Learning Model Research Articles

Machine-Learning Methods Estimating Flights’ Hidden Parameters for the Prediction of KPIs

Complex microscopic simulation models of strategic Air Traffic Management (ATM) performance assessment and decision-making are hindered by several factors. One of the most important is the existence of hidden parameters—such as aircraft take-off weight (TOW) and the selected cost index (CI)—which, if known, would allow for more effective performance modeling methodologies for assessing Key Performance Indicators (KPIs) at various levels of abstraction/detail, e.g., system-wide, or at the level of individual flights. This research proposes a data-driven methodology for the estimation of flights’ hidden parameters combining mechanistic and advanced Artificial Intelligence/Machine Learning (AI/ML) models. Aiming at microsimulation models, our goal is to study the effect of these estimations on the prediction of flights’ KPIs. In so doing, we propose a novel methodology according to which data-driven methods are trained given optimal trajectories (produced by mechanistic models) corresponding to known hidden parameter values, with the aim of predicting hidden parameters’ values of unseen trajectories. The results show that estimations of hidden parameters support the accurate prediction of KPIs regarding the efficiency of flights: fuel consumption, gate-to-gate time and distance flown.

Abstract 4138376: A Machine Learning Approach to Predict Percutaneous Coronary Intervention in Patients with Critical Illness and Signs of Myocardial Injury

Background: Critically ill patients frequently experience multi-organ dysfunction and unstable vital signs, increasing their risk of myocardial injury and elevated serum troponin levels. Myocardial injury from oxygen supply-demand mismatch, whether due to systemic disease or obstructive coronary artery disease (CAD), often leads to patients undergoing an invasive coronary angiogram (ICA) and potentially percutaneous coronary intervention (PCI) if obstructive CAD is identified. However, this procedure carries significant risks for critically ill patients. To address this challenge, we aimed to develop a machine learning (ML) model to predict the need for PCI in critically ill patients with myocardial injury. Methods: The study cohort included critically ill patients with elevated serum troponin levels who underwent ICA during their hospitalization at a single institution from 2012 to 2022. We defined critical illness as a life-threatening condition requiring intensive support for vital sign instability. Patients with atherothrombosis identified during ICA were excluded from the study, focusing only on patients with type 2 MI. We utilized Matplotlib to analyze patient data, including demographics, lab results, vital signs, and comorbidities. We then used XGBoost, a supervised ML algorithm, for binary classification tasks. An ensemble of decision trees was employed, with gradient boosting to correct errors from previous trees. XGBoost iteratively adjusted predictions, creating a model to predict which patients required PCI. Results: Out of 765 patients, 173 (22.6%) underwent PCI. The cohort had a mean age of 60.5 ± 13.5 years, with 41.7% being female. The ML model accurately identified non-PCI candidates at 75% and PCI candidates at 64%, achieving an overall accuracy of 73%. The three most important features identified by the model were a history of diabetes, diastolic heart failure, and whether the patient received a blood transfusion during hospitalization. Conclusion: A ML approach using XGBoost demonstrated moderate accuracy in predicting the need for PCI in critically ill patients with signs of myocardial injury. This prediction holds clinical significance due to the heightened risks associated with ICA in these patients. Given that PCI occurred in only 22.6% of the cohort, future models should include a higher proportion of patients who underwent PCI to improve the robustness and true positive accuracy of the model.

A Systematic Review on Drug-to-Drug Interaction Prediction and Cryptographic Mechanism for Secure Drug Discovery Using AI Techniques

Recently, poly-pharmacy persistence has greatly improved in treating multiple diseases effectively. However, determining potential drug–drug interaction (DDIs) during the drug design is critical for controlling the target clinical drug during secure testing. In the medical field, DDIs are significant for disease diagnosis and treatment, mainly aiding researchers in predicting the link between biomolecules for efficient drug discovery (DD). Artificial intelligence (AI) has recently witnessed researchers accurately predict DDIs at minimum time consumption. Although the AI models show accurate results by aiding physicians to determine poly-pharmacy, several unresolvable issues remain in promoting reliability due to high error, complexity and cost-effectiveness. This paper aims to provide a comprehensive review using AI techniques (machine learning (ML)–deep learning (DL) models) and security enhancement techniques to improve DDI prediction and DD, respectively. The recent state of DDI prediction and the security concerns are presented initially, along with a short discussion about the need for effective techniques. Then, the critical evaluation related to existing studies is analyzed and compared to current issues faced in those existing studies. Various pharmaceutical drugs and their pros are also surveyed in addition to the security analysis for the newly invented drugs. Several assessment measures for the surveyed techniques are also conquered and put forth the need for advancements in future techniques effectively. The performance variations produced by the existing studies are also surveyed, and their use in the medical industry is also provided in this review study. The review of this research encourages the researchers to analyze the various issues faced in the pharmaceutical industry so that a novel technique can be introduced in the upcoming studies.

A deep learning based method for left ventricular strain measurements: repeatability and accuracy compared to experienced echocardiographers

Abstract Background Speckle tracking echocardiography (STE) provides quantification of left ventricular (LV) deformation and is useful in the assessment of LV function. STE is increasingly being used clinically, and every effort to simplify and standardize STE is important. Manual outlining of regions of interest (ROIs) is labor intensive and may influence assessment of strain values. Purpose We hypothesized that a deep learning (DL) model, trained on clinical echocardiographic exams, can be combined with a readily available echocardiographic analysis software, to automate strain calculation with comparable fidelity to trained cardiologists. Methods Data consisted of still frame echocardiographic images with cardiologist-defined ROIs from 672 clinical echocardiographic exams from a university hospital outpatient clinic. Exams included patients with ischemic heart disease, heart failure, valvular disease, and conduction abnormalities, and some healthy subjects. An EfficientNetB1-based architecture was employed, and different techniques and properties including data set size, data quality, augmentations, and transfer learning were evaluated. DL predicted ROIs were reintroduced into commercially available echocardiographic analysis software to automatically calculate strain values. Results DL-automated strain calculations had an average absolute difference of 0.75 (95% CI 0.58–0.92) for global longitudinal strain (GLS), and 1.16 (95% CI 1.03–1.29) for single-projection longitudinal strain (LS), compared to operators. A Bland–Altman plot revealed no obvious bias, though there were fewer outliers in the lower average LS ranges. Techniques and data properties yielded no significant increase/decrease in performance. Conclusion The study demonstrates that DL-assisted, automated strain measurements are feasible, and provide results within interobserver variation. Employing DL in echocardiographic analyses could further facilitate adoption of STE parameters in clinical practice and research, and improve reproducibility.

A New Method of Intelligent Fault Diagnosis of Ship Dual-Fuel Engine Based on Instantaneous Rotational Speed

Ship engine misfire faults not only pose a serious threat to the safe operation of ships but may also cause major safety accidents or even lead to ship paralysis, which brings huge economic losses. Most traditional fault diagnosis methods rely on manual experience, with limited feature extraction capability, low diagnostic accuracy, and poor adaptability, which make it difficult to meet the demand for high-precision diagnosis. To this end, a fusion intelligent diagnostic model—ResNet–BiLSTM—is proposed based on a residual neural network (ResNet) and a bidirectional long short-term memory network (BiLSTM). Firstly, a multi-scale decomposition of the instantaneous rotational speed signal of a ship’s engine is carried out by using the continuous wavelet transform (CWT), and features containing misfire fault information are extracted. Subsequently, the extracted features are fed into the ResNet–BiLSTM model for learning. Finally, the intelligent diagnosis of ship dual-fuel engine misfire faults is realized by the classifier. The model combines the advantages of ResNet18 in image feature extraction and the capability of BiLSTM in temporal information processing, which can efficiently capture the time-frequency features and dynamic changes in the fault signal. Through comparison experiments with fusion models AlexNet–BiLSTM, VGG–BiLSTM, and the existing AlexNet–LSTM and VGG–LSTM models, the results show that the ResNet–BiLSTM model outperforms the other models in terms of diagnostic accuracy, robustness, and generalization ability. This model provides an effective new method for intelligent diagnosis of ship dual-fuel engine misfire faults to solve the traditional diagnostic methods’ limitations.

Hybrid Machine Learning Approaches for 5G Traffic Prediction

ABSTRACT Accurate traffic prediction poses great difficulties because of the continuously increasing scale and diversity of 5G network traffic, which is driven by user demands. Moreover, certain characteristics of 5G traffic are constantly changing; thus, simulations using traditional models often lead to incorrect estimations or inefficient utilization of available resources. Consequently, we propose a hybrid machine learning model that integrates support vector machine (SVM) and decision tree algorithms to enhance efficiency of 5G traffic prediction. The structure of the hybrid model dynamically adjusts by adding or removing hidden layers and units within the network to improve prediction performance. The efficacy of the proposed model is evaluated using metrics like mean squared error, mean absolute error, and root mean squared error (RMSE). Findings show that the hybrid model consistently achieves lower error rates than SVM alone. Further performance enhancement of the hybrid model in predicting 5G traffic is also supported by comparisons of R-squared values against signal-to-noise ratios. These outcomes show the potential of the proposed method to improve traffic prediction accuracy in 5G networks, serving as a powerful tool for network control.

Abstract 4138386: Deep Learning-Enabled Assessment of Right Ventricular Function Using 2D Echocardiograms Improves 1-Year Mortality Prediction in Patients with Severe Mitral Regurgitation Undergoing Transcatheter Edge-to-Edge Repair

Background: Right ventricular (RV) function has a well-established prognostic role in patients with severe mitral regurgitation (MR) undergoing transcatheter edge-to-edge repair (TEER) and is typically assessed using echocardiography-measured tricuspid annular plane systolic excursion (TAPSE). Recently, a deep learning model has been proposed that accurately predicts RV ejection fraction (RVEF) from 2D echocardiographic videos, with similar diagnostic accuracy as 3D imaging. Aims: This study aimed to evaluate the prognostic utility of the deep learning-predicted RVEF values in patients with severe MR undergoing TEER. Methods: This multicenter registry study analyzed the associations between the predicted RVEF values and 1-year mortality in patients with severe MR undergoing TEER. To predict RVEF, 2D apical four-chamber view videos from preprocedural transthoracic echocardiographic studies were exported and processed by a rigorously validated deep learning model. Results: From 1,366 patients undergoing TEER between 2017 and 2023, good-quality 2D apical four-chamber view videos could be retrieved for 1,154 patients (84.5%). Survival at one year after TEER was 84.7%. The predicted RVEF values ranged from 26.6% to 64.0% and correlated only modestly with TAPSE (Pearson correlation coefficient R: 0.33; p -value: <0.001). Importantly, predicted RVEF levels were superior to TAPSE levels in predicting 1-year mortality after TEER (area under the curve: 0.687 vs. 0.625; p -value: 0.029). Furthermore, Kaplan-Meier survival analysis revealed that patients with preserved RV function (defined as a predicted RVEF of ≥45%) had significantly better 1-year survival rates than patients with reduced RV function (92.1% [95% CI: 89.5-94.7%] vs. 80.3% [95% CI: 77.4-83.3%], respectively, hazard ratio for 1-year mortality: 2.67, p -value: <0.001). Conclusion: Deep learning-enabled assessment of RV function using standard 2D echocardiographic videos can refine the prognostication of patients with severe MR undergoing TEER. Thus, it can be used to screen for patients with RV dysfunction who might benefit from intensified follow-up care.

The Use of Artificial Intelligence to Analyze the Exposome in the Development of Chronic Diseases: A Review of the Current Literature

The “Exposome” is a concept that indicates the set of exposures to which a human is subjected during their lifetime. These factors influence the health state of individuals and can drive the development of Noncommunicable Diseases (NCDs). Artificial Intelligence (AI) allows one to analyze large amounts of data in a short time. As such, several authors have used AI to study the relationship between exposome and chronic diseases. Under such premises, this study reviews the use of AI in analyzing the exposome to understand its role in the development of chronic diseases, focusing on how AI can identify patterns in exposure-related data and support prevention strategies. To achieve this, we carried out a search on multiple databases, including PubMed, ScienceDirect, and SCOPUS, from 1 January 2019 to 31 May 2023, using the MeSH terms (exposome) and (‘Artificial Intelligence’ OR ‘Machine Learning’ OR ‘Deep Learning’) to identify relevant studies on this topic. After completing the identification, screening, and eligibility assessment, a total of 18 studies were included in this literature review. According to the search, most authors used supervised or unsupervised machine learning models to study multiple exposure factors’ role in the risk of developing cardiovascular, metabolic, and chronic respiratory diseases. In some more recent studies, authors also used deep learning. Furthermore, the exposome analysis is useful to study the risk of developing neuropsychiatric disorders or evaluating pregnancy outcomes and child growth. Understanding the role of the exposome is pivotal to overcome the classic concept of a single exposure/disease. The application of AI allows one to analyze multiple environmental risks and their combined effects on health conditions. In the future, AI could be helpful in the prevention of chronic diseases, providing new diagnostic, therapeutic, and follow-up strategies.

Abstract 4124675: Deep Learning Screening of Cardiac MRIs Uncovers Undiagnosed Hypertrophic Cardiomyopathy in the UK BioBank

Introduction: The prevalence of hypertrophic cardiomyopathy (HCM) in the UK Biobank based on ICD-10 codes (.07%) is lower than global estimates of disease prevalence (0.2 - 0.5%). Prior studies using this data have remarked on the limitations of findings given likely underdiagnosis. The availability of cardiac MRI scans on a fraction of the participants offers an opportunity to identify missed diagnoses. Aims: This study seeks to utilize a generalizable deep learning model to detect likely cases of undiagnosed hypertrophic cardiomyopathy from cardiac MRIs in the UK Biobank. Methods: The foundational model was trained on a multi-institutional dataset of 14,073 cardiac MRIs via a self-supervised contrastive learning approach that sought to minimize the divergence between scans and their associated radiology reports. The pre-trained model was fine-tuned to diagnose hypertrophic cardiomyopathy on a distinct cohort of 4,870 MRIs with 368 cases of HCM, achieving an AUC of 0.94. The fine-tuned model was applied to the UK Biobank cardiac MRI dataset to ascertain predicted probabilities of HCM. Cases exceeding a threshold of 95% – correlating to the top 0.5% of cases (expected specificity of 97% and sensitivity of 60%) – were screened in for manual reading. In a blinded fashion, a board-certified radiologist was tasked with diagnosing HCM on a sample of cases composed of high and low predicted probabilities. Results: Of the 43,017 patients with cardiac MRIs, only 9 (.02%) had an ICD diagnosis of HCM. 266 cardiac MRIs were manually reviewed: 216 had greater than 95% predicted probability of HCM; 50 negative controls were randomly selected amongst cases with predicted probability less than 10%. The radiologist concurred with an HCM diagnosis for 115 cases (sensitivity 53%, specificity 98%), 112 of which were previously undiagnosed. The prevalence of hypertension and aortic stenosis did not significantly differ between the cohort of true positives (69.2%) and false positives (76.6%). The corrected prevalence of HCM in the UK BioBank MRI cohort is estimated at 0.28%. Conclusions: The findings of this study illustrate the remarkable ability of a generalizable deep learning model to detect undiagnosed cases of a rare disease process from cardiac MRIs. This is an important milestone that may allow for widespread screening of hypertrophic cardiomyopathy while minimizing demand for radiologist labor, and thereby allow patients to reap the substantial benefits of earlier treatment.

Can the Plantar Pressure and Temperature Data Trend Show the Presence of Diabetes? A Comparative Study of a Variety of Machine Learning Techniques

This study aimed to explore the potential of predicting diabetes by analyzing trends in plantar thermal and plantar pressure data, either individually or in combination, using various machine learning techniques. A total of twenty-six participants, comprising thirteen individuals diagnosed with diabetes and thirteen healthy individuals, walked along a 20 m path. In-shoe plantar pressure data were collected and the plantar temperature was measured both immediately before and after the walk. Each participant completed the trial three times, and the average data between the trials were calculated. The research was divided into three experiments: the first evaluated the correlations between the plantar pressure and temperature data; the second focused on predicting diabetes using each data type independently; and the third combined both data types and assessed the effect of such to enhance the predictive accuracy. For the experiments, 20 regression models and 16 classification algorithms were employed, and the performance was evaluated using a five-fold cross-validation strategy. The outcomes of the initial set of experiments indicated that the machine learning models were significant correlations between the thermal data and pressure estimates. This was consistent with the findings from the prior correlation analysis, which showed weak relationships between these two data modalities. However, a shift in focus towards predicting diabetes by aggregating the temperature and pressure data led to encouraging results, demonstrating the effectiveness of this approach in accurately predicting the presence of diabetes. The analysis revealed that, while several classifiers demonstrated reasonable metrics when using standalone variables, the integration of thermal and pressure data significantly improved the predictive accuracy. Specifically, when only plantar pressure data were used, the Logistic Regression model achieved the highest accuracy at 68.75%. Those predictions based solely on temperature data showed the Naive Bayes model as the lead with an accuracy of 87.5%. Notably, the highest accuracy of 93.75% was observed when both the temperature and pressure data were combined, with the Extra Trees Classifier performing the best. These results suggest that combining temperature and pressure data enhances the model’s predictive accuracy. This can indicate the importance of multimodal data integration and their potentials in diabetes prediction.

The Role Of Machine Learning In Transforming Healthcare: A Systematic Review

This systematic review explores the transformative role of machine learning (ML) in healthcare, focusing on its applications in disease diagnosis, personalized medicine, healthcare operations, and patient monitoring. By analyzing 167 peer-reviewed studies published between 2015 and 2024, the review highlights how ML algorithms have significantly improved early disease detection, treatment personalization, and operational efficiencies in healthcare settings. Findings reveal that ML-powered diagnostic tools, especially deep learning models, demonstrate accuracy levels comparable to human experts in areas like cancer detection. Additionally, ML models tailored for personalized medicine have shown promise in optimizing treatment protocols based on genetic profiles, reducing adverse reactions and improving patient outcomes. In healthcare operations, ML applications have streamlined hospital resource management, enhanced workflow efficiency, and reduced administrative burdens through predictive analytics and natural language processing (NLP). Moreover, ML-driven remote patient monitoring systems have enabled proactive interventions for chronic disease management. Despite these advancements, challenges related to data privacy, algorithmic transparency, and regulatory compliance persist. Addressing these barriers is critical for realizing the full potential of ML in healthcare, ensuring ethical deployment and equitable access. The review concludes by emphasizing the need for robust regulatory frameworks and further research to enhance the integration of ML technologies into clinical practice.

Mortality Prediction Modeling for Patients with Breast Cancer Based on Explainable Machine Learning

Background/Objectives: Breast cancer is the most common cancer in women worldwide, requiring strategic efforts to reduce its mortality. This study aimed to develop a predictive classification model for breast cancer mortality using real-world data, including various clinical features. Methods: A total of 11,286 patients with breast cancer from the National Cancer Center were included in this study. The mortality rate of the total sample was approximately 6.2%. Propensity score matching was used to reduce bias. Several machine learning models, including extreme gradient boosting, were applied to 31 clinical features. To enhance model interpretability, we used the SHapley Additive exPlanations method. ML analyses were also performed on the samples, excluding patients who developed other cancers after breast cancer. Results: Among the ML models, the XGB model exhibited the highest discriminatory power, with an area under the curve of 0.8722 and a specificity of 0.9472. Key predictors of the mortality classification model included occurrence in other organs, age at diagnosis, N stage, T stage, curative radiation treatment, and Ki-67(%). Even after excluding patients who developed other cancers after breast cancer, the XGB model remained the best-performing, with an AUC of 0.8518 and a specificity of 0.9766. Additionally, the top predictors from SHAP were similar to the results for the overall sample. Conclusions: Our models provided excellent predictions of breast cancer mortality using real-world data from South Korea. Explainable artificial intelligence, such as SHAP, validated the clinical applicability and interpretability of these models.

Machine learning model reveals the role of angiogenesis and EMT genes in glioma patient prognosis and immunotherapy

Machine learning model reveals the role of angiogenesis and EMT genes in glioma patient prognosis and immunotherapy

Hierarchical Image Quality Improvement Based on Illumination, Resolution, and Noise Factors for Improving Object Detection

Object detection performance is significantly impacted by image quality factors such as illumination, resolution, and noise. This paper proposes a hierarchical image quality improvement process that dynamically prioritizes these factors based on severity, enhancing detection accuracy in diverse conditions. The process evaluates each factor—illumination, resolution, and noise—using discriminators that analyze brightness, edge strength, and noise levels. Improvements are applied iteratively with an adaptive weight update mechanism that adjusts factor importance based on improvement effectiveness. Following each improvement, a quality assessment is conducted, updating weights to fine-tune subsequent adjustments. This allows the process to learn optimal parameters for varying conditions, enhancing adaptability. The image improved through the proposed process shows improved quality through quality index (PSNR, SSIM) evaluation, and the object detection accuracy is significantly improved when the performance is measured using deep learning models called YOLOv8 and RT-DETR. The detection rate is improved by 7% for the ‘Bottle’ object in a high-light environment, and by 4% and 2.5% for the ‘Bicycle’ and ‘Car’ objects in a low-light environment, respectively. Additionally, segmentation accuracy saw a 9.45% gain, supporting the effectiveness of this method in real-world applications.

Supporting long-term condition management: a workflow framework for the co-development and operationalization of machine learning models using electronic health record data insights

The prevalence of long-term conditions such as cardiovascular disease, chronic obstructive pulmonary disease (COPD), asthma, and diabetes mellitus is rising. These conditions are leading sources of premature mortality, hospital admission, and healthcare expenditure. Machine learning approaches to improve the management of these conditions have been widely explored, with data-driven insights demonstrating the potential to support earlier diagnosis, triage, and treatment selection. The translation of this research into tools used in live clinical practice has however been limited, with many projects lacking clinical involvement and planning beyond the initial model development stage. To support the move toward a more coordinated and collaborative working process from concept to investigative use in a live clinical environment, we present a multistage workflow framework for the co-development and operationalization of machine learning models which use routine clinical data derived from electronic health records. The approach outlined in this framework has been informed by our multidisciplinary team’s experience of co-developing and operationalizing risk prediction models for COPD within NHS Greater Glasgow & Clyde. In this paper, we provide a detailed overview of this framework, alongside a description of the development and operationalization of two of these risk-prediction models as case studies of this approach.

Abstract 4135928: Externally Validated Deep Learning Model for Patent Ductus Arteriosus Detection by Echocardiography in Preterm Infants

Introduction: Patent ductus arteriosus (PDA) is a common form of congenital heart disease in premature infants and a source of significant morbidity. Echocardiography is the mainstay modality for diagnosis and monitoring but is resource-intensive and requires expertise for interpretation. Aims: To develop and externally validate a deep learning model to identify PDA in preterm infants by echocardiography. Methods: We trained, validated, and tested a convolutional neural network to detect PDA in raw echocardiogram clips from infants (gestational age <37 weeks) with and without PDAs and no significant additional congenital heart disease at the Medical University of South Carolina (MUSC). For training and validation, we employed a 12-fold cross-validation procedure. Experienced cardiologists defined the ground truth labels. We assessed classification performance on an internal model naïve dataset using the area under the receiver operator curve (AUROC), sensitivity, specificity, positive predictive value, and negative predictive value. For external multicenter testing, we used studies from Children’s Hospital of Orange County (CHOC) and Boston Children’s Hospital (BCH), both of which utilize a different ultrasound system vendor. Results: Training and validation were completed using 1,145 color/color-compare clips (661 clips with PDA and 484 no PDA) from 66 patients. The internal test dataset consisted of 142 clips from 16 patients. The external CHOC and BCH cohorts consisted of 146 clips from 50 patients and 294 clips from 68 patients, respectively. Model performance was similar for internal and external testing (Table 1). Conclusions: Our deep learning model detected the presence of PDA with acceptable performance. This performance generalized well across multiple institutions and ultrasound vendors. This work shows promise for the future development of an automated tool for PDA diagnosis enabling the democratization of pediatric cardiology resources.

Intelligent water quality prediction system with a hybrid CNN–LSTM model

ABSTRACT Water pollution remains a longstanding challenge globally, prompting substantial investment in water quality protection. The integration of advanced machine learning models offers promising avenues for accurate water quality prediction, enabling proactive measures to safeguard water sources. Presently, water quality assessment relies predominantly on physical and chemical metrics. This study developed MultiLayer Perceptron (MLP), eXtreme Gradient Boosting (XGBoost), long short-term memory (LSTM), and a hybrid CNN–LSTM model to forecast pH and dissolved oxygen (DO) levels. Results demonstrated the hybrid model's superior performance, with mean squared errors (MSEs) of 0.0015 and 0.0361 for pH and DO prediction, respectively. For Water Quality Classification (WQC), Random Forest (RF), k-Nearest Neighbors (kNNs), Support Vector Machine (SVM), and Light gradient Boosting Machine (Light GBM) were employed, with SVM achieving the highest accuracy at 88.75%. The research underscores the effectiveness of the CNN–LSTM model in predicting pH and DO levels. Leveraging these predictions as inputs to the SVM model offers valuable insights, particularly in regions where conventional monitoring methods face limitations. This streamlined approach, requiring only two parameters, signifies a significant advancement in accurate water quality prediction.

Abstract 4145884: Left ventricular 3D-sphericity is associated with 92 genetic loci

Introduction: Left ventricular (LV) sphericity is a measure of the degree to which the LV blood pool resembles a sphere. Analyses of cardiovascular magnetic resonance imaging (MRI) in the MESA cohort have shown that LV sphericity is an important mode of variation in cardiac structure that is associated with ischemia, heart failure, and atrial fibrillation. A recent genome-wide association study (GWAS) of a two-dimensional estimate of sphericity in 38,000 UK Biobank participants identified 4 genetic loci (near PDZRN3, HLA, PLN, and ANGPT1). Genetic contributions to three-dimensional (3D) sphericity remain unknown. Aims: To measure 3D sphericity from cardiovascular MRI at scale and characterize the genetic contributions to 3D sphericity. Methods: Deep learning models were constructed to perform semantic segmentation in the short- and long-axis view from cardiovascular MRI in UK Biobank. These models were applied to all participants with MRI. Poisson surface reconstruction was used to build 3D meshes of the left ventricle. Sphericity was estimated at end-systole and end-diastole as the area of a perfect sphere with the same volume as the left ventricle, divided by the estimated surface area from the mesh. Heritability was estimated with ldsc; GWAS was conducted with REGENIE. Results: Sphericity was estimated in 68,978 individuals, of whom 3,096 were excluded due to atrial fibrillation or atrial dysfunction, and 2,686 were excluded during genetic quality control; 63,196 participants were included in the GWAS. Ldsc heritability was 29.7% for sphericity in diastole and 26.0% for sphericity in systole. 49 genetic loci were associated with 3D sphericity in diastole as were 64 in systole (92 distinct loci). 46 of these loci were unique to sphericity and not found for other LV traits, including loci near the genes encoding calsequestrin 2, troponin T2, palladin, supervillin, and angiopoietins 1 and 2. Shared loci included those near RXFP4, encoding a relaxin-family peptide receptor, and MICU2 (previously implicated in cardiac relaxation). Conclusion: Left ventricular sphericity is heritable, with genetic underpinnings distinct from standard LV measurements.

An Improved Transformer Model for Sap Flow Prediction that Efficiently Utilizes Environmental Information

AbstractAs an important reference for assessing plant water consumption and estimating plant transpiration, it is of great significance to achieve accurate prediction of plant sap flow. A number of deep learning models were established and compared using approximately 3 years of continuous eucalyptus flow time series data collected from the SAPFLUXNET open dataset and 6 environmental factors, including shortwave solar incident radiation, air temperature, air relative humidity, net radiation, vapor pressure deficit, and photosynthetic photon flux density. The experimental results show that the improved Transformer model, with the introduction of a two-step self-attention mechanism and simplified design, maintains significant predictive performance advantages compared to the original Transformer model, long short-term memory, gated recurrent unit, and temporal convolutional neural network models. In the shorter 1-h forecast, the mean squared error and coefficient of determination (R2) of the improved Transformer model are 0.0191 and 0.965, respectively. Compared to the suboptimal typical Transformer model, the MSE is reduced by 22.9%, and R2 is increased by 1.0%. Additionally, the improved model maintains stable predictive performance advantages in long-term plant flow prediction. In the longest 8-h advance prediction, the MSE is reduced by 14.9% compared to the suboptimal Transformer model, and R2 increases by 3.0% compared to the Transformer model. The comprehensive experimental results show that the improved Transformer model makes more effective use of environmental information to achieve more accurate and long-term plant flow prediction. This study emphasizes the basic principle and validity of the two-step self-attention network structure and provides a valuable basis for developing more effective methods for predicting plant sap flow.

Abstract 4122612: Validation of a Machine Learning Model for Fetal Echocardiographic Prediction of Critical Coarctation of the Aorta

Background: Current fetal echocardiographic (F-echo) metrics have inadequate specificity for confident prediction of neonatal critical coarctation of the aorta (CoA). Using single-center data, our machine learning model for the prediction of fetal CoA demonstrated improved accuracy compared to published F-echo metrics for critical CoA assessment. External validation of this model is needed. Aim: Validate a machine learning F-echo predictive model for CoA with an external patient cohort. Methods: Initial model training and testing were performed using retrospective single center data on 9 F-echo measurements for patients with prenatal concern for CoA. A random forest classifier with 80:20 split and 5-fold cross-validation predicted CoA intervention within 30 days of life. A SHapley Additive exPlanations (SHAP) analysis assessed the marginal contribution of each feature. The model was retrained using the 5 most influential F-echo features. External validation for this model was then performed using patients with prenatal concern for CoA retrospectively collected at a partner institution. Results: Inclusion criteria were met by 132 patients in the initial cohort and 64 patients in the external validation cohort, of whom 44% (n=58) and 25% (n=16) respectively had CoA requiring intervention. SHAP analysis for both cohorts demonstrated transverse to descending aorta angle as the most influential feature, followed by ascending to descending aorta angle (Figure 1A). Using internal cross-validation on the initial cohort, the area under the receiver operating characteristic curve (AUC) was 0.93 ± 0.05 (sensitivity 0.97, specificity 1.0) with an F1 score of 0.97 ± 0.03. Validation of the model with the external cohort produced an AUC of 0.87 (sensitivity 0.81, specificity 1.0) and an F1 of 0.90 (Figure 1B). Conclusions: A random forest classifier using F-echo features predicted neonatal critical CoA with higher accuracy than previously published metrics. The model maintained high accuracy when validated with an external patient cohort. Arch angles most significantly impacted the model’s accuracy. Future directions include prospective validation and converting the model to a distributable clinical calculator.