Disease Prediction Model Research Articles

Comparative Analysis of Machine Learning, Decision Trees, and K-Nearest Neighbors for Heart Disease Prediction

Abstract. This study investigates the efficacy of Machine Learning (ML), Decision Trees, and K-Nearest Neighbors (KNN) techniques in predicting heart disease, aiming to identify their strengths and limitations. ML models are effective in detecting complex patterns and delivering evolving predictions from large datasets but require high-quality data and can be challenging to interpret. Decision Trees provide clear, understandable decision rules, which is beneficial in clinical settings, yet they are susceptible to overfitting and instability. KNN, valued for its simplicity and flexibility, classifies heart disease based on similarity but struggles with high computational costs and sensitivity to noisy data. Experimental results indicate that each model has distinct advantages: ML excels in pattern recognition, Decision Trees offer interpretability, and KNN handles diverse data effectively. However, each also faces challenges that impact performance, such as data quality issues for ML, overfitting for Decision Trees, and computational demands for KNN. The study suggests that balancing these strengths and weaknesses is crucial for optimizing heart disease prediction models. Future research should explore hybrid approaches that combine these models' advantages while addressing their respective limitations to improve predictive accuracy and practical application in real-world scenarios.

Machine Learning Techniques for Heart Disease Prediction Using a Multi-Algorithm Approach

This analysis explores the efficiency of machine learning systems for heart disease identification through a multi-algorithm approach. The main objective is to identify the best performing algorithm for accurate disease prediction, improving clinical decision making. Using criteria including accuracy, precision, recall, F1 score, and recall, the study assessed four algorithms: Random Forest (RF), Naïve Bayes (NB), Support Vector Machine (SVM), and Decision Tree (DT). The results show that Random Forest outperforms the others, achieving 86.23% precision, 93.76% recall, 89.84% F1 score, and 88.41% accuracy. Random Forest gets an AUC ROC result of 0.94, so Random Forest is considered a superior model in this scenario, especially because it has higher accuracy. The algorithms showed a strong balance between sensitivity and specificity. Decision Tree showed reasonable performance with a precision of 84.18% and a recall of 90.27%, while Naïve Bayes recorded a precision of 87.68% and a recall of 87.03%. SVM showed a precision of 87.40% and a recall of 84.78%, indicating some limitations in capturing positive cases. The novelty of this study lies in the comparative analysis of several algorithms to optimize the heart disease prediction model for clinical use. The random forest algorithm is one of the choices, but there is still a medical standard for classifying people as either indicating or not experiencing heart failure, according to the study.

Integrating the Polysocial Risk Score: Enhancing Comprehensive Healthcare Delivery.

Social determinants of health (SDOH) are known to determine a significant portion of a person's health, influencing downstream outcomes and widespread disparities. Screening for SDOH in clinical practice can improve efficacy of medical care, highlighting the potential for polysocial risk scores (PsRS) to help evaluate a patient's risk of developing atherosclerotic cardiovascular disease and other conditions. This review highlights existing research about the efficacy of PsRS in practical risk assessment, current gaps in the literature, and opportunities to refine the design and implementation of PsRS in real-world clinical settings. PsRS present unique opportunities to improve traditional risk prediction models for heart disease and other conditions, particularly if they examine both individual and area-level SDOH. Future studies should assess novel methods for extracting SDOH data from patients' medical records as well as PsRS implementation strategies that promote efficiency and patient confidentiality in real-world clinical settings.

Transfer Learning with Hybrid Firefly Butterfly Optimization Feature Selection Model for Early Parkinson Disease Prediction

Transfer Learning with Hybrid Firefly Butterfly Optimization Feature Selection Model for Early Parkinson Disease Prediction

From inflammation to depression: key biomarkers for IBD-related major depressive disorder.

Inflammatory bowel disease (IBD) is a chronic, inflammatory, and autoimmune disorder, and its incidence of comorbid with major depressive disorder (MDD) is significantly higher than the general population. However, many patients lack proper recognition and necessary psychological health treatments. We aimed to identify potential biomarkers and mechanisms involved in the development of IBD comorbid with MDD (IBD-MDD). We utilized IBD and MDD-related datasets from the GEO database for differential gene expression analysis, protein-protein interaction (PPI) and pathway enrichment analysis, random forest algorithm, LASSO regression analysis, and construction of a disease prediction model. We assessed the accuracy of the model using ROC curve, explored potential mechanisms through immune infiltration analysis, and validated candidate biomarkers using peripheral blood samples from patients in our center's cohort. We identified 484 IBD-related secreted proteins and 142 key module genes associated with MDD. PPI analysis revealed two crucial modules primarily involved in inflammation and immune regulation. We identified four diagnostic genes (HGF, SPARC, ADAM12, and MMP8) from the 21 shared genes between IBD-related secreted proteins and MDD key module genes, constructed a nomogram model and confirmed its accuracy using ROC curve from an external independent dataset. Immune infiltration analysis revealed significant associations between the four diagnostic genes, and cellular immune dysregulation in MDD. Finally, we validated the expression patterns of the four diagnostic genes in our cohort. Our study discovered four candidate biomarkers for IBD-MDD, providing new insights for the diagnosis and therapeutic intervention of serum-based IBD comorbid with MDD.

Boosting the accuracy of existing models by updating and extending: using a multicenter COVID-19 ICU cohort as a proxy

Most published prediction models for Coronavirus Disease 2019 (COVID-19) were poorly reported, at high risk of bias, and heterogeneous in model performance. To tackle methodological challenges faced in previous prediction studies, we investigated whether model updating and extending improves mortality prediction, using the Intensive Care Unit (ICU) as a proxy. All COVID-19 patients admitted to seven ICUs in the Euregio-Meuse Rhine during the first pandemic wave were included. The 4C Mortality and SEIMC scores were selected as promising prognostic models from an external validation study. Five predictors could be estimated based on cohort size. TRIPOD guidelines were followed and logistic regression analyses with the linear predictor, APACHE II score, and country were performed. Bootstrapping with backward selection was applied to select variables for the final model. Additionally, shrinkage was performed. Model discrimination was displayed as optimism-corrected areas under the ROC curve and calibration by calibration slopes and plots. The mortality rate of the 551 included patients was 36%. Discrimination of the 4C Mortality and SEIMC scores increased from 0.70 to 0.74 and 0.70 to 0.73 and calibration plots improved compared to the original models after updating and extending. Mortality prediction can be improved after updating and extending of promising models.

ML-powered Internet of Medical Things (MLIoMT) Structure for Heart Disease Prediction

Background ML-powered Internet of Medical Things (MLIoMT) is a burgeoning framework poised to transform healthcare, particularly in the timely identification of heart disease. Objectives This article proposes an innovative MLIoMT structure aimed at leveraging machine learning (ML) algorithms for heart disease detection. Materials and Methods Through the integration of wearable sensors, mobile applications, cloud computing, and advanced ML techniques, MLIoMT enables continuous monitoring of vital signs and cardiac health indicators in real time. By analyzing this data stream, abnormalities indicative of heart disease can be detected early, facilitating timely intervention and personalized healthcare recommendations. The MLIoMT framework employs diverse ML methods, such as deep learning and ensemble techniques to enhance the accuracy and reliability of heart disease prediction models. Results The proposed structure holds promise for revolutionizing preventive healthcare, enabling proactive management of cardiac health, and ultimately reducing the burden of heart disease. Results in terms of accuracy, precision, recall and F1 score show that the proposed system has better performance and efficiency. Conclusion Overall, MLIoMT represents a significant advancement in healthcare technology, with the potential to improve patient outcomes and enhance overall quality of life.

Generalization Investigation in Heart Disease Prediction: Comparative Analysis of MLP, Random Forest, and SVM with Cross-Domain Datasets

The traditional way of predicting heart disease is usually through the subjective judgment of doctors, which is high subjectivity. Current machine learning methods do not pay enough attention to its universality. The two datasets used in this study are from Kaggle and preprocessed in advance, including standardization by using Z-Score and dimensionality reduction by KPCA. The two datasets were designated as the source domain and the target domain. The source domain dataset was further divided into two subsets with an 80:20 split, where 80% was used for training the model and the remaining 20% served as the test set. The trained model was then applied to the target domain to compare the differences in prediction results. Through the exploration of Multilayer Perceptron (MLP), Random Forest and Support Vector Machine (SVM), for the data set used in this study, when MLP uses a simple structure, the difference in prediction accuracy dropped from 13.8% to 5.07. For Random Forest, by increasing the number of decision trees and decreasing the minimum number of samples required for splitting, the difference is reduced from 15.6% to 9.32%. By modifying the penalty parameter C value of SVM, the difference on different datasets is reduced from 13.39% to 4.46%. This study is one of the few to explore the generalizations of heart disease prediction. The results demonstrate that the generalization performance of the model for heart disease prediction can be significantly enhanced through appropriate modifications to its structure and hyperparameters.

Enhancing Heart Disease Prediction through Machine Learning: A Comparative Analysis of Algorithm Generalization across Datasets with Various Distributions

Heart disease, due to its high prevalence and mortality, remains a key area of global research. Although traditional diagnostic methods are effective, they are often invasive and time-consuming, highlighting the need for non-invasive, AI-based approaches. A significant challenge in real-world applications is ensuring model generalization across different datasets, particularly when the datasets are small. In this study, the performance of machine learning models, including Decision Tree, Random Forest, Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP), was evaluated on two distinct heart disease datasets with different distributions and relatively small sizes. Two datasets with varying distributions were used for training and testing, with the primary focus on assessing model generalization in crossdataset applications. It is shown in the results that, while the Decision Tree model performed best after hyperparameter tuning, the improvements in Random Forest and MLP were limited, and SVM exhibited a decline in performance after tuning in the cross-dataset task. It was found that grid search tuning has limitations in cross-dataset scenarios, especially with small datasets, where complex models are prone to overfitting. The study demonstrates that, with smaller datasets, simpler models like Decision Trees often adapt better to different datasets. Furthermore, transfer learning and domain adaptation techniques are suggested as crucial for improving model generalization. Future research should focus on employing these techniques to enhance the robustness and accuracy of heart disease prediction models across diverse datasets.

The Molecular Classification of Pheochromocytomas and Paragangliomas: Discovering the Genomic and Immune Landscape of Metastatic Disease.

Pheochromocytomas (PCCs) and paragangliomas (PGLs, together PPGLs) are the most hereditary tumors known. PPGLs were considered benign, but the fourth edition of the World Health Organisation (WHO) classification redefined all PPGLs as malignant neoplasms with variable metastatic potential. The metastatic rate differs based on histopathology, genetic background, size, and location of the tumor. The challenge in predicting metastatic disease lies in the absence of a clear genotype-phenotype correlation among the more than 20 identified genetic driver variants. Recent advances in molecular clustering based on underlying genetic alterations have paved the way for improved cluster-specific personalized treatments. However, despite some clusters demonstrating a higher propensity for metastatic disease, cluster-specific therapies have not yet been widely adopted in clinical practice. Comprehensive genomic profiling and transcriptomic analyses of large PPGL cohorts have identified potential new biomarkers that may influence metastatic potential. It appears that no single biomarker alone can reliably predict metastatic risk; instead, a combination of these biomarkers may be necessary to develop an effective prediction model for metastatic disease. This review evaluates current guidelines and recent genomic and transcriptomic findings, with the aim of accurately identifying novel biomarkers that could contribute to a predictive model for mPPGLs, thereby enhancing patient care and outcomes.

Advances in Plant Disease Diagnostics and Surveillance- A review

Plant diseases pose a significant threat to global food security, leading to substantial yield losses and economic impacts. Early detection and effective monitoring are crucial for managing plant diseases, yet traditional diagnostic methods such as visual inspections, serological tests, and molecular assays face limitations in sensitivity, specificity, and scalability. In recent years, advancements in diagnostic and surveillance technologies have revolutionized plant health management. Next-Generation Sequencing (NGS) enables comprehensive pathogen profiling, while CRISPR-based diagnostics offer rapid and highly specific detection. Similarly, biosensors and portable devices provide on-site diagnostics, and machine learning and AI applications enhance the analysis of complex datasets, supporting automated disease identification and predictive modeling. Concurrently, advances in disease surveillance through remote sensing technologies, including satellites and Unmanned Aerial Vehicles (UAVs), enable large-scale, real-time monitoring of crop health, detecting disease outbreaks and facilitating targeted interventions. Integrating these diverse technologies into multi-platform systems offers a holistic approach to plant disease management, combining molecular diagnostics, environmental monitoring, and digital platforms to support data-driven decision-making. Several challenges remain, including high costs, technical complexities, and the need for standardized data integration. Addressing these barriers is essential to ensure that these technologies are accessible and effective across various agricultural systems, particularly in resource-limited settings. Future research should focus on enhancing the robustness, affordability, and scalability of these tools while promoting interdisciplinary collaborations.

Unveiling diagnostic information for type 2 diabetes through interpretable machine learning

The interpretability of disease prediction models is often crucial for their trustworthiness and usability among medical practitioners. Existing methods in interpretable artificial intelligence improve model transparency but fall short in identifying precise, disease-specific primal information. In this work, an interpretable deep learning-based algorithm called the data space landmark refiner was developed, which not only enhances both global interpretability and local interpretability but also reveals the intrinsic information of the data distribution. Using the proposed method, a type 2 diabetes mellitus diagnostic model with high interpretability was constructed on the basis of the electronic health records from two hospitals. Moreover, effective diagnostic information was directly derived from the model’s internal parameters, demonstrating strong alignment with current clinical knowledge. Compared with conventional interpretable machine learning approaches, the proposed method offered more precise and specific interpretability, increasing clinical practitioners’ trust in machine learning-supported diagnostic models.

From COVID-19 to monkeypox: a novel predictive model for emerging infectious diseases

The outbreak of emerging infectious diseases poses significant challenges to global public health. Accurate early forecasting is crucial for effective resource allocation and emergency response planning. This study aims to develop a comprehensive predictive model for emerging infectious diseases, integrating the blending framework, transfer learning, incremental learning, and the biological feature Rt to increase prediction accuracy and practicality. By transferring features from a COVID-19 dataset to a monkeypox dataset and introducing dynamically updated incremental learning techniques, the model's predictive capability in data-scarce scenarios was significantly improved. The research findings demonstrate that the blending framework performs exceptionally well in short-term (7-day) predictions. Furthermore, the combination of transfer learning and incremental learning techniques significantly enhanced the adaptability and precision, with a 91.41% improvement in the RMSE and an 89.13% improvement in the MAE. In particular, the inclusion of the Rt feature enabled the model to more accurately reflect the dynamics of disease spread, further improving the RMSE by 1.91% and the MAE by 2.17%. This study underscores the significant application potential of multimodel fusion and real-time data updates in infectious disease prediction, offering new theoretical perspectives and technical support. This research not only enriches the theoretical foundation of infectious disease prediction models but also provides reliable technical support for public health emergency responses. Future research should continue to explore integrating data from multiple sources and enhancing model generalization capabilities to further enhance the practicality and reliability of predictive tools.

Air pollution’s numerical, spatial, and temporal heterogeneous impacts on childhood hand, foot and mouth disease: a multi-model county-level study from China

BackgroundWhile stationary links between childhood hand, foot and mouth disease (HFMD) and air pollution are known, a comprehensive study on their heterogeneous relationships (nonstationarity), jointly considering numerical, temporal and spatial dimensions, has not been reported.MethodsMonthly HFMD incidence and air pollution data were collected at the county level from Sichuan-Chongqing, China (2009–2011), alongside meteorological and social environmental covariates. Key influential factors were identified using random forest (RF) under the stationary assumption. Factors’ numerically, temporally, and spatially heterogeneous relationships with HFMD were assessed using generalized additive model (GAM) and geographically and temporally weighted regression (GTWR).ResultsOur findings highlighted the relatively higher stationary contributions of fine particulate matter (PM2.5) and ozone (O3) to HFMD incidence across Sichuan-Chongqing counties. We further uncovered heterogeneous impacts of PM2.5 and O3 from three nonstationary perspectives. Numerically, PM2.5 showed an inverse ‘V’-shaped relationship with HFMD incidence, while O3 exhibited a complex pattern, with increased HFMD incidence at low PM2.5 and moderate O3 concentrations. Temporally, PM2.5’s impact peaked in autumn and was weakest in spring, whereas O3’s effect was strongest in summer. Spatially, hotspot mapping revealed high-risk clusters for PM2.5 impact across all seasons, with notable geographical variations, and for O3 in spring, summer, and autumn, concentrated in specific regions of Sichuan-Chongqing.ConclusionsThis study underscores the nuanced and three-perspective heterogeneous influences of air pollution on HFMD in small areas, emphasizing the need for differentiated, localized, and time-sensitive prevention and control strategies to enhance the precision of dynamic early warnings and predictive models for HFMD and other infectious diseases, particularly in the fields of environmental and spatial epidemiology.

Smart Vision Transparency: Efficient Ocular Disease Prediction Model Using Explainable Artificial Intelligence

The early prediction of ocular disease is certainly an obligatory concern in the domain of ophthalmic medicine. Although modern scientific discoveries have shown the potential to treat eye diseases by using artificial intelligence (AI) and machine learning, explainable AI remains a crucial challenge confronting this area of research. Although some traditional methods put in significant effort, they cannot accurately predict the proper ocular diseases. However, incorporating AI into diagnosing eye diseases in healthcare complicates the situation as the decision-making process of AI demonstrates complexity, which is a significant concern, especially in major sectors like ocular disease prediction. The lack of transparency in the AI models may hinder the confidence and trust of the doctors and the patients, as well as their perception of the AI and its abilities. Accordingly, explainable AI is significant in ensuring trust in the technology, enhancing clinical decision-making ability, and deploying ocular disease detection. This research proposed an efficient transfer learning model for eye disease prediction to transform smart vision potential in the healthcare sector and meet conventional approaches’ challenges while integrating explainable artificial intelligence (XAI). The integration of XAI in the proposed model ensures the transparency of the decision-making process through the comprehensive provision of rationale. This proposed model provides promising results with 95.74% accuracy and explains the transformative potential of XAI in advancing ocular healthcare. This significant milestone underscores the effectiveness of the proposed model in accurately determining various types of ocular disease. It is clearly shown that the proposed model is performing better than the previously published methods.

An efficient plant disease prediction model using darner drain fly optimization-based deep convolutional neural network

An efficient plant disease prediction model using darner drain fly optimization-based deep convolutional neural network

PREDIKSI PENYAKIT JANTUNG MENGGUNAKAN METODE RANDOM FOREST DAN PENERAPAN PRINCIPAL COMPONENT ANALYSIS (PCA)

Heart disease is a significant public health issue and the leading cause of death worldwide. Risk factors such as hypertension, diabetes, obesity, sedentary lifestyle, smoking, and genetic factors contribute to the development of heart disease. This study aims to develop a heart disease prediction model using the Random Forest method. The dataset used comes from the UCI Machine Learning Repository, containing data from 1026 patients with various health features. The methods used include the stages of knowledge discovery in databases (KDD), namely data selection, preprocessing, transformation, data mining, and evaluation. The study results show that the model with 100 decision trees achieved an accuracy of 0.9823. Further evaluation using the confusion matrix and classification report indicates that the Random Forest method provides 98% accuracy, 100% precision, 96% recall, and a 98% F1-score. In conclusion, the Random Forest method is effective in predicting heart disease, with features such as thal having a significant impact on model accuracy.

Development and external validation of a prediction model for interstitial lung disease in systemic lupus erythematosus patients: A cross-sectional study

ObjectiveThe aim of this study is to develop and validate a nomogram that can assist clinicians in identifying female systemic lupus erythematosus (SLE) patients of reproductive age complicated with interstitial lung disease (ILD). MethodsClinical, laboratory data of SLE patients were first collected. Meteorological data were then gathered according to the geographical locations of the SLE patients. Diagnostic results, univariate logistic regression, elastic net regression, and multivariate logistic regression were used to screen for risk factors for female SLE patients of reproductive age complicated with ILD. A nomogram was constructed using these risk factors and was internally and externally validated through methods such as calculating the concordance index, plotting calibration curves, drawing receiver operating characteristic curves, and clinical decision curves. ResultsA total of 4798 SLE patients were included in this study, with 2488 patients in the development set and 2310 patients in the external validation set. The patients in the development set were randomly divided into a training set (N = 1742) and an internal testing set (N = 746) at a ratio of 7:3. Eight independent risk factors for ILD were identified, including APOB, APOA1, ALP, PLT, HCT, EOS-R, LYM-R, and age. The nomogram model was developed, and the areas under the receiver operating characteristic curve was 0.811 (0.748, 0.875), 0.820 (0.727,0.913), and 0.889 (0.869, 0.909) for the three sets, respectively. ConclusionWe established a nomogram model using easily accessible clinical and laboratory data to predict the probability of female SLE patients of reproductive age developing ILD.

Development of a prediction model for the incidence of type 2 diabetic kidney disease and its application based on a regional health data platform

Objective: To construct a risk prediction model for diabetes kidney disease (DKD). Methods: Patients newly diagnosed with type 2 diabetes mellitus (T2DM) between January 1, 2015, and December 31, 2022, were selected as study subjects from the Yinzhou Regional Health Information Platform in Ningbo City. The Lasso method was used to screen the risk factors, and the DKD risk prediction model was established using Cox proportional hazard regression models. Bootstrap 500 resampling was applied for internal validation. Results: The study included 49 706 subjects, with an median (Q1, Q3) age of 60.00 (50.00, 68.00) years old, and 55% were male. A total of 4 405 subjects eventually developed DKD. Age at first diagnosis of T2DM, BMI, education level, fasting plasma glucose, glycated hemoglobin A1c, urinary albumin, past medical history (hyperuricemia, rheumatic diseases), triglycerides, and estimated glomerular filtration rate were included in the final model. The final model's C-index was 0.653, with an average of 0.654 after Bootstrap correction. The final model's area under the receiver operating characteristic curve for predicting 4-year, 5-year, and 6-year was 0.657, 0.659, and 0.664, respectively. The calibration curve was closely aligned with the ideal curve. Conclusions: This study constructed a DKD risk prediction model for newly diagnosed T2DM patients based on real-world data that is simple, easy to use, and highly practical. It provides a reliable basis for screening high-risk groups for DKD.

Risk factor analysis and prediction model construction for severe adenovirus pneumonia in children

BackgroundSevere adenovirus pneumonia in children has a high mortality rate, but research on risk prediction models is lacking. Such models are essential as they allow individualized predictions and assess whether children will likely progress to severe disease.MethodsA retrospective analysis was performed on children with adenovirus pneumonia who were hospitalized at the Children’s Hospital of Nanjing Medical University from January 2017 to March 2024. The patients were grouped according to clinical factors, and the groups were compared using Ridge regression and multiple logistic regression to identify risk factors associated with severe adenovirus pneumonia. A prediction model was constructed, and its value in clinical application was evaluated.Results699 patients were included in the study, with 284 in the severe group and 415 in the general group. Through the screening of 44 variables, the final risk factors for severe adenovirus pneumonia in children as the levels of neutrophils (OR = 1.086, 95% CI: 1.054‒1.119, P < 0.001), D-dimer (OR = 1.005, 95% CI: 1.003‒1.007, P < 0.001), fibrinogen degradation products (OR = 1.341, 95% CI: 1.034‒1.738, P = 0.027), B cells (OR = 1.076, 95%CI: 1.046‒1.107, P < 0.001), and lactate dehydrogenase (OR = 1.008, 95% CI: 1.005‒1.011, P < 0.001). The value of the area under the receiver operating characteristic curve was 0.974, the 95% CI was 0.963–0.985, and the P-value of the Hosmer-Lemeshow test was 0.547 (P > 0.05), indicating that the model had strong predictive power.ConclusionIn this study, the clinical variables of children with adenovirus pneumonia were retrospectively analyzed to identify risk factors for severe disease. A prediction model for severe disease was constructed and evaluated, showing good application value.