Performance of a wearable movement tracking system in detecting hypomobility in acute ischemic cerebrovascular events.

Elevated factor (F)XI and tissue factor (TF) have been reported to occur in patients with acute ischemic stroke (AIS). We sought to investigate whether circulating activated FXI (FXIa) and TF on admission can predict clinical outcomes in patients with acute cerebrovascular events. In the observational study, we evaluated 205 consecutive patients aged 70 years or less within the first 72 h of acute event, including 140 with AIS and 65 with transient ischemic attack (TIA). Plasma TF and FXIa activity were determined on admission in clotting assays by measuring the response to inhibitory monoclonal antibodies. Active TF and FXIa activity were detected in 58 (28·9%) and 132 (64·4%) patients on admission, respectively. Active TF was detected in 45 of the 136 AIS patients with available TF levels (33·1%) and 13 of the 65 patients with acute TIA (20%; 0·05). Corresponding values for FXIa were 99 of the 140 (70·7%) and 33 of the 65 (50·8%; P= 0·006), respectively. Patients with detectable TF were more frequently women and hypertensive, while subjects with detectable FXIa had more often diabetes and higher levels of fibrinogen, C-reactive protein and interleukin-6 (all P < 0·05). Patients with detectable FXIa but not TF had higher National Institutes of Health Stroke Scale score, higher modified Rankin scale score and lower Barthel Index at discharge (all P < 0·05). Circulating active TF and FXIa occur frequently in acute cerebrovascular ischemic events. Active FXIa in plasma might be useful as a novel risk marker of worse functional outcomes in patients with acute cerebrovascular events.

BackgroundOur study aimed to evaluate whether the effects on adverse clinical outcomes, defined as death, recurrent stroke, and poor functional outcomes, differed by leukocyte subtype in patients with acute ischemic cerebrovascular events, including both ischemic stroke and transient ischemic attack (TIA).MethodsWe derived data from the Third China National Stroke Registry (CNSR-III). The counts and percentages of each leukocyte subtype were collected within the first 24 hours after admission. Enrolled patients were classified into four groups by the quartiles of each leukocyte subtype count or percentage. Hazard ratios (HRs) or odds ratios (ORs) and their 95% confidence intervals (CIs) of adverse clinical outcomes were calculated, with the lowest quartile group as the reference category. We used C statistics, integrated discrimination improvement (IDI), and the net reclassification index (NRI) to evaluate each leukocyte subtype’s incremental predictive value beyond conventional risk factors.ResultsA total of 14,174 patients were enrolled. Higher counts of leukocytes, neutrophils, and monocytes were associated with elevated risks of adverse clinical outcomes. In contrast, higher counts of lymphocytes and eosinophils were related to reduced risks of adverse clinical outcomes. Meanwhile, basophil counts seemed to not correlate with adverse clinical outcomes. Furthermore, there were also significant associations between the percentages of leukocyte subtypes and adverse clinical outcomes.ConclusionsLeukocyte subtypes had different relationships with adverse clinical outcomes at 3-month and 1-year follow-up in patients with acute ischemic cerebrovascular events and could slightly increase the predictive value compared with the conventional model.

ObjectivesA radiomics-based explainable eXtreme Gradient Boosting (XGBoost) model was developed to predict central cervical lymph node metastasis (CCLNM) in patients with papillary thyroid carcinoma (PTC), including positive and negative effects.MethodsA total of 587 PTC patients admitted at Binzhou Medical University Hospital from 2017 to 2021 were analyzed retrospectively. The patients were randomized into the training and test cohorts with an 8:2 ratio. Radiomics features were extracted from ultrasound images of the primary PTC lesions. The minimum redundancy maximum relevance algorithm and the least absolute shrinkage and selection operator regression were used to select CCLNM positively-related features and radiomics scores were constructed. Clinical features, ultrasound features, and radiomics score were screened out by the Boruta algorithm, and the XGBoost model was constructed from these characteristics. SHapley Additive exPlanations (SHAP) was used for individualized and visualized interpretation. SHAP addressed the cognitive opacity of machine learning models.ResultsEleven radiomics features were used to calculate the radiomics score. Five critical elements were used to build the XGBoost model: capsular invasion, radiomics score, diameter, age, and calcification. The area under the curve was 91.53% and 90.88% in the training and test cohorts, respectively. SHAP plots showed the influence of each parameter on the XGBoost model, including positive (i.e., capsular invasion, radiomics score, diameter, and calcification) and negative (i.e., age) impacts. The XGBoost model outperformed the radiologist, increasing the AUC by 44%.ConclusionsThe radiomics-based XGBoost model predicted CCLNM in PTC patients. Visual interpretation using SHAP made the model an effective tool for preoperative guidance of clinical procedures, including positive and negative impacts.

PurposeWearables are gaining prominence in the health-care industry and their use is growing. The elderly and other patients can use these wearables to monitor their vitals at home and have them sent to their doctors for feedback. Many studies are being conducted to improve wearable health-care monitoring systems to obtain clinically relevant diagnoses. The accuracy of this system is limited by several challenges, such as motion artifacts (MA), power line interference, false detection and acquiring vitals using dry electrodes. This paper aims to focus on wearable health-care monitoring systems in the literature and provides the effect of MA on the wearable system. Also presents the problems faced while tracking the vitals of users.Design/methodology/approachMA is a major concern and certainly needs to be suppressed. An analysis of the causes and effects of MA on wearable monitoring systems is conducted. Also, a study from the literature on motion artifact detection and reduction is carried out and presented here. The benefits of a machine learning algorithm in a wearable monitoring system are also presented. Finally, distinct applications of the wearable monitoring system have been explored.FindingsAccording to the study reduction of MA and multiple sensor data fusion increases the accuracy of wearable monitoring systems.Originality/valueThis study also presents the outlines of design modification of dry/non-contact electrodes to minimize the MA. Also, discussed few approaches to design an efficient wearable health-care monitoring system.

Effect of pretreatment with statins on the severity of acute ischemic cerebrovascular events

Soil and litter emission sources as important contributors to ozone production from volatile organic compounds in island tropical forests.

Introduction: Early prediction of stroke outcomes using prognostic tools may help clinical decision-making and inform resource allocation. However, clinical information required to inform prediction tools is often missing. We evaluated the performance of machine learning (ML) prediction models of adverse stroke outcome at 90 days post-admission that exploit non-clinical data, and missingness, alongside traditional clinical and demographic predictors. Methods: We used routine hospital data from UK clinical sites (NHS SafeHaven) to train three gradient-boosted models. We compared baseline clinical features with nonclinical features and missingness to predict a composite 90-day adverse stroke outcome: mortality, stroke recurrence, or new care-home discharge. Model validation used 10% of the data. Model performance was evaluated by accuracy (correct predictions/total predictions) and area under the receiver operating characteristics curve (AUC) while DeLong’s test was used to compare performance of the three models. We used Brier score to evaluate model calibration. SHapley Additive exPlanations (SHAP) analyses determined the contribution of each model feature in predicting adverse stroke outcome. Results: The final sample included 3,530 stroke patients with 51% males (mean age = 72 years; SD = 14). Clinical data were incomplete with five clinical features having >63% missing values. The performance of the three models was not significantly different (p = 0.5–0.9). The model with non-clinical and missingness features demonstrated 71% accuracy and AUC of 0.76 with Brier score of 0.19. Nonclinical factors, such as time to clinical assessment and time to admission, were among the five most important predictors of adverse stroke outcome (mean |SHAP| = 0.03 and 0.05), alongside Glasgow Coma Scale (0.08), age (0.03), and temperature (0.02). Missing clinical values (pulse and LDL) predicted adverse stroke outcome (mean |SHAP| = 0.02 and 0.02) and were correlated with age (ρ = 0.2), arrival by ambulance (ρ = 0.3), length of stay (ρ = −0.3), and transient ischaemic attack (ρ = 0.3). Conclusion: We demonstrate that nonclinical factors and missingness of data can assist in early predictions of 90-day adverse stroke outcomes. As these factors are often well documented in electronic health systems, they could complement or supplement traditional clinical predictive factors.

Introduction: Troponin (TnI) elevation in patients with an acute ischemic cerebrovascular event (AICVE) has a poor prognosis and is often thought to be secondary to cardiac failure {(left ventricular ejection fraction (EF) &lt; 55%} or renal failure (creatinine &gt;1.3 mg/dL). However, the prognosis is not well defined in the absence of cardiac or renal failure. Hypothesis: We hypothesize that patients with an elevated TnI (≥0.08 mcg/L) in an AICVE have an increased risk of one-year mortality, even in the absence of cardiac or renal failure. Methods: Three hundred consecutive patients who were admitted with an acute ischemic stroke or a transient ischemic attack in the absence of an acute coronary syndrome or pulmonary edema from january 2004 to january 2006 were studied. Hazard ratios for all-cause mortality were determined using multivariate Cox Proportional hazards analysis employing multiple variables between patients with and without TnI elevation. Results: The final cohort consisted of 207 patients with a mean age 70 ± 14 years, 62% were females. There was a 33% occurrence of TnI elevation among the entire group of 207 patients (Gr. A) and a 20% occurrence among patients, who had a normal EF(≥ 55%) and a creatinine ≤ 1.3mg/dL (Gr. B, n=91). The one-year mortality was significantly higher in patients with TnI elevation (58% in Gr. A; 42% in Gr. B) as compared to the patients without TnI elevation (20% in Gr. A; 11% in Gr. B). Conclusions: The presence of TnI elevation in patients with an AICVE is a significant independent multivariate predictor of one-year mortality in the presence or absence of cardiac or renal failure. It may be plausible that a recent silent myocardial infarction or other neurohormonal mechanisms may cause troponin elevation apart from cardiac or renal failure in the setting of an AICVE. TnI elevation and one-year mortality

ABSTRACTObjective:To construct an eXtreme Gradient Boosting (XGBoost) model for predicting short-term recurrence after first-episode acute pancreatitis (AP) and employ SHapley Additive exPlanations (SHAP) analysis for feature interpretation.Methods:A total of 442 patients with first-episode AP admitted to Cangzhou Central Hospital from October 2018 to June 2023 were retrospectively analyzed. The short-term recurrence was defined as a second attack after first-episode AP within 1 year. The cohort was split randomly, with 70% of the patients (n = 321) used for model training and 30% (n = 121) reserved for validation. Cox regression analysis was employed to identify independent predictors affecting recurrence, and an XGBoost model was constructed based on predictors. The XGBoost model was assessed by using area under the curve (AUC), calibration curve, decision curve analysis (DCA), and SHAP analysis.Results:Three features were determined as predictors of recurrence. They included elevated triglycerides, alcohol drinking, and pancreatic necrosis. The XGBoost model demonstrated favorable performance, achieving an AUC of 0.933 (95% CI: 0.895–0.970) in the training cohort and of 0.874 (95% CI: 0.777–0.970) in the validation cohort. The calibration curve exhibited strong consistency between the anticipated and observed values, and DCA confirmed that the XGBoost model provided great clinical benefit. SHAP analysis also proved that elevated triglycerides, alcohol drinking, and pancreatic necrosis were decisive for the effect of the XGBoost model.Conclusion:The XGBoost model can accurately predict short-term recurrence. The SHAP approach can enhance the interpretability of the machine-learning model and support clinical decision-making.

Hemorrhage is a prevalent and critical condition in the intensive care unit (ICU), characterized by high incidence, elevated mortality rates, and substantial therapeutic challenges. Accurate prediction of mortality in patients with hemorrhage is essential for developing personalized prevention and treatment strategies. Nevertheless, the implementation of effective predictive models in clinical practice remains limited, primarily due to the lack of robust and interpretable tools. This study aimed to develop an interpretable model for predicting mortality risk in critically ill patients with hemorrhage admitted to ICUs. The SHapley Additive exPlanations (SHAP) method was applied to interpret the eXtreme Gradient Boosting (XGBoost)model, identifying key prognostic factors in this population. In this retrospective cohort study, we derived data from the eICU Collaborative Research Database (eICU-CRD) to develop and evaluate a predictive model. ​Clinical data from the first 24h of ICU admission were extracted, and the dataset was randomly split into training (80%) and validation (20%) sets. Model performance was compared​ to four other machine learning algorithms using the area under the curve (AUC). ​SHAP was utilized to interpret the XGBoost model. External validation was subsequently performed using data from the ​Chinese REFRAIN cohort, which focuses on hemorrhage and coagulopathy in critically ill patients.​​. The study protocol was retrospectively registered in the Chinese Clinical Trial Registry (ChiCTR) on December 17, 2024 (Registration number ChiCTR2400094140). A total of 10,306 eligible patients with hemorrhage were included. The observed in-hospital mortality rate was 11.5%.Among the five models compared, XGBoost demonstrated the highest predictive performance (AUC = 0.81), whereas logistic regression (LR) showed the lowest generalizability(AUC = 0.726). Decision curve analysis revealed that the XGBoost model provided a greater net benefit than other models at threshold probabilities of 10-30%. SHAP analysis identified the top 15 predictors of mortality, with bilirubin level ranked as the most influential variable.​​ External validation using the REFRAIN cohort confirmed the robustness of model(AUC = 0.776). The interpretable predictive model improves mortality risk stratification in ICU patients with hemorrhage, supporting clinicians in optimizing treatment plans and resource allocation. Enhanced model transparency through SHAP explanations may facilitate clinical adoption by improving trust in model reliability.

Background and aimsLeft atrial (LA) enlargement has been repeatedly shown to be associated with the diagnosis of atrial fibrillation (AF). In clinical practice, several parameters are available to determine LA enlargement: LA diameter index (LADI), LA area index (LAAI), or LA volume index (LAVI). We investigated the predictive power of these individual LA parameters for AF in patients with acute ischemic stroke or transient ischemic attack (TIA).MethodsLAETITIA is a retrospective observational study that reflects the clinical reality of acute stroke care in Germany. Consecutive patient cases with acute ischemic cerebrovascular event (CVE) in 2019 and 2020 were identified from the Mannheim stroke database. Predictive power of each LA parameter was determined by the area under the curve (AUC) of receiver operating characteristic curves. A cutoff value was determined. A multiple logistic regression analysis was performed to confirm the strongest LA parameter as an independent predictor of AF in patients with acute ischemic CVE.ResultsA total of 1,910 patient cases were included. In all, 82.0% of patients had suffered a stroke and 18.0% had a TIA. Patients presented with a distinct cardiovascular risk profile (reflected by a CHA2DS2-VASc score ≥2 prior to hospital admission in 85.3% of patients) and were moderately affected on admission [median NIHSS score 3 (1; 8)]. In total, 19.5% of patients had pre-existing AF, and 8.0% were newly diagnosed with AF. LAAI had the greatest AUC of 0.748, LADI of 0.706, and LAVI of 0.719 (each p < 0.001 vs. diagonal line; AUC-LAAI vs. AUC-LADI p = 0.030, AUC-LAAI vs. AUC-LAVI p = 0.004). LAAI, increasing NIHSS score on admission, and systolic heart failure were identified as independent predictors of AF in patients with acute ischemic CVE. To achieve a clinically relevant specificity of 70%, a cutoff value of ≥10.3 cm2/m2 was determined for LAAI (sensitivity of 69.8%).ConclusionLAAI revealed the best prediction of AF in patients with acute ischemic CVE and was confirmed as an independent risk factor. An LAAI cutoff value of 10.3 cm2/m2 could serve as an inclusion criterion for intensified AF screening in patients with embolic stroke of undetermined source in subsequent studies.

Extreme gradient boosting model to assess risk of central cervical lymph node metastasis in patients with papillary thyroid carcinoma: Individual prediction using SHapley Additive exPlanations

Climate signals, driven by complex interactions and nonlinear relationships, shape weather patterns and long-term trends, complicating the identification of dominant drivers due to collinearity. This study investigates the consistency and uncertainty of machine learning (ML) techniques for feature importance in climate science, comparing SHapley Additive exPlanations (SHAP), Partial Dependence Plots (PDPs), and gain-based feature importance from Extreme Gradient Boosting (XGBoost). SHAP’s integration with Feed Forward Neural Networks (FFNN) and XGBoost is evaluated to assess model-specific uncertainties. Using winter precipitation data from Ohio, USA, as a case study, the relative contributions of global warming (GW) and the Interdecadal Pacific Oscillation (IPO) to precipitation changes are quantified. Results show GW consistently ranks higher than IPO in at least 60% of stations across all methods, with SHAP and PDPs agreeing in 89% of stations. Global SHAP importance from FFNN and XGBoost aligns in 82% of stations, with GW contributing 15% more than IPO on average, though disagreements in 18% of stations highlight model-dependent uncertainties. Temporal analysis using SHAP values indicates a moderate discrepancy in feature importance between FFNN and XGBoost models (Pearson correlation ≈ 0.5), despite their consensus on the increasing dominance of GW in recent decades, contributing to wetter winters. Regression analysis further confirms that GW accounts for approximately 70% of the multi-decadal variability in winter precipitation across Ohio, with PDPs indicating a strong monotonicity (ρ = 0.94) between warming levels and precipitation increase. PDPs visualize marginal effects but struggle with interactions, while gain-based methods tend to favor features with a greater number of effective split points that reduce loss. SHAP, though robust for ranking, varies with the base model. An ensemble framework is proposed, demonstrating the value of combining these ML techniques complementarily to account for uncertainties and enhance interpretability. This study highlights the importance of addressing methodological uncertainties in feature importance rankings to provide robust insights for climate modeling.

The determination of the minimum miscibility pressure (MMP) in CO2-oil systems is critical for modeling CO2-EOR processes experimentally and numerically. Nevertheless, in nano-confined space, the existing experimental and empirical formula methods present limitations regarding the utilization conditions and prediction accuracy respectively. Thus, in this study, a novel approach combining ML model with Shapley Additive Explanations (SHAP) algorithm is introduced, which aims to provide more precise and physically correct estimates of the MMPs considering the influence of nano-confinement. A database containing MMPs in CO2 injection process under different conditions is firstly established based on 348 samples collected from experimental results and open publications. The input parameters determining MMPs include reservoir temperature, pore size, and oil composition. In this framework, XGBoost and MLP are used to mimic the input-output relations of the database. Then, SHAP is employed to comprehensively interpret the impact of the inputting factors on the MMPs by calculating the SHAP values. The present study revealed that both the proposed XGBoost and MLP models exhibited R2 score exceeding 80% and demonstrated good predictive accuracy, as evidenced by small MAE, MSE, and MAPE values. Moreover, a comparative analysis of the SHAP interpretation results of the two models revealed that the explanatory patterns of the MLP model were more consistent with established physical laws, thereby rendering it more suitable for constructing an MMP prediction model based on the dataset employed in this investigation. It is noteworthy that although the SHAP interpretation of the XGBoost model did not entirely conform to actual physical laws, the influence of pore size on MMP followed the same pattern as elucidated by the MLP model. Specifically, within the nano-confined spaces, MMP decreased as the pore size decreased, and the pore size played a crucial role in predicting MMP (ranking first in the XGBoost model and second in the MLP model). The outcomes demonstrate that the developed interpretable machine learning framework, which incorporates the effects of nano-confinement, can accurately predicts MMP under diverse conditions while maintaining the consistency of physical laws. Consequently, this framework offers valuable insights for the implementation and optimization of CO2-enhanced oil recovery processes.

Accurate prediction of cadmium (Cd) concentrations in wheat grain is essential for ensuring food safety and sustainable agriculture. Here, we developed a predictive model using nine machine learning (ML) algorithms based on a dataset of 1,339 soil-wheat grain pairs, with a focus on soil properties. The results showed that the eXtreme Gradient Boosting (XGBoost) model outperformed others, achieving superior predictive accuracy ( R 2 = 0.90) compared to multiple linear regression ( R 2 = 0.69). Through Shapley Additive Explanations (SHAP) analysis, soil total Cd (mean |SHAP| value, 0.20) and pH (0.08) were identified as key determinants, while soil Mn (0.06) and Zn (0.03) concentrations as minor determinants for wheat grain Cd. Soil Cd had a positive effect on grain Cd concentration, whereas soil pH, Mn and Zn showed negative effects. Extending the XGBoost model with 373 nation-scale paired data confirmed its robustness ( R 2 = 0.86), and identified high-risk areas for Cd accumulation in southwest China and northwestern Henan province. An online application (https://wheat.cdpredict.cn) was developed for rapid Cd predictions in wheat. To ensure compliance with the wheat grain Cd limit of 0.1 mg/kg, soil Cd safety thresholds were established for different soil pH ranges. We further recommend that approximately 3.4% and 10.5% of cultivated soils should maintain Cd levels within 0.30 and 0.34 mg/kg, respectively. This interpretable ML model provides an actionable tool for managing soil contaminated with Cd to ensure the safe production of wheat.