Machine Learning-based Prediction Research Articles

Development and validation of a machine learning-based prediction model for sudden cardiac death in the general population: insights from the community cardiovascular cohort

Abstract Background/Introduction Accurately predicting and managing the risk of sudden cardiac death (SCD) in the general population is a formidable challenge. Purpose This study aimed to develop and validate a machine learning (ML)-based prediction model for SCD using data from the Community Cardiovascular Cohort (CCCC) in Taiwan. Methods A community-based cohort study was used for model construction . Four ML algorithms, including extreme gradient boosting (XGBoost), random forests (RF), logistic regression, and deep neural network (DNN), underwent meticulous evaluation. Performance assessment encompassed receiver operating characteristic (ROC) curves, area under the curves (AUC), and accuracy metrics. Significant risk factors were identified through feature importance analysis. Results We employed a random partitioning strategy, allocating 1744 participants (55%) to the training dataset, 952 participants (30%) to the test dataset, and 476 participants (15%) to the validation dataset. In the data training stage, the XGBoost algorithm demonstrated outstanding prediction performance for SCD (AUC: 1.000); In the validation stage, the XGBoost algorithm demonstrated good prediction performance for SCD prediction (AUC: 0.791, 95%CI: 0.617-0.964; Accuracy: 0.971). Using XGBoost-generated predicted probabilities (P(XGB)), we identified individuals with P(XGB) ≥ 0.5 (Group 1) who displayed significantly higher SCD risk (HR 32.0; 95% CI: 9.29-109.9) compared to those with P(XGB) < 0.5 (Group 0). Conclusions Our study demonstrates the effectiveness of ML algorithms, particularly XGBoost, in predicting event of SCD in the general population. The identification of these pivotal risk factors holds profound implications, empowering the identification of high-risk individuals and facilitating the implementation of precisely tailored preventive strategies.Figure 1:KM sruvival curveFigure 2:Feature importance analysis

Three-dimensional magnetic resonance imaging-based statistical shape analysis and machine learning-based prediction of patellofemoral instability.

This study performed three-dimensional (3D) magnetic resonance imaging (MRI)-based statistical shape analysis (SSA) by comparing patellofemoral instability (PFI) and normal femur models, and developed a machine learning (ML)-based prediction model. Twenty (19 patients) and 31 MRI scans (30 patients) of femurs with PFI and normal femurs, respectively, were used. Bone and cartilage segmentation of the distal femurs was performed and subsequently converted into 3D reconstructed models. The pointwise distance map showed anterior elevation of the trochlea, particularly at the central floor of the proximal trochlea, in the PFI models compared with the normal models. Principal component analysis examined shape variations in the PFI group, and several principal components exhibited shape variations in the trochlear floor and intercondylar width. Multivariate analysis showed that these shape components were significantly correlated with the PFI/non-PFI distinction after adjusting for age and sex. Our ML-based prediction model for PFI achieved a strong predictive performance with an accuracy of 0.909 ± 0.015, and an area under the curve of 0.939 ± 0.009 when using a support vector machine with a linear kernel. This study demonstrated that 3D MRI-based SSA can realistically visualize statistical results on surface models and may facilitate the understanding of complex shape features.

MEDICAL INSURANCE PREMIUM PREDICTION WITH MACHINE LEARNING

A machine learning method for predicting health insurance rates is presented in this article. With healthcare expenditures becoming more complex, it is critical for insurance companies and policyholders to accurately estimate insurance prices. Utilizing a dataset that included medical history, demographic data, and other pertinent variables, a variety of machine learning techniques, such as ensemble methods and regression, were used to create prediction models. R-Squared and mean absolute error were two measures used to assess these models' performance. According to the developed models' results, insurance premiums can be predicted with accuracy, offering useful information for insurance counteragents. This approach has the potential to optimize pricing strategies, enhance risk assessment, and improve decision-making in the healthcare insurance sector. Machine Learning-Based Prediction of Medical Insurance Premiums Make predictions about health insurance companies based on personal traits. A dataset of policyholder attributes (such as age, gender, BMI, number of children, smoking behaviors, and geography) was gathered and preprocessed .Divide the data into sets for testing and training. Create and train a model for an artificial neural network with TensorFlow and Karas. R-squared metrics and mean R-squared error were used to assess the performance of the model. created a high R-Squared predictive model that was accurate. determined the main determinants of insurance rates. Machine learning has shown promise in estimating healthcare costs. This experiment demonstrates how well machine learning predicts medical insurance rates. Insurance companies may offer more individualized insurance plans, expedite the underwriting process, and help customers make well-informed decisions about their healthcare coverage by creating these predictive models. The created model can help policyholders make educated judgments and insurance companies establish proper prices. In the long run, our research helps the insurance industry enhance data-driven techniques, which benefits insurers as well as insured individuals in general.

Machine Learning-Based Prediction of Suicidal Thinking in Adolescents by Derivation and Validation in 3 Independent Worldwide Cohorts: Algorithm Development and Validation Study.

Suicide is the second-leading cause of death among adolescents and is associated with clusters of suicides. Despite numerous studies on this preventable cause of death, the focus has primarily been on single nations and traditional statistical methods. This study aims to develop a predictive model for adolescent suicidal thinking using multinational data sets and machine learning (ML). We used data from the Korea Youth Risk Behavior Web-based Survey with 566,875 adolescents aged between 13 and 18 years and conducted external validation using the Youth Risk Behavior Survey with 103,874 adolescents and Norway's University National General Survey with 19,574 adolescents. Several tree-based ML models were developed, and feature importance and Shapley additive explanations values were analyzed to identify risk factors for adolescent suicidal thinking. When trained on the Korea Youth Risk Behavior Web-based Survey data from South Korea with a 95% CI, the XGBoost model reported an area under the receiver operating characteristic (AUROC) curve of 90.06% (95% CI 89.97-90.16), displaying superior performance compared to other models. For external validation using the Youth Risk Behavior Survey data from the United States and the University National General Survey from Norway, the XGBoost model achieved AUROCs of 83.09% and 81.27%, respectively. Across all data sets, XGBoost consistently outperformed the other models with the highest AUROC score, and was selected as the optimal model. In terms of predictors of suicidal thinking, feelings of sadness and despair were the most influential, accounting for 57.4% of the impact, followed by stress status at 19.8%. This was followed by age (5.7%), household income (4%), academic achievement (3.4%), sex (2.1%), and others, which contributed less than 2% each. This study used ML by integrating diverse data sets from 3 countries to address adolescent suicide. The findings highlight the important role of emotional health indicators in predicting suicidal thinking among adolescents. Specifically, sadness and despair were identified as the most significant predictors, followed by stressful conditions and age. These findings emphasize the critical need for early diagnosis and prevention of mental health issues during adolescence.

Machine Learning-Based Prediction of Cattle Activity Using Sensor-Based Data.

Livestock monitoring is a task traditionally carried out through direct observation by experienced caretakers. By analyzing its behavior, it is possible to predict to a certain degree events that require human action, such as calving. However, this continuous monitoring is in many cases not feasible. In this work, we propose, develop and evaluate the accuracy of intelligent algorithms that operate on data obtained by low-cost sensors to determine the state of the animal in the terms used by the caregivers (grazing, ruminating, walking, etc.). The best results have been obtained using aggregations and averages of the time series with support vector classifiers and tree-based ensembles, reaching accuracies of 57% for the general behavior problem (4 classes) and 85% for the standing behavior problem (2 classes). This is a preliminary step to the realization of event-specific predictions.

Machine and deep learning-based prediction of flexural moment capacity of ultra-high performance concrete beams with/out steel fiber

Machine and deep learning-based prediction of flexural moment capacity of ultra-high performance concrete beams with/out steel fiber

Three distinct patterns of mental health response following accidents in mountain sports: a follow-up study of individuals treated at a tertiary trauma center.

The restorative effect of physical activity in alpine environments on mental and physical health is well recognized. However, a risk of accidents and post-accident mental health problems is inherent to every sport. We aimed to characterize mental health in individuals following mountain sport accidents requiring professional medical management. Adult victims of mountain sport accidents treated at the hospital of the Medical University of Innsbruck (Austria) between 2018 and 2020 completed a cross-sectional survey at least 6months following the admission (median 44 months, n = 307). Symptoms of post-traumatic stress disorder (PTSD, PCL-5), anxiety, depression, and somatization (PHQ), resilience (RS-13), sense of coherence (SOC-9L), post-traumatic growth (PTGI), and quality of life (EUROHIS-QOL), as well as sociodemographic and clinical information, were obtained from an online survey and extracted from electronic health records. Mental health outcome patterns were investigated by semi-supervised medoid clustering and modeled by machine learning. Symptoms of PTSD were observed in 19% of participants. Three comparably sized subsets of participants were identified: a (1) neutral, (2) post-traumatic growth, and (3) post-traumatic stress cluster. The post-traumatic stress cluster was characterized by high prevalence of symptoms of mental disorders, low resilience, low sense of coherence, and low quality of life as well as by younger age, the highest frequency of pre-existing mental disorders, and persisting physical health consequences of the accident. Individuals in this cluster self-reported a need for psychological or psychiatric support following the accident and more cautious behavior during mountain sports since the accident. Reliability of machine learning-based prediction of the cluster assignment based on 40 variables available during acute medical treatment of accident victims was limited. A subset of individuals show symptoms of mental health disorders including symptoms of PTSD when assessed at least 6 months after mountain sport accident. Since early identification of these vulnerable patients remains challenging, psychoeducational measures for all patients and low-threshold access to mental health support are key for a successful interdisciplinary management of victims of mountain sport accidents.

Machine Learning Models Identify Inhibitors of New Delhi Metallo-β-lactamase.

The worldwide spread of the metallo-β-lactamases (MBL), especially New Delhi metallo-β-lactamase-1 (NDM-1), is threatening the efficacy of β-lactams, which are the most potent and prescribed class of antibiotics in the clinic. Currently, FDA-approved MBL inhibitors are lacking in the clinic even though many strategies have been used in inhibitor development, including quantitative high-throughput screening (qHTS), fragment-based drug discovery (FBDD), and molecular docking. Herein, a machine learning-based prediction tool is described, which was generated using results from HTS of a large chemical library and previously published inhibition data. The prediction tool was then used for virtual screening of the NIH Genesis library, which was subsequently screened using qHTS. A novel MBL inhibitor was identified and shown to lower minimum inhibitory concentrations (MICs) of Meropenem for a panel of E. coli and K. pneumoniae clinical isolates expressing NDM-1. The mechanism of inhibition of this novel scaffold was probed utilizing equilibrium dialyses with metal analyses, native state electrospray ionization mass spectrometry, UV-vis spectrophotometry, and molecular docking. The uncovered inhibitor, compound 72922413, was shown to be 9-hydroxy-3-[(5-hydroxy-1-oxa-9-azaspiro[5.5]undec-9-yl)carbonyl]-4H-pyrido[1,2-a]pyrimidin-4-one.

Machine learning-based prediction models affecting the recovery of postoperative bowel function for patients undergoing colorectal surgeries

PurposeThe debate surrounding factors influencing postoperative flatus and defecation in patients undergoing colorectal resection prompted this study. Our objective was to identify independent risk factors and develop prediction models for postoperative bowel function in patients undergoing colorectal surgeries.MethodsA retrospective analysis of medical records was conducted for patients who undergoing colorectal surgeries at Peking University People’s Hospital from January 2015 to October 2021. Machine learning algorithms were employed to identify risk factors and construct prediction models for the time of the first postoperative flatus and defecation. The prediction models were evaluated using sensitivity, specificity, the Youden index, and the area under the receiver operating characteristic curve (AUC) through logistic regression, random forest, Naïve Bayes, and extreme gradient boosting algorithms.ResultsThe study included 1358 patients for postoperative flatus timing analysis and 1430 patients for postoperative defecation timing analysis between January 2015 and December 2020 as part of the training phase. Additionally, a validation set comprised 200 patients who undergoing colorectal surgeries from January to October 2021. The logistic regression prediction model exhibited the highest AUC (0.78) for predicting the timing of the first postoperative flatus. Identified independent risk factors influencing the time of first postoperative flatus were Age (p < 0.01), oral laxatives for bowel preparation (p = 0.01), probiotics (p = 0.02), oral antibiotics for bowel preparation (p = 0.02), duration of operation (p = 0.02), postoperative fortified antibiotics (p = 0.02), and time of first postoperative feeding (p < 0.01). Furthermore, logistic regression achieved an AUC of 0.72 for predicting the time of first postoperative defecation, with age (p < 0.01), oral antibiotics for bowel preparation (p = 0.01), probiotics (p = 0.01), and time of first postoperative feeding (p < 0.01) identified as independent risk factors.ConclusionsThe study suggests that he use of probiotics and early recovery of diet may enhance the recovery of bowel function in patients undergoing colorectal surgeries. Among the various analytical methods used, logistic regression emerged as the most effective approach for predicting the timing of the first postoperative flatus and defecation in this patient population.

Machine learning-based prediction of length of stay (LoS) in the neonatal intensive care unit using ensemble methods

AbstractNeonatal medical data holds critical information within the healthcare industry, and it is important to analyze this data effectively. Machine learning algorithms offer powerful tools for extracting meaningful insights from the medical data of neonates and improving treatment processes. Knowing the length of hospital stay in advance is very important for managing hospital resources, healthcare personnel, and costs. Thus, this study aims to estimate the length of stay for infants treated in the Neonatal Intensive Care Unit (NICU) using machine learning algorithms. Our study conducted a two-class prediction for long and short-term lengths of stay utilizing a unique dataset. Adopting a hybrid approach called Classifier Fusion-LoS, the study involved two stages. In the initial stage, various classifiers were employed including classical models such as Logistic Regression, ExtraTrees, Random Forest, KNN, Support Vector Classifier, as well as ensemble models like AdaBoost, GradientBoosting, XGBoost, and CatBoost. Random Forest yielded the highest validation accuracy at 0.94. In the subsequent stage, the Voting Classifier—an ensemble method—was applied, resulting in accuracy increasing to 0.96. Our method outperformed existing studies in terms of accuracy, including both neonatal-specific length of stay prediction studies and other general length of stay prediction research. While the length of stay estimation offers insights into the potential suitability of the incubators in the NICUs, which are not universally available in every city, for patient admission, it plays a pivotal role in delineating the treatment protocols of patients. Additionally, the research provides crucial information to the hospital management for planning such as beds, equipment, personnel, and costs.

Machine learning-based prediction of polaron-vacancy patterns on the TiO2(110) surface

The multifaceted physics of oxides is shaped by their composition and the presence of defects, which are often accompanied by the formation of polarons. The simultaneous presence of polarons and defects, and their complex interactions, pose challenges for first-principles simulations and experimental techniques. In this study, we leverage machine learning and a first-principles database to analyze the distribution of surface oxygen vacancies (VO) and induced small polarons on rutile TiO2(110), effectively disentangling the interactions between polarons and defects. By combining neural-network supervised learning and simulated annealing, we elucidate the inhomogeneous VO distribution observed in scanning probe microscopy (SPM). Our approach allows us to understand and predict defective surface patterns at enhanced length scales, identifying the specific role of individual types of defects. Specifically, surface-polaron-stabilizing VO-configurations are identified, which could have consequences for surface reactivity.

Machine learning-based prediction of intensive care during hospitalization for COVID-19 using laboratory test results at admission

Machine learning-based prediction of intensive care during hospitalization for COVID-19 using laboratory test results at admission

Machine learning-based prediction of abdominal aortic aneurysms for individualized patient care: Presented at the Forty-eighth Annual Symposium for the Society of Clinical Vascular Surgery, Miami, Florida, March 14-17, 2021.

Machine learning-based prediction of abdominal aortic aneurysms for individualized patient care: Presented at the Forty-eighth Annual Symposium for the Society of Clinical Vascular Surgery, Miami, Florida, March 14-17, 2021.

Machine Learning-Based Prediction of Stability in High-Entropy Nitride Ceramics

The field of materials science has experienced a transformative shift with the emergence of high-entropy materials (HEMs), which possess a unique combination of properties that traditional single-phase materials lack. Among these, high-entropy nitrides (HENs) stand out for their exceptional mechanical strength, thermal stability, and resistance to extreme environments, making them highly sought after for applications in aerospace, defense, and energy sectors. Central to the design of these materials is their entropy forming ability (EFA), a measure of a material’s propensity to form a single-phase, disordered structure. This study introduces the application of the sure independence screening and sparsifying operator (SISSO), a machine learning technique, to predict the EFA of HEN ceramics. By utilizing a rich dataset curated from theoretical computational data, SISSO has been trained to identify the most critical features contributing to EFA. The model’s strong interpretability allows for the extraction of complex mathematical expressions, providing deep insights into the material’s composition and its impact on EFA. The predictive performance of the SISSO model is meticulously validated against theoretical benchmarks and compared with other machine learning methodologies, demonstrating its superior accuracy and reliability. This research not only contributes to the growing body of knowledge on HEMs but also paves the way for the efficient discovery and development of new HEN materials with tailored properties for advanced technological applications.

Machine Learning-Based Prediction of Reduction Potentials for PtIV Complexes.

Some of the well-known drawbacks of clinically approved PtII complexes can be overcome using six-coordinate PtIV complexes as inert prodrugs, which release the corresponding four-coordinate active PtII species upon reduction by cellular reducing agents. Therefore, the key factor of PtIV prodrug mechanism of action is their tendency to be reduced which, when the involved mechanism is of outer-sphere type, is measured by the value of the reduction potential. Machine learning (ML) models can be used to effectively capture intricate relationships within PtIV complex data, leading to highly accurate predictions of reduction potentials and other properties, and offering significant insights into their electrochemical behavior and potential applications. In this study, a machine learning-based approach for predicting the reduction potentials of PtIV complexes based on relevant molecular descriptors is presented. Leveraging a data set of experimentally determined reduction potentials and a diverse range of molecular descriptors, the proposed model demonstrates remarkable predictive accuracy (MSE = 0.016 V2, RMSE = 0.13 V, R2 = 0.92). Ab initio calculations and a set of different machine learning algorithms and feature engineering techniques have been employed to systematically explore the relationship between molecular structure and similarity and reduction potential. Specifically, it has been investigated whether the reduction potential of these compounds can be described by combining ML models across different combinations of constitutional, topological, and electronic molecular descriptors. Our results not only provide insights into the crucial factors influencing reduction potentials but also offer a rapid and effective tool for the rational design of PtIV complexes with tailored electrochemical properties for pharmaceutical applications. This approach has the potential to significantly expedite the development and screening of novel PtIV prodrug candidates. The analysis of principal components and key features extracted from the model highlights the significance of structural descriptors of the 2D Atom Pairs type and the lowest unoccupied molecular orbital energy. Specifically, with just 20 appropriately selected descriptors, a notable separation of complexes based on their reduction potential value is achieved.

Machine Learning-Based Prediction of Malnutrition in Surgical In-Patients: A Validation Pilot Study.

Malnutrition in hospitalised patients can lead to serious complications, worse patient outcomes and longer hospital stays. State-of-the-art screening methods rely on scores, which need additional manual assessments causing higher workload. The aim of this prospective study was to validate a machine learning (ML)-based approach for an automated prediction of malnutrition in hospitalised patients. For 159 surgical in-patients, an assessment of malnutrition by dieticians was compared to the ML-based prediction conducted in the evening of admission. The model achieved an accuracy of 83.0% and an AUROC of 0.833 in the prospective validation cohort. The results of this pilot study indicate that an automated malnutrition screening could replace manual screening tools in hospitals.

Machine Learning-based Prediction Models for C difficile Infection: A Systematic Review.

Despite research efforts, predicting Clostridioides difficile incidence and its outcomes remains challenging. This systematic review aimed to evaluate the performance of machine-learning (ML) models in predicting CDI incidence and complications using clinical data from electronic health records. We conducted a comprehensive search of databases (OVID, Embase, MEDLINE ALL, Web of Science, and Scopus) from inception up to September 2023. Studies employing ML techniques for predicting CDI or its complications were included. The primary outcome was the type and performance of ML models assessed using the area under the receiver operating characteristic curve (AUROC). Twelve retrospective studies that evaluated CDI incidence and/or outcomes were included. The most common used ML models were random forest and Gradient Boosting. The AUROC ranged from 0.60 to 0.81 for predicting CDI incidence, 0.59 to 0.80 for recurrence, and 0.64 to 0.88 for predicting complications. Advanced ML models demonstrated similar performance to traditional logistic regression. However, there was notable heterogeneity in defining CDI and the different outcomes, including incidence, recurrence, and complications, and a lack of external validation in most studies. ML models show promise in predicting CDI incidence and outcomes. However, the observed heterogeneity in CDI definitions and the lack of real-world validation highlight challenges in clinical implementation. Future research should focus on external validation and the use of standardized definitions across studies.

Prediction of Pralidoxime Dose in Patients with Organophosphate Poisoning Using Machine Learning Techniques

Background: Early and appropriate antidotal therapy is crucial for patients with organophosphate poisoning. Objectives: Given the lack of a comprehensive consensus on the optimal dose of pralidoxime for patients with organophosphate poisoning, this study aims to develop a machine learning-based prediction model to determine the individualized pralidoxime dose for these patients. Methods: The dataset was divided into training and test sets with a 70:30 ratio. Feature selection was conducted using Pearson’s correlation coefficient (filter approach) method. Both classification and regression were employed to develop the prediction model using the selected features. The performance of the developed models was evaluated using ten-fold cross-validation and various metrics, including sensitivity, specificity, accuracy, F1-score, and AUC. The models were implemented and assessed using the scikit-learn library in Python. Results: After applying exclusion criteria, data from 325 patients were utilized to train and test the machine-learning models. In the classification approach, the random forest method achieved superior performance with an AUC of 98.6. In the regression approach, the gradient boosting regressor, with an R2 value of 65.4, outperformed other algorithms. Feature selection revealed that muscular weakness, plasma cholinesterase activity, and blood urea nitrogen were the most significant predictors of pralidoxime dose in the classification model. In the regression model, the top predictors were age, HCO3-VBG, and atropine bolus. Many of the selected features coincide with those identified in previous studies, with muscular weakness being particularly significant in both models. Conclusions: The most effective algorithms could be employed to develop a clinical decision support system for personalized pralidoxime dosage prediction in patients with organophosphorus poisoning. However, the study is constrained by its small sample size, retrospective design, and the absence of an external validation cohort. Conducting a prospective multicenter study with a larger sample size is crucial to validate the findings of this study.

DETECTA – MULTIPLE DISEASE DETECTION

Machine Learning Techniques for Predictive Analytics in Healthcare There are multiple techniques in machine learning that can in a variety of industries, do predictive analytics on large amounts of data. Predictive analytics in healthcare is a difficult endeavor, but it can eventually assist practitioners in making timely decisions regarding patients' health and treatment based on massive data. Diseases like Breast cancer, diabetes, and heart-related diseases are causing many deaths globally but most of these deaths are due to the lack of timely check-ups of the diseases. The above problem occurs due to a lack of medical infrastructure and a low ratio of doctors to the population. The statistics clearly show the same, WHO recommended, the ratio of doctors to patients is 1:1000 whereas India's doctor-to- population ratio is 1:1456, this indicates the shortage of doctors. The diseases related to heart, cancer, and diabetes can cause a potential threat to mankind, if not found early. Therefore, early recognition and diagnosis of these diseases can save a lot of lives. This work is all about predicting diseases that are harmful using machine learning classification algorithms. In this work, breast cancer, heart, and diabetes are included. To make this work seamless and usable by the mass public, our team made a medical test web application that makes predictions about various diseases using the concept of machine learning. In this work, our aim to develop a disease-predicting web app that uses the concept of machine learning-based predictions about various diseases like Breast cancer, Diabetes, Heart diseases, Covid, Pneumonia, Alzheimer.

Interpretable Machine Learning-Based Prediction Model for Concrete Cover Separation of FRP-Strengthened RC Beams.

This study focuses on the prediction of concrete cover separation (CCS) in reinforced concrete beams strengthened by fiber-reinforced polymer (FRP) in flexure. First, machine learning models were constructed based on linear regression, support vector regression, BP neural networks, decision trees, random forests, and XGBoost algorithms. Secondly, the most suitable model for predicting CCS was identified based on the evaluation metrics and compared with the codes and the researcher's model. Finally, a parametric study based on SHapley Additive exPlanations (SHAP) was carried out, and the following conclusions were obtained: XGBoost is best-suited for the prediction of CCS and codes, and researchers' model accuracy needs to be improved and suffers from over or conservative estimation. The contributions of the concrete to the shear force and the yield strength of the reinforcement are the most important parameters for the CCS, where the shear force at the onset of CCS is approximately proportional to the contribution of the concrete to the shear force and approximately inversely proportional to the yield strength of the reinforcement.