Risk Early Detection Research Articles

Quantitative Analysis on Vessel Stiffness and Vector Flow Imaging in the Assessment of Carotid Artery Structural and Functional Changes in Patients With Type 2 Diabetes

ObjectiveTo explore the value of RF-data-based quantitative analysis on vessel stiffness (R-QVS) combined with dynamic vector flow imaging (VFI) in evaluating structural and functional changes in the carotid arteries of patients with type 2 diabetes mellitus (T2DM). MethodsA prospective study was conducted between October 2022 and April 2024, including 275 consecutive subjects (50 volunteers as controls, 108 patients with T2DM and normal carotid intima-media thickness (CIMT), and 117 patients with T2DM and thickened CIMT). Carotid intima-media thickness (IMT) was measured using real-time intima-media thickness (RIMT) technology, while R-QVS was employed to measure the systolic diameter (Diam), displacement (Dist), hardness coefficient (HC), and pulse wave velocity (PWV) of the distal segment of the carotid artery. VFI was used to measure the maximum wall shear stress (WSSmax), mean wall shear stress (WSSmean), and maximum instantaneous velocity (Vmax) of the vessel wall. Differences in ultrasound parameters among the three groups were compared, and receiver operating characteristic (ROC) curves were plotted to calculate the area under the curve (AUC), evaluating the efficacy of these parameters in assessing structural and functional changes in the carotid arteries of patients with T2DM. ResultsThere were statistically significant differences in carotid IMT, Diam, Dist, HC, PWV, WSSmax, and Vmax among the three groups (all p < 0.01). The AUCs for evaluating structural and functional changes in the carotid arteries of patients with T2DM using carotid ultrasound parameters Diam, Dist, HC, PWV, WSSmax, and Vmax were 0.64, 0.68, 0.83, 0.88, 0.86, and 0.82, respectively. Multiple linear regression analysis identified Dist., HC, PWV, WSSmax, and WSSmean as influencing factors for CIMT in T2DM patients (with β values of -0.406, 0.515, 0.564, -0.472, and -0.438, respectively; all p < 0.05). ConclusionR-QVS and VFI techniques contribute to the early assessment of structural and functional changes in the carotid arteries of patients with type 2 diabetes mellitus. Compared with controls, T2DM patients exhibit more advanced functional changes than morphological changes despite normal CIMT. The enhanced sensitivity, reproducibility, and detailed assessment capabilities of these methods make them valuable tools in the early detection and intervention of cardiovascular risk in T2DM.

Prevalence of peripheral artery disease in young coronary artery disease patients

Background and objectives. Peripheral artery disease (PAD) and coronary artery disease (CAD) are progressive inflammatory conditions caused by arteriosclerosis, typically presenting after the age of 50. However, assessing peripheral vascular disease (PVD) in younger populations may offer early indications of coronary heart disease (CHD) risk. This study investigates the prevalence of abnormal ankle brachial index (ABI) values among young myocardial infarction (MI) patients and examines the correlation of ABI with other cardiovascular risk factors. Material and methods. This cross-sectional study was conducted at Saveetha Medical College and Hospital, involving 147 patients aged 40 years or younger who were admitted with MI symptoms. The study focused on the incidence and severity of MI in relation to age, sex, and the presence of risk factors such as smoking, alcohol use, dyslipidemia, hypertension (HTN), and diabetes mellitus (DM). Results. The study analyzed the incidence of myocardial infarction (MI) in a population under 40 years old. It was found that the incidence rate increased with age within this group. Specifically, males were more frequently affected than females, with 70% of cases occurring in males. Among female participants, all were over 30 years old. In terms of ankle-brachial index (ABI) values, 40% of females exhibited abnormal ABI, compared to 25% of males. Significant risk factors identified included smoking, with 60% of participants reporting tobacco use, alcohol consumption at 50%, and dyslipidemia present in 45% of cases. Hypertension (HTN) and diabetes mellitus (DM) were less prevalent, affecting 20% and 15% of participants, respectively. There was a significant correlation between low ABI values and the use of tobacco (p&lt;0.01) and alcohol (p&lt;0.05). However, the analysis showed no significant relationship between the number of vascular involvements indicated by ABI and the length of hospital stay. The length of hospital stay did increase with patient age, with an average increase of 2 days for every decade of age, but this was not significantly associated with ABI values. Conclusion. ABI is a valuable diagnostic tool in young populations for detecting early signs of CHD, offering advantages over routine blood pressure measurements. This study supports the broader use of ABI in both young and older populations to improve early detection and management of cardiovascular risks. Further research is needed to explore the implications of ABI in routine clinical practice and its correlation with other cardiovascular risk factors.

Implementing K-Nearest Neighbors (k-NN) Algorithm and Backward Elimination on Cardiotocography Datasets

Having a healthy baby is a dream for mothers. Unfortunately, high maternal and fetal mortality has become a vital problem that requires early risk detection for pregnant women. A cardiotocograph examination is necessary to maintain maternal and fetal health. One method that can solve this problem is classification. This research analyzes the optimal use of k values and distance measurements in the k-NN method. This research expects to become the primary reference for other studies examining the same dataset or developing k-NN. A selection feature is needed to optimize the classification method, particularly for improving accuracy results. This study used the cardiotocography dataset from cardiotocograph examinations related to fetal conditions. The cardiotocography dataset consisted of 2,126 records with 22 features and variables. It also had three classification classes, normal, suspect, and pathological, from the Universal Child Immunization Machine Learning Repository website. It employed the K-Nearest Neighbor (k-NN) method and the backward elimination feature with ordinary least squares regression. The test in this research applied the scenarios of three distance calculations, i.e., Euclidean distance, Manhattan distance, and Minkowski distance, as well as four variations of k values. Evaluation of each scenario indicated the accuracy of the confusion matrix and execution time. This study compared K-Nearest Neighbor (k-NN) and Backward Elimination methods with K-nearest neighbor (k-NN) without selection features. The best accuracy of the Backward Elimination and K-Nearest Neighbor (K-NN) methods was 91%, as was the K-Nearest Neighbor (k-NN) method without selection features. Both had similar k values (k = 3) and Manhattan distance. The backward elimination method reduced the number of features from 22 to 14. Meanwhile, the execution times of the Backward Elimination and K-Nearest Neighbor (k-NN) methods got better results as each distance averaged 26.54, 19.23, and 68.09 seconds. K-Nearest Neighbor (k-NN) execution times without selection features were 26.83, 19.39, and 68.84, respectively. In conclusion, backward elimination did not increase accuracy because it yielded the same accuracy. However, backward elimination and K-nearest Neighbor (k-NN) produced faster results, with differences of 29%, 16%, and 75%, respectively.

PELAKSANAAN ANTENATAL CARE DENGAN 10 T DIPUSKESMAS MUNGKUR AGUNG KECAMATAN KELUA

Maternal and child health is a priority for health development in Indonesia. The implementation of Ante Natal Care with 10 T in pregnant women affects the results of early detection of risks and complications during pregnancy. This cause of maternal death shows that maternal death can be prevented if the coverage of services is accompanied by good quality service. The purpose of the study was to determine the Implementation of Antenatal Care with 10 T at the Mungkur Agung Health Center, Kelua District. This research method with quantitative descriptive, with a population of all pregnant women at 20 weeks gestational age and over trimester II, III with a total sampling technique, namely pregnant women totaling 38 people Results: It was found that the implementation of ANC with 10 T according to the standard was (97.37%), %) and there was 1 (2.63%) pregnant women who in the implementation of ANC did not meet the 10 T standard.

Wearable Sensors for Healthcare of Industrial Workers: A Scoping Review

Background and Objectives: This scoping review evaluates the use of wearable sensor technologies for workplace safety and health monitoring in industrial settings. The aim is to synthesize evidence on the impact of these sensors and their application in high-risk environments. Materials and Methods: Following the PRISMA guidelines, a systematic search across four international electronic databases yielded 59 studies, of which 17 were included in the final review. The selection criteria involved studies that specifically utilized wearable sensors to monitor various health and environmental parameters relevant to industrial workers. Results: The analysis categorizes wearable technologies into five distinct groups based on their function: gas monitoring technologies, heart rate and physiological data collection, fatigue and activity monitoring, comprehensive environmental and physiological monitoring, and advanced sensing and data collection systems. These devices demonstrated substantial benefits in terms of early detection of health risks and enhancement of safety protocols. Conclusions: The review concludes that wearable sensor technologies significantly contribute to workplace safety by providing real-time, data-driven insights into environmental hazards and workers’ physiological status, thus supporting proactive health management practices in industrial settings. Further research is recommended to address the challenges of data privacy, sensor reliability, and cost-effective integration to maximize their potential in occupational health safety.

Identifying biological markers and sociodemographic factors that influence the gap between phenotypic and chronological ages

ABSTRACT Introduction The world’s population is aging rapidly, leading to increased public health and economic burdens due to age-related cardiovascular and neurodegenerative diseases. Early risk detection is essential for prevention and to improve the quality of life in elderly individuals. Plus, health risks associated with aging are not directly tied to chronological age, but are also influenced by a combination of environmental exposures. Past research has introduced the concept of “Phenotypic Age,” which combines age with biomarkers to estimate an individual’s health risk. Methods This study explores which factors contribute most to the gap between chronological and phenotypic ages. We combined ten machine learning regression techniques applied to the NHANES dataset, containing demographic, laboratory and socioeconomic data from 41,474 patients, to identify the most important features. We then used clustering analysis and a mixed-effects model to stratify by sex, ethnicity, and education. Results We identified 28 demographic, biological and environmental factors related to a significant gap between phenotypic and chronological ages. Stratifying for sex, education and ethnicity, we found statistically significant differences in the outcome distributions. Conclusion By showing that health risk prevention should consider both biological and sociodemographic factors, we offer a new approach to predict aging rates and potentially improve targeted prevention strategies for age-related conditions.

Machine Learning-Driven Prediction of Brain Age for Alzheimer's Risk: APOE4 Genotype and Gender Effects.

Background: Alzheimer's disease (AD) is a leading cause of dementia, and it is significantly influenced by the apolipoprotein E4 (APOE4) gene and gender. This study aimed to use machine learning (ML) algorithms to predict brain age and assess AD risk by considering the effects of the APOE4 genotype and gender. Methods: We collected brain volumetric MRI data and medical records from 1100 cognitively unimpaired individuals and 602 patients with AD. We applied three ML regression models-XGBoost, random forest (RF), and linear regression (LR)-to predict brain age. Additionally, we introduced two novel metrics, brain age difference (BAD) and integrated difference (ID), to evaluate the models' performances and analyze the influences of the APOE4 genotype and gender on brain aging. Results: Patients with AD displayed significantly older brain ages compared to their chronological ages, with BADs ranging from 6.5 to 10 years. The RF model outperformed both XGBoost and LR in terms of accuracy, delivering higher ID values and more precise predictions. Comparing the APOE4 carriers with noncarriers, the models showed enhanced ID values and consistent brain age predictions, improving the overall performance. Gender-specific analyses indicated slight enhancements, with the models performing equally well for both genders. Conclusions: This study demonstrates that robust ML models for brain age prediction can play a crucial role in the early detection of AD risk through MRI brain structural imaging. The significant impact of the APOE4 genotype on brain aging and AD risk is also emphasized. These findings highlight the potential of ML models in assessing AD risk and suggest that utilizing AI for AD identification could enable earlier preventative interventions.

Artificial intelligence based real-time prediction of imminent heart failure hospitalisation in patients undergoing non-invasive telemedicine.

Remote patient management may improve prognosis in heart failure. Daily review of transmitted data for early recognition of patients at risk requires substantial resources that represent a major barrier to wide implementation. An automated analysis of incoming data for detection of risk for imminent events would allow focusing on patients requiring prompt medical intervention. We analysed data of the Telemedical Interventional Management in Heart Failure II (TIM-HF2) randomized trial that were collected during quarterly in-patient visits and daily transmissions from non-invasive monitoring devices. By application of machine learning, we developed and internally validated a risk score for heart failure hospitalisation within seven days following data transmission as estimate of short-term patient risk for adverse heart failure events. Score performance was assessed by the area under the receiver-operating characteristic (ROCAUC) and compared with a conventional algorithm, a heuristic rule set originally applied in the randomized trial. The machine learning model significantly outperformed the conventional algorithm (ROCAUC 0.855 vs. 0.727, p < 0.001). On average, the machine learning risk score increased continuously in the three weeks preceding heart failure hospitalisations, indicating potential for early detection of risk. In a simulated one-year scenario, daily review of only the one third of patients with the highest machine learning risk score would have led to detection of 95% of HF hospitalisations occurring within the following seven days. A machine learning model allowed automated analysis of incoming remote monitoring data and reliable identification of patients at risk of heart failure hospitalisation requiring immediate medical intervention. This approach may significantly reduce the need for manual data review.

Correlation between serum hemoglobin levels and bone mineral density in adults: A cross-sectional study.

Serum hemoglobin plays an important role in bone metabolism. However, the association between serum hemoglobin levels and bone mineral density (BMD) remains unclear. Therefore, this study aimed to explore the relationship between serum hemoglobin levels and lumbar spine BMD in adults. We conducted a cross-sectional study by utilizing data from the National Health and Nutrition Examination Survey from 2011 to 2018. The serum hemoglobin level was examined as an independent variable, while the lumbar spine BMD was utilized as the dependent variable. Weighted multivariate linear regression models and stratified analysis by age, sex, and race/ethnicity were applied after controlling for confounding factors to assess the relationship between serum hemoglobin levels and the lumbar spine BMD. Additionally, smooth curve fitting and threshold effect analyses were utilized to depict the nonlinear relationship between the 2 variables. A total of 11,658 participants (6004 men and 5654 women) aged ≥ 18 years were included in this study. When the serum hemoglobin level was represented as a continuous variable and fully adjusted in the regression model, the hemoglobin level was significantly negatively correlated with the lumbar spine BMD (β = -0.0035, 95% confidence interval: -0.0065 to -0.0004, P = .024555); this significant negative correlation persisted when the serum hemoglobin level was transformed into a categorical variable, except in the Q2 group (β = -0.0046, 95% confidence interval: -0.0142 to -0.0050, P = .348413). When different confounding factors were used including sex, age, and race/ethnicity, the stratified subgroups exhibited a negative correlation between the serum hemoglobin level and the lumbar spine BMD. Additionally, smooth curve fitting and threshold effect analyses showed a negative correlation between the serum hemoglobin level and the lumbar spine BMD, with a saturation effect at 15 g/dL. Our findings demonstrated an association between hemoglobin levels and the lumbar spine BMD in adults, characterized by a nonlinear relationship. Thus, monitoring the serum hemoglobin level could aid in the early detection of risks associated with bone metabolic disorders such as osteoporosis.

Fed-CL- an atrial fibrillation prediction system using ECG signals employing federated learning mechanism

Deep learning has shown great promise in predicting Atrial Fibrillation using ECG signals and other vital signs. However, a major hurdle lies in the privacy concerns surrounding these datasets, which often contain sensitive patient information. Balancing accurate AFib prediction with robust user privacy remains a critical challenge to address. We suggest Federated Learning , a privacy-preserving machine learning technique, to address this privacy barrier. Our approach makes use of FL by presenting Fed-CL, a advanced method that combines Long Short-Term Memory networks and Convolutional Neural Networks to accurately predict AFib. In addition, the article explores the importance of analysing mean heart rate variability to differentiate between healthy and abnormal heart rhythms. This combined approach within the proposed system aims to equip healthcare professionals with timely alerts and valuable insights. Ultimately, the goal is to facilitate early detection of AFib risk and enable preventive care for susceptible individuals.

Association Between Coronary Calcium Detection on Chest Computed Tomography and Ischemic Cardiovascular Events and Mortality in Asymptomatic Chronic Obstructive Pulmonary Disease Patients. Systematic Review of the Literature

IntroductionLiterature suggests that there is a close relationship between chronic obstructive pulmonary disease (COPD) and cardiovascular (CV) disease. The aim of this study was to assess whether the presence of coronary calcium (CC) on chest computed tomography (CT) in asymptomatic COPD patients is associated with an increased risk of CV events and mortality. Material and methodsA systematic review of the literature was performed following PRISMA recommendations. Studies published in the last 20 years in four databases (PubMed, Web of Science, Embase and MEDLINE) were included. ResultsThree hundred fifty articles were identified, eight of them met the selection criteria. The included studies, conducted between 2013 and 2024, were predominantly multicentre cohort studies. The meta-analysis showed that the presence of CC on chest CT of COPD patients is an independent predictor of CV events (hazard ratio 1.44, 95% CI 1.22–1.70) and associated with an increased mortality during the follow-up period (hazard ratio 1.57, 95% CI 1.35–1.83). ConclusionsOur analysis suggests that the identification of CC on chest CT scans of COPD patients may be useful in the early detection and treatment of CV disease in asymptomatic patients. Prospective, multicentre studies confirming our findings are needed to explore the potential impact of early detection and treatment of CV risk in COPD patients.

The KIA Book's digitalization as a means to educate breastfeeding and postpartum moms on their children's health

The study aims to develop skilled and empowered human resources, particularly through interventions like strengthening governance and increased availability of services for the health of mothers and children. One major focus is on the postpartum period and breastfeeding, where efforts include providing support through digital tools for new mothers. The study seeks to identify a mentoring model for postpartum and breastfeeding mothers using a digital version of the KIA book. A non-equivalent control group was used in a pretest-posttest setting as part of a quasi-experimental design. The study involved 86 postpartum and breastfeeding mothers, with 43 receiving digital accompaniment through the KIA book as an intervention, while the other 43 served as a control group. Additionally, a qualitative approach was used, involving in-depth interviews with 12 postpartum and breastfeeding mothers, 6 primary healthcare midwives, and health service staff. The study found that digital accompaniment via the KIA book significantly influenced early risk detection, knowledge, and actions among the mothers. The digital assistance provided to postpartum and breastfeeding mothers positively impacted maternal and child health, enabling independent detection of health risks, increasing knowledge, and encouraging proactive behavior, along with family support. The research suggests the effectiveness of a mentoring model for these mothers through the digitization of the KIA book.

Association between long-term PM1 exposure and cognition in middle-aged and older adults: Evidence from China and the United Kingdom

Early risk detection and management are essential for cognitive preservation. While particulate matters of diameter small than 2.5 μm (PM2.5) is considered harmful to cognition, the effect of smaller, more penetrative particulate matters of diameter small than 1 μm (PM1) requires further evidence and explicit safety thresholds. In this study, we explored the effects of long-term PM1 exposure on early cognitive impairment and longitudinal cognitive changes in middle-aged and older populations. This study assessed data from two large-scale longitudinal surveys: the China Health and Retirement Longitudinal Study (CHARLS) and UK Biobank (UKB). Cross-sectional, longitudinal, and trajectory analyses were conducted to investigate the association between long-term PM1 exposure and cognition. Additionally, the exposure–response curves were fitted to determine the customized thresholds. The findings indicated that sustained PM1 exposure may lead to mild cognitive impairment, particularly at concentrations exceeding 30 and 5.6 μg·m−3 in CHARLS and UKB participants, respectively. Furthermore, we found that long-term PM1 exposure can contribute to rapid cognitive decline at concentrations exceeding 23 and 5.5 μg·m−3 in CHARLS and UKB participants, respectively. In conclusion, reducing PM1 exposure can improve the cognitive health of middle-aged and older adults.

P12-19 Early detection of hepatotoxicity risks by investigating drug impact on mitochondrial activity in HepaSH™ cells

P12-19 Early detection of hepatotoxicity risks by investigating drug impact on mitochondrial activity in HepaSH™ cells

8-OxodG: A Potential Biomarker for Chronic Oxidative Stress Induced by High-LET Radiation.

Oxidative stress-mediated biomolecular damage is a characteristic feature of ionizing radiation (IR) injury, leading to genomic instability and chronic health implications. Specifically, a dose- and linear energy transfer (LET)-dependent persistent increase in oxidative DNA damage has been reported in many tissues and biofluids months after IR exposure. Contrary to low-LET photon radiation, high-LET IR exposure is known to cause significantly higher accumulations of DNA damage, even at sublethal doses, compared to low-LET IR. High-LET IR is prevalent in the deep space environment (i.e., beyond Earth's magnetosphere), and its exposure could potentially impair astronauts' health. Therefore, the development of biomarkers to assess and monitor the levels of oxidative DNA damage can aid in the early detection of health risks and would also allow timely intervention. Among the recognized biomarkers of oxidative DNA damage, 8-oxo-7,8-dihydro-2'-deoxyguanosine (8-OxodG) has emerged as a promising candidate, indicative of chronic oxidative stress. It has been reported to exhibit differing levels following equivalent doses of low- and high-LET IR. This review discusses 8-OxodG as a potential biomarker of high-LET radiation-induced chronic stress, with special emphasis on its potential sources, formation, repair mechanisms, and detection methods. Furthermore, this review addresses the pathobiological implications of high-LET IR exposure and its association with 8-OxodG. Understanding the association between high-LET IR exposure-induced chronic oxidative stress, systemic levels of 8-OxodG, and their potential health risks can provide a framework for developing a comprehensive health monitoring biomarker system to safeguard the well-being of astronauts during space missions and optimize long-term health outcomes.

The Effects of Seismic Behavior on High Ground Stress Soft Rock Tunnel: A Review

The purpose of this review is to critically assess seismic activity's effects on soft rock tunnels under high ground stress scenarios. The paper seeks to identify key novelties and research gaps in the existing literature, offering new insights into analytical techniques, excavation methods, support systems, and monitoring technologies. A comprehensive review of recent studies was conducted, focusing on seismic behavior, analytical techniques, and mitigation strategies for soft rock tunnels. Case studies were selected based on their relevance to high ground stress conditions and their contribution to understanding seismic resilience. Significant findings include the identification of specific geological conditions that exacerbate seismic risks and the comparative effectiveness of various analytical techniques and support systems. Novel insights into the interaction of structural reinforcements and monitoring systems are also discussed. The review highlights new analytical techniques and advanced monitoring systems that improve predictive accuracy and early detection of seismic risks. It also proposes a refined approach to integrating mitigation strategies for enhanced tunnel resilience. Doi: 10.28991/CEJ-2024-010-09-020 Full Text: PDF

The research and development of an IoT device for early detection of fire and explosion risks and monitoring air quality in computer labs

The research and development of an IoT device for early detection of fire and explosion risks and monitoring air quality in computer labs

Fall risk prediction using temporal gait features and machine learning approaches.

Falls have been acknowledged as a major public health issue around the world. Early detection of fall risk is pivotal for preventive measures. Traditional clinical assessments, although reliable, are resource-intensive and may not always be feasible. This study explores the efficacy of artificial intelligence (AI) in predicting fall risk, leveraging gait analysis through computer vision and machine learning techniques. Data was collected using the Timed Up and Go (TUG) test and JHFRAT assessment from MMU collaborators and augmented with a public dataset from Mendeley involving older adults. The study introduces a robust approach for extracting and analyzing gait features, such as stride time, step time, cadence, and stance time, to distinguish between fallers and non-fallers. Two experimental setups were investigated: one considering separate gait features for each foot and another analyzing averaged features for both feet. Ultimately, the proposed solutions produce promising outcomes, greatly enhancing the model's ability to achieve high levels of accuracy. In particular, the LightGBM demonstrates a superior accuracy of 96% in the prediction task. The findings demonstrate that simple machine learning models can successfully identify individuals at higher fall risk based on gait characteristics, with promising results that could potentially streamline fall risk assessment processes. However, several limitations were discovered throughout the experiment, including an insufficient dataset and data variation, limiting the model's generalizability. These issues are raised for future work consideration. Overall, this research contributes to the growing body of knowledge on fall risk prediction and underscores the potential of AI in enhancing public health strategies through the early identification of at-risk individuals.

Blood-based multivariate methylation risk score for cognitive impairment and dementia.

The established link between DNA methylation and pathophysiology of dementia, along with its potential role as a molecular mediator of lifestyle and environmental influences, positions blood-derived DNA methylation as a promising tool for early dementia risk detection. In conjunction with an extensive array of machine learning techniques, we employed whole blood genome-wide DNA methylation data as a surrogate for 14 modifiable and non-modifiable factors in the assessment of dementia risk in independent dementia cohorts. We established a multivariate methylation risk score (MMRS) for identifying mild cognitive impairment cross-sectionally, independent of age and sex (P=2.0×10-3). This score significantly predicted the prospective development of cognitive impairments in independent studies of Alzheimer's disease (hazard ratio for Rey's Auditory Verbal Learning Test (RAVLT)-Learning=2.47) and Parkinson's disease (hazard ratio for MCI/dementia=2.59). Our work shows the potential of employing blood-derived DNA methylation data in the assessment of dementia risk. We used whole blood DNA methylation as a surrogate for 14 dementia risk factors. Created a multivariate methylation risk score for predicting cognitive impairment. Emphasized the role of machine learning and omics data in predicting dementia. The score predicts cognitive impairment development at the population level.

A Predictive Model of the Progression to Alzheimer's Disease in Patients with Mild Cognitive Impairment Based on the MRI Enlarged Perivascular Spaces.

Mild cognitive impairment (MCI) is a heterogeneous condition that can precede various forms of dementia, including Alzheimer's disease (AD). Identifying MCI subjects who are at high risk of progressing to AD is of major clinical relevance. Enlarged perivascular spaces (EPVS) on MRI are linked to cognitive decline, but their predictive value for MCI to AD progression is unclear. This study aims to assess the predictive value of EPVS for MCI to AD progression and develop a predictive model combining EPVS grading with clinical and laboratory data to estimate conversion risk. We analyzed 358 patients with MCI from the ADNI database, consisting of 177 MCI-AD converters and 181 non-converters. The data collected included demographic information, imaging data (including perivascular spaces grade), clinical assessments, and laboratory test results. Variable selection was conducted using the Least Absolute Shrinkage and Selection Operator (LASSO) method, followed by logistic regression to develop predictive model. In the univariate logistic regression analysis, both moderate (OR = 5.54, 95% CI [3.04-10.18]) and severe (OR = 25.04, 95% CI [10.07-62.23]) enlargements of the centrum semiovale perivascular space (CSO-PVS) were found to be strong predictors of disease progression. LASSO analyses yielded 12 variables, refined to six in the final model: APOE4 genotype, ADAS11 score, CSO-PVS grade, and volumes of entorhinal, fusiform, and midtemporal regions, with an AUC of 0.956 in the training and 0.912 in the validation cohort. Our predictive model, emphasizing EPVS assessment, provides clinicians with a practical tool for early detection and management of AD risk in MCI patients.