Browse Articles
Discover research articles across all indexed journals
Interpretable machine learning for predicting isolated basal septal hypertrophy
Background The basal septal hypertrophy(BSH) is an often under-recognized morphological change in the left ventricle. This is a common echocardiographic finding with a prevalence of approximately 7–20%, which may indicate early structural and functional remodeling of the left ventricle in certain pathologies. It also poses a risk of severe left ventricular outflow tract obstruction and is a significant cause of postoperative complications in patients undergoing transcatheter aortic valve implantation (TAVI). Compared to traditional algorithms, machine learning algorithms are more effective at capturing nonlinear relationships and developing more accurate diagnostic and predictive models. However, no predictive models for BSH have been developed using machine learning algorithms. Objective To evaluate the effectiveness of five machine learning algorithms in predicting thickening of the basal segment of the interventricular septum and to develop a simple, yet efficient, prediction model for BSH. Methods Echocardiographic and clinical data from 902 patients were collected from the First Central Hospital of Baoding City, including 91 BSH patients and 811 non-BSH patients. The data were divided into training and test sets in a 7:3 ratio. Five machine learning algorithms -XGBoost, Random Forest(RF), Dicision tree(DT), K-Nearest Neighbor classification(KNN), and Naive Bayes(NB) were applied to construct the models, combined with logistic regression (LR) based on Lasso regression. The performance of each model was evaluated using Receiver Operating Characteristic curve (ROC),calibration curves and Decision Curve Analysis (DCA)curve, with the model demonstrating the best performance being selected. The shapley additive explanation (SHAP) method was employed to interpret the XBoost and RF models. Results The logistic regression (LR) of the Lasso regression model showed that IVS-AO Angle, Left Ventricular Mass Index (LVMI), Diastolic Left Ventricular Internal Diameter Index (LVIDdI), Systolic Blood Pressure (SBP), Diastolic Blood Pressure (DBP), Distance from mitral valve closure point to basal segment of interventricular septum (MVCP-Sd), GLU, and Mitral Valve peak A (MV-A) were associated with BSH, with odds ratios (OR) of 0.86 (0.831–0.888), 1.034 (1.018–1.052), 0.104 (0.023–0.403), 1.041 (1.021–1.064), 0.964 (0.93–0.998), 0.852 (0.764–0.949), 1.146 (1.023–1.281), and 0.967 (0.947–0.987), respectively. The area under the ROC curve (AUC) for Model-relevant variable IVS-AO Angle, MVCP_Sd,LVMI, GLU, LVIDdI, SBP,DBP,LVIDdI,MV_A were 0.87,0.68,0.66,0.55,0.56,0.67,0.75,0.75. The AUC for the algorithms (XGBoost, RF, DT, KNN, NB) in the test set were 0.92, 0.91, 0.85, 0.84, and 0.88, respectively. The SHAP method identified eight predictor variables for BSH based on importance rankings, with the top four being IVS-AO Angle, LVMI, LVIDdI, and SBP, with IVS-AO Angle emerging as the most important predictor. The external validation of the RF model yielded an AUC of 0.86. Conclusion Machine learning can effectively predict BSH, with IVS-AO Angle identified as an independent predictor. The RF model, being simple to operate, can be applied to the risk management of BSH patients.
Author Correction: Oenothera biennis improves pregnancy outcomes by suppressing inflammation and fibrosis in an intra-uterine adhesion rat model
Delayed surgery among patients diagnosed with spinal disorders: Retrospective analysis
To determine the association between race and access to healthcare services with respect to the treatment of spinal cord disorders, a retrospective cohort study of patients receiving an initial diagnosis, two Boston hospitals, September 1, 2017, to June 1, 2018, follow-up through December 31, 2019. Data from patients (18–89 years) diagnosed with spinal cord disorders were extracted retrospectively from a centralized database. Kaplan-Meier curves and multivariable Cox proportional hazards models analyzed the time to spine surgery following initial diagnosis. Patient race was the primary explanatory variable, with five racial groups (Asian, Black, Hispanic, Other, and White) based on a combination of their self-reported race and ethnicity. Hispanic ethnicity (regardless of race), non-Hispanic ethnicity (designated Asian, Black, or White), and “Other” (non-Hispanic patients who designated their race as other than Asian, Black, or White; this included American Indian, Alaska Native, Native Hawaiian or other Pacific Islander, or two or more races). Among 56,186 patients (4% Asian, 7% Black, 5% Hispanic, 6% Other, 77% White) meeting inclusion criteria, Asian (hazard ratio (HR) 0.67 (0.55, 0.82)), Black (HR 0.55 (0.47, 0.63)), Hispanic (HR 0.43 (0.35, 0.52)), and Other (HR 0.59 (0.51, 0.69)) patients had significantly longer times to surgery compared with White patients.
Correction: The role of C5aR1-mediated hepatic macrophage efferocytosis in NASH
Small flakes for sharp needs: Technological behaviour in the Lower Palaeolithic site of Marathousa 1, Greece
Marathousa 1 (~430 ka BP), located in the Megalopolis Basin, Greece, represents the earliest documented butchery site in the Southern Balkans, providing clear evidence of a direct association between artefacts and remains of Palaeoloxodon antiquus. The lithic assemblage features a distinctive small tools industry, primarily produced from local radiolarite, comprising both simple flakes and retouched tools. Through technological analysis, raw material characterisation, experimental knapping, and statistical analyses, this study explores how Middle Pleistocene hominins organised their technological behaviour as reflected in the lithic assemblage, and how these behaviours were shaped by the resource-rich setting of the Megalopolis Basin, characterised by abundant raw materials, water sources, and faunal availability. Results demonstrate the interplay between freehand and bipolar knapping, reflecting a flexible technological strategy to exploit the available radiolarite. Freehand percussion was mainly used in flake production, while the bipolar technique facilitated initial core reduction and late-stage exhaustion. The consistent microlithisation at the site is also evident in the exploitation of other locally available raw materials, such as limestone, flint, and quartz, supporting previous studies demonstrating small flakes’ effectiveness in diverse tasks. Technological patterns at Marathousa 1 broadly correspond to those observed at other Middle Pleistocene small tool sites; however, its distinctive intersection of raw material availability, technological choices and functional demands provides new insights into regional patterns of lithic variability across Eurasia during this period.
A neuro-symbolic AI approach for translating children’s stories from English to Tamil with emotional paraphrasing
Prevalence and associated factors of depression among stroke family caregivers on follow up at Jimma medical center, southwest, Ethiopia: A cross-sectional study
Background Taking care of stroke patients puts a high burden on their caregivers, and this leads to emotional disturbances like depression. However, little is known about the prevalence and associated factors of depression among family caregivers of stroke patients in Ethiopia. The aim of this study was to assess the prevalence and associated factors of depression among family caregivers of patients with stroke who have follow-up in Jimma Medical Center. Method An institution-based cross-sectional study of 306 family caregivers of stroke patients was conducted using a consecutive sampling method. A structured interviewer-administered questionnaire was used to collect data. The Patient Health Questionnaires-9 (PHQ-9) was used to screen outcome variable (i.e., depression). The data was entered into Epi-data version 4.6 and exported to the statistical package for social science version 25 for analysis. Bivariable analyses followed by multivariable logistic regression models were performed. The association between depression and associated factors was estimated using an odds ratio of 95%CI and a p-value of less than 0.05 in the final model. Result From a total 310 sample size 306 family caregivers were participated, making a response rate of 98.7%. The prevalence of depression among family caregivers was found to be 35.9% (95% CI = 30.54, 41.35). Poor social support (AOR = 2.31, 95% CI: 1.05–5.08), severe physical dependence of patients (AOR = 3.09, 95% CI: 1.44–6.60), lack of medical insurance (AOR = 2.52, 95% CI: 1.34–4.75), spending more than 13 hours per day on care (AOR = 5.72, 95% CI: 2.32–8.12), and illness duration of 6 months (AOR = 3.50, 95% CI: 1.61–7.60) were factors significantly associated with depression. Conclusions and recommendations This study found that more than one third of family caregivers of stroke patients have depression and almost the same with similar studies conducted across different countries of the world. Poor social support of caregivers, no health insurance by caregivers, greater than 13 hours of care per day, less than six months of illness duration, and severe dependence of patients on caregivers were variables associated with depression. Early detection of depression by health professional working at outpatient service and intervention of identified risk factors among stroke family caregivers were recommended for Jimma medical center and local health sector directors were recommended.
Parameter optimization for fly ash geopolymer mixtures: molarity, silica modulus, and solution/binder influence
Ageing is linked to inflammation — but only in the industrialized world
Daily briefing: NIH still uses directives deemed illegal to screen grants
If you’re a US researcher, now is the time to establish a plan B
Trump team says it’s axing some contracts with publishing giant Springer Nature
Author Correction: Single-shot reconstruction of three-dimensional morphology of biological cells in digital holographic microscopy using a physics-driven neural network
Millennial-timescale thermogenic CO2 release preceding the Paleocene-Eocene Thermal Maximum
Abstract Geologic records support a short-lived carbon release, known as the pre-onset excursion (POE), shortly before the Paleocene-Eocene Thermal Maximum (PETM; ~ 56 Ma). However, the source and pace of the POE carbon release and its relationship to the PETM remain unresolved. Here we show a high-temporal-resolution stratigraphic record spanning the POE and PETM from the eastern Tethys Ocean that documents the evolution of surface ocean carbon cycle, redox and eutrophication, confirming the global nature of the POE. Biomarkers extracted from the sedimentary record indicate a smaller environmental perturbation during the POE than that during the PETM in the eastern Tethys Ocean. Earth system modeling constrained by observed δ13C and pH data indicates that the POE was driven by a largely thermogenic CO2 source, likely associated with sill intrusions prior to the main eruption phase of the North Atlantic Igneous Province and possibly biogeochemical feedbacks involving the release of biogenic methane.