Predictive Index Research Articles

Winter Wheat Yield Prediction Using Satellite Remote Sensing Data and Deep Learning Models

Accurate crop yield prediction is crucial for formulating agricultural policies, guiding agricultural management, and optimizing resource allocation. This study proposes a method for predicting yields in China’s major winter wheat-producing regions using MOD13A1 data and a deep learning model which incorporates an Improved Gray Wolf Optimization (IGWO) algorithm. By adjusting the key parameters of the Convolutional Neural Network (CNN) with IGWO, the prediction accuracy is significantly enhanced. Additionally, the study explores the potential of the Green Normalized Difference Vegetation Index (GNDVI) in yield prediction. The research utilizes data collected from March to May between 2001 and 2010, encompassing vegetation indices, environmental variables, and yield statistics. The results indicate that the IGWO-CNN model outperforms traditional machine learning approaches and standalone CNN models in terms of prediction accuracy, achieving the highest performance with an R2 of 0.7587, an RMSE of 593.6 kg/ha, an MAE of 486.5577 kg/ha, and an MAPE of 11.39%. The study finds that April is the optimal period for early yield prediction of winter wheat. This research validates the effectiveness of combining deep learning with remote sensing data in crop yield prediction, providing technical support for precision agriculture and contributing to global food security and sustainable agricultural development.

Evolution of Perioperative Hemodynamic Monitoring from the Hand Oon Pulse to Hypotension Prediction Index

This manuscript describes the evolution of hemodynamic monitoring from simple manual methods to artificial intelligenceintegrated monitoring and prediction systems. Manual methods, like palpation of peripheral pulse, capillary refill time and auscultation are simple and crucial in detecting hemodynamic changes during surgery. However, these methods are taking time consuming, difficult to monitor continuously and have limited reliability in critical situations like hypotension or hypothermia. Over time, advances in technology have improved perioperative monitoring through the invention of various non-invasive monitors like electrocardiogram, pulse oximetry, oscillometric blood pressure measurement, capnography, echocardiography, tissue oximetry, etc. and invasive monitors to measure arterial pressures, venous pressures and cardiac output. These monitors have improved the accuracy of hemodynamic measurements and fluid management in critically ill patients. Recently, there has been a growing emphasis on non-invasive or minimally invasive monitoring approaches, which have fewer complications than invasive techniques. However, most of these techniques show limited accuracy during major surgeries involving major hemodynamic changes and in critically ill patients. Monitors incorporating artificial intelligence (AI)-based tools, such as the hypotension prediction index (HPI), automated echocardiographic measurements (AEM), etc., have been demonstrated to be effective in making quick and accurate diagnoses as well as in predicting perioperative complications.

Role of Ankle Brachial Index (ABI) in Prediction of Peripheral Arterial Disease among Asymptomatic Patients with Atherosclerotic Risk Factors

Role of Ankle Brachial Index (ABI) in Prediction of Peripheral Arterial Disease among Asymptomatic Patients with Atherosclerotic Risk Factors

Quantitative electroencephalography predicts postoperative delirium in adult cardiac surgical patients from a prospective observational study

The diagnostic and prognostic value of quantitative electroencephalogram (qEEG) in the the onset of postoperative delirium (POD) remains an area of inquiry. We aim to determine whether qEEG could assist in the diagnosis of early POD in cardiac surgery patients. We prospectively studied a cohort of cardiac surgery patients undergoing qEEG for evaluation of altered mental status. Delirium was assessed with the Confusion Assessment Method for the intensive care unit (CAM-ICU). The qEEG were interpreted by clinician, and reports were reviewed to identify features such as amplitude-integrated EEG (aEEG), relative band energy in ɑ/β/θ/δ frequencies, α variability and spectral entropy. The raw EEG was also preprocessed offline for nonlinear analysis including Multi-scale Entropy analysis (MSE) and Detrended Fluctuation Analysis (DFA). Linear regression was performed to quantify associations among EEG findings, delirium, and clinical outcomes. Receiver operating characteristic (ROC) analysis was used to assess the accuracy of the qEEG as POD prediction index. Meanwhile, a comprehensive comparison of dynamic complexity across time scales and DFA exponent α was conducted between the non-delirium and delirium groups. Among those recruited initially (n = 64), 60 patients were evaluated and 29 patients (48.3%) met delirium criteria. When comparing delirious and non-delirious participants, significant differences were found in terms of age (p = 0.03), APACHE II scores (p = 0.004), lactate (p = 0.03), and hospital days (p = 0.048). Multivariate regression analysis revealed that the first quartile (Q1) and fourth quartile (Q4) of peak or valley value of F3-P3/F4-P4 derivation (for example, Q1 of peak value for F3-P3 derivation: OR 12.4, 95% CI 1.72–89.76, p = 0.012) showed a higher association with the incidence of POD. ROC analysis demonstrated qEEG could predict POD with high sensitivity and specificity, yielding an overall good accuracy. For instance, the peak value of F3-P3 derivation (the area under the curve of 0.81), as a predictor of POD showed a sensitivity of 90% and specificity pf 72% (p < 0.001). Furthermore, the MSE curves indicated that the non-delirium group exhibited higher complexity values at fine scales, while the delirium group had significantly higher complexity at coarse scales. The DFA comparison results revealed that long-term fractal exponent alpha2 values were higher in delirium patients than in non-delirium patients, with significant differences observed at the F4-P4 electrodes (p = 0.04). The qEEG can reliably predict delirium after heart cardiac surgery. It is helpful for clinicians to early diagnose and manage these patients.Trial registration: Clinical Trials.gov Identifier, NCT03351985. Registered 1 December 2017.

Clinical characteristics and risk factors for Mycoplasma pneumoniae pneumonia in children

BackgroundMycoplasma pneumoniae (M. pneumoniae) is one of the most common pathogens of community-acquired pneumonia (CAP) in children. Although Mycoplasma pneumoniae pneumonia (MPP) is considered a self-limiting disease, severe MPP (SMPP) occurs in some cases. This study aims to analyze clinical features of MPP and to explore predictive indicators in the early stage of M. pneumoniae infection.MethodsWe retrospectively enrolled patients with MPP and non-MPP (NMPP) hospitalized to the Department of Pediatrics, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine from 2023 to 2024. A total of 757 children with CAP were divided into MPP group and NMPP group. Patients with MPP included SMPP group and mild MPP (MMPP) group. Demographic and clinical characteristics as well as laboratory and imaging tests were deemed to be baseline data within 24 h after admission. We compared differences between MPP group and NMPP group as well as SMPP group and MMPP group. To exclude the impacts of age and gender, analysis of covariance and Logical regression was used to account for the baseline differences in the probability between MPP group and NMPP group, SMPP group and MMPP group. Logistic regression analysis was used to screen markers as potential early clinical predictors. ROC curves were applied to estimate the diagnostic and predictive value of different indicators for SMPP group.ResultsAmong the 757 cases of CAP, 464 cases were MPP group and 226 cases were SMPP group. There were significant differences in hospital stay and fever duration between the MPP and NMPP groups. Compared to NMPP group, MPP group exhibited higher levels of platelet count (PLT), heparin-binding protein (HBP), erythrocyte sedimentation rate (ESR), immunoglobulin G (IgG) (P &amp;lt; 0.05). The levels of C-reactive protein (CRP), erythrocyte sedimentation rate (ESR), serum ferritin (SF), prothrombin time (PT), fibrinogen (Fg), interleukin-5 (IL-5) and Gamma interferon (IFN-γ) were significantly increased in SMPP group compared to MMPP group. PT, Fg, SF, IL-5 and IFN-γ were independent risk factors for SMPP group. Significantly, IL-5 and IFN-γ served as reliable predictive indices of SMPP.ConclusionsNotable differences were observed in both clinical characteristics and serum inflammatory markers between the MPP group and the NMPP group, as well as between the SMPP group and the MMPP group. Consequently, PT, Fg, SF, IL-5 and IFN-γ hold the potential to be employed as efficacious predictors for SMPP.

A Longitudinal Multimodal Imaging Study in Patients with Temporo-Insular Diffuse Low-Grade Tumors: How the Inferior Fronto-Occipital Fasciculus Provides Information on Cognitive Outcomes.

Tractography allows the in vivo study of subcortical white matter, and it is a potential tool for providing predictive indices on post-operative outcomes. We aim at establishing whether there is a relation between cognitive outcome and the status of the inferior fronto-occipital fasciculus's (IFOF's) microstructure. The longitudinal neuropsychological data of thirty young (median age: 35 years) patients operated on for DLGG in the left temporo-insular cortex along with pre-surgery tractography data were processed. A degraded integrity of the left (vs. right) IFOF (lower fractional anisotropy and length, p < 0.001; higher mean and axial diffusivity, p < 0.01) was found, with lower microstructural variables in the infiltration (vs. dislocation) group. Significant decreases immediately post-surgery vs. pre-surgery mainly occurred in lexico-semantics (p < 0.001), with significant improvements at follow-up in all the tests (p < 0.01 to p < 0.001), despite values in the range of 44% to 47.82% of patients with below cut-off scores regarding naming verbs and making visual lexical decisions. The status of left and right IFOFs is predictive of a decrease in immediate post-surgery performance for several tests (p < 0.05); similarly, it is predictive of better recovery in the follow-up performance for naming nouns, naming verbs, making phonological fluency lexical decisions, and the token test (p < -0.05). For the ROC analysis, a significant result was obtained for the verb-naming test, with a cut-off of 79%. This study supports the role of the predictive value of pre-operative tractography for assessing the immediate post-operative result and at follow-up the risk of developing a cognitive deficit.

Predictive properties of novel anthropometric and biochemical indexes for prediction of cardiovascular risk

ObjectiveOur aim was to examine the correlation between CVDs and various anthropometric and biochemical indices in the Iranian population.Methods9704 healthy individuals without CVD aged 35–65 were enrolled in our study. The anthropometric indices including Body Adiposity Index (BAI), Abdominal Volume Index (AVI), Body Roundness Index (BRI), Waist to Hip Ratio (WHR), Weight-adjusted Waist Index (WWI), Conicity Index (C-Index), A Body Shape Index (ABSI), Waist to Height Ratio (WHtR), Body Surface Area (BSA), Body Mass Index (BMI), Lipid Accumulation Product (LAP) and Visceral Adiposity Index (VAI) were calculated. The biochemical indices including Cardiac Risk Ratio (CRR), Atherogenic Index of Plasma (AIP), Triglycerides-Glucose Index (TyG), Cardiac Risk Index (CRI), Atherogenic Coefficient (AC), and high-sensitivity C-Reactive Protein (hs-CRP) were investigated. The association of the above indices with CVD was analyzed using logistic regression (LR) and the decision tree (DT) models.ResultsThe LR showed age, hs-CRP, AIP, AVI, LAP, and TyG had significant associations with CVDs in men (p-value < 0.002). Also, age, hs-CRP, LAP, TyG, BRI, VAI, and CRR had significant associations with CVDs in women (p-value < 0.002). The DT showed 95% of men with age > = 48, AIP > = 0.94, TyG > = 9.71, and AVI > = 14.24 had CVDs. Also, 97% of women with age > = 54, TyG > = 8.33, and hs-CRP > = 36.69 had CVDs.ConclusionAge, TyG, AIP, AVI, hs-CRP and LAP were the best predictors of CVD in men. Moreover, age, TyG, hs-CRP and BAI were the best indicators of CVD in women.Graphical

Performance of different dynamic oxygenation indices incorporating heart rate to predict non-invasive ventilation outcomes in hypoxemic respiratory failure

BackgroundNon-invasive ventilation (NIV) becomes crucial ventilatory support for respiratory failure patients, but wasting time in high-risk patients for suspected NIV failure and delayed intubation with invasive mechanical ventilation (IMV) is also fatal. Early prediction of NIV succeeded or failed patients is a potentially effective strategy for minimizing mortality and improving outcomes. This study evaluated the predictive power of dynamic change of hypoxemic indices incorporating heart rate (HR) [ROX-HR and POX-HR] in predicting NIV outcomes in hypoxemic acute respiratory failure (ARF), to get the best benefits of NIV and avoiding delayed intubation and IMV aiming to decrease intensive care unit (ICU) mortality risk.ResultsThis study enrolled 120 patients who were admitted and initiated NIV at Respiratory ICU and Anesthesia and Surgical ICU at Zagazig University Hospitals for ARF from June 2023 to May 2024. Enrolled patients were 80 males and 40 females with mean ± SD of their age 51.5 ± 13.4yrs. 40 (33.3%) had failed NIV and 80 (66.7%) had succeeded with the mean ± SD of NIV duration being 26.4 ± 15.6 h. Several oxygenation indices in the form of ROX, POX, ROX-HR, and POX-HR were measured at different points of time during NIV (baseline, after 2 h, 12 h, and after 24 h). Patients with failed NIV showed a highly statistically significant drop in ROX, POX, ROX-HR, and POX-HR than patients with succeeded NIV. At all measured time points, indices incorporating heart rate (ROX-HR and POX-HR) had better performance in predicting NIV outcomes. POX-HR had the highest accuracy than other measured indices in early prediction (after 2 h) of NIV outcomes. A ROX-HR index of > 5 and a POX-HR index of > 4 were correlated with a low chance of NIV failure at all time points during the first 24 h, even after applying multivariate regression analysis for confounders.ConclusionsHeart rate–based indices are more reliable in predicting NIV outcomes. Among the assessed indicators, POX-HR has the highest accuracy in predicting the outcomes of NIV at an early stage.

Comparative analysis and application of rockburst prediction model based on secretary bird optimization algorithm

The accurate rockburst prediction is crucial for ensuring the safety of underground engineering construction. Among the various methods, machine learning-based rockburst prediction can better solve the nonlinear relationship between rockbursts and influencing factors and thus has great potential for engineering applications. However, current research often faces certain challenges related to the feature selection of prediction indices and poor model optimization performance. This study compiled 342 rockburst cases from domestic and international sources to construct an initial database. In order to determine the relevant prediction indicators, a feature selection method based on the ReliefF-Kendall model was proposed. The initial database was equalized and visualized using the Adasyn and t-SNE algorithms. Five rockburst prediction models [support vector machine (SVM), least-squares support vector machine (LSSVM), kernel extreme learning machine (KELM), Random Forest (RF), and XGBoost] were established by employing the Secretary Bird Optimization (SBO) algorithm and 5-fold cross-validation to optimize performance. The optimal model was selected based on a comprehensive assessment of generalization ability (accuracy, kappa, precision, recall, and F1-score) and stability (average accuracy). The reliability of the proposed feature selection, model optimization, and data balancing methods was verified by comparing the optimal model with other methods. The results indicate that the PSO-SVM model demonstrated superior prediction accuracy and generalization performance; the accuracy can reach 81.4% (optimal) and 80.1% (average). The main factors affecting the occurrence of rockburst are Wet, maximum tangential stress (MTS), D, and uniaxial compressive strength (UCS). Finally, the model was applied to the domestic rockburst engineering cases, achieving a prediction accuracy of 90% and verifying its engineering applicability.

Plasma lipidomics and fungal peptide-based community analysis identifies distinct signatures of early mortality in acute liver failure.

Acute liver failure (ALF) has high mortality predominantly due to compromised immune system and increase vulnerability to bacterial and fungal infections. Plasma lipidome and fungal peptide-based-community (mycobiome) analysis were performed in Discovery cohort (40-ALF, 5-healthy) and validated in a validation cohort of 230-ALF using High-resolution-mass-spectrometry, artificial-neural-network (ANN) and machine-learning (ML). Untargeted lipidomics identified 2,013 lipids across 8 lipid-groups. 5 lipid-species (Phosphatidylcholine, PC(15:0/17:0), PC(20:1/14:1), PC(26:4/10:0), PC(32:0) and TG(4:0/10:0/23:6)) significantly differentiated ALF-NS (FC>10, p<0.05, FDR<0.01). Mycobiome (alpha/beta diversity) was significantly higher and showed 4 phyla and >20 species significantly dysregulated in ALF-NS linked with lipid-metabolism, fatty-acid-elongation in ER, and others (p<0.05). Lipid and mycobiome diversity in ALF-NS were strongly correlated(r2>0.7, p<0.05). Multi-modular correlation network showed striking associations between lipid, Fungal-peptides modules, and Clinical parameters specific to ALF-NS (p<0.05). Cryptococcus amylolentus CBS6039 and Penicillium oxalicum1142 directly correlated with Phosphatidylcholine, Triglycerides, and severity in ALF-NS(r2>0.85, p<0.05). POD-fungus and POD-lipids showed direct association with infection, necrosis, and hepatic encephalopathy (Beta>1.2, p<0.05). POD-lipid (AUC=0.969) and HR=1.99(1.02-2.04) superseded POD-fungus and severity indices for early-mortality prediction. Finally, significant increase in PC(15:0/17:0) level showed highest normalized importance and predicted early-mortality with >95% accuracy/sensitivity/specificity using ANN and ML. Interestingly, fungal surveillance protein Clec7a was significantly downregulated (>2-fold), leading to a notable rise in fungal infection-mediated choline/phosphatidylcholine and associated enzymes (FC>1.5; Kennedy cycle). This contributed to phosphatidic acid-mediated hyper-inflammation in ALF-non-survivors. In ALF plasma lipidome and mycobiome are dysregulated. Increase circulating phosphatidylcholine could stratify ALF predisposed to early-mortality or require emergency liver transplantation.

Mean arterial pressure is a major determinant of hypotension prediction index: An explanation for the debate on its clinical utility?

Mean arterial pressure is a major determinant of hypotension prediction index: An explanation for the debate on its clinical utility?

Research on NBA Event Prediction Based on Hybrid Machine Learning Model

NBA is one of the top basketball events in the world. It is of great significance to predict NBA events comprehensively and accurately. Therefore, this paper puts forward the research on the prediction of NBA events based on a hybrid machine learning model. Construct a hybrid machine learning model, set the pre-processing flow of NBA event prediction data, solve the probability core cluster of NBA event prediction data, and form a data stream mining matrix of NBA event prediction; based on the integrated learning method in machine learning, according to the principle of constructing the prediction index of NBA events, the prediction index is constructed; based on the deep learning method in machine learning, the weight of target factors is used as a parameter to measure the prediction accuracy, and hierarchical evaluation is carried out to realize the prediction of NBA events. The experimental results show that the research method shows a high goodness of fit in all NBA games, and the predicted results are highly consistent with the actual results, and the predicted results are closer to the real results, with small root mean square error and average absolute error, which has a good prediction effect.

Risk stratification for ventricular tachyarrhythmias after cardioverter-defibrillator implantation for primary prevention of sudden cardiac death: results of the IDEAL single-center prospective study

Aim. The aim of this study was to develop additional selection criteria for implanted cardioverter-defibrillator (ICD) implantation in the primary prevention of sudden cardiac death (SCD) based on the risk stratification for the development of sustained ventricular tachycardia (VT).Methods. The study included 451 patients with heart failure and reduced left ventricular ejection fraction (HFrEF) who were referred for ICD implantation for primary prevention of SCD. Participants underwent pre-implantation screening of clinical, instrumental, and laboratory parameters, followed by prospective observation for 24 months to record the first occurrence of sustained VT or justified ICD therapy. To achieve the study’s goal, training and test samples were formed.Results. The arrhythmic endpoint was recorded in 84 patients (26%) in the training group and in 35 patients (27%) in the test group. Univariate analysis identified 11 factors with the highest predictive potential (p&lt;0.1) associated with the occurrence of the studied endpoint. These included clinical data: coronary artery disease, arterial hypertension, resting heart rate &gt;80 bpm; electrocardiographic parameters: complete left bundle branch block according to Strauss criteria, P-wave duration (lead II) &gt;120 ms, or the presence of atrial fibrillation (in the case of persistent form), index of cardiac electrophysiological balance (ICEB) &gt;3.1; echocardiographic parameters: presence of eccentric left ventricular hypertrophy, global longitudinal strain ≥ minus 6%; laboratory markers: galectin-3 &gt;12 ng/ml, sST-2 &gt;35 ng/ml, NT-proBNP &gt;2000 pg/ml. Based on the regression coefficients, points were assigned to each factor, and the sum of these points determined the value of a new proposed index - the arrhythmic risk index (ARI). ARI values &gt;5 points predicted the two-year likelihood of VT in HFrEF patients with a sensitivity of 78.6% and specificity of 64.3% (AUC=0.788±0.028 with 95% confidence interval (CI): 0.732-0.843; p=0.0001). The application of ARI in the test group demonstrated good model performance in predicting two-year VT risk (AUC=0.652±0.053 with 95% CI: 0.547-0.757; p=0.008).Conclusion. Based on the obtained results, a predictive index was developed, allowing for personalized and timely risk assessment of VT in patients with HFrEF.

Linear Water Erosion Incisions in the Central-West Region of Brazil: A Bibliometric Analysis

This study presents the results of a comprehensive bibliometric analysis of research on linear water erosion incisions in the Central-West region of Brazil. A total of 91 documents, including scientific articles, dissertations and academic theses, were analyzed to map the research trends and patterns in this field. The results indicate a predominance of geospatial and geodynamic studies. A multidisciplinary methodological approach is evident in 71% of the studies that combine multiple procedures to obtain more robust results. Most studies are multifactorial, using indicators of vegetation, land use and management, and geomorphology, reflecting the complexity of the processes involved. The main research focuses include modeling, mapping, and prediction indices. The results show that multiscale approaches are essential for integrating local and regional knowledge, offering a comprehensive understanding of the challenges and solutions for the erosive phenomenon. In addition, the geographical distribution of the studies reveals a greater concentration in the states of Goiás and Mato Grosso, associated with the intense agricultural and livestock activity in these areas. It is concluded that interdisciplinary approaches and the use of advanced technologies to address the challenges of linear water erosion should be intensified to promote sustainable land use and management practices.

Prognostic model based on disulfidptosis-related lncRNAs for predicting survival and therapeutic response in bladder cancer.

With poor treatment outcomes and prognosis, bladder cancer remains a focus for clinical research in the precision oncology era. However, the potential of disulfidptosis, a novel cell death mechanism, and its related long non-coding RNAs to support selective cancer cell killing in this disease is still unclear. We identified key disulfidptosis-related lncRNAs in bladder cancer, constructed a prognostic risk model with potential therapeutic targets, and confirmed the findings through quantitative PCR analysis. We identified five crucial lncRNAs (AC005840.4, AC010331.1, AL021707.6, MIR4435-2HG and ARHGAP5-AS1) and integrated them into a predictive model centered on disulfidptosis-associated lncRNAs. Reliability and validity tests demonstrated that the lncRNA prediction index associated with disulfidptosis effectively discerns patients' prognosis outcomes. Additionally, high-risk patients exhibited elevated expression levels of genes involved in the PI3K-Akt signaling pathway, extracellular matrix organization, and immune escape mechanisms, which are associated with poor prognosis. Notably, high-risk patients demonstrated higher sensitivity to Sorafenib, Oxaliplatin and MK-2206, underscoring the promise of these lncRNAs as precise therapeutic targets in bladder cancer. By revealing the predictive importance of disulfidptosis-associated lncRNAs in bladder cancer, our research offers new perspectives and pinpoints potential therapeutic targets in clinical environments.

Prognostic value of Apparent Diffusion Coefficient for Mechanical Thrombectomy in Patients with Acute Posterior Ischemic Stroke

BackgroundThis study investigates the prognostic value of the apparent diffusion coefficient (ADC) in MRI for patients with acute posterior circulation stroke (PCS) undergoing endovascular therapy (EVT). MethodsA retrospective analysis was conducted on patients with acute PCS from January 2017 to December 2021, confirmed by Diffusion Weighted Imaging (DWI)-ADC within 24 hours of onset. Patients were categorized based on their 3-month mRS score post-EVT. Data on NIHSS at admission, ADC value, and 3-month mRS were collected. Multivariable logistic regression analyzed the impact of various factors on ADC values. The receiver operating characteristic curve assessed predictive indices. ResultsAmong 94 patients, 47 had a good prognosis, and 47 had a poor prognosis. Univariate analysis revealed that factors significantly associated with a good prognosis included lower NIHSS at admission, higher ADC values, smaller infarct areas, unilateral infarction, basilar artery occlusion, lower PMT scores, intravenous thrombolysis, intra-arterial thrombolysis, and fewer perioperative complications (p < 0.05). Multivariable logistic regression identified high ADC values (p=0.002) and unilateral infarction (p=0.017) as independent predictive factors for prognosis. An ADC value > 549×10− 6 mm2/s was associated with a higher rate of good prognosis. Combining ADC values with unilateral infarction resulted in the highest AUC and Youden index of 0.766, with sensitivity and specificity of 89.36% and 87.23%, respectively (p<0.05). ConclusionHigh ADC values and unilateral infarction are independent predictive factors for the prognosis of PCS patients after EVT. Combining these factors provides the highest predictive accuracy, aiding in clinical decision-making for PCS treatment.

Effect of a Machine Learning-Derived Early Warning Tool With Treatment Protocol on Hypotension During Cardiac Surgery and ICU Stay: The Hypotension Prediction 2 (HYPE-2) Randomized Clinical Trial.

Cardiac surgery is associated with perioperative complications, some of which might be attributable to hypotension. The Hypotension Prediction Index (HPI), a machine-learning-derived early warning tool for hypotension, has only been evaluated in noncardiac surgery. We investigated whether using HPI with diagnostic guidance reduced hypotension during cardiac surgery and in the ICU. Randomized clinical trial conducted between May 2021 and February 2023. Single-center study conducted in an academic hospital in the Netherlands. Adults undergoing elective on-pump coronary artery bypass grafting, with or without single heart valve surgery, were enrolled if a mean arterial pressure (MAP) greater than or equal to 65 mm Hg was targeted during the surgical off-pump phases and ICU stay. After eligibility assessment, 142 of 162 patients approached gave informed consent for participation. Patients randomized 1:1 received either diagnostic guidance in addition to standard care if HPI reached greater than or equal to 75 (n = 72) or standard care alone (n = 70). The primary outcome was the severity of hypotension, measured as time-weighted average (TWA) of MAP less than 65 mm Hg. Secondary outcomes encompassed hypertension severity and intervention disparities. Of 142 patients randomized, 130 were included in the primary analysis. The HPI group showed 63% reduction in median TWA of hypotension compared with the standard care group, with a median of differences of -0.40 mm Hg (95% CI, -0.65 to -0.27; p < 0.001). In the HPI group, patients spent a median 28 minutes (95% CI, 17-44 min) less in hypotension, with a measurement duration of 322 minutes in the HPI group and 333 minutes in the standard care group. No significant differences were observed in hypertension severity, treatment choice, or fluid, vasopressors, and inotrope amounts. Using HPI combined with diagnostic guidance on top of standard care significantly decreased hypotension severity in elective cardiac surgery patients compared with standard care.

The functional TNF-α-308G > a single-nucleotide polymorphism (rs1800629): association with the predictive indices of breast cancer carcinogenesis.

Compared with all other cancer types, Breast cancer (BC) among women has now exceeded them all as the primary reason for cancer worldwide. The BC represents 11.7% of all cancer cases and accounts for a predestined 2.3 million new cases. It is the fourth primary reason for cancer-associated deaths in women. With a staggering 200-400% increase in the relative incidence of BC in Egypt, there is an urgent need for new diagnostic or predictive markers. The current investigation aims to explore the connection of the functional TNF-α-308G > A (rs1800629) single-nucleotide polymorphism (SNP) with different breast cancer predictive indices. The ARMS-PCR method was used for genotyping TNF-α-308G > A SNP. Three groups were recruited for the study: 79 patients with benign breast inflammation (BBI); 163 with breast cancer (BC) and 144 controls (C). The TNF-α-308G > A SNP was distributed among different groups in a unique pattern; in the control group 63.9% of cases were in the GG, 34% were in the GA, and 2.1% were in the AA. The BC group had 14% GG, 79% GA, and 7% AA, while the BBI group had 24% GG, 76% GA, and 0% AA. The AA genotype and A allele represented a strong significant correlation with risk factors in the BC group (ORAA: 14.67 [95% CI = 3.78-56.91] and ORA: 0.27 [95% CI = 0.19-0.39], respectively; P < 0.0001) in contrast to the control group. However, in the BBI group, a strong significant correlation was noted with the GA genotype (ORGA: 5.93 [95% CI = 3.18-11.04] P < 0.0001). In the BC group, the AA genotype shows a significant increase in Nottingham Prognostic Index (NPI) in positive ER and PR in contrast to the relevant negative ones (P = 0.02 and 0.002, respectively). However, the GA genotype significantly increased NPI in positive Her2 and metastatic patients (P = 0.03 and 0.01, respectively). This research is the first to correlate TNF-α-308G > A (rs1800629) SNP in Egyptian BC patients. The A allele, GA & AA genotypes, and the Overdominant model of the TNF-α-308G > A gene variants were recorded as prognostic risk factors for BC carcinogenesis.

Serum creatinine- and cystatin C-based indices are associated with the risk of subsequent sarcopenia: evidence from the China Health and Retirement Longitudinal Study.

Serum creatinine (Cr)- and cystatin C (CysC)-based indices have been suggested as alternative markers for sarcopenia, but their predictive value for sarcopenia risk is uncertain, which was investigated in the present study in the Chinese population with the middle and older ages. Data from the China Health and Retirement Longitudinal Study (CHARLS) were collected in the 2011 and 2015 waves. All participants were free of sarcopenia at the baseline. Sarcopenia was diagnosed when low muscle mass and grip strength or low physical performance were present. Four indices were computed: predictive skeletal muscle mass index (pSMI), total-body muscle mass (TBMM), creatinine-to-cystatin C ratio (CCR), and sarcopenia index (SI). Restricted cubic splines and logistic regression models were used to assess the effects of these indices on sarcopenia risk. Among 4,527 participants without sarcopenia at the baseline (2011), the median age was 58 year-old (IQR: 52-65), with 52.7% women. Followed up in year 2015, the incidence of sarcopenia was 20.8 per 1,000 person-years (376/4,527). Neither CCR nor SI showed linear or non-linear associations with the risk of subsequent sarcopenia. However, a decrease in pSMI and TBMM was significantly associated with an increased risk of sarcopenia [adjusted per-SD decrease OR, 2.93; 95% CI, 2.09-4.13, p < 0.001; adjusted per-SD decrease OR: 2.38, 95% CI: 1.80-3.16, p < 0.001, respectively]. In the middle and older age of Chinese population, decreased pSMI and TBMM were associated with an increased risk of subsequent sarcopenia, whereas CCR and SI showed no such correlation. Thus, pSMI and TBMM may serve as potential biological indicators for predicting the risk of sarcopenia, and decreased pSMI and TBMM may be the early biomarkers for diagnosis and intervention of sarcopenia.

Changes in the metabolic score for insulin resistance index for risk prediction of stroke in middle-aged and older Chinese population.

As a major noncommunicable disease, stroke poses a major threat to public health. In the context of predictive, preventative, and personalised medicine (PPPM/3PM), early identification of high-risk individuals is crucial for targeted prevention and personalised treatment for stroke. This study aimed to investigate the association between changes in the Metabolic Score for Insulin Resistance Index (METS-IR) and incident stroke. From the perspective of PPPM/3PM, we hypothesised that monitoring dynamic changes of the METs-IR levels and targeting cumulative METs-IR index contribute to risk prediction, targeted prevention, and personalised management of stroke. All data were obtained from the China Health and Retirement Longitudinal Study (CHARLS), a nationwide prospective cohort study. The individuals were categorised into four subgroups based on the quartiles (Q) of the cumulative METS-IR index as a reflection of changes in the METS-IR values from 2012 to 2015. Logistic regression was employed to examine the association between cumulative METS-IR index and stroke incidence. Additionally, restricted cubic spline regression analysis was used to assess potential linearity. Among the 4288 participants, 275 (6.4%) experienced a stroke. The risk of stroke events increased with higher cumulative METS-IR index levels. Compared with the lowest quartile (Q1), the OR of having a stroke was 1.20 (0.81, 1.78) for Q2, 1.51 (1.04, 2.21) for Q3 and 2.17 (1.52, 3.10) for the highest quartile (Q4). After adjusting for multiple potential confounders, Q4 (OR: 1.57, 95% CI: 1.04, 2.35) remained significantly associated with stroke. The association between the cumulative METS-IR index and stroke incidence was linear in males, females, and the overall population (all P values for nonlinearity > 0.05). A higher cumulative METS-IR index was associated with an increased risk of incident stroke among middle-aged and older Chinese individuals. In the context of PPPM/3PM, incorporating metabolic health into stroke risk assessment advances the prediction, prevention and personalised management of stroke. The online version contains supplementary material available at 10.1007/s13167-024-00388-y.