Risk Prediction Research Articles

Improved Heart Diseases Risk Prediction Using Optimized Super Learner Ensemble Model

Improved Heart Diseases Risk Prediction Using Optimized Super Learner Ensemble Model

A modified Delphi exercise in physician-perceived risk factors for drug-induced pneumotoxicity in patients with rheumatological disease

BackgroundDrugs used to treat rheumatic disease are associated with pneumotoxicity (drug-induced lung disease), but little is known about associated risk factors.AimTo determine expert physician-perceived risk factors for developing pneumotoxicity in patients with rheumatologic conditions.MethodsA modified international 3-tier Delphi exercise was performed. Tier 1 determined patient and drug variables that physicians perceive to be risk factors. Tier 2 determined degree of risk associated with the Tier-1 derived variables. Tier 3 aimed to internally validate and stratify exemplar cases into risk categories.Results134 pulmonologists and 49 rheumatologists responded to Tier 1;157 physicians completed all tiers. Perceived risk factors included: drug type; history of previous pneumotoxicity; age; smoking; underlying rheumatic disease type and activity; renal function; pulmonary hypertension; left ventricular failure;presence, nature, severity and progression of pre-existing interstitial lung disease. Tier 2 data stratified these variables into risk profiles e.g. never versus current smoking was perceived as low and high risk respectively. An example of perceived high risk resulting from Tier 3 is a 75-year-old current smoker with high-activity rheumatoid arthritis (RA) with severe, progressive ILD being started on methotrexate. A perceived low risk is a 75-year-old currentsmoker with moderate-activity RA and emphysema with no cardiac or renal disease and no pre-existing ILD being started on rituximab. A risk prediction scoring tool is being developed to be used in validation studies.ConclusionThis modified Delphi exercise defined and stratified the perceived risk factors for developing pneumotoxicity. Age, current smoking, high underlying rheumatological disease activity, HRCT definite UIP and honeycombing, severity and progression of pre-existing ILD were perceived to be the highest risk-factors.

Comparing methods for risk prediction of multicategory outcomes: dichotomized logistic regression vs. multinomial logit regression

BackgroundMedical outcomes of interest to clinicians may have multiple categories. Researchers face several options for risk prediction of such outcomes, including dichotomized logistic regression and multinomial logit regression modeling. We aimed to compare these methods and provide guidance needed for practice.MethodsWe described dichotomized logistic regression, multinomial continuation-ratio logit regression, which is an alternative to standard multinomial logit regression for ordinal outcomes, and logistic competing risks regression. We then applied these methods to develop prediction models of survival and neurodevelopmental outcomes based on the NICHD Extremely Preterm Birth Outcome Tool model. The statistical and practical advantages and flaws of these methods were examined. Both discrimination and calibration of the estimated logistic models of dichotomized outcomes and continuation-ratio logit model were assessed.ResultsThe dichotomized logistic models and multinomial continuation-ratio logit model had similar discrimination and calibration in predicting death and survival without neurodevelopmental impairment. But the continuation-ratio logit model had better discrimination and calibration in predicting neurodevelopmental impairment. The sum of predicted probabilities of outcome categories from the dichotomized logistic models could deviate from 100% substantially, ranging from 87.7 to 124.0%, and the dichotomized logistic model of neurodevelopmental impairment greatly overpredicted low risks and underpredicted high risks.ConclusionsEstimating multiple logistic regression models of dichotomized outcomes may result in poorly calibrated predictions for an outcome with multiple ordinal categories. Multinomial continuation-ratio logit regression produces better calibrated predictions, constrains the sum of predicted probabilities to 100%, and has the advantages of simplicity in model interpretation, flexibility to include outcome category-specific predictors and random-effect terms for patient heterogeneity by hospital. It also accounts for mutual dependence among multiple categories and accommodates competing risks.

Association of estimated glucose disposal rate with incident cardiovascular disease under different metabolic and circadian rhythm states: findings from a national population-based prospective cohort study

BackgroundRecent studies have shown that both metabolic syndrome and circadian rhythm syndrome are firmly associated with the occurrence of cardiovascular disease (CVD), with insulin resistance playing a significant role. The estimated glucose disposal rate (eGDR) is considered to be a reliable surrogate marker for insulin resistance. However, the relationship between eGDR and CVD under different metabolic and circadian rhythm states has not been thoroughly studied, and large-scale prospective cohort studies are needed to clarify this relationship.MethodsThis study is based on the China Health and Retirement Longitudinal Study (CHARLS), recruiting individuals aged 45 and above with complete eGDR data. The eGDR was calculated by the formula: eGDR(mg/kg/min) = 21.158 − (0.09 × WC) − (3.407 × hypertension) − (0.551 × HbA1c) [WC (cm), hypertension (yes = 1/no = 0), and HbA1c (%)] (Zabala et al. in Cardiovasc Diabetol 20(1):202; 2021).Participants were divided into four subgroups based on the quartiles (Q) of eGDR.The cumulative incidence rates and hazard ratios (HR) with 95% confidence intervals (CI) were calculated, with the lowest eGDR quartile (representing the highest degree of insulin resistance) as the reference. Participants were further divided into subgroups based on the diagnosis of Metabolic syndrome (MetS) or circadian syndrome (CircS) to explore the relationship between eGDR and CVD under different metabolic and circadian rhythm conditions. The dose–response relationship between eGDR and CVD incidence was investigated using a restricted cubic spline (RCS) based on a Cox regression model. Receiver operating characteristic (ROC) curves were generated to assess the predictive value of eGDR for CVD incidence. A clinical decision curve analysis (DCA) was also conducted to assess the clinical utility of the basic model.Results6507 participants were included, with a median age of 58 years [52 years, 64 years], and 55% were female. Over a median follow-up duration of 87 months, 679 first-episode CVD events were recorded, including heart disease and stroke. The RCS curves demonstrated a significant dose–response relationship between eGDR and the incidence of first-presentation CVD in different metabolic and circadian rhythm subgroups (all P-values < 0.001, non-linearity P > 0.05). eGDR exhibited a significant linear relationship with all outcomes (non-linearity P < 0.05). The Kaplan–Meier cumulative incidence curves showed that as eGDR levels increased, the cumulative incidence rates of first CVD, heart disease, and stroke gradually decreased from Q1 to Q4 groups. Significant differences were observed across all metabolic and circadian rhythm subgroups (log-rank test P < 0.001). Through the Cox proportional hazards model, we confirmed a significant association between baseline eGDR levels and first-onset CVD, heart disease, and stroke. Subgroup analyses indicated that the predictive ability of eGDR for CVD risk varied across different Body mass index (BMI) (P for interaction = 0.025) and age (P for interaction = 0.045) subgroups. Mediation analysis revealed that CircS partially mediated this association. Furthermore, time-dependent ROC curves demonstrated the potential of eGDR as a predictor of CVD risk, revealing possible differences in the model's application across different cardiovascular conditions.ConclusioneGDR is an independent predictor of CVD risk, with lower eGDR levels being closely associated with a higher risk of CVD (including heart disease and stroke). In populations with MetS or CircS, the association between lower eGDR levels and increased risk is more pronounced.

Tracing the Lipid Fingerprints of Preeclampsia.

Preeclampsia (PE) is the most common pregnancy-related complication responsible for maternal mortality and morbidity. PE pathogenesis is characterized by placental dysfunction, impaired invasion of trophoblast, and defective spiral artery remodelling. Even after many years of research on PE, the etiology and pathophysiology of PE is still elusive. Our earlier studies have shown deregulated maternal and placental fatty acid and lipid metabolism to be associated with the pathogenesis of PE. Currently available lipidomics data have shown that glycerophospholipids, sphingolipid and cholesterol metabolism are mainly altered in preeclampsia. Including these five metabolites (SM C28:1, SM C30:1, LPC C19:0, LPE C20:0, propane-1,3-diol) with currently used protein biomarkers like sFlt-1/PlGF will improve PE prediction. Similarly, CE17:1 and CER(d20:1/24:1) alongwith sFlt-1/PlGF makes a better prediction of PE than sFlt-1/PlGF alone A comprehensive map of lipid profiles in early pregnancy may provide an improved understanding of disease pathogenesis and will be useful predictive biomarkers. In this article, we aimed to summarize the significance of lipid metabolism in the preeclampsia pathogenesis and altered lipidome signatures in preeclampsia. We also discuss the future scope of lipidomics in aiding early prediction of PE and future cardiovascular risk in both mother and child.

A Cross-sectional Survey to Assess the Risk Factors of Cardiovascular Disease among College Students

Abstract Introduction: Cardiovascular diseases (CVDs) are the number one cause of death globally which claim an estimated 17.9 million lives each year. It is a major cause of disability and premature death throughout the world and contributes substantially to the escalating costs of health care. Modification of risk factors has been shown to reduce mortality and morbidity in people with diagnosed or undiagnosed CVDs. Prior assessment is found to be helpful in predictions of absolute cardiovascular risks among young adults. Objectives: The objective of the study was to assess the risk factors of cardiovascular diseases among college students. Materials and Methods: A descriptive survey was conducted among 207 college students at Najath College of Science and Technology, Karuvarakundu, Kerala from October 10, 2019, to October 18, 2019. Convenient sampling method was used to select the samples. Structured risk factor assessment Pro forma and Biophysical measurements were used as tools. Result: The study identified 40.57% of students as at moderate risk and 5.31% were at high risk for developing cardiovascular diseases. The study reported that 6.2% of students were overweight, whereas 45% had elevated blood pressure. It was found that 64.25% of the students had a family history of chronic illnesses such as diabetes, hypertension, stroke, and obesity. The 8.21% of students were smokers out of these, 17.39% were using smokeless tobacco, whereas 31.88% were exposed to passive smoking and 12.56% of students were drinkers. In terms of physical activity, 62.31% of the students were sedentary. The food habits of 98.56% of students were nonvegetarian and 46.85% of them were consuming red meat. Conclusions: Periodic assessment and comprehensive health awareness would be helpful to modify unhealthy habits and minimize the risk of cardiovascular problems among the college students.

Malnutrition and Fall Risk in Older Adults: A Comprehensive Assessment Across Different Living Situations

Background: Malnutrition among older adults is associated with numerous adverse effects, including increased morbidity, mortality, prolonged hospital stays, and a heightened risk of falls. This study aims to investigate the prevalence of malnutrition in different groups of older adults using the F-MNA, anthropometry, and s-albumin and the association between nutritional status and fall risk. Methods: A total of 228 participants aged 60 years and older were divided into three groups: (1) patients in an internal medicine ward, (2) individuals living in family homes, and (3) residents of care homes. Disease profiles, nutritional status (assessed using the F-MNA and SNAQ), body composition, fall risk, and biochemical markers were evaluated. Results: The results indicated the highest prevalence of malnutrition among hospitalized individuals. Fall risk was associated with age, calf circumference, the F-MNA, the SNAQ, serum albumin levels, residence in a care home, comorbidities, and the number of medications taken daily. Regression analysis revealed that age, calf circumference, and residence in a care home were independent predictors of fall risk in older adults. Conclusion: Older adults are at significant risk of malnutrition, with the risk notably increasing during hospitalization and long-term stays in care homes. Hospitalized individuals had the poorest nutritional status and were at significant risk of further weight loss, underscoring the importance of post-discharge care and rehabilitation.

Application of a Body Shape Index as an Anthropometric Predictor of Cardiometabolic Risks in Children and Adolescents (Systematic Review)

Application of a Body Shape Index as an Anthropometric Predictor of Cardiometabolic Risks in Children and Adolescents (Systematic Review)

Universal prediction of vertebrate species age at maturity

Animal age at maturity can be used as a universal and simple predictor of species extinction risk. At present, methods to estimate age at maturity are typically species-specific, limiting comparisons among species, or are infeasible due to practical constraints. To overcome this, here we develop a universal predictor of species-level age at maturity for vertebrates. We show that modelling the frequency of ‘CG’ sequences (CpG sites) in gene promoter regions yields rapid predictions of vertebrate age at maturity. Our models predict age at maturity with remarkable accuracy and generalisability, with median error rates of 30% (less than 1 year) and are robust to genome assemblies of varying quality. We generate predictions for 1912 vertebrate species for which age at maturity estimates were previously absent from public databases. The predictions can be used to help to inform management decisions for the many species for which more detailed population information is currently unavailable.

Development and validation of an early acute kidney injury risk prediction model for patients with sepsis in emergency departments

In this study, we aimed to develop and validate a nomogram to predicting the risk of sepsis-associated acute kidney injury (SA-AKI) in patients admitted to emergency departments (EDs). We randomly divided a retrospective dataset of 391 patients with sepsis into a 294-person training cohort and a 97-person validation cohort, and developed three predictive models using multivariate logistic regression analysis and clinical insight. No difference was observed between the three models using the DeLong test and Model 3 was selected as the risk prediction model based on the principle of least inclusion indicators. The use of vasopressor drugs, patient age, platelet count, procalcitonin, and D-dimer levels were included. The training and validation cohorts had a consistency index of 0.832 and 0.866, respectively, indicating high accuracy and stability in predicting SA-AKI risk. The area under the receiver operating characteristic curve was 0.832, showing excellent discrimination. The calibration curves for the training and validation cohorts showed excellent calibration. The decision curve and clinical impact curve analyses showed that the net clinical benefit of using the nomogram was greatest over a probability threshold of 0.05–0.90. In addition, the model showed moderate validity in predicting the 30-day survival and the incidence of major adverse renal events within 30 days. The nomogram developed for SA-AKI risk assessment in patients in EDs showed good discriminability and clinical utility. It can provide a theoretical basis for emergency physicians to prevent SA-AKI.

Modeling the distribution of jet fuel price returns based on fat-tail stable Paretian distribution.

Jet fuel plays a crucial role as an essential energy source in aerospace and aviation operations. The recent increase in fuel prices has presented airlines with the new challenge of managing jet fuel costs to ensure consistent cash flow and minimize operational uncertainties. The conventional risk prediction models used by airlines often assume that risks are normally distributed according to the classical Central Limit Theorem, which can lead to under-hedging. This paper proposes an innovative approach using the stable Paretian model to analyze the price return of jet fuel in large samples. It comprehensively compares the fitting effect of the stable Paretian distribution with that of the normal distribution based on specific criteria and non-parametric significance tests. Furthermore, it investigates the accuracy of risk measures such as Value at Risk (VaR) and Conditional Value at Risk (CVaR) predicted by both models. In addition to comparing differences in VaR between predicted values and actual values, this paper provides a more comprehensive comparison of risk measures under rolling window forecast situation. Results suggest that despite indistinguishable results in VaR backtest, the stable Paretian distribution has a overall better fitting effect as well as a less biased predicted CVaR based on the AIC of -14099.46, BIC of -14110.98, p = 0.58 in Kolmogorov-Smirnov test and p = 0.46(0.92) in the 0.01(0.05) significance level of Expected Shortfall Regression Test. This might be explained by its ability to capture asset return dynamics while maintaining shape stability with few parameters. This research can provide valuable insights for guiding airlines' risk management decisions. its ability to capture asset return dynamics while maintaining shape stability with few parameters. This research can provide valuable insights for guiding airlines' risk management decisions.

A nomogram incorporating linezolid and metabolite concentrations for predicting linezolid induced thrombocytopenia in patients with renal impairment

A nomogram to estimate the risk of linezolid-induced thrombocytopenia in patients with renal impairment is not available. The aim of the study is to develop a nomogram for predicting linezolid-induced thrombocytopenia in patients with renal impairment and to investigate the incremental value of PNU-142300 concentration beyond clinical factors and linezolid trough concentration (Cmin) for risk prediction. Logistic regression was used to identify independent risk factors for linezolid-induced thrombocytopenia in patients with renal impairment and nomograms were established. The performance of the nomograms was assessed in terms of area under the receiver operating characteristic curve (AUROC), net reclassification improvement (NRI), integrated discrimination improvement (IDI) , decision curve analysis (DCA) and calibration. Internal validation and external validation of the nomograms were also performed. Four nomograms were created: nomogram A including total bilirubin, creatinine clearance and concomitant mannitol use; nomogram B containing linezolid Cmin additionally; nomogram C containing total bilirubin, concomitant mannitol use, linezolid Cmin, and PNU142300 concentration; nomogram D including total bilirubin, concomitant mannitol use, and PNU142300 concentration. Nomogram C improved the prediction performance than nomogram A (AUROC 0.881 vs. 0.749; NRI 0.290; IDI 0.226) and nomogram B (AUROC 0.881 vs. 0.812; NRI 0.152; IDI 0.130) in the training cohort. DCA analysis showed that nomogram C yielded a greater net benefit. Compared with nomogram A and nomogram B, nomogram C also showed superior discriminatory efficacy, good calibration and clinical usefulness in the external validation cohort. The nomogram containing PNU-142300 concentration and linezolid Cmin had better predictive capability than that containing linezolid Cmin for predicting linezolid-induced thrombocytopenia in patients with renal impairment.

Construction of nomogram for wound recurrence in elderly patients with venous leg ulcers

BackgroundVenous Leg Ulcers (VLUs) are one of the most serious and intractable complications of chronic venous insufficiency. This study aims to develop a nomogram based on a theoretical model to predict the probability of wound recurrence in older patients with VLUs.MethodsThe elderly patients with VLUs attending the five hospitals between September 2021 and October 2022 were enrolled in this research, and randomized to the training and validation cohorts based on the corresponding ratio (7:3). Recurrent events were recorded during a six-month follow-up after the baseline data collection. The univariate analysis, the least absolute shrinkage and selection operator (LASSO) regression method were used to screen variables, and multiple logistic regression was used to establish a risk prediction model, which was presented by nomogram. Receiver operating curves (ROC), Hosmer–Lemeshow test, as well as calibration curves, were adopted to assess the effectiveness of the nomogram. The prognostic value of the nomogram was also examined.ResultsA total of 608 elderly patients with VLUs were included in the study. They were randomly divided into the training cohort (N = 421) and the validation cohort (N = 187). In the training cohort, Lasso regression and multivariate logistic regression analysis indicated that previous recurrence number, last ulcer duration, lower extremity DVT history, and frailty were independent risk factors for wound recurrence in elderly patients with VLUs, while daily exercise time and self-efficacy were protective factors. A nomogram was established with a good discrimination capacity and predictive efficiency with and the area under the curve (AUC) of 0.869 (95%CI: 0.831–0.908) in the training set and 0.890 (95%CI: 0.841–0.938) in the validation set. The p values of the Hosmer-Lemeshow test for both sets were 0.887 and 0.772, respectively, both greater than 0.05. The calibration degree charts showed that the data point connection was similar to the diagonal, indicating that the model’s prediction probability of wound recurrence in elderly VLUs patients is close to the actual probability.ConclusionThis study constructed a new nomogram to predict the risk of wound recurrence in elderly patients with VLUs. The nomogram has excellent accuracy and reliability, which can help healthcare workers and patients actively monitor and follow up with patients to prevent the recurrence of ulcers and make clinical decisions.

Leveraging advanced financial analytics for predictive risk management and strategic decision-making in global markets

Leveraging advanced financial analytics for predictive risk management and strategic decision-making in global markets

The Role of Artificial Intelligence (AI) and machine learning in social work practice

The integration of Artificial Intelligence (AI) and Machine Learning (ML) into social work practice is transforming the landscape of service delivery and decision-making. This paper explores how these technologies enhance case management, predictive analytics, and resource allocation in critical areas such as child welfare, mental health, and substance abuse treatment. Key trends highlighted include the use of AI-based predictive analytics to identify at-risk populations and facilitate early interventions, as well as the deployment of chatbots and virtual assistants for providing accessible mental health counselling and social support. Furthermore, the paper addresses ethical considerations and challenges associated with AI implementation, particularly the potential biases in algorithms that may affect the assessment of social needs. Additionally, the integration of AI tools into social work education and training is examined to prepare future professionals for a technology-driven environment. By analysing the current applications of Natural Language Processing (NLP) for client data analysis, AI-powered software for predictive risk assessments, and automated case management systems, this paper advocates for a balanced approach to AI adoption, ensuring that the core values of social work, such as equity and social justice, remain central to practice. Ultimately, this exploration underscores the potential of AI and ML to enhance social work outcomes while also emphasizing the necessity of ethical frameworks and ongoing training for practitioners.

The association between ADAMTS14/rs4747096 gene polymorphism and some risk factors and knee osteoarthritis

Knee osteoarthritis (KOA) is an important cause of disability in the world and it denotes a public health defiance of the upcoming years.Aim To examine the connection between ADAMTS14 gene rs4747096 polymorphism and KOA and to assess risk factors associated with KOA.Methods A case control study was conducted on 158 patients with KOA and 120 controls with comparable age and sex randomly recruited from National Research Centre employees. All participants were subjected to full history taking, assessment of KOA severity using WOMAC scoring system, and thorough clinical examination. Blood sample was collected for detection of ADAMTS14/rs4747096 gene polymorphism.Results The frequency of ADAMTS14 gene rs4747096 genotypes among patients with KOA was 73.5% for AA, 25.7% for AG, and 0.7% for GG compared to controls 963%, 31.3%, and 5.6% respectively and the frequency of alleles among patients was 86.4% for A and 78.7% for G compared to controls (78.7% and 21.3% respectively, P < 0.05. The study found that the median levels of total WOMAC score and its domains were significantly higher among KOA patients than controls. The logistic regression analysis revealed that age ≥ 50 years, BMI ≥ 35, and long standing at work were predictive factors for KOA (P < 0.05). Regarding different genetic patterns, only the A recessive pattern of inheritance was found to be a predictive risk factor for KOA.Conclusion For ADAMTS14 rs4747096 genotype, the AA and AG genotypes significantly increased the risk of KOA. The recessive pattern of inheritance, older age, morbid obesity, and prolonged standing at work were the predictive risk factors for KOA. Further studies with larger sample size are encouraged to investigate the mechanism by which this genotype can affect the development of KOA.

Use of anthropometric parameters, body composition and conicity index as predictors of cardiovascular risk in overweight and obese women

Introduction: Obesity is a growing global public health problem. Currently, more than 2 billion people in the world are overweight, and around 670 million of them have been diagnosed with obesity. Objective: To relate anthropometric parameters, body composition markers and the conicity index as predictors of cardiovascular risk in overweight or obese adult women. Methods: This was a cross-sectional study of 62 women. Body weight, height, waist and hip circumference were assessed. Based on these data, body mass index, waist-to-hip ratio, waist-to-height ratio and conicity index were obtained. Total and visceral fat percentages were also determined. Results: The patients were characterized by a mean age of 39.7 years (SD± 11.58), a mean BMI of 33.72 kg/m2 (SD± 4.74), WC of 100.27 cm (SD± 11.86); WC of 116.09 cm (SD± 9.53); WHR of 0.86 cm (SD± 0.07); WHtR of 0.64 cm (SD±0.07); %BF of 48% (SD± 639.11); %GV of 9% (SD± 2), and IC of 1.27 (SD± 0.09). There was a statistically significant difference between WHR and the parameters of %BF (P-value: 0.022), %GV (P-value: 0.001), and IC (P-value: 0.000). There was also a significant association between WHtR and GV percentages (P-value: 0.000) and IC (P-value: 0.001). With regard to IC, the analysis showed a significant difference for %GV (P-value: 0.002) and WC (P-value: 0.000). Conclusion: The use of anthropometric indicators such as waist-to-height ratio, waist-to-hip ratio and conicity index is an easy-to-apply and low-cost tools that can be used to assess and diagnose cardiovascular risk in overweight women.

Cognitive impairment among older persons with chronic illness attending primary care and its association with cardiovascular risk using the Framingham risk score

BackgroundDementia is a major public health burden, particularly among the older persons with significant implications for individuals, caregivers, and society. Identifying mild cognitive impairment early can facilitate timely intervention and care.This cross-sectional study aims to investigate the association between Framingham risk score (FRS), a widely used tool for cardiovascular disease (CVD) risk prediction, and cognitive impairment among older persons with chronic illness in Malaysia.MethodsA total of 289 participants aged 60 years and above with chronic illness were recruited from Klinik Primer Hospital Tuanku Chanselor Muhriz via simple random sampling via computer generator. The Montreal Cognitive Assessment Bahasa Malaysia version (MoCA-BM) was used to assess cognitive function and the FRS was calculated on the basis of CVD risk factors.ResultsThe prevalence of cognitive impairment among the participants was found to be 19.7%. Multiple Logistic Regression revealed that age (AOR 1.101, 95% CI = 1.041,1.163, p < 0.001), systolic blood pressure (AOR 1.048, 95%CI = 1.024, 1.072, p < 0.001) diabetes (AOR 2.655, 95% CI = 1.194, 5.906, p = 0.017) increased the odds of having cognitive impairment among older persons with chronic illness whereas secondary education ( AOR 0.087, 95% CI = 0.008, 0.963, p = 0.047) and higher education ( AOR 0.037, 95% CI = 0.002, 0.833, p = 0.038) reduced the likelihood of having cognitive impairment. Individuals with higher FRS were more likely to have cognitive impairment (AOR 1.099, 95% CI = 1.049, 1.172, p < 0.001). The optimal cutoff point for the FRS to determine cognitive impairment is 30 for males with a sensitivity and specificity of 84.4% and 51.2% while the optimal cut off point for females is 18.5 with a sensitivity and specificity of 76% and 63.1% respectively.ConclusionsThese findings suggest that the FRS which was originally designed for CVD risk assessment may also serve as a valuable predictive tool for cognitive impairment among older persons with chronic illness. Integrating FRS into routine primary care assessments could enhance the early identification of individuals at risk and enable appropriate cognitive screenings and interventions. Further research such as a longitudinal cohort study in a larger and more diverse population is warranted to validate the association of CVD risks with the development of dementia.

Lung Ultrasound in the Acute Phase of ST-Segment-Elevation Acute Myocardial Infarction: 1-Year Prognosis and Improvement in Risk Prediction.

Lung ultrasound (LUS) has emerged as a useful tool in the acute phase of patients admitted for ST-segment-elevation myocardial infarction. However, its long-term significance remains uncertain, and risk scores do not include LUS findings as a predictor. This study aims to assess the 1-year prognostic value of LUS and its ability to enhance existing risk scores. This is a multicenter prospective cohort study involving 373 patients with ST-segment-elevation myocardial infarction. LUS was performed during the first 24 hours after angiography. LUS results were assessed both as a categorical (wet/dry lung) and continuous variable (LUS score). The primary end point comprised the following major adverse cardiovascular events: all-cause mortality or hospitalization for heart failure, acute coronary syndrome, or stroke within 1 year. We also evaluated whether LUS could enhance the predictive value of the GRACE (Global Registry of Acute Coronary Events) score. Major adverse cardiovascular events occurred in 51 (13.7%) patients over a median follow-up of 368 days. After multivariate analysis, the LUS score was an independent predictor (hazard ratio [HR], 1.06 [95% CI, 1.01-1.10]; P=0.009] for each additional B-line), whereas the categorical classification was an independent predictor in patients with ST-segment-elevation myocardial infarction Killip I (HR, 3.12 [95% CI, 1.34-7.31]; P=0.009). Incorporating LUS into GRACE resulted in a net reclassification index of 31.6% and a significant increase in the area under the curve; GRACE alone scored 0.705 compared with GRACE+LUS 0.791 (P=0.002). Detecting B-lines on LUS at the acute phase predicts major adverse cardiovascular events at 1 year in patients with ST-segment-elevation myocardial infarction and enhances the predictive value of the GRACE score. REGISTRATION: URL: https://www.clinicaltrials.gov; Unique identifier: NCT04526535.

Forecasting Patient Early Readmission from Irish Hospital Discharge Records Using Conventional Machine Learning Models

Background/Objectives: Predicting patient readmission is an important task for healthcare risk management, as it can help prevent adverse events, reduce costs, and improve patient outcomes. In this paper, we compare various conventional machine learning models and deep learning models on a multimodal dataset of electronic discharge records from an Irish acute hospital. Methods: We evaluate the effectiveness of several widely used machine learning models that leverage patient demographics, historical hospitalization records, and clinical diagnosis codes to forecast future clinical risks. Our work focuses on addressing two key challenges in the medical fields, data imbalance and the variety of data types, in order to boost the performance of machine learning algorithms. Furthermore, we also employ SHapley Additive Explanations (SHAP) value visualization to interpret the model predictions and identify both the key data features and disease codes associated with readmission risks, identifying a specific set of diagnosis codes that are significant predictors of readmission within 30 days. Results: Through extensive benchmarking and the application of a variety of feature engineering techniques, we successfully improved the area under the curve (AUROC) score from 0.628 to 0.7 across our models on the test dataset. We also revealed that specific diagnoses, including cancer, COPD, and certain social factors, are significant predictors of 30-day readmission risk. Conversely, bacterial carrier status appeared to have minimal impact due to lower case frequencies. Conclusions: Our study demonstrates how we effectively utilize routinely collected hospital data to forecast patient readmission through the use of conventional machine learning while applying explainable AI techniques to explore the correlation between data features and patient readmission rate.