Evaluation Of Machine Learning Models Research Articles

Variance‐driven security optimisation in industrial IoT sensors

AbstractThe Industrial Internet of Things (IIoT) has transformed industrial operations with real‐time monitoring and control, enhancing efficiency and productivity. However, this connectivity brings significant security challenges. This study addresses these challenges by identifying abnormal sensor data patterns using machine learning‐based anomaly detection models. The proposed framework employs advanced algorithms to strengthen industrial defences against cyber threats and disruptions. Focusing on temperature anomalies, a critical yet often overlooked aspect of industrial security, this research fills a gap in the literature by evaluating machine learning models for this purpose. A novel variance‐based model for temperature anomaly detection is introduced, demonstrating high efficacy with accuracy scores of 0.92 and 0.82 on the NAB and AnoML‐IOT datasets, respectively. Additionally, the model achieved F1 scores of 0.96 and 0.89 on these datasets, underscoring its effectiveness in enhancing IIoT security and optimising cybersecurity for industrial processes. This research not only identifies security vulnerabilities but also presents concrete solutions to improve the security posture of IIoT systems.

Comparative evaluation of machine learning models for assessment of seabed liquefaction using finite element data

Predicting wave-induced liquefaction around submarine pipelines is crucial for marine engineering safety. However, the complex of interactions between ocean dynamics and seabed sediments makes rapid and accurate assessments challenging with traditional numerical methods. Although machine learning approaches are increasingly applied to wave-induced liquefaction problems, the comparative accuracy of different models remains under-explored. We evaluate the predictive accuracy of four classical machine learning models: Gradient Boosting (GB), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Random Forest (RF). The results indicate that the GB model exhibits high stability and accuracy in predicting wave-induced liquefaction, due to its strong ability to handle complex nonlinear geological data. Prediction accuracy varies across output parameters, with higher accuracy for seabed predictions than for pipeline surroundings. The combination of different input parameters significantly influences model predictive accuracy. Compared to traditional finite element numerical methods, employing machine learning models significantly reduces computation time, offering an effective tool for rapid disaster assessment and early warning in marine engineering. This research contributes to the safety of marine pipeline protections and provides new insights into the intersection of marine geological engineering and artificial intelligence.

Development and Evaluation of Machine Learning Models for Air-to-Land Temperature Conversion Using the Newly Established Kunlun Mountain Gradient Observation System

Mountainous land types are characterized by a scarcity of observational data, particularly in remote areas such as the Kunlun Mountains, where conventional Automatic Weather Stations (AWSs) typically do not record land surface temperature (LST) data. This study aims to develop and evaluate models for converting air temperature (TA) to LST using newly established meteorological station data from the Kunlun Mountain Gradient Observation System, thereby providing time-continuous LST data for AWSs. We constructed a conceptual model to explore the relationship between 1.5 m TA and LST and instantiated it using three machine learning algorithms: Support Vector Machine (SVR), Convolutional Neural Network (CNN), and CatBoost. The results demonstrated that the CatBoost algorithm outperformed the others under complex terrain and climatic conditions, achieving a coefficient of determination (R2) of 0.997 and the lowest root mean square error (RMSE) of 0.627 °C, indicating superior robustness and accuracy. Consequently, CatBoost was selected as the optimal model. Additionally, this study analyzed the spatiotemporal distribution characteristics of cloud cover in the Kunlun Mountain region using the MOD11A1 product and assessed the uncertainties introduced by the 8-day average compositing method of the MOD11A2 product. The results revealed significant discrepancies between the monthly average LST derived from polar-orbiting satellites and the hourly composite monthly LST measured on-site or under ideal cloud-free conditions. These differences were particularly pronounced in high-altitude regions (4000 m and above), with the greatest differences occurring in winter, reaching up to 10.2 °C. These findings emphasize the importance of hourly LST calculations based on AWSs for accurately assessing the spatiotemporal characteristics of LST in the Kunlun Mountains, thus providing more precise spatiotemporal support for remote sensing applications in high-altitude regions.

Machine learning-based infection diagnostic and prognostic models in post-acute care settings: a systematic review.

This study aims to (1) review machine learning (ML)-based models for early infection diagnostic and prognosis prediction in post-acute care (PAC) settings, (2) identify key risk predictors influencing infection-related outcomes, and (3) examine the quality and limitations of these models. PubMed, Web of Science, Scopus, IEEE Xplore, CINAHL, and ACM digital library were searched in February 2024. Eligible studies leveraged PAC data to develop and evaluate ML models for infection-related risks. Data extraction followed the CHARMS checklist. Quality appraisal followed the PROBAST tool. Data synthesis was guided by the socio-ecological conceptual framework. Thirteen studies were included, mainly focusing on respiratory infections and nursing homes. Most used regression models with structured electronic health record data. Since 2020, there has been a shift toward advanced ML algorithms and multimodal data, biosensors, and clinical notes being significant sources of unstructured data. Despite these advances, there is insufficient evidence to support performance improvements over traditional models. Individual-level risk predictors, like impaired cognition, declined function, and tachycardia, were commonly used, while contextual-level predictors were barely utilized, consequently limiting model fairness. Major sources of bias included lack of external validation, inadequate model calibration, and insufficient consideration of data complexity. Despite the growth of advanced modeling approaches in infection-related models in PAC settings, evidence supporting their superiority remains limited. Future research should leverage a socio-ecological lens for predictor selection and model construction, exploring optimal data modalities and ML model usage in PAC, while ensuring rigorous methodologies and fairness considerations.

Predictive modeling of gestational weight gain: a machine learning multiclass classification study

BackgroundGestational weight gain (GWG) is a critical factor influencing maternal and fetal health. Excessive or insufficient GWG can lead to various complications, including gestational diabetes, hypertension, cesarean delivery, low birth weight, and preterm birth. This study aims to develop and evaluate machine learning models to predict GWG categories: below, within, or above recommended guidelines.MethodsWe analyzed data from the Araraquara Cohort, Brazil, which comprised 1557 pregnant women with a gestational age of 19 weeks or less. Predictors included socioeconomic, demographic, lifestyle, morbidity, and anthropometric factors. Five machine learning algorithms (Random Forest, LightGBM, AdaBoost, CatBoost, and XGBoost) were employed for model development. The models were trained and evaluated using a multiclass classification approach. Model performance was assessed using metrics such as area under the ROC curve (AUC-ROC), F1 score and Matthew’s correlation coefficient (MCC).ResultsThe outcomes were categorized as follows: GWG within recommendations (28.7%), GWG below (32.5%), and GWG above recommendations (38.7%). The XGBoost presented the best overall model, achieving an AUC-ROC of 0.79 for GWG within, 0.76 for GWG below, and 0.65 for GWG above. The LightGBM also performed well with an AUC-ROC of 0.79 for predicting GWG within recommendations, 0.76 for GWG below, and 0.624 for GWG above. The most important predictors of GWG were pre-gestational BMI, maternal age, glycemic profile, hemoglobin levels, and arm circumference.ConclusionMachine learning models can effectively predict GWG categories, offering a valuable tool for early identification of at-risk pregnancies. This approach can enhance personalized prenatal care and interventions to promote optimal pregnancy outcomes.

Deep learning for 3D vascular segmentation in hierarchical phase contrast tomography: a case study on kidney

Automated blood vessel segmentation is critical for biomedical image analysis, as vessel morphology changes are associated with numerous pathologies. Still, precise segmentation is difficult due to the complexity of vascular structures, anatomical variations across patients, the scarcity of annotated public datasets, and the quality of images. Our goal is to provide a foundation on the topic and identify a robust baseline model for application to vascular segmentation using a new imaging modality, Hierarchical Phase-Contrast Tomography (HiP-CT). We begin with an extensive review of current machine-learning approaches for vascular segmentation across various organs. Our work introduces a meticulously curated training dataset, verified by double annotators, consisting of vascular data from three kidneys imaged using HiP-CT as part of the Human Organ Atlas Project. HiP-CT pioneered at the European Synchrotron Radiation Facility in 2020, revolutionizes 3D organ imaging by offering a resolution of around 20 μm/voxel and enabling highly detailed localised zooms up to 1–2 μm/voxel without physical sectioning. We leverage the nnU-Net framework to evaluate model performance on this high-resolution dataset, using both known and novel samples, and implementing metrics tailored for vascular structures. Our comprehensive review and empirical analysis on HiP-CT data sets a new standard for evaluating machine learning models in high-resolution organ imaging. Our three experiments yielded Dice similarity coefficient (DSC) scores of 0.9523, 0.9410, and 0.8585, respectively. Nevertheless, DSC primarily assesses voxel-to-voxel concordance, overlooking several crucial characteristics of the vessels and should not be the sole metric for deciding the performance of vascular segmentation. Our results show that while segmentations yielded reasonably high scores-such as centerline DSC ranging from 0.82 to 0.88, certain errors persisted. Specifically, large vessels that collapsed due to the lack of hydrostatic pressure (HiP-CT is an ex vivo technique) were segmented poorly. Moreover, decreased connectivity in finer vessels and higher segmentation errors at vessel boundaries were observed. Such errors, particularly in significant vessels, obstruct the understanding of the structures by interrupting vascular tree connectivity. Our study establishes the benchmark across various evaluation metrics, for vascular segmentation of HiP-CT imaging data, an imaging technology that has the potential to substantively shift our understanding of human vascular networks.

Prediction of Severe Acute Pancreatitis at a Very Early Stage of the Disease Using Artificial Intelligence Techniques, Without Laboratory Data or Imaging Tests: The PANCREATIA Study.

To evaluate machine learning models' performance in predicting acute pancreatitis severity using early-stage variables while excluding laboratory and imaging tests. Severe acute pancreatitis (SAP) affects approximately 20% of acute pancreatitis (AP) patients and is associated with high mortality rates. Accurate early prediction of SAP and in-hospital mortality is crucial for effective management. Traditional scores such as APACHE-II and BISAP are complex and require laboratory tests, while early predictive models are lacking. Machine learning (ML) has shown promising results in predictive modelling, potentially outperforming traditional methods. We analysed data from a prospective database of AP patients admitted to Vall d'Hebron Hospital from November 2015 to January 2022. Inclusion criteria were adults diagnosed with AP according to the 2012 Atlanta classification. Data included basal characteristics, current medication, and vital signs. We developed machine learning models to predict SAP, in-hospital mortality, and intensive care unit (ICU) admission. The modelling process included two stages: Stage 0, which used basal characteristics and medication, and Stage 1, which included data from Stage 0 and vital signs. Out of 634 cases, 594 were analysed. The Stage 0 model showed AUC values of 0.698 for mortality, 0.721 for ICU admission, and 0.707 for persistent organ failure. The Stage 1 model improved performance with AUC values of 0.849 for mortality, 0.786 for ICU admission, and 0.783 for persistent organ failure. The models demonstrated comparable or superior performance to APACHE-II and BISAP scores. The ML models showed good predictive capacity for SAP, ICU admission, and mortality using early-stage data without laboratory or imaging tests. This approach could revolutionise AP patients' initial triage and management, providing a personalised prediction method based on early clinical data.

Evaluation of Machine Learning Models for Predicting Soil Texture Using Sentinel-1A SAR and Topographic Information

Evaluation of Machine Learning Models for Predicting Soil Texture Using Sentinel-1A SAR and Topographic Information

Evaluating Machine Learning Models for Stroke Prognosis and Prediction in Atrial Fibrillation Patients: A Comprehensive Meta-Analysis.

Atrial fibrillation (AF) complicates the management of acute ischemic stroke (AIS), necessitating precise predictive models to enhance clinical outcomes. This meta-analysis evaluates the efficacy of machine learning (ML) models in three key areas: stroke prognosis in AF patients, stroke prediction in AF patients, and AF prediction in stroke patients. The study aims to assess the accuracy and variability of ML models in forecasting AIS outcomes and detecting AF in stroke patients, while exploring the clinical benefits and limitations of integrating these models into practice. We conducted a systematic search of PubMed, Embase, and Cochrane databases up to June 2024, selecting studies that evaluated ML accuracy in stroke prognosis and prediction in AF patients and AF prediction in stroke patients. Data extraction and quality assessment were performed independently by two reviewers, with random-effects modeling applied to estimate pooled accuracy metrics. The meta-analysis included twenty-four studies comprising 7,391,645 patients, categorized into groups for stroke prognosis in AF patients (eight studies), stroke prediction in AF patients (thirteen studies), and AF prediction in stroke patients (three studies). The pooled AUROC was 0.79 for stroke prognosis and 0.68 for stroke prediction in AF, with higher accuracy noted in short-term predictions. The mean AUROC across studies was 0.75, with models such as Extreme Gradient Boosting (XGB) and Random Forest (RF) showing superior performance. For stroke prognosis in AF, the mean AUROC was 0.78, whereas stroke prediction yielded a mean AUROC of 0.73. AF prediction post-stroke had an average AUROC of 0.75. These findings indicate moderate predictive capability of ML models, underscoring the need for further refinement and standardization. The absence of comprehensive sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) metrics limited the ability to conduct full meta-analytic modeling. While ML models demonstrate potential for enhancing stroke prognosis and AF prediction, they have yet to meet the clinical standards required for widespread adoption. Future efforts should focus on refining these models and validating them across diverse populations to improve their clinical utility.

Predictive machine learning models for anticipating loss to follow-up in tuberculosis patients throughout anti-TB treatment journey

Loss to follow-up (LTFU) in tuberculosis (TB) management increases morbidity and mortality, challenging effective control strategies. This study aims to develop and evaluate machine learning models to predict loss to follow-up in TB patients, improving treatment adherence and outcomes. Retrospective data encompassing tuberculosis patients who underwent treatment or registration at the National Center for Clinical Medical Research on Infectious Diseases from January 2017 to December 2021 were compiled. Employing machine learning techniques, namely SVM, RF, XGBoost, and logistic regression, the study aimed to prognosticate LTFU. A comprehensive cohort of 24,265 tuberculosis patients underwent scrutiny, revealing a LTFU prevalence of 12.51% (n = 3036). Education level, history of hospitalization, alcohol consumption, outpatient admission, and prior tuberculosis history emerged as precursors for pre-treatment LTFU. Employment status, outpatient admission, presence of chronic hepatitis/cirrhosis, drug adverse reactions, alternative contact availability, and health insurance coverage exerted substantial influence on treatment-phase LTFU. XGBoost consistently surpassed alternative models, boasting superior discriminative ability with an average AUC of 0.921 for pre-treatment LTFU and 0.825 for in-treatment LTFU. Our study demonstrates that the XGBoost model provides superior predictive performance in identifying LTFU risk among tuberculosis patients. The identification of key risk factors highlights the importance of targeted interventions, which could lead to significant improvements in treatment adherence and patient outcomes.

Evaluation of machine learning models for the accelerated prediction of density functional theory calculated 19F chemical shifts based on local atomic environments

The introduction of fluorine in compounds plays a crucial role in drug development as it greatly influences their final pharmacokinetic and dynamic properties. Due to the prevalence of fluorine in FDA-approved drugs in recent years, identifying the mechanisms driving their chemical transformations has become crucial in the drug discovery landscape. 19F NMR spectroscopy is a powerful analytical technique that allows for the examination of fluorine-containing compounds, offering valuable information about their structure, dynamics, and reactivity. NMR spectra can be interpreted through the leveraging of Density Functional Theory (DFT). However, the screening of compounds and discovery of feasible drug candidates is limited due to its computational cost. Here, we present a machine learning approach to accelerate the prediction of DFT-calculated 19F NMR chemical shifts. The fluorine atoms’ features in the models were derived from their local three-dimensional environments, representing their neighboring atoms within a radius of n Å away from the given fluorine atom in the compound. A comparative analysis of thirteen regression models was conducted using features extracted from 501 fluorinated compounds in our laboratory’s chemical inventory. Among the models, Gradient Boosting Regression (GBR) exhibited the highest performance, achieving a mean absolute error of 3.31 ppm with a local environment radius of 3 Å. This demonstrates a comparable accuracy to DFT calculations while reducing computational time from several hundred seconds to milliseconds. 3 Å was also found to be the most optimal radius across all models when encoding features for local atomic environments.

Comparative Evaluation of Machine Learning Models for Mobile Phone Price Prediction: Assessing Accuracy, Robustness, and Generalization Performance

These days, mobile phones are the most commonly purchased goods. Thousands of new models with improved features, designs, and specifications are released yearly. An autonomous mobile price prediction system is required to assist customers in determining whether or not they can afford these devices. Many machine learning models exhibit varying performance degrees based on their architecture and learning properties. Ten widely used classifiers were assessed in this study: Logistic Regression (LR), Random Forest (RF), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Decision Tree (DT), Naïve Bayes (NB), Linear Discriminant Analysis (LDA), AdaBoost, and Light Gradient Boosting (LGB). The F1-score, recall, accuracy, and precision of these models were evaluated. According to the findings, the results indicated that LR, with its use of the Elastic Net parameter, outperformed the others with 96% accuracy, 97% precision, 94% recall, and 96% F1-score. Other models like XGBoost, LGB, and SVM also showed strong performance, whereas KNN had the poorest performance. The study highlights the importance of selecting the appropriate model for accurate mobile price prediction. Among all the machine learning used in this paper, the LR classifier outperforms the other state-of-the-art models because of the elastic Net parameter used for mobile phone price prediction.

Spectral data driven machine learning classification models for real time leaf spot disease detection in brinjal crops

This study presents the development and evaluation of machine learning models for detecting leaf spot disease in brinjal crops using spectral sensor data. The spectral reflectance of diseased and healthy tissues was recorded across nine wavelength bands (F1: 415 nm, F2: 445 nm, F3: 480 nm, F4: 515 nm, F5: 555 nm, F6: 590 nm, F7: 630 nm, F8: 680 nm, and F9: NIR-750 nm). The data revealed distinct spectral signatures, particularly between F5 (555 nm) and F9 (NIR), where diseased tissues consistently showed lower reflectance compared to healthy tissues. Two machine learning algorithms, Decision Tree (DT) and Support Vector Machine (SVM), were employed to classify the spectral data. The DT model achieved a maximum testing accuracy of 88.2 %, with a Gini index and a depth of 4 as optimal hyperparameters. The confusion matrix indicated that the DT model correctly identified 883 diseased instances and 667 healthy cases, while misclassifying 213 healthy tissues as diseased and 25 diseased tissues as healthy. The SVM model, configured with a cost parameter of 10.0 and a tolerance of 0.01, outperformed the DT model, achieving a testing accuracy of 92.4 %. The SVM model correctly classified 99.3 % of diseased instances and 94.1 % of healthy cases. The results demonstrate the potential of spectral sensor data combined with ML algorithms for precise disease detection, facilitating targeted pesticide application, and reducing input costs. The high accuracy of the SVM model underscores its utility in agricultural disease management, enabling early intervention and enhancing crop health monitoring. Future research may explore integrating multiple sensors and advanced feature extraction methods to further improve the efficiency and accuracy of these systems.

S840 Evaluation of Machine Learning Models for the Assessment of the Endoscopic Mayo Score in Ulcerative Colitis: A Systematic Review

S840 Evaluation of Machine Learning Models for the Assessment of the Endoscopic Mayo Score in Ulcerative Colitis: A Systematic Review

MMIFR: Multi-modal industry focused data repository

In the rapidly advancing field of industrial automation, the availability of robust and diverse datasets is crucial for the development and evaluation of machine learning models. The data repository consists of four distinct versions of datasets: MMIFR-D, MMIFR-FS, MMIFR-OD and MMIFR-P. The MMIFR-D dataset comprises a comprehensive assemblage of 5907 images accompanied by corresponding textual descriptions, notably facilitating the application of industrial equipment classification. In contrast, the MMIFR-FS dataset serves as an alternative variant characterized by the inclusion of 129 distinct classes and 5907 images, specifically catering to the task of few-shot learning within the industrial domain. MMIFR-OD is another alternative variant, comprising 8,839 annotation instances across 128 distinct categories, is predominantly utilized for object detection tasks. Additionally, the MMIFR-P dataset consists of 142 textual-visual information pairs, making it suitable for detecting pairs of industrial equipment. Furthermore, we conduct a comprehensive comparative analysis of our dataset in relation to other datasets used in industrial settings. Benchmark performances for different industrial tasks on our data repository are provided. The proposed multimodal dataset, MMIFR, can be utilized for research in industrial automation, quality control, safety monitoring, and other relevant domains.

Machine Learning Techniques for Monitoring Water Quality in Water Resources

More than 66% of the Earth's total surface area is covered by water. Clean water is one of the basic needs of everyday life. Consistent pollution of water bodies can have far-reaching effects on the lives of living organisms. The World Health Organization has reported that the provision of safe drinking water for human consumption is a challenge that has reached alarming levels. This is because nearly 70% of the total water withdrawals worldwide are used in agriculture. To determine the water's suitability for human consumption, Tests are typically conducted by examining the properties of water in terms of physical, biological, and chemical conditions. There are various methods to measure water quality. Recently, an ongoing process has been shown to improve water quality. To solve this problem, this paper is using a machine learning model to Contribution for creation a smart model capable of classifying potable and non-potable water that is released to the water share by the competent authorities and the ability of Machine Learning models to monitor and predict water, especially Managing and Planning Water Resources. datasets were utilized in training and evaluating machine learning models, which includes (3276) samples with nine attributes and two labels indicating water usability According to the in our work the (Random Forest) algorithm have the best Through the results that appeared by accuracy (0.954084, 0. 882484, and 0. 931849 for three sizes of data.) and then (Decision Tree, K-Nearest Neighbor, Logistic Regression, SVC) sequentially. Index Terms—Machine Learning, potable water, Water Quality, water resources.

Empirical evaluation of machine learning models for analysis of CoVID related diseases on different body organs

Empirical evaluation of machine learning models for analysis of CoVID related diseases on different body organs

Computer Vision Identification of Trachomatous Inflammation-Follicular Using Deep Learning.

Trachoma surveys are used to estimate the prevalence of trachomatous inflammation-follicular (TF) to guide mass antibiotic distribution. These surveys currently rely on human graders, introducing a significant resource burden and potential for human error. This study describes the development and evaluation of machine learning models intended to reduce cost and improve reliability of these surveys. Fifty-six thousand seven hundred twenty-five everted eyelid photographs were obtained from 11,358 children of age 0 to 9 years in a single trachoma-endemic region of Ethiopia over a 3-year period. Expert graders reviewed all images from each examination to determine the estimated number of tarsal conjunctival follicles and the degree of trachomatous inflammation-intense. The median estimate of the 3 grader groups was used as the ground truth to train a MobileNetV3 large deep convolutional neural network to detect cases with TF. The classification model predicted a TF prevalence of 32%, which was not significantly different from the human consensus estimate (30%; 95% confidence interval of difference, -2 to +4%). The model had an area under the receiver operating characteristic curve of 0.943, F1 score of 0.923, 88% accuracy, 83% sensitivity, and 91% specificity. The area under the receiver operating characteristic curve increased to 0.995 when interpreting nonborderline cases of TF. Deep convolutional neural network models performed well at classifying TF and detecting the number of follicles evident in conjunctival photographs. Implementation of similar models may enable accurate, efficient, large-scale trachoma screening. Further validation in diverse populations with varying TF prevalence is needed before implementation at scale.

A review of model evaluation metrics for machine learning in genetics and genomics.

Machine learning (ML) has shown great promise in genetics and genomics where large and complex datasets have the potential to provide insight into many aspects of disease risk, pathogenesis of genetic disorders, and prediction of health and wellbeing. However, with this possibility there is a responsibility to exercise caution against biases and inflation of results that can have harmful unintended impacts. Therefore, researchers must understand the metrics used to evaluate ML models which can influence the critical interpretation of results. In this review we provide an overview of ML metrics for clustering, classification, and regression and highlight the advantages and disadvantages of each. We also detail common pitfalls that occur during model evaluation. Finally, we provide examples of how researchers can assess and utilise the results of ML models, specifically from a genomics perspective.

Optimal inputs for machine learning models in predicting total joint arthroplasty outcomes: a systematic review.

Machine learning (ML) models may offer a novel solution to reducing postoperative complication rates and improving post-surgical outcomes after total joint arthroplasty (TJA). However, the variety of different ML models that exist paired with the increasing number of potential inputs can make the implementation of this tool challenging. Therefore, we conducted a systematic review to assess the most optimal inputs of different ML models in predicting postoperative (1) medical outcomes, (2) orthopedic outcomes, and (3) patient-reported outcome measures (PROMs) after total joint arthroplasty. The PubMed, MEDLINE, EBSCOhost, and Google Scholar databases were utilized to identify all studies evaluating ML models predicting outcomes following TJA between January 1, 2000, and June 23, 2023 (PROSPERO study protocol registration: CRD42023437586). The mean risk of bias in non-randomized studies-of interventions score, was 13.8 ± 0.5. Our initial query yielded 656 articles, of which 25 articles aligned with our aims, examining over 20 machine learning models and 1,555,300 surgeries. The area under the curve (AUC), accuracy, inputs, and the importance of each input were reported. Twelve studies evaluating medical complications with 13ML models reported AUCs ranging from 0.57 to 0.997 and accuracy between 88% and 99.98%. Key predictors included age, hyper-coagulopathy, total number of diagnoses, admission month, and malnutrition. Five studies evaluating orthopedic complications with 10ML models reported AUCs from 0.49 to 0.93 and accuracy ranging from 92 to 97%, with age, BMI, CCI, AKSS scores, and height identified as key predictors. Ten studies evaluating PROMs comprising of 12 different ML models had an AUC ranging from 0.453 to 0.97 ranked preoperative PROMs as the post-predictive input. Overall, age was the most predictive risk factor for complications post-total joint arthroplasty (TJA). These studies demonstrate the predictive capabilities of these models for anticipating complications and outcomes. Furthermore, these studies also highlight ML models' ability to identify non-classical variables not commonly considered in addition to confirming variables known to be crucial. To advance the field, forthcoming research should adhere to established guidelines for model development and training, employ industry-standard input parameters, and subject their models to external validity assessments.