The aim of this study was to compare the performance of 4 machine learning models—Lasso regression model, random forest model, Boruta algorithm model, and the Boruta algorithm combined with Lasso regression—in predicting stroke risk among hypertensive patients. The study evaluated the strengths and weaknesses of each model to provide a more clinically valuable prediction model for stroke risk. The study included 3472 hypertensive patients, of which 312 had experienced a stroke, and 3160 had not. Various health indicators were analyzed using Lasso regression, random forest, Boruta algorithm, and the Boruta algorithm combined with Lasso regression. Model performance was evaluated based on the area under the curve (AUC) of the receiver operating characteristic curve, the precision–recall curve, calibration curve, and decision curve analysis to assess classification ability, precision, calibration, and clinical benefit. The Lasso regression and Boruta algorithm models both have an AUC of 0.716, making them the best-performing models in terms of classification ability. The Boruta algorithm combined with Lasso regression model has an AUC of 0.705, slightly lower than the previous 2 models but still shows good predictive capability, with better interpretability due to feature selection. The random forest model has an AUC of 0.626, which is the lowest among the models, indicating weaker classification performance compared to the others. Among the 4 models, the Lasso regression model and Boruta algorithm model performed similarly in terms of classification ability, both demonstrating moderate predictive power, while the random forest model performed relatively poorly. The Boruta combined with Lasso regression model was precise in variable selection but had limited clinical utility. Therefore, the Lasso regression model appears to be the most balanced in predicting stroke risk and is the recommended model based on this study.

Diagnosis of hydrocephalus involves a careful check of the patient’s history and thorough neurological assessment. The traditional diagnosis has predominantly depended on the professional judgment of physicians based on clinical experience, but with the advancement of precision medicine and individualized treatment, such experience-based methods are no longer sufficient to keep pace with current clinical requirements. To fit this adjustment, the medical community actively devotes itself to data-driven intelligent diagnostic solutions. Building a prognosis prediction model for hydrocephalus has thus become a new focus, among which intelligent prediction systems supported by deep learning offer new technical advantages for clinical diagnosis and treatment decisions. Over the past several years, algorithms of deep learning have demonstrated conspicuous advantages in medical image analysis. Studies revealed that the accuracy rate of the diagnosis of hydrocephalus by magnetic resonance imaging can reach 90% through convolutional neural networks, while their sensitivity and specificity are also better than these of traditional methods. With the extensive use of medical technology in terms of deep learning, its successful use in modeling hydrocephalus prognosis has also drawn extensive attention and recognition from scholars. This review explores the application of deep learning in hydrocephalus diagnosis and prognosis, focusing on image-based, biochemical, and structured data models. Highlighting recent advancements, challenges, and future trajectories, the study emphasizes deep learning’s potential to enhance personalized treatment and improve outcomes.

Stroke is a serious condition associated with high rates of incidence and mortality. Timely and accurate risk assessment is critical for improving prevention and clinical intervention. This study investigates the application of machine learning models in evaluating the risk of stroke. The data for this study were drawn from the National Health and Nutrition Examination Survey, covering the years 1999 to 2002. To construct predictive models and select relevant variables, 3 approaches were applied: LASSO regression combined with stepwise selection, random forest, and the boruta algorithm in conjunction with LASSO regression. Model performance was evaluated through multiple metrics, including receiver operating characteristic and precision–recall curves, as well as calibration and decision curve analyses. The study analyzed data from 9922 participants, among whom 358 had a history of stroke. Key predictors were identified through a combination of LASSO and stepwise regression, producing a model with strong discriminative performance (area under the curve [AUC] = 0.843). In comparison, the random forest approach selected fewer predictors and showed lower predictive accuracy (AUC = 0.612). A model developed using the boruta algorithm followed by LASSO regression achieved a similarly high level of performance (AUC = 0.828). These findings illustrate how different variable selection methods can influence the predictive accuracy of the resulting models. The machine learning model, which is created using the National Health and Nutrition Examination Survey database, and serves as a reliable means of predicting stroke risk. There is every possibility to set up accurate predictive models with the help of different variable selection techniques and modeling methods that have high accuracy and clinical value.

To identify key risk factors for acute kidney injury (AKI) in patients with intracerebral hemorrhage (ICH) using bibliometric analysis and machine learning, and to explore the mediating role of hemoglobin (Hb) in the association between hypertension and AKI. A bibliometric analysis of English-language publications from 2014 to 2024 was conducted to evaluate research trends and thematic clusters related to ICH and AKI. Clinical data from 944 ICH patients in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database were analyzed, including 46 patients who developed AKI. A total of 120 machine learning model combinations were developed and compared using area under the receiver operating characteristic curve (AUC). SHapley Additive exPlanations (SHAP) and clustering heatmaps were employed to interpret feature importance and patient-level heterogeneity. Mediation analysis was used to assess the indirect effect of Hb on the relationship between hypertension and AKI. A total of 122 relevant publications were identified, revealing a growing academic focus on integrated neurocritical care and the emergence of stable interdisciplinary research clusters. Among the machine learning models, the Random Forest (RF) + NaiveBayes + Tree ensemble achieved the highest predictive performance (AUC = 0.764). SHAP analysis identified platelet count (PLT) as the most influential predictor of AKI risk. Clustering analysis revealed substantial heterogeneity in feature contributions across patient subgroups. Mediation analysis confirmed that Hb significantly and negatively mediated the effect of hypertension on AKI occurrence ( P < .05). The RF + NaiveBayes + Tree ensemble demonstrated superior predictive power for early AKI risk identification. SHAP analysis highlighted PLT as a key predictor, with notable inter-individual variability in risk profiles. The observed mediating effect of Hb between hypertension and AKI offers exploratory mechanistic insights that warrant further validation. While these findings contribute to the understanding of ICH-associated AKI, the current model remains exploratory and is not yet ready for direct clinical implementation. Future studies with larger, multicenter cohorts are needed to refine the model and assess its clinical utility.