Search Results (4,683)

Background: Hypotension following epidural labor analgesia (ELA) is its most common complication, affecting approximately 20% of patients and posing risks to both maternal and fetal health. As digital tools and predictive analytics increasingly shape perioperative and obstetric anesthesia practices, real-world implementation data are needed to guide their integration into clinical care. Current monitoring practices rely on intermittent non-invasive blood pressure (NIBP) measurements, which may delay recognition and treatment of hypotension. The Hypotension Prediction Index (HPI) algorithm uses continuous arterial waveform monitoring to predict hypotension for potentially earlier intervention. This clinical trial evaluated the feasibility, acceptability, and efficacy of continuous HPI-guided treatment in reducing time-to-treatment for ELA-associated hypotension and improving maternal hemodynamics. Methods: This was a prospective randomized controlled trial design involving healthy pregnant individuals receiving ELA. Participants were randomized into two groups: Group CM (conventional monitoring with NIBP) and Group HPI (continuous noninvasive blood pressure monitoring). In Group HPI, hypotension treatment was guided by HPI output; in Group CM, treatment was based on NIBP readings. Feasibility, appropriateness, and acceptability outcomes were assessed among subjects and their bedside nurse using the Acceptability of Intervention Measure (AIM), Intervention Appropriateness Measure (IAM), and Feasibility of Intervention Measure (FIM) instruments. The primary efficacy outcome was time-to-treatment of hypotension, defined as the duration between onset of hypotension and administration of a vasopressor or fluid therapy. This outcome was chosen to evaluate the clinical responsiveness enabled by HPI monitoring. Hypotension is defined as a mean arterial pressure (MAP) < 65 mmHg for more than 1 min in Group CM and an HPI threshold < 75 for more than 1 min in Group HPI. Secondary outcomes included total time in hypotension, vasopressor doses, and hemodynamic parameters. Results: There were 30 patients (Group HPI, n = 16; Group CM, n = 14) included in the final analysis. Subjects and clinicians alike rated the acceptability, appropriateness, and feasibility of the continuous monitoring device highly, with median scores ≥ 4 across all domains, indicating favorable perceptions of the intervention. The cumulative probability of time-to-treatment of hypotension was lower by 75 min after ELA initiation in Group HPI (65%) than Group CM (71%), although this difference was not statistically significant (log-rank p = 0.66). Mixed models indicated trends that Group HPI had higher cardiac output (β = 0.58, 95% confidence interval −0.18 to 1.34, p = 0.13) and lower systemic vascular resistance (β = −97.22, 95% confidence interval −200.84 to 6.40, p = 0.07) throughout the monitoring period. No differences were found in total vasopressor use or intravenous fluid administration. Conclusions: Continuous monitoring and precision hypotension treatment is feasible, appropriate, and acceptable to both patients and clinicians in a labor and delivery setting. These hypothesis-generating results support that HPI-guided treatment may be associated with hemodynamic trends that warrant further investigation to determine definitive efficacy in labor analgesia contexts. Full article

Environmental comfort and air pollution are among the most important indicators for assessing the population’s quality of life in urban agglomerations. This study aims to explore long-term memory in air pollution time series by analyzing the dynamics of the Hurst exponent and evaluating the predictability index. This type of statistical pre-forecast analysis is essential for developing accurate forecasting models for such time series. The effectiveness of air quality monitoring systems largely depends on the precision of these forecasts. The Ekibastuz coal-mining center, which houses one of the largest coal-fired power stations in Kazakhstan and the world, with a capacity of about 4000 MW, was chosen as an example for the study. Data for the period from 1 March 2023 to 31 December 2024 were collected and analyzed at the Ekibastuz coal-fired power station. During the specified period, 14 indicators (67,527 observations) were collected at 10 min intervals, including mass concentrations of CO, NO, NO₂, SO₂, PM_2.5, and PM₁₀, as well as current mass consumption of CO, NO, NO₂, SO₂, dust, and NO_x. The detrended fluctuation analysis of a time series of air pollution indicators was used to calculate the Hurst exponent and identify long-term memory. Changes in the Hurst exponent in regards to dynamics were also investigated, and a predictability index was calculated to monitor emissions of pollutants in the air. Long-term memory is recorded in the structure of all the time series of air pollution indicators. Dynamic analysis of the Hurst exponent confirmed persistent time series characteristics, with an average Hurst exponent of about 0.7. Identifying the time series plots for which the Hurst exponent is falling (analysis of the indicator of dynamics), along with the predictability index, is a sign of an increase in the influence of random factors on the time series. This is a sign of changes in the dynamics of the pollutant release concentrations and may indicate possible excess emissions that need to be controlled. Calculating the dynamic changes in the Hurst exponent for the emission time series made it possible to identify two distinct clusters corresponding to periods of persistence and randomness in the operation of the coal-fired power station. The study shows that evaluating the predictability index helps fine-tune the parameters of time series forecasting models, which is crucial for developing reliable air pollution monitoring systems. The results obtained in this study allow us to conclude that the method of trended fluctuation analysis can be the basis for creating an indicator of the level of air pollution, which allows us to quickly respond to possible deviations from the established standards. Environmental services can use the results to build reliable monitoring systems for air pollution from coal combustion emissions, especially near populated areas. Full article

This work presents a multiscale, microstructure-aware framework for predicting fatigue strength distributions in additively manufactured (AM) alloys—specifically, laser powder bed fusion (L-PBF) AlSi10Mg and Ti-6Al-4V—by integrating density functional theory (DFT), instrumented indentation, and Bayesian inference. The methodology leverages principles common to all 3D printing (additive manufacturing) processes: layer-wise material deposition, process-induced defect formation (such as porosity and residual stress), and microstructural tailoring through parameter control, which collectively differentiate AM from conventional manufacturing. By linking DFT-derived cohesive energies with indentation-based modulus measurements and a MAP-based statistical model, we quantify the effect of additive-manufactured microstructural heterogeneity on fatigue performance. Quantitative validation demonstrates that the predicted fatigue strength distributions agree with experimental high-cycle and very-high-cycle fatigue (HCF/VHCF) data, with posterior modes and 95 % credible intervals of ${\widehat{\sigma }}_f^{\mathrm{AlSi}10\mathrm{Mg}}={86}_{-7}^{+8}\mathrm{MPa}$ and ${\widehat{\sigma }}_f^{\mathrm{Ti}–6\mathrm{Al}–4\mathrm{V}}={115}_{-9}^{+10}\mathrm{MPa}$, respectively. The resulting Woehler (S–N) curves and Paris crack-growth parameters envelop more than 92 % of the measured coupon data, confirming both accuracy and robustness. Furthermore, global sensitivity analysis reveals that volumetric porosity and residual stress account for over 70 % of the fatigue strength variance, highlighting the central role of process–structure relationships unique to AM. The presented framework thus provides a predictive, physically interpretable, and data-efficient pathway for microstructure-informed fatigue design in additively manufactured metals, and is readily extensible to other AM alloys and process variants. Full article

Background: The ability of Graph Neural Networks (GNNs) to analyse brain structural patterns in various kinds of neurodegenerative diseases, including Parkinson’s disease (PD), has drawn a lot of interest recently. One emerging technique in this field is brain age prediction, which estimates biological age to identify ageing patterns that may serve as biomarkers for such disorders. However, a significant problem with most of the GNNs is their depth, which can lead to issues like oversmoothing and diminishing gradients. Methods: In this study, we propose SAGEFusionNet, a GNN architecture specifically designed to enhance brain age prediction and assess PD-related brain ageing patterns using T1-weighted structural MRI (sMRI). SAGEFusionNet learns important ROIs for brain age prediction by incorporating ROI-aware pooling at every layer to overcome the above challenges. Additionally, it incorporates multi-layer feature fusion to capture multi-scale structural information across the network hierarchy and auxiliary supervision to enhance gradient flow and feature learning at multiple depths. The dataset utilised in this study was sourced from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. It included a total of 580 T1-weighted sMRI scans from healthy individuals. The brain sMRI scans were parcellated into 56 regions of interest (ROIs) using the LPBA40 brain atlas in CAT12. The anatomical graph was constructed based on grey matter (GM) volume features. This graph served as input to the GNN models, along with GM and white matter (WM) volume as node features. All models were trained using 5-fold cross-validation to predict brain age and subsequently tested for performance evaluation. Results: The proposed framework achieved a mean absolute error (MAE) of $4.24\pm 0.38$ years and a mean Pearson’s Correlation Coefficient (PCC) of $0.72\pm 0.03$ during cross-validation. We also used 215 PD patient scans from the Parkinson’s Progression Markers Initiative (PPMI) database to assess the model’s performance and validate it. The initial findings revealed that out of 215 individuals with Parkinson’s disease, 213 showed higher and 2 showed lower predicted brain ages than their actual ages, with a mean MAE of 13.36 years (95% confidence interval: 12.51–14.28). Conclusions: These results suggest that brain age prediction using the proposed method may provide important insights into neurodegenerative diseases. Full article

Background: Pulmonary embolism (PE) increases right ventricular (RV) afterload, potentially leading to myocardial stress and electrocardiographic abnormalities. Although QTc prolongation has been suggested as a marker of RV dysfunction, its prevalence, clinical significance, and prognostic value in acute PE remain poorly defined. Objective: The objective of this study is to evaluate the prevalence and clinical implications of QTc prolongation in patients with intermediate–high and high-risk acute PE. Methods: We retrospectively analyzed 95 consecutive patients admitted with intermediate–high or high-risk PE between September 2021 and December 2023. QTc prolongation was defined as ≥470 ms in males and ≥480 ms in females. Clinical, imaging, and laboratory data were compared between patients with normal and prolonged QTc intervals. QTc was assessed at admission, after treatment, and prior to discharge. Results: QTc prolongation was observed in 28.4% of patients at presentation. This group had significantly higher lactate levels (2.3 vs. 1.8 mmol/L, p = 0.03) and a non-significant trend toward elevated troponin and lower oxygen saturation. No differences were observed in echocardiographic or CT-based RV dysfunction parameters. QTc values normalized by discharge irrespective of treatment modality. There was no association between QTc prolongation and in-hospital or long-term mortality. A trend toward more aspiration thrombectomy was noted in the prolonged QTc group (29.6% vs. 11.8%, p = 0.06). Conclusions: QTc prolongation is common in acute intermediate–high and high-risk PE and may reflect transient myocardial stress. While not predictive of clinical outcomes, it should be considered in the differential diagnosis of QTc prolongation in patients presenting with dyspnea and chest pain. Full article

Background: Early identification of sepsis is critical for improving outcomes, particularly in low-resource emergency settings. In Thai community hospitals, where physicians may not always be available, triage is often nurse-led. Selecting accurate and practical sepsis screening tools is essential not only for timely clinical decision-making but also for timely diagnosis and promoting appropriate antibiotic use. Methods: This cross-sectional study analyzed 475 adult patients with suspected sepsis who presented to the emergency department of a Thai community hospital, using retrospective data from January 2021 to December 2022. Six screening tools were evaluated: Systemic Inflammatory Response Syndrome (SIRS), Quick Sequential Organ Failure Assessment (qSOFA), Modified Early Warning Score (MEWS), National Early Warning Score (NEWS), National Early Warning Score version 2 (NEWS2), and Search Out Severity (SOS). Diagnostic accuracy was assessed using International Classification of Diseases, Tenth Revision (ICD-10) codes as the reference standard. Performance metrics included sensitivity, specificity, predictive values, likelihood ratios, and the area under the receiver operating characteristic (AUROC) curve, all reported with 95% confidence intervals. Results: SIRS had the highest sensitivity (84%), while qSOFA demonstrated the highest specificity (91%). NEWS2, NEWS, and MEWS showed moderate and balanced diagnostic accuracy. SOS also demonstrated moderate accuracy. Conclusions: A two-step screening approach—using SIRS for initial triage followed by NEWS2 for confirmation—is recommended. This strategy enhances nurse-led screening and optimizes limited resources in emergency care. Early sepsis detection through accurate screening tools constitutes a feasible public health intervention to support appropriate antibiotic use and mitigate antimicrobial resistance, especially in resource-limited community hospital settings. Full article

Urban traffic congestion poses persistent challenges to mobility, public safety, and governance efficiency in metropolitan areas. This study proposes an intelligent traffic flow forecasting framework based on an extended Long Short-Term Memory (xLSTM) model, specifically designed for real-time congestion prediction and proactive police dispatch support. Utilizing a real-world dataset collected from over 300 vehicle detector (VD) sensors, the proposed model integrates vehicle volume, speed, and lane occupancy data at five-minute intervals. Methodologically, the xLSTM model incorporates matrix-based memory cells and exponential gating mechanisms to enhance spatio-temporal learning capabilities. Model performance is evaluated using multiple metrics, including congestion classification accuracy, F1-score, MAE, RMSE, and inference latency. The xLSTM model achieves a congestion prediction accuracy of 87.3%, an F1-score of 0.882, and an average inference latency of 41.2 milliseconds—outperforming baseline LSTM, GRU, and Transformer-based models in both accuracy and speed. These results validate the system’s suitability for real-time deployment in police control centers, where timely prediction of traffic congestion enables anticipatory patrol allocation and dynamic signal adjustment. By bridging AI-driven forecasting with public safety operations, this research contributes a validated and scalable approach to intelligent transportation governance, enhancing the responsiveness of urban mobility systems and advancing smart city initiatives. Full article

Background/Objectives: Peri-implant mucosa plays a key role in both peri-implant health and aesthetics. Differences in contour and color between implants and natural teeth can negatively affect patient satisfaction, while soft tissue deficiency may lead to complications such as peri-implantitis. Peri-implant plastic surgery aims to improve these conditions. The objective of this study is to describe the trouser-shaped connective tissue graft technique designed to enhance vestibular and interproximal peri-implant tissue volume in a single surgical procedure, and to assess its effectiveness and morbidity. Methods: Ten patients requiring soft tissue augmentation in edentulous areas prior to delayed implant placement were selected. Intraoral scanning was performed before and 6 months after treatment to evaluate tissue thickness gain. Results: Significant soft tissue volume gain was observed at both the coronal (mean: 2.74 mm with a 95% confidence interval of 2.21–3.26 mm) and vestibular (mean: 2.79 mm with a 95% confidence interval of 2.24–3.35 mm) levels in all analyzed positions (p < 0.001). The procedure exhibited low morbidity, with minimal complications and discomfort reported by the patients. Conclusions: The trouser-shaped connective tissue graft technique is effective in increasing peri-implant soft tissue. It allows for vestibular and interproximal tissue augmentation in a single procedure, minimizing tissue contraction and morbidity. This technique could be a predictable and minimally invasive alternative for managing volume deficiencies in peri-implant tissues, particularly in aesthetic areas. Full article

Background/Objectives: The aim of this study was to assess the role of histological activity in individual segments of the colon in predicting disease relapse in patients with ulcerative colitis. Methods: This was a prospective observational study on patients with ulcerative colitis in clinical remission. Biopsies were taken of multiple segments of the colon, and histological activity was assessed using the Geboes (GB) score. Patients were monitored for disease relapse for 12 months. The primary objective was to determine the predictive value of histological activity of the individual segments of the colon on disease relapse. The secondary objective was to assess whether having multiple segments in histological remission is associated with disease relapse. Results: Of 253 patients, 19% had disease relapse. Histological activity (GB ≥ 3.1) was not predictive of disease relapse for the rectum (adjusted odds ratio [aOR] 0.95, confidence interval [CI] 0.46–1.98, p = 0.894), sigmoid (aOR 0.67, CI 0.24–1.90, p = 0.451), descending colon (aOR 1.52, CI 0.43–5.39, p = 0.519), transverse colon (aOR 0.47, CI 0.10–2.18, p = 0.332), and right colon (aOR 1.75 CI 0.73–4.18, p = 0.209). Histological remission (GB ≤ 2.0) was also not predictive of remaining in remission for any individual colonic segment nor was there any benefit of having multiple segments with histological remission compared to having ≤1 segment in histological remission (aOR 0.56, CI 0.28–1.10, p = 0.093). Conclusions: Histological activity in any individual colonic segment or the number of colonic segments with histological remission was not predictive of disease relapse. Full article

Safe and efficient operation of port cranes is vital for maintaining the efficiency of global maritime logistics. However, traditional non-destructive testing methods face significant limitations in harsh port environments, such as periodic inspection intervals, restricted access to structural components, and a lack of real-time monitoring. This review explores the emerging paradigm of remote non-destructive testing through the integration of vibration and acoustic emission sensors with Internet of Things platforms. By enabling continuous, real-time monitoring, these sensor systems can detect early indicators of mechanical degradation, structural fatigue, and corrosion. This study synthesizes findings from over 100 peer-reviewed sources and identifies a significant gap in the application of these technologies to port cranes. Although vibration and acoustic emission sensors have been widely studied in various fields, their application to port cranes remains underexplored, presenting a novel and promising avenue for future research and practical applications. The unique operational demands and structural complexities of port cranes, coupled with their critical role in global trade logistics, make them ideal for leveraging these sensors in tandem with Internet of Things solutions. This integration not only overcomes the limitations of traditional non-destructive testing methods, but also offers substantial benefits, including enhanced safety, reduced inspection costs, and improved operational efficiency. This review concludes by proposing future research directions to enhance sensor performance, data analytics, and Internet of Things integration, paving the way for predictive maintenance strategies that increase operational uptime and improve safety in port crane operations. Full article

The combination of Chinsurah Boro II (BT)-type cytoplasmic male sterility (CMS) and Rf1, the main fertility restorer gene (Rf) for CMS-BT, has been extensively utilized for the production of three-line commercial japonica hybrid seeds. The identification of new Rf genes holds significance for the breeding of BT-type restorer lines, aiming to enhance the heterosis level of BT-type japonica hybrids. In the present study, ‘02428’, a wide-compatibility japonica variety, was observed to partially restore fertility to BT-type CMS lines. Genetic analysis revealed that ‘02428’ carries a dominant Rf gene, Rf21(t), responsible for the fertility restoration of BT-type CMS lines. Leveraging bulked segregant analysis (BSA) resequencing technology and molecular markers, the Rf21(t) locus was identified, and mapped within a candidate interval of 6–12.5 Mb on chromosome 2. Using the iso-cytoplasmic restorer populations, Rf21(t) was ultimately mapped to an interval of approximately 77 kb, encompassing 12 predicted genes, including LOC_Os02g17360, encoding a PPR-domain-containing protein and LOC_Os02g17380 (Rf2), a cloned Rf for Lead-rice-type CMS. A comparative sequence analysis, gene expression profiling and gene knockout experiments confirmed that LOC_Os02g17360 and LOC_Os02g17380 are the most likely candidates of Rf21(t). Furthermore, Rf21(t) showed the dosage effect on the fertility restoration of BT-type CMS lines. This newly identified Rf21(t) represents a valuable genetic resource for the breeding of BT-type japonica restorer lines. Our findings offer practical insights for breeders interested in advancing BT-type japonica hybrid development. Full article

Colorectal cancer (CRC) is one of the most prevalent and deadly neoplasms globally; this fact puts emphasis on the need for accurate molecular biomarkers for early detection and accurate prognosis. Circular RNAs (circRNAs) have recently emerged as very promising cancer biomarkers. In this study, we thoroughly examined whether the expression levels of circular transcripts of the protein arginine methyltransferase 1 (PRMT1) gene can predict the prognosis of patients diagnosed with colorectal adenocarcinoma, the most frequent type of CRC. Hence, a highly sensitive quantitative PCR (qPCR) assay was developed and applied to quantify circ-PRMT1 expression in cDNAs from 210 primary colorectal adenocarcinoma tissue specimens and 86 paired normal colorectal mucosae. Extensive biostatistical analysis was then performed to assess the potential prognostic power of circ-PRMT1. Significant overexpression of this molecule was observed in colorectal adenocarcinoma tissue samples in contrast to their non-cancerous counterparts. Moreover, higher circ-PRMT1 expression was correlated with poorer disease-free survival (DFS) and worse overall survival (OS) in colorectal adenocarcinoma patients. Interestingly, multivariate Cox regression analysis revealed that the prognostic value of the expression of this circRNA does not depend on other established prognostic factors included in the prognostic model. Furthermore, the stratification of patients based on TNM staging revealed that higher circ-PRMT1 levels were significantly related to shorter DFS and OS intervals, particularly in patients with colorectal adenocarcinoma of TNM stage II or III. In summary, this original research study provides evidence that circ-PRMT1 overexpression represents a promising molecular biomarker of poor prognosis in colorectal adenocarcinoma, not depending on other established prognostic factors such as TNM staging. Full article

Since farmers in the inland valley region of the Niger Delta mostly rely on experience rather than empirical evidence when it comes to irrigation, flood irrigation being the most popular technique, the region’s agricultural sector needs more efficient water management. In order to better understand the intricate hydrodynamics of water flow through the soil subsurface, this study aimed to develop a soil column laboratory experimental setup for soil water infiltration. The objective was to measure the soil water content and soil matric potential at 10 cm intervals to study the soil water characteristic curve as a relationship between the two hydraulic parameters, mimicking drip soil subsurface micro-irrigation. A specially designed cylindrical vertical soil column rig was built, and an EQ3 equitensiometer of Delta-T Devices was used in the laboratory as a precision sensor to measure the soil matric potential Ψ (kPa), and the volumetric soil water content θ (%) was measured using a WET150 sensor of Delta-T Devices. The relationship between the volumetric soil water content and the soil matric potential resulted in the generation of the soil water characteristic curve. Two separate monoliths of undisturbed soil samples from Ivrogbo and Oleh in the Nigerian inland valley of the Niger Delta, as well as a uniformly packed sample of soil from Aberdeen, UK, for comparison, were used in gravity-driven flow experiments. In each case, tests were performed once on the monoliths of undisturbed soil samples. In contrast, the packed sample was subjected to an experiment before being further agitated to simulate ploughing and then subjected to an infiltration experiment, resulting in a total of four samples. The Van Genuchten model of the soil water characteristic curve was used for the verification of the experimental results. Comparing the four samples’ volumetric soil water contents and soil matric potentials at various depths revealed a significant variation in their behaviour. However, compared to the predicted curve, the range of values was narrower. Compared to n = 2 in the Van Genuchten curve, the value of n at 200 mm depth was found to be 15, with θr of 0.046 and θs of 0.23 for the packed soil sample, resulting in a percentage difference of 86.7%. Additionally, n = 10 for the ploughed sample resulted in an 80% difference, yet θr = 0.03 and θs = 0.23. For the Ivrogbo sample and the Oleh sample, the range of the matric potential was relatively too small for the comparison. The pre-experiment moisture content of the soil samples was part of the cause of this, in addition to differences in the soil types. Furthermore, the data revealed a remarkable agreement between the measured behaviour and the projected technique of the soil water characteristic curve. Full article

The determination of the live body weight of camels (required for their successful breeding) is a rather difficult task due to the problems with handling and restraining these animals. Therefore, the main aim of this study was to predict the ABW of eight indigenous camel (Camelus dromedarius) breeds of Pakistan (Bravhi, Kachi, Kharani, Kohi, Lassi, Makrani, Pishin, and Rodbari). Selected productive (hair production, milk yield per lactation, and lactation length) and reproductive (age of puberty, age at first breeding, gestation period, dry period, and calving interval) traits served as the predictors. Six data mining methods [classification and regression trees (CARTs), chi-square automatic interaction detector (CHAID), exhaustive CHAID (EXCHAID), multivariate adaptive regression splines (MARSs), MLP, and RBF] were applied for ABW prediction. Additionally, hierarchical cluster analysis with Euclidean distance was performed for the phenotypic characterization of the camel breeds. The highest Pearson correlation coefficient between the observed and predicted values (0.84, p < 0.05) was obtained for MLP, which was also characterized by the lowest root-mean-square error (RMSE) (20.86 kg), standard deviation ratio (SD_ratio) (0.54), mean absolute percentage error (MAPE) (2.44%), and mean absolute deviation (MAD) (16.45 kg). The most influential predictor for all the models was the camel breed. The applied methods allowed for the moderately accurate prediction of ABW (average R² equal to 65.0%) and the identification of the most important productive and reproductive traits affecting its value. However, one important limitation of the present study is its relatively small dataset, especially for training the ANN (MLP and RBF). Hence, the obtained preliminary results should be validated on larger datasets in the future. Full article

Background/Objectives: Transcatheter aortic valve replacement (TAVR) has been introduced as an optimal treatment for patients with severe aortic stenosis, offering a minimally invasive alternative to surgical aortic valve replacement. Predicting these outcomes following TAVR is crucial. Artificial intelligence (AI) has emerged as a promising tool for improving post-TAVR outcome prediction. In this systematic review and meta-analysis, we aim to summarize the current evidence on utilizing AI in predicting post-TAVR outcomes. Methods: A comprehensive search was conducted to evaluate the studies focused on TAVR that applied AI methods for risk stratification. We assessed various ML algorithms, including random forests, neural networks, extreme gradient boosting, and support vector machines. Model performance metrics—recall, area under the curve (AUC), and accuracy—were collected with 95% confidence intervals (CIs). A random-effects meta-analysis was conducted to pool effect estimates. Results: We included 43 studies evaluating 366,269 patients (mean age 80 ± 8.25; 52.9% men) following TAVR. Meta-analyses for AI model performances demonstrated the following results: all-cause mortality (AUC = 0.78 (0.74–0.82), accuracy = 0.81 (0.69–0.89), and recall = 0.90 (0.70–0.97); permanent pacemaker implantation or new left bundle branch block (AUC = 0.75 (0.68–0.82), accuracy = 0.73 (0.59–0.84), and recall = 0.87 (0.50–0.98)); valve-related dysfunction (AUC = 0.73 (0.62–0.84), accuracy = 0.79 (0.57–0.91), and recall = 0.54 (0.26–0.80)); and major adverse cardiovascular events (AUC = 0.79 (0.67–0.92)). Subgroup analyses based on the model development approaches indicated that models incorporating baseline clinical data, imaging, and biomarker information enhanced predictive performance. Conclusions: AI-based risk prediction for TAVR complications has demonstrated promising performance. However, it is necessary to evaluate the efficiency of the aforementioned models in external validation datasets. Full article