaches. For instance, it has been shown that fairly simple, purely data-driven logistic regression models for 24-h precipitation occurrence outperform both climatological and NWP forecasts for the West African summer monsoon. More complex neural network–based approaches, however, remain underdeveloped due to the non-Gaussian character of precipitation. In this study, we develop, apply, and evaluate a novel two-stage approach, where we train a U-Net convolutional neural network (CNN) model on gridded rainfall data to obtain a deterministic forecast and then apply the recently developed, nonparametric Easy Uncertainty Quantification (EasyUQ) approach to convert it into a probabilistic forecast. We evaluate CNN+EasyUQ for 1-day-ahead 24-h accumulated precipitation forecasts over northern tropical Africa for 2011–19, with the Integrated Multi-satellitE Retrievals for GPM (IMERG) data serving as ground truth. In the most comprehensive assessment to date, we compare CNN+EasyUQ to state-of-the-art physics-based and data-driven approaches such as monthly probabilistic climatology, raw and postprocessed ensemble forecasts from the European Centre for Medium-Range Weather Forecasts (ECMWF), and traditional statistical approaches that use up to 25 predictor variables from IMERG and the ERA5 reanalysis. Generally, statistical approaches perform about on par with postprocessed ECMWF ensemble forecasts. The CNN+EasyUQ approach, however, clearly outperforms all competitors in terms of both occurrence and amount. Hybrid methods that merge CNN+EasyUQ and physics-based forecasts show slight further improvement. Thus, the CNN+EasyUQ approach can likely improve operational probabilistic forecasts of rainfall in the tropics and potentially even beyond. Significance Statement Precipitation forecasts in the tropics remain a great challenge despite their enormous potential to create socioeconomic benefits in sectors such as food and energy production. Here, we develop a purely data-driven, machine learning–based prediction model that outperforms traditional, physics-based approaches to 1-day-ahead forecasts of rainfall occurrence and rainfall amount over northern tropical Africa in terms of both forecast skill and computational costs. A combined data-driven and physics-based (hybrid) approach yields further (slight) improvement in terms of forecast skill. These results suggest new avenues to more accurate and more resource-efficient operational precipitation forecasts in the Global South.

Integrating StEP-COMPAC definition and enhanced recovery after surgery status in a machine-learning-based model for postoperative pulmonary complications in laparoscopic hepatectomy

BackgroundPostoperative pulmonary complications (PPCs) contribute to high mortality rates and impose significant financial burdens. In this study, a machine learning-based prediction model was developed to identify patients at high risk of developing PPCs following laparoscopic hepatectomy. MethodsData were collected from 1022 adult patients who underwent laparoscopic hepatectomy at two centres between January 2015 and February 2021. The dataset was divided into a development set and a temporal external validation set based on the year of surgery. A total of 42 factors were extracted for pre-modelling, including the implementation status of Enhanced Recovery after Surgery (ERAS). Feature selection was performed using the least absolute shrinkage and selection operator (LASSO) method. Model performance was assessed using the area under the receiver operating characteristic curve (AUC). The model with the best performance was externally validated using temporal data. ResultsThe incidence of PPCs was 8.7%. Lambda.1se was selected as the optimal lambda for LASSO feature selection. For implementation of ERAS, serum gamma-glutamyl transferase levels, malignant tumour presence, total bilirubin levels, and age-adjusted Charleston Comorbidities Index were the selected factors. Seven models were developed. Among them, logistic regression demonstrated the best performance, with an AUC of 0.745 in the internal validation set and 0.680 in the temporal external validation set. ConclusionsBased on the most recent definition, a machine learning model was employed to predict the risk of PPCs following laparoscopic hepatectomy. Logistic regression was identified as the best-performing model. ERAS implementation was associated with a reduction in the number of PPCs.

Impact of a machine learning–based prediction model on annual surveillance endoscopy costs for detecting gastric cancer

Background and AimsIn this study, we assessed our machine learning (ML)-based model's impact on reducing annual surveillance endoscopy costs for detecting gastric cancer (GC). MethodsAnalyzing 1099 patients with chronic gastritis undergoing annual esophagogastroduodenoscopy (EGD), we randomly divided them into training and test sets (4:1). Using gradient boosting decision trees and incorporating patient characteristics, the ML model was developed. In the test sets, we compared the EGD number needed to screen (NNS) one GC, the cost, and the GC detection rate across different risk stratification strategies. ResultsThe ML-selected high-risk cohort demonstrated low NNS values, low total cost, low cost per one GC, and high GC detection rates compared to alternative risk stratification approaches including operative link for gastric atrophy assessment, and operative link for gastric intestinal metaplasia assessment. ConclusionOur ML model holds promise in reducing endoscopy surveillance costs while maintaining a robust gastric cancer detection rate.

Construction of a machine learning-based prediction model for unfavorable discharge outcomes in patients with ischemic stroke

BackgroundIschemic stroke is a common and serious disease with economic and healthcare burdens. Predicting the unfavorable discharge outcome of patients is essential for formulating appropriate treatment strategies and providing personalized care. Therefore, this study aims to establish and validate a prediction model based on machine learning methods to accurately predict the discharge outcome of ischemic stroke patients, providing valuable information for clinical decision making. MethodsThe derivation data consisted of 964 patients from Guangdong Provincial People's Hospital and was used for training and internal validation. A favourable discharge outcome was defined as a National Institutes of Health Stroke Scale score of ≤1 or a decrease of ≥8 points compared to the admission score. A predictive model was created based on 88 medical characteristics gathered during the patient's initial admission, using nine machine learning algorithms. The model's predictive performance was compared using various evaluation metrics. The final model's feature importance was ranked and explained using the Shapley additive explanation method. FindingsThe random forest model demonstrated the greatest discriminative ability among the nine machine learning models. We created an interpretable random forest model by ranking and reducing the features based on their importance, which included eight features. In internal validations, the final model accurately predicted the discharge outcomes of ischemic stroke with AUC values of 0.903 and has been translated into a convenient tool to facilitate its utility in clinical settings. ConclusionsOur explainable ML model was not only successfully developed to accurately predict discharge outcomes in patients with ischemic stroke and it mitigated the concern of the “black-box” issue with an undirect interpretation of the ML technique.

Development and validation of machine learning-based prediction model for severe pneumonia: A multicenter cohort study

Severe pneumonia (SP) is a prevalent respiratory ailment characterized by high mortality and poor prognosis. Current scoring systems for pneumonia are not only time-consuming but also exhibit limitations in early SP prediction. To address this gap, this study aimed to develop a machine-learning model using inflammatory markers from peripheral blood for early prediction of SP. A total of 204 pneumonia patients from seven medical centers were studied, with 143 (68 SP cases) in the training cohort and 61 (32 SP cases) in the test cohort. Clinical characteristics and laboratory test results were collected at diagnosis. Various models including Logistic Regression, Random Forest, Naïve Bayes, XGBoost, Support Vector Machine, and Decision Tree were built and evaluated. Seven predictors—age, sex, WBC count, T-lymphocyte count, NLR, CRP, TNF-α, IL-4/IFN-γ ratio, IL-6/IL-10 ratio—were selected through LASSO regression and clinical insight. The XGBoost model, exhibiting best performance, achieved an AUC of 0.901 (95 % CI: 0.827 to 0.985) in the test cohort, with an accuracy of 0.803, sensitivity of 0.844, specificity of 0.759, and F1_score of 0.818. Indeed, SHAP analysis emphasized the significance of elevated WBC counts, older age, and elevated CRP as the top predictors. The use of inflammatory biomarkers in this concise predictive model shows significant potential for the rapid assessment of SP risk, thereby facilitating timely preventive interventions.

Machine Learning-Based Predictive Model for Mortality in Female Breast Cancer Patients Considering Lifestyle Factors.

To construct a free and accurate breast cancer mortality prediction tool by incorporating lifestyle factors, aiming to assist healthcare professionals in making informed decisions. In this retrospective study, we utilized a ten-year follow-up dataset of female breast cancer patients from a major Chinese hospital and included 1,390 female breast cancer patients with a 7% (96) mortality rate. We employed six machine learning algorithms (ridge regression, k-nearest neighbors, neural network, random forest, support vector machine, and extreme gradient boosting) to construct a mortality prediction model for breast cancer. This model incorporated significant lifestyle factors, such as postsurgery sexual activity, use of totally implantable venous access ports, and prosthetic breast wear, which were identified as independent protective factors. Meanwhile, ten-fold cross-validation demonstrated the superiority of the random forest model (average AUC = 0.918; 1-year AUC = 0.914, 2-year AUC = 0.867, 3-year AUC = 0.883). External validation further supported the model's robustness (average AUC = 0.782; 1-year AUC = 0.809, 2-year AUC = 0.785, 3-year AUC = 0.893). Additionally, a free and user-friendly web tool was developed using the Shiny framework to facilitate easy access to the model. Our breast cancer mortality prediction model is free and accurate, providing healthcare professionals with valuable information to support their clinical decisions and potentially promoting healthier lifestyles for breast cancer patients.

Construction and verification of a machine learning-based prediction model of deep vein thrombosis formation after spinal surgery

BackgroundDeep vein thromboembolism (DVT) is a common postoperative complication with high morbidity and mortality rates. However, the safety and effectiveness of using prophylactic anticoagulants for preventing DVT after spinal surgery remain controversial. Hence, it is crucial to predict whether DVT occurs in advance following spinal surgery. The present study aimed to establish a machine learning (ML)-based prediction model of DVT formation following spinal surgery. MethodsWe reviewed the medical records of patients who underwent elective spinal surgery at the Third Affiliated Hospital of Zunyi Medical University (TAHZMU) from January 2020 to December 2022. We ultimately selected the clinical data of 500 patients who met the criteria for elective spinal surgery. The Boruta-SHAP algorithm was used for feature selection, and the SMOTE algorithm was used for data balance. The related risk factors for DVT after spinal surgery were screened and analyzed. Five ML algorithm models were established. The data of 150 patients treated at the Affiliated Hospital of Zunyi Medical University (AHZMU) from July 2023 to October 2023 were used for external verification of the model. The area under the curve (AUC), geometric mean (G-mean), sensitivity, accuracy, specificity, and F1 score were used to evaluate the performance of the models. ResultsThe results revealed that activated partial thromboplastin time (APTT), age, body mass index (BMI), preoperative serum creatinine (Crea), anesthesia time, rocuronium dose, and propofol dose were the seven important characteristic variables for predicting DVT after spinal surgery. Among the five ML models established in this study, the random forest classifier (RF) showed superior performance to the other models in the internal validation set. ConclusionSeven preoperative and intraoperative variables were included in our study to develop an ML-based predictive model for DVT formation following spinal surgery, and this model can be used to assist in clinical evaluation and decision-making.

A machine learning-based prediction model for architectural heritage: The case of domed Sinan mosques

This study presents a machine learning-based prediction model (PM) customized to predict missing components of historical mosques. Domed mosques built by Architect Sinan during the Classical Ottoman Period (16th century) are selected due to their distinctive features and stylistic similarities. The model development process includes data collection (46 domed Sinan mosques), data preparation and refinement, training, testing, and validation. The Pix2Pix method is used to train and validate the machine learning models, and the Structural Similarity (SSIM) metric is used to objectively evaluate the outcomes. Preliminary results indicate that the success of the PMs is not directly proportional to the number of input components. Instead, factors such as overall mass organization, the curvature of the dome, and the number of balconies on the minaret play crucial roles in determining the success of the outcomes.

Predicting all-cause mortality and premature death using interpretable machine learning among a middle-aged and elderly Chinese population

ObjectiveTo develop machine learning-based prediction models for all-cause and premature mortality among the middle-aged and elderly population in China. MethodAdults aged 45 years or older at baseline of 2011 from the China Health and Retirement Longitudinal Study (CHARLS) were included. The stacked ensemble model was built utilizing five selected machine learning algorithms. These models underwent training and testing using the CHARLS 2011–2015 cohort (derivation cohort) and subsequently underwent external validation using the CHARLS 2015–2018 cohort (validation cohort). SHapley Additive exPlanations (SHAP) was introduced to quantify the importance of risk factors and explain machine learning algorithms. ResultIn derivation cohort, a total of 10,677 subjects were included, 478 died during the follow-up. The stacked ensemble model demonstrated the highest efficacy in terms of its discrimination capability for predicting all-cause mortality and premature death, with an AUC[95 % CI] of 0.826[0.792–0.859] and 0.773[0.725–0.821], respectively. In validation cohort, the corresponding AUC[95 % CI] were 0.803[0.743–0.864] and 0.791[0.719–0.863], respectively. Risk factors including age, sex, self-reported health, activities of daily living, cognitive function, ever smoker, levels of systolic blood pressure, Cystatin C and low density lipoprotein were strong predictors for both all-cause mortality and premature death. ConclusionStacked ensemble models performed well in predicting all-cause and premature death in this Chinese cohort. Interpretable techniques can aid in identifying significant risk factors and non-linear relationships between predictors and mortality.

Machine learning-based prediction model for the yield of nitrogen-enriched biomass pyrolysis products: Performance evaluation and interpretability analysis

The process optimization and control of nitrogen-rich biomass pyrolysis technology is crucial. This technology effectively converts agricultural waste into high-value energy products. The aim of this study is to develop an accurate model for predicting the yield of nitrogen-rich biomass pyrolysis products using machine learning techniques. The goal is to improve both the yield and quality of the products. This study uses machine learning techniques to develop an accurate model for predicting the yield of three-phase products from nitrogen-rich biomass pyrolysis. The goal is to optimize the biomass energy conversion process. The study builds a dataset containing 468 samples. This dataset comprehensively characterizes the chemical, elemental, and industrial properties of biomass, as well as the pyrolysis operating parameters. Models with high prediction accuracy are achieved by comparing various machine learning algorithms. These algorithms include Random Forest, GBDT, SVR, and ANN. Fine feature selection and hyper-parameter tuning are used to enhance the performance. In particular, the optimized GBDT model achieves a performance of MSE of 10.04 and R² of 0.92 in cross-validation. SHAP value analysis is used to further interpret the prediction results of the model. Sensitivity analysis, conducted through Monte Carlo simulation, identifies key features that have a high impact on the target value. Additionally, two-feature partial correlation analysis reveals the importance and dependence of the model features. This provides crucial technical support and a scientific basis for the industrial application of biomass energy and the optimization of the pyrolysis process.

Use of Machine Learning Techniques to Predict the In-situ Concrete Compressive Strength using Non-Destructive Testing

Recently, machine learning-based prediction models have gained considerable popularity in predicting the compressive strength of concrete using results from Non-Destructive Testing (NDT) methods. This research considers NDT results from Rebound Hammer (RH) and Ultrasonic Pulse Velocity (UPV) tests for concrete samples with different concrete grades. 270 test samples were considered for the analysis using different machine learning techniques such as Multi-Layer Perceptron (MLP), Long Short-Term Memory network (LSTM), and Convolutional Neural Network (CNN). Concrete compressive strength results are obtained from Destructive Test (DT) results of the same for the purpose of labelling. Each model's performance is evaluated through the computation of the Coefficient of Determination (R²), Mean Square Error (MSE), and Mean Absolute Percentage Error (MAPE). The findings of this study underscore the potential of machine learning techniques in predicting concrete compressive strength based on Non-Destructive Test (NDT) results. The analysis findings suggested that employing UPV and RH data in conjunction with a trained MLP model to be an effective approach for accurately estimating the compressive strength of concrete specimens. The outcomes of the research serve as a valuable reference for researchers and industry practitioners alike when assessing in-situ concrete compressive strength through Non-Destructive Testing (NDT) methods.

Predicting compressive strength of hollow concrete prisms using machine learning techniques and explainable artificial intelligence (XAI)

The design of masonry structures requires accurate estimation of compressive strength (CS) of hollow concrete masonry prisms. Generally, the CS of masonry prisms is determined by destructive laboratory testing which results in time and resource wastage. Thus, this study aims to provide machine learning-based predictive models for CS of hollow concrete masonry blocks using different algorithms including Multi Expression Programming (MEP), Random Forest Regression (RFR), and Extreme Gradient Boosting (XGB) etc. A dataset of 159 experimental results was collected from published literature for this purpose. The collected dataset consisted of four input parameters including strength of masonry units (fb), height-to-thickness ratio (h/t), strength of mortar (fm), and ratio of fm/fb and only one output parameter i.e., CS. Out of all the algorithms employed in current study, only MEP and GEP expressed their output in the form of an empirical equation. The accuracy of developed models was assessed using root mean squared error (RMSE), objective function (OF), and R2 etc. Among all algorithms assessed, XGB turned out to be the most accurate having R2 = 0.99 and least OF value of 0.0063 followed by AdaBoost, RFR, and other algorithms. The developed XGB model was also used to conduct different explainable artificial intelligence (XAI) analysis including sensitivity and shapley analysis and the results showed that strength of masonry unit (fb) is the most significant variable in predicting CS. Thus, the ML-based predictive models presented in this study can be utilized practically for determining CS of hollow concrete masonry prisms without requiring expensive and time-consuming laboratory testing.