Receiver Operating Characteristic Area Research Articles

Abstract Su804: Use of Machine Learning Models to Predict Neurologically Intact Survival for Advanced Age Adults Following Out-of-hospital Cardiac Arrest

Background: We recently published a multivariable logistic regression model that successfully predicted neurologic outcomes in advanced age adults (≥ 65 years old) who achieve return of spontaneous circulation following out-of-hospital cardiac arrest (OHCA). Prior to externally validating this model, we sought to compare the predictive performance of our logistic regression model against common machine learning (ML) algorithms using the same dataset. Methods: We performed a retrospective observational analysis of the Cardiac Arrest Registry to Enhance Survival database from 2013-2021. All non-traumatic OHCA occurring in adults (≥65 years) who survived to hospital admission were included. The primary outcome measure was neurologically intact survival defined as a cerebral performance category (CPC) score of 1 or 2 at hospital discharge. Our original logistic regression model was compared to Boosted Trees and Decision Tree ML algorithms and assessed using accuracy, Area Under the Receiver Operating Characteristic Curve (AUC-ROC) and Area Under the Precision-Recall Curve (AUC-PR). The model variables included age, gender, race/ethnicity, location, witnessed status, who initiated cardiopulmonary resuscitation, whether an automated external defibrillator was applied prior to emergency medical services arrival, and first monitored rhythm. Results: A total of 83,561 OHCA were included. Median age was 75 years (IQR 69-82), 58.9% were male, 53% were White, 67% experienced an OHCA at home, 52% were witnessed by a bystander, 44% received bystander CPR, and 34% were found in shockable rhythm. Neurologically intact survival (CPC 1 or 2) occurred in 23% of patients. The logistic regression model had an accuracy of 79.6%, AUC-PR 0.542, and AUC-ROC of 0.774. The Boosted Trees model had an accuracy of 79.2%, AUC-PR 0.555, and AUC-ROC of 0.774. The Decision Tree Model had an accuracy of 79.3%, AUC-PR 0.490, and AUC-ROC of 0.717. Conclusion: Boosted Trees and Decision Tree ML models performed comparably to the logistic regression model in predicting favorable versus unfavorable neurological outcomes following successful resuscitation from OHCA in advanced-age adults. Given their similar performance, logistic regression may be preferred for its simplicity and interpretability over alternative ML models. Future efforts to improve and ultimately externally validate the model are warranted.

Federated learning with tensor networks: a quantum AI framework for healthcare

Abstract The healthcare industries frequently handle sensitive and proprietary data, and due to strict
privacy regulations, they are often reluctant to share data directly. In today’s context, Federated
Learning (FL) stands out as a crucial remedy, facilitating the rapid advancement of distributed machine
learning while effectively managing critical concerns regarding data privacy and governance.
The fusion of federated learning and quantum computing represents a groundbreaking interdisciplinary
approach with immense potential to revolutionize various industries, from healthcare to
finance. In this work, we propose a federated learning framework based on quantum tensor networks
that takes advantage of the principles of many-body quantum physics. Currently, there are
no known classical tensor networks implemented in federated settings. Furthermore, we investigated
the effectiveness and feasibility of the proposed framework by conducting a differential privacy analysis
to ensure the security of sensitive data across healthcare institutions. Experiments on popular
medical image datasets show that the federated quantum tensor network model achieved a mean
receiver-operator characteristic area under the curve (ROC-AUC) of 91-98%, outperforming several
state-of-the-art federated learning methods while using fewer parameters. Experimental results
demonstrate that the quantum federated global model, consisting of highly entangled tensor network
structures, showed better generalization and robustness and achieved higher testing accuracy,
surpassing the performance of locally trained clients under unbalanced data distributions among
healthcare institutions.

Predicting full-thickness necrosis in adult acute corrosive ingestion injuries in a sub-Saharan African setting.

Corrosive ingestion remains an important global pathology with high morbidity and mortality. Data on the acute management of adult corrosive injuries from sub-Saharan Africa is scarce, with international investigative algorithms, relying heavily on computed tomography (CT), having limited availability in this setting. To investigate the corrosive injury spectrum in a low-resource setting and the applicability of parameters for predicting full-thickness (FT) necrosis and mortality. A retrospective analysis of a prospective corrosive injury registry (March 1, 2017-October 31, 2023) was performed to include all adult patients with acute corrosive ingestion managed at a single, academic referral centre in Cape Town, South Africa. Patient demographics, corrosive ingestion details, initial investigations, management, and short-term outcomes were described using descriptive statistics while multivariate analysis with receiver operator characteristic area under the curve graphs (ROC AUC) were used to identify factors predictive of FT necrosis and 30-day mortality. One-hundred patients were included, with a mean age of 32 years (SD: 11.2 years) and a male predominance (65.0%). The majority (73.0%) were intentional suicide attempts. Endoscopy on admission was the most frequent initial investigation performed (95 patients), while only 17 were assessed with CT. Seventeen patients had full thickness necrosis at surgery, of which eleven underwent emergency resection and six were palliated. Thirty-day morbidity and mortality were 27.0% and 14.0%, respectively. Patients with full thickness necrosis and those with an established perforation had a 30-day mortality of 58.8% and 91.0%, respectively. Full thickness necrosis was associated with a cumulative 2-year survival of only 17.6%. Multivariate analyses with ROC AUC showed admission endoscopy findings, CT findings, and blood gas findings (pH, base excess, lactate), to all have significant predictive value for full thickness necrosis, with endoscopy proving to have the best predictive value (AUC 0.850). CT and endoscopy findings were the only factors predictive of early mortality, with CT performing better than endoscopy (AUC 0.798 vs 0.759). Intentional corrosive injuries result in devastating morbidity and mortality. Locally, early endoscopy remains the mainstay of severity assessment, but referral for CT imaging should be considered especially when blood gas findings are abnormal.

Critical risk factors analysis of infection-associated hemophagocytic lymphohistiocytosis in children.

To analyze the critical factors of infection-associated Hemophagocytic lymphohistiocytosis (HLH) in children, so as to provide theoretical basis for clinicians to evaluate the disease condition, formulate treatment plan and improve prognosis.This study is a retrospective analysis. 60 cases of children with infection-associated HLH were divided into critical and non-critical groups based on the presence of multiple organ dysfunction syndrome (MODS), and the clinical characteristics and laboratory data of the two groups of children were analyzed. A multifactor logistic regression analysis model was used to assess the independent risk factors affecting critical illness in children with infection-associated HLH, and the Receiver Operating Characteristic (ROC) curve analysis was used to evaluate the predictive value of risk factors for critical illness in children with infection-associated HLH. Children in the critical group with HLH had a younger age at onset. Alanine aminotransferase (ALT), aspartate aminotransferase (AST), lactate dehydrogenase (LDH), gamma-glutamyl transferase (GGT), D-dimer (DD), and triglycerides (TG) were significantly higher in the critical group, while albumin (ALB) was significantly lower, showing statistical significance (P < 0.05). Multifactorial logistic regression analysis of age, ALB, and TG showed that younger age and lower ALB were associated with a higher risk of MODS in children with infection-associated HLH, with age and ALB being independent risk factors for critical illness. ALB predicted the ROC area under the curve for critical children with infection-associated HLH was 0.765 (95% CI: 0.643-0.888, P = 0.011), with the optimal cut-off value being 32.50g/L (sensitivity = 68.3%, specificity = 84.2%); age predicted the ROC area under the curve for critical children with infection-associated HLH was 0.711 (95% CI: 0.570-0.851, P = 0.009), with the optimal cut-off value being 1.50 years (sensitivity = 70.7%, specificity = 68.4%). This study suggests that younger patients and those with hypoalbuminemia among infection-related HLH patients are more likely to develop MODS. In the future, verification will be required through large-scale, multi-center studies.

Remote patient-reported outcome measure triage score for monitoring disease activity and allocation of consultations in rheumatoid arthritis patients

Objective Currently, expedited by the coronavirus disease 2019 pandemic, there is high demand for allocating patients in a state of low disease activity to telehealth, ideally based on remote measurements. This cross-sectional study assesses the discriminative accuracy of the Rheumatoid Arthritis Impact of Disease (RAID) questionnaire regarding high and low disease activity. Furthermore, we aimed to optimize this classification, developing a remote triage score based on RAID and other patient-reported outcome measures (PROMs). Method Data were acquired from an outpatient clinic cohort of chronic rheumatoid arthritis patients at a large trainee hospital in the Netherlands. Patients were divided into high and low disease categories, based on 28-joint Disease Activity Score–C-reactive protein. Least absolute shrinkage and selection operator logistic regression were performed, including RAID item scores and other PROMs. Receiver operating characteristics curves and areas under the curve (AUCs) were obtained, and cut-off scores were based on predefined criteria of 90% and 95% sensitivity. Results In total, 278 patients were analysed, of whom 77.2% were identified as having low disease activity. RAID results correlated with DAS28-CRP, showing good performance. The regression model included the RAID items pain and functional disability assessment, and the self-reported swollen joint count (SR-SJC). With an AUC of 0.88 (95% confidence interval 0.84–0.92), this model performed better than the RAID total score. Conclusion A remote triage score based on a composite score of pain, functional disability assessment, and SR-SJC can detect a sufficient proportion of patients with low disease activity who can be allocated to remote consultations.

Combined mammographic breast density and breast arterial calcification is incrementally predictive of coronary artery disease beyond traditional risk factors

Abstract Background Coronary artery disease (CAD) risk is underestimated in women using current risk stratification tools. The mammographic finding of breast arterial calcification (BAC) associates with CAD. Furthermore, breast adipose tissue, measured through breast density (BD) on mammography (low breast density indicates high adiposity) has shown potential to act as a pro-inflammatory, pro-atherogenic fat deposit. Given its uptake in screening programs, mammography may therefore represent a novel risk stratification tool for cardiovascular disease in women. Purpose To evaluate the association between the combined mammographic features of BD and BAC, with CAD. Methods Single-centre, retrospective, cross-sectional study, including 153 women, mean age 62±10, who had both clinically indicated mammography, and coronary computed tomography angiogram (CCTA) for suspected CAD. CAD risk was identified by the CAD Consortium Score, with a 15% threshold for low and high risk. BD was visually assessed and categorised by 4-level BI-RADS grade with grade A-B representing low density, and C-D representing high density (Figure 1). BAC was visually assessed and categorised as present/absent (Figure 1). CAD was categorised as presence/absence of coronary artery plaque on CCTA. Logistic regression was performed with results presented as Odds Ratio (OR) and [95% Confidence Intervals]. Receiver operator characteristic area under the curve (AUC) was used for model discrimination. Results Low BD (n=103 (67%)) was associated with CAD (OR 3.20 [1.58-6.53], p=0.001, as was BAC presence (n=37 (24%), OR 4.36 [1.58-12], p=0.004). There were 51 (33%) with elevated CAD risk. Participants were categorised into 4 subgroups based on low/high BD and presence/absence of BAC: 29 (19%) had low BD and BAC, 74 (48%) had low BD and no BAC, 8 (5%) had high BD and BAC and 42 (27%) had high BD and no BAC. Significantly higher proportions of CAD were noted with low BD and BAC alone, as well as combined low BD and BAC (Figure 2). Compared with high BD/BAC negative, the presence of low BD and BAC independently associated with CAD (OR 5.27 [1.19-23.3], p=0.03). Significant incremental benefit was seen after adding BD/BAC status to CAD Consortium Score (AUC 0.65 vs. 0.72, p=0.004). Conclusions Combined, and individual mammographic features of low BD and BAC presence are associated with CAD and improve risk prediction beyond standard coronary risk probabilities. Standardised reporting of these features to inform risk identification may be of further benefit and should be tested in prospective screening studies.

Predicting atrial fibrillation within 7 years follow-up using machine learning models

Abstract Background The prevalence of atrial fibrillation (AF), the most common type of cardiac arrhythmia, has increased globally. AF is also the leading cardiac factor for several cardiovascular and cerebrovascular events. Early prediction and treatment of AF prevents major cardiovascular and cerebrovascular events. Purpose Our objective is to predict AF risk within 7-years follow-up using only twelve basic factors and applying machine learning (ML) models. Methods Data from the German epidemiological trial on ankle brachial index (getABI) were utilized in this work. GetABI includes 6,457 patients with mean age of 72.53 years. 3,985 individuals were assessed for AF of which 393 patients suffered from AF at 7-years follow-up. The feature selection was initially done manually, ending up in 45 features. The 10 best features were extracted from this dataset according to the SHAP (SHapley Additive exPlanations) values. The final features were body mass index, sensitive CRP, cholesterol, LDL-cholesterol, troponin I, NT-pro-BNP, glomerular filtration rate, ratio of triglycerides and HDL-cholesterol, gamma-GT, heart rate, including age and sex as major factors. The handling of missing values was achieved by SimpleImputer, estimating the mean values. XGBoost and Random Forest predicted AF. Logistic Regression was also used as a baseline model. The data were split into training and test set and ML models were applied for 100 iterative runs, extracting results with mean values. Results XGBoost was the most accurate model, predicting the AF with 71.19 % mean accuracy, 66.37 % mean sensitivity and 75.61 % mean specificity. Figure 1 depicts the performance of all models. Additionally, Receiver Operating Characteristic Curve (ROC) and Area Under Curve (AUC) for each model are presented in Figure 2. XGBoost also outperformed all the others models, achieving the highest mean AUC value, equal to 70.99 %. Contrariwise, logistic regression had the lowest overall performance. Conclusion ML models, specifically XGBoost, achieved accurate AF prediction in 3,985 individuals utilizing only twelve clinical-routine data.Evaluation results of each used model.ROC curve and AUC value of each model.

CCTA and CTP imaging for detecting clinically suspected in-stent restenosis: a meta-analysis

Abstract Background The evaluation of coronary artery stents via Coronary Computed Tomography Angiography (CCTA) can be compromised by artefacts, potentially undermining its diagnostic accuracy. The integration of CT Perfusion (CTP) with CCTA (CCTA+CTP) has been proposed to enhance the diagnostic yield in detecting in-stent restenosis (ISR). Purpose This meta-analysis aims to assess the diagnostic performance of CCTA and combined CCTA+CTP in detecting ISR. Methods A comprehensive literature search of studies from 2005 to 2022 identified 13,747 articles. Inclusion criteria comprised the utilization of multidetector CT scanners with ≥64 slices and invasive coronary angiography as the reference standard. Studies that systematically evaluated stent patency in asymptomatic patients as part of their protocol were excluded. Results After removing duplicates, screening titles and abstracts, and conducting full-text reviews, 20 studies met the inclusion criteria (17 CCTA, 3 CCTA+CTP). Data on 2,674 CCTA-assessed stents and 752 CCTA+CTP-assessed stents were analyzed. The meta-analysis revealed that CCTA alone achieved a sensitivity of 90% (95% CI; 84-94%) and a specificity of 89% (95% CI; 86-92%)(Figure 1). CCTA+CTP exhibited comparable diagnostic performance, with a per-stent sensitivity of 88% (95% CI; 80-94%) and a specificity of 88% (95% CI; 84-93%) (Figure 2). The summary Receiver Operating Characteristic (sROC) Area Under the Curve (AUC) was 0.96 (95% CI; 0.94-0.97) for CCTA and 0.96 (95% CI; 0.89-1.00) for CCTA+CTP, indicating a high overall performance for both diagnostic modalities. Conclusion Utilizing contemporary imaging hardware, both CCTA and CCTA+CTP demonstrate high diagnostic performance in evaluating ISR. The findings suggest that the presence of coronary artery stents should not preclude the use of these non-invasive diagnostic tests in clinical practice.Figure 1Figure 2

Development of machine learning models for prediction of left ventricular systolic dysfunction in patients with isolated left ventricular dilation

Abstract Background/Introduction Isolated left ventricular dilation (ILVD), in the absence of concomitant LV systolic dysfunction, is a risk factor for new reduction in LV ejection fraction (LVEF) and adverse clinical outcomes. We assessed the performance of different machine learning (ML) models in predicting new reduction in LVEF in patients with ILVD. Methods A retrospective analysis of de-identified patient records in the Tempus Database with at least two transthoracic echocardiograms (TTE) conducted between January 2019 and December 2022 were retrospectively analyzed, with the follow up period ending in January 2023. Inclusion/exclusion criteria are shown in Figure 1A. Briefly, patients with ILVD were defined based on echocardiographic parameters as those with LVEF &amp;gt; 50% and LV end diastolic volume indexed (LVEDVi) &amp;gt; 62 mL/m2 for females and &amp;gt; 75 mL/m2 for males, without prior LVEF &amp;lt; 50% and/or grade 2/3 diastolic dysfunction. The endpoint was LVEF &amp;lt; 40% on future (≥90 days) TTE. Five hard voting ML models and one soft voting ensemble model were trained with data parsed from TTE reports (Figure 1B). Feature importance (SHAP) was calculated, and receiver operating characteristic (ROC) and Kaplan Meier curves evaluated the final model (Figure 1C-E). Results A total of 2,962 patients met the inclusion criteria. The median time from index to last TTE was 578 (IQR = 500) days. LVEF &amp;lt; 40% on follow up TTE was noted in 6% of patients (177 patients, median 478 days to endpoint, IQR = 535 days). Of the six models developed, the ensemble model had the highest ROC area under the curve (0.791, Figure 1D), precision (0.163), F1-score (0.266), and specificity (0.773). The ensemble model also had the lowest predicted prevalence (25.5%), although this was higher than the observed prevalence in the test set (5.7%). Patients predicted to develop LVEF &amp;lt; 40% had a 8.2x higher risk of developing LVEF &amp;lt; 40% within five years of index (p&amp;lt;0.001, Figure 1E). Feature importance showed that male gender, higher heart rate, lower LVEF at index TTE, higher LVEDVi, and lower tricuspid annular plane systolic excursion had the highest mean absolute impact on the model’s output probability (Figure 1C). Conclusion Using only data parsed from the index TTE, ensembling a model for the prediction of developing LVEF &amp;lt; 40% in patients with ILVD and without a history of LV diastolic or systolic dysfunction performed the best. Additional analyses including clinical variables such as comorbidities, symptoms, and medications may improve the model’s performance.

Exploring trimethylamine n-oxide's role in coronary microvascular dysfunction and prognostic outcomes in ST-elevation myocardial infarction patients

Abstract Background Coronary microvascular dysfunction (CMD) subsequent to ST-elevation myocardial infarction (STEMI) is increasingly recognized as a determinant of adverse clinical prognoses. Despite its significance, CMD diagnosis is rare in clinical settings, mainly due to its complexity and technical challenges. Considering these challenges, this study endeavors to explore the diagnostic potential of Trimethylamine N-oxide (TMAO), a metabolite derived from gut microbiota. TMAO has been implicated in the pathogenesis of endothelial dysfunction and atherosclerosis, suggesting its utility as a novel biomarker for CMD and determining prognosis. Purpose To investigate the association between TMAO levels and CMD in STEMI patients, evaluating TMAO's utility as a biomarker for CMD and prognosis predictor. Methods In this prospective, observational study, 210 STEMI patients were enrolled. At the 3-month follow-up, these patients were subjected to comprehensive coronary physiology assessments, including measurements of coronary flow reserve (CFR), fractional flow reserve (FFR), and the index of microcirculatory resistance (IMR) via utilization of pressure-temperature sensor-tipped wires. CMD was diagnosed in patients presenting with an IMR ≥ 25 or a CFR &amp;lt; 2.0, alongside an FFR &amp;gt; 0.80. Levels of TMAO, C-reactive protein (CRP), and brain natriuretic peptide (BNP), along with other traditional biomarkers were measured at baseline, 3 and 12-month follow-up. Using the Delong test and Youden index to find optimal TMAO cutoffs for CMD detection, due to no predefined TMAO threshold. The primary endpoint was the incidence of CMD at 3 months, with the secondary endpoint being major adverse cardiovascular and cerebrovascular events (MACCE) at 12 months. Results Among enrolled patients, 85 (40.5%) were female, with a median age of 65 (IQR: 58-76). TMAO's baseline receiver operating characteristic (ROC) curve area was 0.55 (95% CI: 0.46-0.64; p=0.426), improving to 0.80 (95% CI: 0.73-0.87; P&amp;lt;0.001) at 3-month follow-up. An optimal TMAO cutoff of 3.91 μM achieved 75% sensitivity (95% CI: 0.63-0.86) and 82% specificity (95% CI: 0.76-0.88), outperforming BNP and CRP with ROC areas of 0.62 and 0.67, respectively. Patients were divided into low (n=140) and high (n=70) TMAO groups at the 3.91 μM threshold. A higher percentage of females was noted in the high TMAO group (55.7% vs. 32.9%; p&amp;lt;0.001). Clinical characteristics and risk factors like stroke and CAD history showed no significant differences across TMAO groups. Multivariable logistic regression revealed TMAO levels at 3 months as an independent predictor for CMD. A cubic spline curve indicated a marked increase in CMD odds with TMAO between 3 and 6 μM.The Incidence of MACCE was significantly higher in patients with a TMAO≥3.91 (41.4% vs 10.7%; p &amp;lt; 0.001). Conclusion Elevated TMAO levels 3 months post-STEMI are significantly associated with increased CMD risk, and significantly predict MACCE.TMAO as a Biomarker for CMD and MACCETMAO Cubic Spline Analysis for CMD Odds

Respiratory rate-oxygenation index on the 3rd day is the best predictor of treatment failure in COVID-19 patients.

Predictors of outcomes are essential to identifying severe COVID-19 cases and optimizing treatment and care settings. The respiratory rate-oxygenation (ROX) index, originally introduced for predicting the failure of non-invasive support in acute hypoxemic respiratory failure (AHRF), has not been extensively studied over time during hospitalization. This multicenter prospective observational study analyzed COVID-19-related AHRF patients admitted to eight Italian hospitals during the second pandemic wave. The study assessed the ROX index using receiver operator characteristic curves and areas under the curve with 95% confidence intervals to predict treatment failure, defined as endotracheal intubation (ETI) or death. A total of 227 patients (69.2% males) were enrolled, with a median arterial partial pressure of oxygen (PaO2)/fraction of inspired oxygen (FiO2) ratio at admission of 248 (interquartile range: 170-295). Nearly one-third (29.5%) required ETI or died during hospitalization. Those who experienced treatment failure were older (median age 70 versus 61 years, p<0.001), more likely to be current or former smokers (8.5% versus 6.4% and 42.4% versus 25.5%, p=0.039), had a higher prevalence of cardiovascular diseases (74.6% versus 46.3%, p<0.001), and had a lower PaO2/FiO2 ratio at presentation (median 229 versus 254, p=0.014). Gender, body mass index, and other comorbidities showed no significant differences. In patients who failed treatment, the ROX index was higher at presentation and worsened sharply by days 3 and 4. Conversely, in patients who survived without requiring ETI, the ROX index remained stable and reduced after 5-6 days. The ROX index's predictive ability improved notably by the third day of hospitalization, with the best cut-off value identified at 8.53 (sensitivity 75%, specificity 68%). Kaplan-Meier curves indicated that a ROX index of 8.53 or lower on days 1, 2, or 3 was associated with a higher risk of treatment failure. Thus, a single ROX index assessment on day 3 is more informative than its variability over time, with values of 8.53 or lower predicting non-invasive respiratory support failure in hospitalized COVID-19 patients.

Examining thedrivers of forest cover change and deforestation susceptibility in Northeast India using multicriteria decision-makingmodels.

The increasing rates of forest cover change and heightened vulnerability to deforestation present significant environmental challenges in Northeast India. This study investigates the dynamics of forest cover changeand susceptibility to deforestation in this region from 2001 to 2021, utilizing data from the Hansen Global Forest Change (HGFC) productonthe Google Earth Engine (GEE) platform. A suite of multicriteria decision-making (MCDM) models-including VlseKriterijumska optimizacija I Kompromisno Resenje (VIKOR), Simple Additive Weighting (SAW), Evaluation Based on Distance from Average Solution (EDAS), and Weighted Aggregates Sum Product Assessment (WASPAS)-was employed to assess changes in forest cover and deforestation susceptibility across varied zones. Multicollinearity tests confirmed the relevance of the factors influencing deforestation. Statistical validations, such as the Wilcoxon Signed Ranks Test, underscored the models' robustness, revealing statistically significant outcomes. Additionally, Receiver Operating Characteristic (ROC) curve and Area Under the Curve (AUC) analysis demonstrated the superior fit of the VIKOR model (AUC = 0.938) compared to SAW (AUC = 0.901), EDAS (AUC = 0.895), and WASPAS (AUC = 0.864) in predicting current deforestation susceptibility. Validation affirmed the reliability of all MCDM methods, with VIKOR displaying high sensitivity (True Positive Rate, TPR = 0.878) and optimal AUC (0.938). Correlation analyses among the models identified significant inter-relationships, notably a positive correlation between EDAS and SAW, and a negative correlation between VIKOR and SAW. The regions of Assam, Nagaland, Mizoram, and Arunachal Pradesh were identified as experiencing significant forest cover loss, indicating a pronounced susceptibility to future deforestation. These findings underscore the need for immediate intervention to address this critical environmental issue.

ML-Based Models as a Strategy to Discover Novel Antiepileptic Drugs Targeting Sodium Receptor Channel.

Epilepsy remains the most common and chronic disorder demanding longterm management. The impact of epilepsy disease is a cause of great concern and has resulted in efforts to develop treatment for epilepsy. It occurs due to an increase in neuronal excitability produced by changes affecting the voltage-dependent properties of Voltage-gated Sodium Channels (VGSCs). Weka, a popular suite for machine learning techniques, was used on a dataset comprising 1781 chemical compounds, showing inhibition activity for sodium channel protein IX alpha subunit. After the analysis of the dataset obtained from ChEMBL, molecular fingerprints were computed for the molecules by the ChemDes server. Different classifiers available in the Weka software were explored to find out the algorithm that could be more suitable for the dataset or produce the highest accuracy for the classification of molecules as active or inactive. In this work, a comprehensive comparison of different classifiers in the Weka suite for the prediction of active, inactive, and intermediate classes of molecules showing inhibition against human NaV1.7 protein was made. The prediction accuracy of these classifiers was assessed based on performance measures, including accuracy, Root Mean Squared Error (RMSE), Receiver Operating Characteristic (ROC), precision, Mathews Correlation Coefficient (MCC), recall, and Fmeasure. The comparison of results for model performance demonstrated that the OneR classifier performed best over others when validated using percentage split, cross-validation, and supplied test methods. J48 and Bagging also performed equally well in the prediction of different classes with an MCC value of 1, ROC area equal to 1, and RMSE close to 0. Machine Learning (ML) tools provide a fast, reliable, and cost-effective approach required to identify or predict inhibitory molecules for the treatment of a disease. This study shows that the ML methods, particularly OneR, J48, and Bagging have the ability to identify active and inactive classes of compounds for the human NaV1.7 protein target. Such predictive models may provide a reliable and time-saving approach that can aid in the design of potential inhibitors for the treatment of epilepsy disease.

Data-driven Machine Learning Models for Risk Stratification and Prediction of Emergence Delirium in Pediatric Patients Underwent Tonsillectomy/Adenotonsillectomy.

In the pediatric surgical population, Emergence Delirium (ED) poses a significant challenge. This study aims to develop and validate machine learning (ML) models to identify key features associated with ED and predict its occurrence in children undergoing tonsillectomy or adenotonsillectomy. The analysis involved data cleaning, exploratory data analysis (EDA), supervised predictive modeling, and unsupervised learning on a medical dataset (n = 423). After preliminary data cleaning, EDA encompassed plotting histograms, boxplots, pairplots, and correlation heatmaps to understand variable distributions and relationships. Four predictive models were trained including logistic regression (LR), random forest (RF), Support Vector Machine (SVM), and Gradient Boosting (XGBoost). The models were evaluated and compared using Receiver Operating Characteristic (ROC) Area Under the Curve (AUC), precision, recall, and feature importance. The RF model showed better performance and was used for the test (AUC-ROC 0.96, precision 1.00, and recall 0.92 on the validation set). K-means clustering was applied to find groups within the data. Elbow method and silhouette scores were used to determine the optimal number of clusters. The formed clusters were analyzed by aggregating features to understand the characteristics of each cluster. EDA revealed significant positive correlations between age, weight, American Society of Anesthesiologists (ASA) health score, and surgery duration with the risk of developing ED. Among the ML models, RF achieved the highest performance. Key predictive variables, based on the model's feature importance, included delirium screening scales, extubation time, and time to regain consciousness. Unsupervised K-means clustering identified 2-3 optimal clusters, which represented distinct patient subgroups: younger, healthier, low-risk individuals (cluster 0), and older patients with increasing chronic disease burden, higher delirium screening scores, and consequently higher post-operative delirium risk (clusters 1 and 2). ML techniques are valuable tools for extracting insights and making accurate predictions from healthcare data. High-performing algorithm-based models can be implemented for clinical decision support systems, facilitating early identification and intervention for ED in pediatric patients. By investigating various variables, it is possible to assess risk and implement preventive measures effectively. Furthermore, unsupervised clustering reveals distinct patient subgroups, enabling personalized perioperative management strategies and enhancing overall patient care.

Comparison of Multi-Armed Bandit Algorithms in Advertising Recommendation Systems

In today's rapidly evolving online environment, advertising recommendation systems utilize multi-armed bandit algorithms like dynamic collaborative filtering Thompson sampling (DCTS), upper confidence bound based on recommender system (UCB-RS), and dynamic -greedy algorithm (DEG) to optimize ad displays and enhance click-through rates (CTR). These algorithms must adapt to limited information and update strategies based on immediate feedback.This study employs an experimental comparison to assess the performance of the DCTS, UCB-RS, and DEG algorithms using the click-through rate prediction database from Kaggle. Five experimental sets under varied parameter settings were analyzed, employing the Receiver Operating Characteristic (ROC) curve, accuracy, and area under the curve (AUC) metrics.Results show that the DEG algorithm consistently outperforms the others, achieving higher AUC values and demonstrating robust sample identification capabilities. DEG also exhibits superior precision at high recall levels, showcasing its potential in dynamic advertising environments. Its dynamic adjustment strategy effectively balances exploration and exploitation, optimizing ad displays.The findings suggest that DEG's adaptability and stability make it particularly suitable for dynamic ad recommendation scenarios. Future research should focus on optimizing DEG's parameter settings and possibly integrating UCB-RS's exploration mechanisms to enhance performance and develop more effective strategies for advertising recommendation systems.

The mitral to aortic/pulmonary velocity-time integral ratio is a simple, feasible and accurate discriminator for echocardiographic evaluation of severe isolated mitral regurgitation.

Echocardiographic quantification of mitral regurgitation (MR) remains challenging, requiring dedicated image acquisition, and is limited by potential error from geometric assumptions of annular dimensions. Volume is a product of area and flow and assuming proportional mitral/aortic areas, an increased mitral-inflow volume compared to LV/RV-outflow semi-quantitatively represents greater MR regurgitant volume. Therefore, we investigated the feasibility and diagnostic performance of the mitral-aortic velocity-time integral(VTI) ratio in isolated MR. We also investigated the use of the mitral-pulmonary VTI ratio as an alternative in clinical situations where the LV outflow tract(LVOT) VTI could not be used. We reviewed 166 consecutive patients (33%, n = 54 severe MR by multi-parameter integrated expert opinion). Pulsed wave Doppler VTI at the mitral leaflet tips and the left ventricular outflow and continuous-wave Doppler of the RV outflow tract were measured individually and independently by blinded readers(expert and trainee status) to derive the ratio. Receiver operator characteristic area under the curve(AUC) comparison was calculated and compared with effective regurgitant orifice area(EROA > 40mm), regurgitant volume(RVol > 60mL), vena contracta(VC > 0.7cm), E-velocity > 1.2cm, systolic flow reversal(SFR), left atrial and ventricular dilatation. Increasing ratio was associated with severe MR(AUC 0.94) with optimal threshold defined at 1.3. This provided significant discrimination for severe MR(AUC 0.81) compared to EROA(0.68), VC(0.52), LV dilatation(0.69), LA dilatation(0.70), SFR(0.73), E-velocity(0.68) all p < 0.05, with sensitivity 82% and specificity 94%. The mitral-pulmonary VTI ratio demonstrated similar discrimination(AUC 0.92) with optimal threshold defined at 1.14. Excellent inter-observer reproducibility(intra-class correlation 0.97) was seen between trainee and expert readers. There was no difference in AUC comparison by MR mechanism or patient rhythm. The mitral-aortic and mitral-pulmonary VTI ratios are simple, geometric-free parameters feasibly reproducible from routine echocardiographic datasets and are excellent discriminative tools for severe MR. Readers should consider integration of this parameter in routine reporting.

Exploring a GIS-based analytic hierarchy process for spatial flood risk assessment in Egypt: a case study of the Damietta branch

Floods are the most common and costly disasters worldwide, while spatial flood risk assessment is still challenging due to fewer observations and method limitations. In this study, the flood risk zonation in the Nile districts of the Damietta branch, Egypt, is delineated and assessed by integrating remote sensing with a geographic information system, and an analytical hierarchy process (AHP). Twelve thematic layers (elevation, slope, normalized difference vegetation index, topographic wetness index, modified normalized difference water index, topographic positioning index, stream power index, modified Fournier index, drainage density, distance to the river, sediment transport index, and lithology) are used for producing flood susceptibility zonation (FSZ) and six parameters (total population, distance to hospital, land use/land cover, population density, road density, and distance to road) are utilized for producing flood vulnerability zonation. Multicollinearity analysis is applied to identify highly correlated independent variables. Sensitivity studies have been used to assess the effectiveness of the AHP model. The results indicate that the high and very high flood risk classes cover 21.40% and 8.26% of the area, respectively. In 14.07%, 27.01%, and 29.26% of the research area, respectively, flood risk zones classified as very low, low, and moderate are found. Finally, FSZ is validated using the receiver operating characteristics curve and area under curve (AUC) analysis. A higher AUC value (0.741) in the validation findings demonstrated the validity of this AHP approach. The results of this study will help planners, hydrologists, and managers of water resources manage areas that are susceptible to flooding and reduce potential harm.

Heartbeat classification using various machine learning models: A comparative study

Cardiac arrhythmias, known as irregular heartbeats, pose a notable health threat that necessitates prompt diagnosis, as untreated arrhythmias can lead to severe heart complications. Among the various methods for arrhythmia detection, electrocardiography is the most prevalent due to its non-invasive monitoring of heart activity. However, manual electrocardiogram (ECG) analysis is inefficient and prone to errors, prompting the exploration of machine learning (ML) models for ECG feature recognition. Integrating ML models with ECG analysis can revolutionize cardiac diagnostics by improving healthcare efficiency and outcomes by enhancing the accuracy and consistency of existing approaches as well as their processing speed for large datasets. Unfortunately, current ML methods encounter two key limitations: prolonged training times and the need for manual feature selection. To address these issues, we propose using ML models enhanced with innovative techniques such as the Fourier transform (FT) and Gaussian noise injection for improved cardiac health assessment. To validate this approach, we utilized statistical tools, including Pearson correlation and p-values, to uncover relationships within the data. In addition, we employed the FT technique to extract and analyze frequency-domain features. Our comparative study of different ML models relied on metrics such as accuracy, precision, recall, F1 score, and receiver operating characteristic area under the receiver operating characteristic curve, demonstrating XGBoost&amp;rsquo;s impressive average recall of 0.956 with 99.96% overall accuracy. An average precision of 0.956 further underscored the accuracy of XGBoost&amp;rsquo;s predictions, indicating its high level of reliability in distinguishing various cardiac conditions. These results highlight the considerable potential of ML techniques for precise ECG-based clinical diagnoses, helping healthcare professionals make more accurate and timely decisions in patient care.

Large ischemic core defined by visually assessed ASPECTS predicts functional outcomes comparably accurate to automated CT perfusion in the 6-24 h window.

Automated CT perfusion (aCTP) is commonly used to select patients with anterior circulation large vessel occlusion (aLVO) for endovascular treatment (EVT). The equivalence of visually assessed Non-contrast CT Alberta Stroke Program Early CT Scores (ASPECTS) and aCTP based selection in predicting favorable functional outcomes remains uncertain. Retrospective multicenter study of adult aLVO patients from the Swiss Stroke Registry (2014-2021) treated with EVT or best medical treatment 6-24 h after stroke onset. We assessed ASPECTS on non-contrast CT visually and ischemic core volumes on aCTP, defining ASPECTS 0-5 and aCTP CBF < 30% volumes ⩾50 mL as large ischemic cores. We used logistic regression to explore the association between CT modalities and favorable functional outcomes (modified Rankin Scale [mRS] score shift toward lower categories) at 3 months. Receiver operating characteristic (ROC) curve analysis compared the predictive accuracy of visually assessed ASPECTS and aCTP ischemic core for favorable outcomes (mRS 0-2) at 3 months. Of 210 patients, 11.4% had ASPECTS 0-5, and 12.9% aCTP core volumes ⩾50 mL. Within the same model, ASPECTS but not aCTP core volumes were associated with favorable outcomes (ASPECTS: acOR 1.85, 95%CI 1.27-2.70, p = 0.001). The ROC curve analyses showed comparable diagnostic accuracy in predicting favorable functional outcomes (mRS 0-2) at 3 months (ROC areas: ASPECTS 0.80 [95%CI 0.74-0.86] vs aCTP core 0.79 [95%CI 0.72-0.85]). In patients with aLVO, visually assessed ASPECTS showed at least comparable accuracy to automatically generated CTP core volumes in predicting functional outcomes at 3 months.

A comparative study of early stage Alzheimer’s disease classification using various transfer learning CNN frameworks

ABSTRACT The current research explores the improvements in predictive performance and computational efficiency that machine learning and deep learning methods have made over time. Specifically, the application of transfer learning concepts within Convolutional Neural Networks (CNNs) has proved useful for diagnosing and classifying the various stages of Alzheimer’s disease. Using base architectures such as Xception, InceptionResNetV2, DenseNet201, InceptionV3, ResNet50, and MobileNetV2, this study extends these models by adding batch normalization (BN), dropout, and dense layers. These enhancements improve the model’s effectiveness and precision in addressing the specified medical issue. The proposed model is rigorously validated and evaluated using publicly available Kaggle MRI Alzheimer’s data consisting of 1280 testing images and 5120 patient training images. For comprehensive performance evaluation, precision, recall, F1-score, and accuracy metrics are utilized. The findings indicate that the Xception method is the most promising of those considered. Without employing five K-fold techniques, this model obtains a 99% accuracy and 0.135 loss score. In addition, integrating five K-fold methods enhances the accuracy to 99.68% while decreasing the loss score to 0.120. The research further included the evaluation of the Receiver Operating Characteristic Area Under the Curve (ROC-AUC) for various classes and models. As a result, our model may detect and diagnose Alzheimer’s disease quickly and accurately.