Systematic review identifies the design and methodological conduct of studies on machine learning-based prediction models

Background: A mechanism to predict graft failure before the actual kidney transplantation occurs is crucial to clinical management of chronic kidney disease patients. Several kidney graft outcome prediction models, developed using machine learning methods, are available in the literature. However, most of those models used small datasets and none of the machine learning-based prediction models available in the medical literature modelled time-to-event (survival) information, but instead used the binary outcome of failure or not. The objective of this study is to develop two separate machine learning-based predictive models to predict graft failure following live and deceased donor kidney transplant, using time-to-event data in a large national dataset from Australia. Methods: The dataset provided by the Australia and New Zealand Dialysis and Transplant Registry will be used for the analysis. This retrospective dataset contains the cohort of patients who underwent a kidney transplant in Australia from January 1 st, 2007, to December 31 st, 2017. This included 3,758 live donor transplants and 7,365 deceased donor transplants. Three machine learning methods (survival tree, random survival forest and survival support vector machine) and one traditional regression method, Cox proportional regression, will be used to develop the two predictive models. The best predictive model will be selected based on the model's performance. Discussion: This protocol describes the development of two separate machine learning-based predictive models to predict graft failure following live and deceased donor kidney transplant, using a large national dataset from Australia. Furthermore, these two models will be the most comprehensive kidney graft failure predictive models that have used survival data to model using machine learning techniques. Thus, these models are expected to provide valuable insight into the complex interactions between graft failure and donor and recipient characteristics.

Prediction models: stepwise development and simultaneous validation is a step back

Due to the highly variable clinical phenotype, Klinefelter Syndrome is underdiagnosed. Assessment of supervised machine learning based prediction models for identification of Klinefelter Syndrome among azoospermic patients, and comparison to expert clinical evaluation. Retrospective patient data (karyotype, age, height, weight, testis volume, follicle-stimulating hormone, luteinizing hormone, testosterone, estradiol, prolactin, semen pH and semen volume) collected between January 2005 and June 2019 were retrieved from a patient data bank of a University Centre. Models were trained, validated and benchmarked based on different supervised machine learning algorithms. Models were then tested on an independent, prospectively acquired set of patient data (between July 2019 and July 2020). Benchmarking against physicians was performed in addition. Based on average performance, support vector machines and CatBoost were particularly well-suited models, with 100% sensitivity and >93% specificity on the test dataset. Compared to a group of 18 expert clinicians, the machine learning models had significantly better median sensitivity (100% vs. 87.5%, p=0.0455) and fared comparably with regards to specificity (90% vs. 89.9%, p=0.4795), thereby possibly improving diagnosis rate. A Klinefelter Syndrome Score Calculator based on the prediction models is available on http://klinefelter-score-calculator.uni-muenster.de. Differentiating Klinefelter Syndrome patients from azoospermic patients with normal karyotype (46,XY) is a problem that can be solved with supervised machine learning techniques, improving patient care. Machine learning could improve the diagnostic rate of Klinefelter Syndrome among azoospermic patients, even more for less-experienced physicians.

Performance evaluation of machine learning techniques in predicting cumulative absolute velocity

Three machine learning classifiers: random forest, decision tree and support vector machine were used to build predictive models of an anti-mycobacterial ChEMBL database and evaluated for their predictive capability. Before the development of predictive models, data pre-processing was carried out to fix the class imbalance problem by applying cost-sensitive classifier, and filtration of data instance by supervised synthetic minority oversampling technique (SMOTE), spread subsample and resample method. The statistical evaluation indicated that random forest model was the best model as it showed the best accuracy 93.83%, specificity 90.5%, receiver operating characteristic (ROC) 0.984, MCC 0.772 and kappa statistics 0.768 in comparison to other models whereas LibSVM showed the highest sensitivity 94.4% compared with others. Additionally, toxicity predictive models based on SingleCellcall DSSTox carcinogenicity database (AID1189) was developed which resulted in random forest model as the best model. The deployment of both RF predictive models on two unknown datasets resulted in 1317 compounds out of 1554 approved drugs and 2234 compounds out of 18,746 ChEMBL anti-malarial dataset as non-toxic and anti-mycobacterial compounds. Thus machine learning models present highly efficient methods to find out novel hit anti-mycobacterial compounds. We suggest that such machine learning techniques could be very useful to screen drug candidates not only for tuberculosis but also for other diseases.

Dementia is among the most distressing and burdensome health challenges in aging populations. Treatment efficacy is limited; however, early diagnosis can delay or prevent disease progression. Previous machine learning-based prediction models have limitations (e.g., they are based on clinical parameters or are not generalizable). Thus, in this study, prediction models were developed for current and future dementia solely based on demographic, socioeconomic, and health-related features. Demographic, socioeconomic, and health-related variables collected from the Korean Longitudinal Study of Ageing (KLoSA) were used to develop machine learning-based prediction models for current and future dementia with various algorithms. Two sampling strategies were used for feature selection, one based on domain knowledge and the other based on statistical testing. Hyperparameter tuning was performed using grid search with cross-validation on the training set, and model evaluation was conducted on a separate test set. In the initial no-follow-up dataset, 92 of 6,898 participants exhibited dementia. Among 6,207 participants without dementia initially, 69 developed dementia within 2 years. Linear support vector machine (SVM) and radial bias function SVM exhibited the best sensitivity for current and future dementia (79.4% and 77.7%, respectively). The SHAP (SHapley Additive exPlanations) approach improved the transparency of the model by highlighting the top ten features most strongly associated with increased dementia risk. We achieved reasonably accurate prediction results for dementia using only non-clinical features.

Smart cities are centres of economic opulence and hope for standardized living. Understanding the shades of urban resilience and livability in smart city models is of paramount importance. This study presents a novel two-stage data-driven framework combining a multivariate metric-distance analysis with machine learning (ML) techniques for resilience and livability assessment of smart cities. A longitudinal dataset for 35 top-ranked European smart cities from 2015 till 2020 applied as the case study under the proposed framework. Initially, a metric distance-based weighting approach is used to weight the indicators and quantify the scores across each aspect under city resilience and urban livability. The key aspects under city resilience include social, economic, infrastructure and built environment and, institutional resilience, while under urban livability, the aspects include accessibility, community well-being, and economic vibrancy. Fuzzy c-means clustering as an unsupervised machine learning technique is used to sort smart cities based on the degree of performance. In addition, an intelligent approach is presented for the prediction of the degree of livability, resilience, and aggregate performance of smart cities based on various supervised ML techniques. Classification models such as Naïve Bayes, k-nearest neighbors (kNN), support vector machine (SVM), Classification and Regression Tree (CART) and, ensemble models including Random Forest (RF) and Gradient Boosting machine (GBM) were used. Three coefficients (accuracy, Cohen's Kappa (κ) and average area under the precision-recall curve (AUC-PR)) along with confusion matrix were used to appraise the performance of the classifier ML models. The results revealed GBM as the best classification and predictive model for the resilience, livability, and aggregate performance assessment. The study also revealed Copenhagen, Geneva, Stockholm, Munich, Helsinki, Vienna, London, Oslo, Zurich, and Amsterdam as the smart cities that co-create resilience and livability in their development model with superior performance.

Efficient spare part management plays a crucial role in supporting operational continuity at PT. Setia Karya Transport (Great Giant Foods). The current spare part forecasting process is still reactive and relies on periodic evaluations, resulting in potential inefficiencies in procurement planning. This study aims to develop a machine learning-based predictive model to forecast spare part requirements using historical transaction data from January to July 2025. The research applied three modeling scenarios: (1) a hybrid model combining Support Vector Regression (SVR), Random Forest, and Statistical methods; (2) pure statistical methods with zero-ratio classification; and (3) the XGBoost algorithm with zero-ratio classification. Model performance was evaluated using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) metrics. The results showed that the hybrid approach achieved the best performance with an MAE of 2.919 and an RMSE of 8.056, indicating higher prediction accuracy compared to other models. The findings demonstrate that integrating machine learning with statistical approaches can effectively enhance forecasting accuracy and support data-driven decision-making in warehouse management. Keywords : Machine Learning, Forecasting, Spare Part, Random Forest, Support Vector Regression

The cutting-edge wireless technologies offer huge array of services, from ultra-high-speed data communications to internet of things. But the current existing infrastructure cannot handle these use cases. Consequently, it is becoming a trend to apply computational intelligence algorithms such as machine learning (ML), deep learning (DL), reinforcement learning (RL) and artificial intelligence (AI) to wireless network infrastructures. And one of these applications is on wireless indoor localization. Wireless indoor localization takes advantage of wireless access points (WAPs) received signal strength indicators (RSSI) values to pinpoint the location of a user, similar to concept of GPS but indoors. The goal of this paper is to develop predictive models that can be used to predict the location of a user using RSSI readings that his smartphone receives. In this study, four ML algorithms are used which are support vector machines, random forest, Naïve-Bayes classifier and neural networks. The accuracy of each model are 97.83%, 97.67%, 98.50% and 97.33% respectively. Also, a recursive feature elimination algorithm is also used to determine the predictor that has the least impact amongst all other features and it is found out in the study that WAP2 is contributes the least influence when the predictive models are developed.

Spinal cord Tumor has been characterized as a heterogeneous disease consisting of many different subtypes. The early diagnosis and prognosis of a cancer type have become a necessity in cancer research, as it can facilitate the subsequent clinical management of patients. The importance of classifying cancer patients into Bening or malignant has led many re- search teams, from the biomedical and the bioinformatics field, to study the application of machine learning (ML) methods. Therefore, these techniques have been utilized as an aim to model the progression and treatment of cancerous conditions. In addition, the ability of ML tools to detect key features from complex datasets reveals their importance. A variety of these techniques, Logistic regression, Support Vector Machines (SVMs), Decision Trees (DTs), Random forest classifier(RFs) have been widely applied in cancer research for the development of predictive models, resulting in effective and accurate decision making. Even though it is evident that the use of ML methods can improve our understanding of cancer progression, an appropriate level of validation is needed in order for these methods to be considered in the everyday clinical practice. In this work, we have discussed a predictive model based on various supervised ML techniques.

Predictive analytics including statistical techniques, predictive modelling, machine learning, and data mining that analyse current and historical facts to make predictions about future or otherwise unknown events. Higher education institutions nowadays are under increasing pressure to respond to national and global economic, political and social changes such as the growing need to increase the proportion of students in certain disciplines, embedding workplace graduate attributes and ensuring that the quality of learning programs are both nationally and globally relevant. However, in higher education institution, there are significant numbers of students that stop their studies before graduation, especially for undergraduate students. Problem related to stopping out student and late or not graduating student can be improved by applying analytics. Using analytics, administrators, instructors and student can predict what will happen in future. Administrator and instructors can decide suitable intervention programs for at-risk students and before students decide to leave their study. Many different machine learning techniques have been implemented for predictive modelling in the past including decision tree, k-nearest neighbour, random forest, neural network, support vector machine, naïve Bayesian and a few others. A few attempts have been made to use Bayesian network and dynamic Bayesian network as modelling techniques for predicting at- risk student but a few challenges need to be resolved. The motivation for using dynamic Bayesian network is that it is robust to incomplete data and it provides opportunities for handling changing and dynamic environment. The trends and directions of research on prediction and identifying at-risk student are developing prediction model that can provide as early as possible alert to administrators, predictive model that handle dynamic and changing environment and the model that provide real-time prediction.

Context: Primary aldosteronism (PA) is a common cause of secondary hypertension and is associated with an increased risk of cardiometabolic diseases, especially in unilateral subtype. Despite its high prevalence, the case detection rate of PA is limited, partly because of no clinical models available in general practice to identify patients highly suspicious of unilateral subtype of PA, who can be cured by unilateral adrenalectomy and should be referred to specialized centers. The use of machine learning has been introduced in some fields of clinical prediction. Combining machine learning with clinical data could lead to the development of new models for predicting unilateral subtype of PA. Objective: The aim of this study was to develop a predictive model of subtype diagnosis of PA based on machine learning methods using clinical data available in general practice. Design and setting: This was a retrospective cross-sectional study in referral centers. Patients: We retrospectively analyzed 91 patients with unilateral and 138 patients with bilateral subtype of PA diagnosed according to adrenal venous sampling findings, and stratified randomly split to the training (80%) and test cohorts (20%). Four supervised machine learning classifiers; logistic regression, support vector machines, random forests (RF), and gradient boosting decision trees, were used to develop prediction models from 21 clinical variables. Classifiers were trained using stratified 10 fold cross-validation of the training cohort and hyperparameters of each classifier were adjusted using grid search to optimize the accuracy in the training cohort. Main Outcome Measures: The accuracy and the area under the receiver operating characteristic curve (AUC) for subtype prediction in the test cohort were compared among the optimized classifiers. Results: Of the four classifiers, the accuracy and AUC were highest in RF, with 95.7% and 0.990, respectively. Serum potassium levels, plasma aldosterone concentrations, and serum sodium levels were highlighted as important variables in this model. For feature-selected RF with the three variables, the accuracy and AUC were 89.1% and 0.950, respectively. With an independent external PA cohort, we confirmed a similar accuracy for feature-selected RF. Conclusions: Machine learning models developed using blood test can help predict subtype diagnosis of PA in general practice.

Incorporating crumb rubber in slag-based geopolymer: Experimental work and predictive modelling

The main obstacle to a patient's recovery following a tonsillectomy is complications, and bleeding is the most frequent culprit. Predicting post-tonsillectomy hemorrhage (PTH) allows for accurate identification of high-risk populations and the implementation of protective measures. Our study aimed to investigate how well machine learning models predict the risk of PTH. Data were obtained from 520 patients who underwent a tonsillectomy at The 940th Hospital of Joint Logistics Support Force of Chinese People's Liberation Army. The age range of the patients was 2-57 years, and 364 (70%) were male. The prediction models were developed using five machine learning models: decision tree, support vector machine (SVM), extreme gradient boosting (XGBoost), random forest, and logistic regression. The performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC). Shapley additive explanation (SHAP) was used to interpret the results of the best-performing model. The frequency of PTH was 11.54% among the 520 patients, with 10.71% in the training group and 13.46% in the validation set. Age, BMI, season, smoking, blood type, INR, combined secretory otitis media, combined adenoidectomy, surgical wound, and use of glucocorticoids were selected by mutual information (MI) method. The XGBoost model had best AUC (0.812) and Brier score (0.152). Decision curve analysis (DCA) showed that the model had a high clinical utility. The SHAP method revealed the top 10 variables of MI according to the importance ranking, and the average of the age was recognized as the most important predictor variable. This study built a PTH risk prediction model using machine learning. The XGBoost model is a tool with potential to facilitate population management strategies for PTH.

Sepsis is a leading cause of death in patients with trauma, and the risk of mortality increases significantly for each hour of delay in treatment. A hypermetabolic baseline and explosive inflammatory immune response mask clinical signs and symptoms of sepsis in trauma patients, making early diagnosis of sepsis more challenging. Machine learning-based predictive modeling has shown great promise in evaluating and predicting sepsis risk in the general intensive care unit (ICU) setting, but there has been no sepsis prediction model specifically developed for trauma patients so far. To develop a machine learning model to predict the risk of sepsis at an hourly scale among ICU-admitted trauma patients. We extracted data from adult trauma patients admitted to the ICU at Beth Israel Deaconess Medical Center between 2008 and 2019. A total of 42 raw variables were collected, including demographics, vital signs, arterial blood gas, and laboratory tests. We further derived a total of 485 features, including measurement pattern features, scoring features, and time-series variables, from the raw variables by feature engineering. The data set was randomly split into 70% for model development with stratified 5-fold cross-validation, 15% for calibration, and 15% for testing. An Extreme Gradient Boosting (XGBoost) model was developed to predict the hourly risk of sepsis at prediction windows of 4, 6, 8, 12, and 24 hours. We evaluated model performance for discrimination and calibration both at time-step and outcome levels. Clinical applicability of the model was evaluated with varying levels of precision, and the potential clinical net benefit was assessed with decision curve analysis (DCA). A Shapley additive explanation algorithm was applied to show the effect of features on the prediction model. In addition, we trained an L2-regularized logistic regression model to compare its performance with XGBoost. We included 4603 trauma patients in the study, 1196 (26%) of whom developed sepsis. The XGBoost model achieved an area under the receiver operating characteristics curve (AUROC) ranging from 0.83 to 0.88 at the 4-to-24-hour prediction window in the test set. With a ratio of 9 false alerts for every true alert, it predicted 73% (386/529) of sepsis-positive timesteps and 91% (163/179) of sepsis events in the subsequent 6 hours. The DCA showed our model had a positive net benefit in the threshold probability range of 0 to 0.6. In comparison, the logistic regression model achieved lower performance, with AUROC ranging from 0.76 to 0.84 at the 4-to-24-hour prediction window. The machine learning-based model had good discrimination and calibration performance for sepsis prediction in critical trauma patients. Using the model in clinical practice might help to identify patients at risk of sepsis in a time window that enables personalized intervention and early treatment.