Predictive Power Research Articles

Impella effects on reverse myocardial remodeling in anterior ST-elevation myocardial infarction: insights from a comprehensive analysis of acute and chronic MRI findings

ABSTRACT Background Late adverse myocardial remodeling after ST elevation myocardial infarction (STEMI) is strongly associated with cardiac death. Global Longitudinal strain (GLS) and circumferential diastolic strain rate (CDSR) derived cardiovascular magnetic resonance imaging (CMRI) is a powerful predictor of late myocardial remodeling. However, the Impella’s effects on CMRI after STEMI are not fully understood. Research design and methods We retrospectively compared the CMRI in the acute (18 [14–22] vs. 14 [6–22] days, p = 0.43) and chronic phases (118 [102–242] vs. 117 [101–202] days, p = 1.0) after anterior STEMI. Results Five patients received Impella before percutaneous coronary intervention (PCI), and seven underwent intra-aortic balloon pumping (IABP). There were no significant differences in the peak creatine kinase levels (2595 [2069 -12,932] vs. 4372 [2941–5601] IU/L, p = 0.76) and LVEF upon admission (51 ± 11 vs. 50 ± 9%, p = 1.0). The Impella group had significantly better acute CMRI-derived LVEF (49 ± 10 vs. 35 ± 7%, p = 0.02) and CDSR (0.9 ± 0.2 vs. 0.5 ± 0.3 s− 1, p = 0.018). In the chronic phase, the CMRI-derived LVEF and GLS were significantly higher in the Impella group (54 ± 9 vs. 39 ± 5%, p = 0.01; −9.9 ± 1.3 vs. −6.5 ± 2.2%, p = 0.01). Conclusions The Impella implantation led to better LVEF and CDSR in the acute phase than IABP and better maintenance of both the LVEF and GLS through the chronic phase.

Assessment of the prognostic performance of TIMI, PAMI, CADILLAC and GRACE scores for short-term major adverse cardiovascular events in patients undergoing emergent percutaneous revascularisation: a prospective observational study

ObjectivesAccurately predicting short-term MACE (major adverse cardiac events) following primary percutaneous coronary intervention (PCI) remains a clinical challenge. This study aims to assess the effectiveness of four established risk scores...

Unmasking metabolic clues: adipsin, irisin and osteopontin as biomarkers in polycystic ovary syndrome and their impact on metabolic dynamics: a case-control study.

Polycystic ovary syndrome (PCOS) is a common endocrine disorder in women of reproductive age, often associated with metabolic alterations. This study assessed serum levels of adipsin, irisin, and osteopontin in patients with PCOS and examined their correlations with metabolic parameters. A case-control study was conducted involving 96 women with PCOS and 80 healthy controls. Serum levels of adipsin, irisin, and osteopontin were measured; demographic, clinical, and metabolic characteristics were evaluated. Patients with PCOS were significantly younger than controls (p < 0.001). The PCOS group included a significantly greater proportion of obese individuals (p = 0.013). Patients with PCOS exhibited elevated serum adipsin (p = 0.020) and reduced osteopontin (p < 0.001) levels relative to controls; obesity and age influenced these differences. Osteopontin demonstrated superior predictive power for PCOS diagnosis [area under the curve (AUC) = 0.802] compared with adipsin (AUC = 0.602). A combination of osteopontin and adipsin yielded the highest predictive value (AUC = 0.817) among double or triple biomarker combinations. This study identified potential associations among adipsin, osteopontin, irisin, and PCOS. Further research is warranted to elucidate their roles and clinical implications in PCOS and its metabolic alterations. The findings highlight the impact of age and obesity on these biomarkers and their relationships with PCOS, providing insight into the syndrome's complex pathophysiology.

The Predictive and Explanatory Power of the Contrast Theory of Myopia.

The Predictive and Explanatory Power of the Contrast Theory of Myopia.

Preoperative hemoglobin A1c as a predictor of lymph node metastasis in diabetic women with endometrial cancer.

Glycated hemoglobin A1c (HbA1c) is a well-established marker for glycemic control; recent studies suggest its potential role in cancer prognosis. Understanding the relationship between preoperative HbA1c levels and lymph node metastasis (LNM) in diabetic women with endometrial cancer (EC) can enhance prognostic assessments and treatment strategies. This study aimed to evaluate the predictive value of preoperative HbA1c levels for LNM in diabetic women with EC. A retrospective analysis was conducted on 233 diabetic women who underwent surgery for endometrioid-type EC at a tertiary referral hospital between 2010 and 2021. Data collected included demographic information, fasting plasma glucose, HbA1c levels, ultrasound findings, and tumor characteristics. Receiver operating characteristic (ROC) analysis was used to assess the predictive power of HbA1c levels for LNM. Univariate and multivariate regression analyses were performed to identify independent risk factors for LNM. The mean preoperative HbA1c level was 7.03 ±1.37%. A cutoff HbA1c level ≥7.26% demonstrated a sensitivity of 73.7%, a specificity of 72.3% and an area under the curve (AUC) of 0.781 for predicting LNM (p < 0.001). Significant correlations were found between HbA1c levels and endometrial thickness (r = 0.231, p < 0.001), primary tumor diameter (PTD) (r = 0.173, p = 0.008) and duration of diabetes (r = 0.203, p = 0.002). Multivariate analysis identified HbA1c level (odds ratio (OR) = 2.621, 95% confidence interval (95% CI): 1.722-3.987, p < 0.001), lymphovascular space involvement (LVSI) (OR = 19.193, 95% CI: 5.805-63.458, p < 0.001), body mass index (BMI) (OR = 1.095, 95% CI: 1.010-1.188, p = 0.029), and duration of diabetes (OR = 1.019, 95% CI: 1.001-1.301, p = 0.039) as independent risk factors for LNM. Preoperative HbA1c levels serve as a significant predictor for LNM in diabetic women with EC. A cutoff HbA1c level ≥7.26% indicates higher risk of LNM. These findings underscore the importance of glycemic control in reducing cancer progression risks and improving the prognosis of diabetic patients with EC. Integrating HbA1c monitoring into preoperative assessments can help tailor personalized treatment strategies for better outcomes.

Individual and integrated indexes of inflammation predicting the risks of mental disorders - statistical analysis and artificial neural network

ObjectiveThe prevalence of mental illness in Taiwan increased. Identifying and mitigating risk factors for mental illness is essential. Inflammation may be a risk factor for mental illness; however, the predictive power of inflammation test values is unclear. Artificial intelligence can predict the risk of disease. This study was the first to conduct risk prediction based on the combination of individual inflammation test values.MethodsA retrospective longitudinal design was adopted to analyze data obtained from a medical center. Patients were enrolled if they had received blood tests for inflammation. Propensity score matching was employed for within-group comparisons. A total of 231,306 patients were enrolled. A deep neural network model was employed to establish a predictive model.ResultsAmong inflammation markers, high-sensitivity C-reactive protein concentrations were associated with the greatest risk of mental illness (37.45%), followed by the combination of individual inflammation test values (32.21%). The more abnormal a participant’s inflammation values were, the higher the risk of mental illness (aHR = 1.301, p <.001). Specifically, high-sensitivity C-reactive protein concentration was the most indicative marker for predicting mental illness. Inflammation markers exhibited certain correlations with the type of mental illness. When the same variables were considered, statistical analysis and the deep neural network had similar results. After feature extraction was incorporated, the performance of the deep neural network model improved (excellent, area under the curve = 0.9162) and could effectively predict the risk of mental illness.ConclusionInflammation values could predict the risk of developing mental illnesses in general and the risk of developing certain types of mental illness.

Response of neuronal populations to phase-locked stimulation: model-based predictions and validation.

Modulation of neuronal oscillations holds promise for the treatment of neurological disorders. Nonetheless, conventional stimulation in a continuous open-loop manner can lead to side effects and suboptimal efficiency. Closed-loop strategies such as phase-locked stimulation aim to address these shortcomings by offering a more targeted modulation. While theories have been developed to understand the neural response to stimulation, their predictions have not been thoroughly tested using experimental data. Using a mechanistic coupled oscillator model, we elaborate on two key predictions describing the response to stimulation as a function of the phase and amplitude of ongoing neural activity. To investigate these predictions, we analyze electrocorticogram recordings from a previously conducted study in Parkinsonian rats, and extract the corresponding phase and response curves. We demonstrate that the amplitude response to stimulation is strongly correlated to the derivative of the phase response ([Formula: see text] > 0.8) in all animals except one, thereby validating a key model prediction. The second prediction postulates that the stimulation becomes ineffective when the network synchrony is high, a trend that appeared missing in the data. Our analysis explains this discrepancy by showing that the neural populations in Parkinsonian rats did not reach the level of synchrony for which the theory would predict ineffective stimulation. Our results highlight the potential of fine-tuning stimulation paradigms informed by mathematical models that consider both the ongoing phase and amplitude of the targeted neural oscillation.Significance Statement This study validates a mathematical model of coupled oscillators in predicting the response of neural activity to stimulation for the first time. Our findings also offer further insights beyond this validation. For instance, the demonstrated correlation between phase response and amplitude response is indeed a key theoretical concept within a subset of mathematical models. This prediction can bring about clinical implications in terms of predictive power for manipulation of neural activity. Additionally, while phase dependence in modulation has been previously studied, we propose a general framework for studying amplitude dependence as well. Lastly, our study reconciles the seemingly contradictory views of pathologic hypersynchrony and theoretical low synchrony in Parkinson's disease.

Adaptive intrusion detection in IoT: combining batch and incremental learning for enhanced security

Abstract The Internet of Things (IoT) has become an integral part of everyday life, and plays a significant role in various sectors by enabling device-to-device communication without human intervention. However, the constant connectivity of these devices to the Internet exposes them to numerous cyberattacks, potentially leading to data breaches, device malfunctions, and unauthorized network access. The diverse range of threats targeting IoT systems highlights the need for robust security solutions, such as machine learning-based intrusion detection systems, which have attracted growing research interest. This study proposes a novel adaptive approach for intrusion detection in IoT environments by combining batch and incremental learning models. Our work overcomes the limitations of traditional machine learning-based intrusion detection methods, emphasizing the potential of incremental learning to develop more effective and resilient solutions. Unlike most existing approaches that rely solely on batch learning and lack adaptability to integrate new data for long-term security, our method offers a more flexible alternative. Specifically, we leverage the predictive power of LightGBM in batch mode to improve the performance of a Passive-Aggressive classifier as a meta-learner in incremental mode. This dual learning approach aims to enhance intrusion detection in two key ways: effectively capturing diverse attack patterns with batch learning and adapting to emerging attack patterns with incremental learning. Experiments conducted on the CICIoT2023 dataset demonstrate that the proposed approach successfully balances performance and adaptability. It maintains accurate detection capabilities across various classification tasks while remaining responsive to evolving attack patterns.

Prognostic value of tumor deposits and positive lymph nodes in colorectal cancer surgery: improved staging for long-term prognosis

BackgroundTo evaluate the prognostic value of the presence and number of tumor deposits (TDs) and the combination of TDs and number of positive lymph nodes (PLNs) in patients undergoing colorectal cancer (CRC) surgery, and to modify N staging.MethodThe clinical data of 1470 patients with stage I-IV CRC who underwent surgery in Wuhan Union Hospital from February 2014 to May 2018 were collected. The optimal cutoff value for TD + PLNs was obtained using X-tile software, and patients were regrouped accordingly. Cox univariate and multivariate analysis were used to screen the factors affecting the prognosis of patients. The receiver operating characteristic (ROC) curve and the area under the curve (AUC) were used to evaluate the predictive ability of independent prognostic factors for overall survival (OS) and disease-free survival (DFS) of patients.ResultThe presence of TD was associated with poor OS (HR = 2.478, 95%CI: 1.794–3.422, P<0.001) and DFS (HR = 2.516, 95%Cl: 1.874–3.377, P<0.001). Combined with TD and PLNs, a total of 128 of 395 N1 patients were reclassified re-staged as N2(TD + PLNs ≥ 3), which had a worse prognosis than those diagnosed with N1. Compared with Tumor Node Metastasis stage and TD number, the multivariate model constructed using independent prognostic factors showed better predictive power for OS (AUC:0.769 vs. 0.681 vs. 0.650) and DFS (AUC:0.757 vs. 0.702 vs. 0.650).ConclusionTD significantly affects the long-term prognosis of CRC patients. Combining TD and PLNs to redefine the tumor staging of CRC patients can improve the accuracy of long-term prognosis of surgical patients.

CT-based vertebral three-dimensional Hounsfield unit can predict the new vertebral fracture after percutaneous vertebral augmentation in postmenopausal women: a retrospective study

BackgroundVertebral Hounsfield unit (HU) were regarded as a new way to predict fragility fracture. However, HU values were measured in a single plane, which is not accurate for the entire vertebral body. This study aimed to create a new CT-based metric for assessing bone mineral density, three-dimensional Hounsfield unit value (3D-HU), and to evaluate its effect in independently predicting new vertebral fracture (NVF) after percutaneous vertebral augmentation (PVA) in postmenopausal women.MethodsThis study reviewed female patients with osteoporotic vertebral compression fracture (OVCF) who were treated at our hospital. Patients were divided into NVF and control groups according to whether they had NVF. 3D-HU of the L1-4 vertebrae was measured using preoperative computed tomography (CT) scanning of the lumbar spine. Demographics, procedure-related data, and radiological data were collected. Pearson correlation test was used to determine the correlation between 3D-HU and BMD T-score. The independent risk factors of NVF were determined by multivariate logistic regression analyses. Receiver operating characteristic curve (ROC) was used to evaluate the predictive performance of 3D-HU.ResultsThis study involved 349 postmenopausal women who were treated with PVA between January 2017 and August 2022. Among them, 61 people suffered the NVF following PVA. The mean 3D-HU was 40.64 ± 22.43 in the NVF group and 79.93 ± 25.69 in the without NVF group (p < 0.001). Multivariate analysis showed that lower 3D-HU (OR = 0.927; 95%CI = 0.906–0.945; p < 0.001) was the only independent predictor of NVF following PVA. The predictive accuracy of 3D-HU was 87.7%, which was higher than that of the HU value (82.3%), and it was highly positively correlated with BMD T-score (r = 0.628, p < 0.001).ConclusionsLower 3D-HU was significantly associated with NVF following PVA in postmenopausal women. In addition, vertebral 3D-HU had better predictive power than HU values. 3D-HU assessment prior to PVA may provide insight into a patient’ s risk for NVF.

Using Causal Graph Model variable selection for BERT models Prediction of Patient Survival in a Clinical Text Discharge Dataset

Feature selection in most black-box machine learning algorithms, such as BERT, is based on the cor-relations between features and the target variable rather than causal relationships in the dataset. This makes their predictive power and decisions questionable because of their potential bias. This paper presents novel BERT models that learn from causal variables in a clinical discharge dataset. The causal-directed acyclic Graphs (DAG) identify input variables for patients’ survival rate prediction and decisions. The core idea behind our model lies in the ability of the BERT-based model to learn from the causal DAG semi-synthetic dataset, enabling it to model the underlying causal structure accurately in-stead of the generic spurious correlations devoid of causation. The results from Causal DAG Conditional Independence Test (CIT) validation metrics showed that the conceptual assumptions of the causal DAG were supported, the Pearson correlation coefficient ranges between -1 and 1, the p-value was (&gt;0.05), and the confidence interval of 95% and 25% were satisfied. We further mapped the semi-synthetic dataset that evolved from the Causal DAG to three BERT models. Two metrics, pre-diction accuracy, and AUC score, were used to compare the performance of the BERT models. The accuracy of the BERT models showed that the regular BERT has a performance of 96%, while Clinical-BERT performance was 90%, and Clinical-BERT-Discharge-summary was 92%. On the other hand, the AUC score for BERT was 79%, ClinicalBERT was 77%, while ClinicalBERT-discharge summary was 84%. Our experiments on the synthetic dataset for the patient’s survival rate from the causal DAG datasets demonstrate high predictive performance and explainable input variables for human under-standing to justify prediction.

Development of a miRNA-Based Model for Lung Cancer Detection

Background: Lung cancer is the leading cause of cancer-related mortality globally, with late-stage diagnoses contributing to poor survival rates. While lung cancer screening with low-dose computed tomography (LDCT) has proven effective in reducing mortality among heavy smokers, its limitations, including high false-positive rates and resource intensiveness, restrict widespread use. Liquid biopsy, particularly using microRNA (miRNA) biomarkers, offers a promising adjunct to current screening strategies. This study aimed to evaluate the predictive power of a panel of serum miRNA biomarkers for lung cancer detection. Patients and Methods: A case-control study was conducted at two tertiary hospitals, enrolling 82 lung cancer cases and 123 controls. We performed an extensive literature review to shortlist 25 candidate miRNAs, of which 16 showed a significant two-fold increase in expression compared to the controls. Machine learning techniques, including Random Forest, K-Nearest Neighbors, Neural Networks, and Support Vector Machines, were employed to identify the top six miRNAs. We then evaluated predictive models, incorporating these biomarkers with lung nodule characteristics on LDCT. Results: A prediction model utilising six miRNA biomarkers (mir-196a, mir-1268, mir-130b, mir-1290, mir-106b and mir-1246) alone achieved area under the curve (AUC) values ranging from 0.78 to 0.86, with sensitivities of 70–78% and specificities of 73–85%. Incorporating lung nodule size significantly improved model performance, yielding AUC values between 0.96 and 0.99, with sensitivities of 92–98% and specificities of 93–98%. Conclusions: A prediction model combining serum miRNA biomarkers and nodule size showed high predictive power for lung cancer. Integration of the prediction model into current lung cancer screening protocols may improve patient outcomes.

Equitable machine learning counteracts ancestral bias in precision medicine

Gold standard genomic datasets severely under-represent non-European populations, leading to inequities and a limited understanding of human disease. Therapeutics and outcomes remain hidden because we lack insights that could be gained from analyzing ancestrally diverse genomic data. To address this significant gap, we present PhyloFrame, a machine learning method for equitable genomic precision medicine. PhyloFrame corrects for ancestral bias by integrating functional interaction networks and population genomics data with transcriptomic training data. Application of PhyloFrame to breast, thyroid, and uterine cancers shows marked improvements in predictive power across all ancestries, less model overfitting, and a higher likelihood of identifying known cancer-related genes. Validation in fourteen ancestrally diverse datasets demonstrates that PhyloFrame is better able to adjust for ancestry bias across all populations. The ability to provide accurate predictions for underrepresented groups, in particular, is substantially increased. Analysis of performance in the most diverse continental ancestry group, African, illustrates how phylogenetic distance from training data negatively impacts model performance, as well as PhyloFrame’s capacity to mitigate these effects. These results demonstrate how equitable artificial intelligence (AI) approaches can mitigate ancestral bias in training data and contribute to equitable representation in medical research.

Development of a Metabolic Syndrome Prediction Model Using HOMA-IR and Multivariate Factors

We aimed to develop a multiple logistic regression model for predicting the occurrence of metabolic syndrome (MetS) using homeostasis model assessment of insulin resistance (HOMA-IR) levels, gender, age, and Diabetes Mellitus (DM) status, and to evaluate its predictive accuracy. Data from 6134 participants in the 2019 Korea National Health and Nutrition Examination Survey were analyzed. MetS was diagnosed using the Adult Treatment Panel III criteria. A logistic regression model was developed based on the regression coefficients of each variable. Model performance was evaluated through a receiver operating characteristic analysis, revealing an overall area under the curve (AUC) of 0.819, a sensitivity of 80%, and a specificity of 68.9%. Age-specific analysis showed that the model’s predictive power was highest among those aged 20–29 years (AUC: 0.864). Conversely, the AUC progressively decreased in individuals aged ≥50 years, indicating reduced predictive power in older adults. These findings suggest the importance of adopting a multidimensional approach that considers HOMA-IR, age, gender, and DM status for predicting MetS. The developed prediction model can be used as a valuable tool for the early diagnosis of MetS and the development of tailored MetS prevention programs. It also provides foundational data for shaping public health policies related to MetS.

Robustness of Machine Learning Predictions for Determining Whether Deep Inspiration Breath-Hold Is Required in Breast Cancer Radiation Therapy

Background/Objectives: Deep inspiration breath-hold (DIBH) is a commonly used technique to reduce the mean heart dose (MHD), which is critical for minimizing late cardiac side effects in breast cancer patients undergoing radiation therapy (RT). Although previous studies have explored the potential of machine learning (ML) to predict which patients might benefit from DIBH, none have rigorously assessed ML model performance across various MHD thresholds and parameter settings. This study aims to evaluate the robustness of ML models in predicting the need for DIBH across different clinical scenarios. Methods: Using data from 207 breast cancer patients treated with RT, we developed and tested ML models at three MHD cut-off values (240, 270, and 300 cGy), considering variations in the number of independent variables (three vs. six) and folds in the cross-validation (three, four, and five). Robustness was defined as achieving high F2 scores and low instability in predictive performance. Results: Our findings indicate that the decision tree (DT) model demonstrated consistently high robustness at 240 and 270 cGy, while the random forest model performed optimally at 300 cGy. At 240 cGy, a threshold critical to minimize late cardiac risks, the DT model exhibited stable predictive power, reducing the risk of overestimating DIBH necessity. Conclusions: These results suggest that the DT model, particularly at lower MHD thresholds, may be the most reliable for clinical applications. By providing a tool for targeted DIBH implementation, this model has the potential to enhance patient-specific treatment planning and improve clinical outcomes in RT.

A Comparative Analysis of the Sensitivity, Specificity, Concordance, and the 5-year Predictive Power of Diabetes-related Autoantibody Assays

This study compares novel type 1 diabetes-related autoantibody assays developed to improve upon the standard radiobinding assay (RBA). Samples from 1505 individuals, followed for 5 years or to clinical type 1 diabetes, originally tested by RBA were aliquoted and sent blindly to 5 laboratories (BDC, IDR, DRI, MSD, Enable) to be tested by electrochemiluminescence (ECL) assays, Luciferase Immuno Precipitation System (LIPS) assays, multiplex antibody detection by agglutination-PCR (ADAP) assays, and N-terminally truncated GAD65 or IA2β autoantibody RBAs (tGADA/IA2βA). Findings: The fraction of samples that were concordant for negative/positive interpretations across all assays were 79.7% (GADA), 65.2% (IA-2A), 36.2% (IAA), and 67.5% (ZnT8A). The assays with the highest Youden index for predicting the previous RBA results differed by autoantibody: 0.65 LIPS(IDR) for IAA, 0.91 ECL(BDC) for ZnT8A, 0.82 tGADA RBA(IDR) for GADA, 0.91 ECL(MSD and BDC) for IA-2A. The Youden index for predicting 5-year type 1 diabetes varied significantly across assays and was highest for LIPS(DRI) for all autoantibody combinations, with little variation in the respective maximum Youden index. The discordance between assays makes it problematic to interpret positivity when comparing results from different assays. Longitudinal autoantibody assessments should be tested with the same assay.

Fetal Birth Weight Prediction in the Third Trimester: Retrospective Cohort Study and Development of an Ensemble Model

Abstract Background Accurate third-trimester birth weight prediction is vital for reducing adverse outcomes, and machine learning (ML) offers superior precision over traditional ultrasound methods. Objective This study aims to develop an ML model on the basis of clinical big data for accurate prediction of birth weight in the third trimester of pregnancy, which can help reduce adverse maternal and fetal outcomes. Methods From January 1, 2018 to December 31, 2019, a retrospective cohort study involving 16,655 singleton live births without congenital anomalies (&gt;28 weeks of gestation) was conducted in a tertiary first-class hospital in Shanghai. The initial set of data was divided into a train set for algorithm development and a test set on which the algorithm was divided in a ratio of 4:1. We extracted maternal and neonatal delivery outcomes, as well as parental demographics, obstetric clinical data, and sonographic fetal biometry, from electronic medical records. A total of 5 basic ML algorithms, including Ridge, SVM, Random Forest, extreme gradient boosting (XGBoost), and Multi-Layer Perceptron, were used to develop the prediction model, which was then averaged into an ensemble learning model. The models were compared using accuracy, mean squared error, root mean squared error, and mean absolute error. International Peace Maternity and Child Health Hospital's Research Ethics Committee granted ethical approval for the usage of patient information (GKLW2021-20). Results Train and test sets contained a total of 13,324 and 3331 cases, respectively. From a total of 59 variables, we selected 17 variables that were readily available for the “few feature model,” which achieved high predictive power with an accuracy of 81% and significantly exceeded ultrasound formula methods. In addition, our model maintained superior performance for low birth weight and macrosomic fetal populations. Conclusions Our research investigated an innovative artificial intelligence model for predicting fetal birth weight and maximizing health care resource use. In the era of big data, our model improves maternal and fetal outcomes and promotes precision medicine.

Predicting adherence and clinical response of cognitive behavioral therapy among individuals with chronic low back pain plus depressive symptoms: A secondary analysis of a randomized controlled trial

Abstract Background Identifying predictors for adherence and clinical response to psychological therapies is essential for improving individual treatment outcomes. Objective To explore predictors of adherence and clinical response among individuals with co-occurring chronic low back pain (CLBP) and depression receiving cognitive behavioral therapy (CBT). Methods This study employs a secondary analysis of data from a randomized controlled trial (NCT04140838), including 156 individuals with CLBP plus depressive symptoms who received CBT. Multiple linear regression analyses were conducted to assess the predictive power of sociodemographic, health status, pain-related, and therapy-related variables on adherence and clinical response. Adherence was measured by therapy progress (number of completed sessions) and therapy completion (attendance at least six out of eight sessions). Clinical response was assessed by a clinically relevant reduction in posttreatment pain interference. Results Older age, higher therapy credibility, and higher education level predicted greater therapy progress, while higher therapy credibility and lower baseline stress levels predicted greater therapy completion. In addition, higher opioid use, baseline pain interference, and baseline depression levels predicted lower clinical response; in contrast, higher behavioral activation levels, older age, and unemployment predicted higher clinical response. Conclusion Therapy credibility, age, and education level are key predictors of adherence, and baseline levels of pain interference, depression, and behavioral activation are key predictors of clinical response. These findings may inform opportunities to develop more effective personalized therapeutic plans for individuals with CLBP and depression.

Remnant cholesterol, lipid ratios, and the severity of coronary artery lesions: a retrospective cohort study in patients with coronary heart disease

BackgroundEmerging genetic and observational evidence indicates that remnant cholesterol (RC) is a significant residual risk factor for cardiovascular diseases. However, there is a relative paucity of evidence exploring the correlation among RC, lipid ratios, and atherosclerotic lesion severity. This study aimed to investigate the predictive value of RC and lipid ratios alone or in combination for the severity of coronary artery stenosis in patients with coronary heart disease (CHD).MethodsThe Gensini score was used to assess the severity of coronary atherosclerotic lesions. CHD patients were categorized into mild stenosis and moderate-to-severe stenosis groups. Logistic regression was used to evaluate the risk of a high Gensini score associated with RC and lipid ratios. Our study also examined the relationship between inconsistencies in RC and non-high-density lipoprotein cholesterol (non-HDL-C) levels and the severity of coronary artery stenosis. Receiver operating characteristic (ROC) curves were used to assess the predictive power of RC and lipid ratios alone or in combination for moderate to severe coronary artery lesions.ResultsMultivariate regression models suggested that RC was a strong predictor of moderate to severe coronary artery stenosis [odds ratio (OR): 5.44, P &amp;lt; 0.001]. When grouped by curve-fitting inflection points, the group with inconsistent high RC/low non-HDL-C, rather than the low RC/high non-HDL-C group, was associated with an increased risk of moderate to severe coronary stenosis compared with the consistent low RC group (OR: 2.72, P &amp;lt; 0.001). ROC curves showed that RC predicted an area under the curve (AUC) of 0.715 for coronary stenosis severity, improving the predictive efficacy of the combined predictors comprising lipid ratios (AUC: 0.723 vs. 0.703, P &amp;lt; 0.05).ConclusionsRC and various lipid ratios [triglyceride/HDL-C, total cholesterol/HDL-C, low-density lipoprotein cholesterol/HDL-C, and apoloprotein (apo)B/apoA] correlated with the degree of coronary artery stenosis in patients with CHD, suggesting that RC has potential value as a biomarker reflecting the degree of coronary artery stenosis independent of the traditional risk factors and the levels of non-HDL-C. This could enhance the predictive efficacy based on the lipid ratio model and had better predictive value for moderate to severe coronary artery lesions.

Forecasting the Market Returns And Portfolio Enhancement With Frequency‐Decomposed Institutional Investor Sentiment: Evidence From the Taiwan Futures Market

ABSTRACTThis study examines the predictive power of changes in institutional investor sentiment in the Taiwan futures market for forecasting stock index futures and aggregate stock market returns. Using wavelet decomposition, the results show that long‐term sentiment changes outperform the buy‐and‐hold strategy, historical averages, undecomposed sentiment, and sentiment measures at other time scales in terms of predictive power and portfolio enhancement across the full sample. Additionally, a Markov‐switching model is applied to identify bull and bear market regimes and then to assess portfolio enhancement performance within each regime. The empirical findings reveal that, in bull markets, the long‐term sentiment‐based strategy outperforms the benchmarks mentioned above. In bear markets, a medium‐term sentiment‐based strategy delivers significant improvements in portfolio enhancement performance compared to the same aforementioned benchmarks. These results deepen our understanding of how institutional investor sentiment influences asset returns and offer valuable insights for tailoring portfolio management.