Early Failure Detection Research Articles

Ultrahigh Selectivity H2S Gas Sensor Based CsPbBr3 Perovskites via Pb-S Bonding Interaction.

High selectivity and sensitivity sensing of H2S gas play a decisive role in the early detection of sulfide solid-state battery failure. Herein, we construct the CsPbBr3 perovskite-based sensor that exhibits outstanding gas-sensing performance to H2S at room temperature, including high selectivity, fast response/recovery speed (73.5/275.6 s), humidity insensitivity, and long-term stability (6 weeks without degradation). The excellent selectivity of CsPbBr3 for H2S results from the formation of lead-sulfur (Pb-S) bonds exclusive to other molecules and upshifted the Fermi level at the perovskite interface by density functional theory (DFT) calculations. The in-situ experiments reveal the interaction of Pb-S bonding and the transformation of H2S molecules on the perovskite surface. The simple synthesis method and unique sensing mechanism based on perovskite semiconductors help build the room-temperature metal halide perovskite (MHP)-based gas sensors with high selectivity and fast response/recovery speed for solid-state battery failure detection in the future.

Rationale and Design of the HERZCHECK trial: Detection of Early Heart Failure Using Telemedicine and CMR in Structurally Weak Regions (NCT05122793)

Rationale and Design of the HERZCHECK trial: Detection of Early Heart Failure Using Telemedicine and CMR in Structurally Weak Regions (NCT05122793)

Early detection of heart failure using in-patient longitudinal electronic health records.

Heart Failure (HF) is common, with worldwide prevalence of 1%-3% and a lifetime risk of 20% for individuals 40 years or older. Despite its considerable health economic burden, techniques for early detection of HF in the general population are sparse. In this work we tested the hypothesis that a simple Transformer neural network, trained on comprehensive collection of secondary care data across the general population, can be used to prospectively (three-year predictive window) identify patients at an increased risk of first hospitalisation due to HF (HHF). The model was trained using routinely-collected, secondary care health data, including patient demographics, A&E attendances, hospitalisations, outpatient data, medications, blood tests, and vital sign measurements obtained across five years of longitudinal electronic health records (EHRs). The training cohort consisted of n = 183,894 individuals (n = 161,658 age/sex-matched controls and n = 22,236 of first hospitalisation due to HF after a three-year predictive window). Model performance was validated in an independent testing set of n = 8,977 patients (n = 945 HHF patients). Testing set probabilities were well-calibrated and achieved good discriminatory power with Area Under Receiver Operating Characteristic Curve (AUROC]) of 0.86, sensitivity of 36.4% (95% CI: 33.33%-39.56%), specificity of 98.26% (95% CI: 97.95%-98.53%), and PPV of 69.88% (95% CI: 65.86%-73.62%). At Probability of HHF ≥ 90% the model achieved 100% PPV (95% CI: 96.73%-100%) and sensitivity of 11.7% (95% CI: 9.72%-13.91%). Performance was not affected by patient sex or socioeconomic deprivation deciles. Performance was significantly better in Asian, Black, and Mixed ethnicities (AUROC 0.932-0.945) and in the 79-86 age group (AUROC 0.889). We present the first evidence that routinely collected secondary care health record data can be used in the general population to stratify patients at risk of first HHF.

Integrated Multi-Scale Analysis and Advanced Prototype Model for Early Detection of Gearbox Failures Using Infrared Thermal Image Data Under Dynamic Conditions

Integrated Multi-Scale Analysis and Advanced Prototype Model for Early Detection of Gearbox Failures Using Infrared Thermal Image Data Under Dynamic Conditions

The molecular bacterial load assay predicts treatment responses in patients with pre-XDR/XDR-tuberculosis more accurately than GeneXpert Ultra MTB/Rif.

Early detection of treatment failure is essential to improve the management of drug-resistant tuberculosis (DR-TB). We evaluated the molecular bacterial load assay (MBLA) in comparison to standard diagnostic tests for monitoring therapy of patients affected by drug-resistant TB. The performance of MBLA in tracking treatment response in a prospective cohort of patients with pulmonary MDR/RR- and pre-XDR/XDR-TB was compared with mycobacterial culture, mycobacterial DNA detection using GeneXpert (Xpert) and microscopy detection of sputum acid-fast-bacilli. Mycobacterium tuberculosis culture conversion was used as the read-out for treatment responses. The MBLA was most concordant during the early phase of treatment, detecting changes in bacterial load with similar accuracy to microscopy and outperforming Xpert. When considering all timepoints, concordance with MGIT results was 72.1% for MBLA, 57.4% for Xpert and 76.7% for microscopy. The AUC for culture conversion was higher for MBLA (0.88, CI 0.84-0.95) than for Xpert (0.78, CI 0.72-0.85) and microscopy (0.77, CI 0.71-0.83). MBLA was superior in the early identification of successful culture conversion compared to microscopy and Xpert and could be a useful biomarker to evaluate novel entities in Phase IIA early-bactericidal-activity drug trials regardless of the degree of M. tuberculosis drug resistance.

Examination of condition of rolling bearings

Bearings operating properties impact the function of the whole machine therefore their investigation is an important topic. Early detection of failure of bearings allows for the replacement of them during planned maintenance, thus avoiding sudden downtime or unexpected accidents. There are several methods for monitoring the operating conditions of bearings, which help determine the residual lifetime of the bearings. This paper focuses on a test procedure which can be used to determine the condition of rolling element bearings.

Cardiovascular profile score (CVPS) and selected cardiac parameters in fetuses with Vein of Galen Malformation.

Vein of Galen Malformation (VGAM) is a rare congenital cerebrovascular anomaly. Early detection and monitoring of concurrent fetal heart failure in VGAM are crucial for improving outcomes. The study aims to evaluate heart anatomy, systolic and diastolic heart function, and indicators of heart failure in fetuses referred to a tertiary center due to VGAM detected in the second or third trimester. This single-center retrospective study of echocardiographic data from five fetuses with VGAM examined between 2008 and 2023. Parameters analyzed included gestational age, reason for referral, cardiovascular profile score (CVPS), systolic and diastolic heart function and selected cardiac parameters RESULTS: Cardiomegaly as a sign of congestive heart failure was the main reason for referral most of the fetuses (4/5 - 80%) diagnosed later as VGAM in our center. Abnormal cerebral vessel flow was visualized in all cases, with normal umbilical arterial flow. Three fetuses were treated prenatally with digoxin due to congestive heart failure. Monophasic tricuspid valve inflow and decreased shortening fraction (SF) were observed in three fetuses (60%) at the time of diagnosis. CVPS scores ranged from 2 to 10, correlating with the severity of cardiac compromise. All five patients demised, three died in utero, and two shortly after birth. This study emphasizes the severe cardiac implications of VGAM detected in utero and the need for early and comprehensive fetal assessment. Despite early diagnosis, outcomes remain poor, necessitating further research into effective prenatal treatments and management protocols to enhance survival for affected fetuses.

Electrodeposited Magnetoelastic Sensors for Ground Fault Current Detection

Magnetostrictive NiFeCo alloy films were investigated for use as sensors for ground fault current detection in photovoltaic systems. The magnetic field generated by a ground fault current applies a bias magnetic field to the magnetoelastic sensor, shifting the resonant frequency, and allowing for the detection of current in the microamp range. These are low-cost, passive sensors, that can be implemented to provide real time monitoring of PV systems and the early detection of failures in a system. Electrodepositing these films enables batch fabrication of thick (10-100µm) resonators with controlled resonant frequencies and optimization of material properties (magnetic, mechanical, and electrical) for increased sensitivity and signal amplitude.Dopants such as boron and holmium were used to increase electrical resistivity and magnetic permeability respectively. Controlling intrinsic stress was managed through additive selection and allowed for the release of planar resonators with a multistep microfabrication process. The composition and properties of the deposited films were controlled by temperature, agitation, concentrations in the electrodeposition chemistry, current density, and a post processing anneal step. The samples were analyzed with EDS to determine the composition and XRD to look at film texture. Magnetic testing was performed using a super conducting quantum interference device (SQUID) magnetometry and vibrating sample magnetometry (VSM). Magnetostriction was measured using an optical method and correlated to material properties. Acknowledgement Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Abstract 4120990: Classification of Echocardiography Videos Using TimeSformer for Detecting Incipient Heart Failure in Asymptomatic Patients with Normal Ejection Fraction and Patients with Heart Failure

Background: Recent advancements have seen deep learning models help differentiate echocardiography images of patients with heart failure with preserved ejection fraction (HFpEF) from normal controls. Our aim was to develop a model capable of detecting early signs of heart failure in asymptomatic patients with a normal ejection fraction. Methods: We employed the TimeSformer, a video transformer model that classifies video data using a novel attention-based mechanism. This self-attention mechanism that diverges from traditional convolutional neural networks (CNNs). It focuses on relevant parts of the video across both space and time, split into spatial attention, which processes each frame individually, and temporal attention, which integrates information across different frames. The training and validation of the TimeSformer model were conducted on the same dataset of echocardiography videos from 50 normal controls and 50 patients diagnosed with HFpEF, employing 5-fold cross-validation to ensure robust performance evaluation. Results: The TimeSformer model effectively identified HFpEF in patients, as all diagnosed with HFpEF were flagged as abnormal. The echocardiography assessment, along with NT pro BNP levels, supported the diagnoses, with patients showing NT pro BNP levels of 1016±32 pg/ml. Conversely, 46 out of 50 normal controls were correctly identified, with their NT pro BNP levels averaging 52±12 pg/ml. These controls remained asymptomatic. Conclusions: The TimeSformer model demonstrated capability in identifying subtle deviations indicative of incipient heart failure in videos of normal controls, despite normal NT pro BNP levels. This suggests potential for early detection of heart failure in asymptomatic individuals. Further longitudinal studies are necessary to determine whether individuals identified as abnormal develop heart failure symptoms subsequently.

Exploring machine learning algorithms in sickle cell disease patient data: A systematic review.

This systematic review explores the application of machine learning (ML) algorithms in sickle cell disease (SCD), focusing on diagnosis and several clinical characteristics, such as early detection of organ failure, identification of drug dosage, and classification of pain intensity. A comprehensive analysis of recent studies reveals promising results in using ML techniques for diagnosing and monitoring SCD. The review covers various ML algorithms, including Multilayer Perceptron, Support Vector Machine, Random Forest, Logistic Regression, Long short-term memory, Extreme Learning Machines, Convolutional Neural Networks, and Transfer Learning methods. Despite significant advances, challenges such as limited dataset sizes, interpretability concerns, and risks of overfitting are identified in studies. Future research directions entail addressing these limitations by harnessing larger and more representative datasets, enhancing model interpretability, and exploring advanced ML techniques like deep learning. Overall, this review underscores the transformative potential of ML in increasing the diagnosis, monitoring and define prognosis of sickle cell disease while also highlighting the need for further investigation in the field.

Heart Failure Prediction Using Machine Learning

This study explores the use of XGBoost and Shapley values for heart failure prediction, in addition to processing models such as neural network, CNN, and SVM. By comparing the performance of these different machine learning algorithms, we aim to develop a robust and accurate predictive model for identifying individuals at risk of heart failure. Our findings highlight the strengths and limitations of each approach, providing valuable insights for future research in this area. Ultimately, this research aims to improve the early detection and management of heart failure, leading to better patient outcomes and more efficient healthcare practices. Key Words: heart failure prediction, XGBoost, SHAPley values, neural network, CNN, SVM, machine learning algorithms, early detection, death events.

Serum metabolomics improve risk stratification for incident heart failure

Abstract Background The prediction and early detection of heart failure (HF) is vital to reduce its substantial impact on quality of life, survival and healthcare expenditure. Current incident HF risk stratification strategies achieve only modest performance. Moreover, state-of-the-art risk scores focus on commonly acknowledged clinical risk factors, thus necessitating the integration of heterogenous data sources and prioritizing individuals with obvious risk constellations. Purpose Here, we explored the predictive value of serum metabolomics (168 metabolites detected by proton nuclear magnetic resonance (1H-NMR) spectroscopy) for incident HF. Methods Leveraging data of n = 68,311 individuals and > 0.8 million person-years of follow-up from the UK Biobank (UKB) cohort, we (I) evaluated the association of individual metabolites with incident HF via fitting of per-metabolite COX proportional hazards models and (II) trained and validated elastic net (EN) models to predict incident HF using the serum metabolome. Discriminative performance was benchmarked against a comprehensive, well-validated clinical risk score (Pooled Cohort Equations to Prevent HF, PCP-HF). External validation was conducted in the independent FINRISK study. Results Several metabolites were independently associated with incident HF (90/168 adjusting for age and sex, 48/168 adjusting for PCP-HF). Performance-optimized risk models effectively retained key predictors representing highly correlated clusters (≈ 80 % feature reduction). The addition of metabolomics to PCP-HF improved predictive performance (Harrel’s C: 0.768 vs. 0.755, ΔC = 0.013 (95% confidence interval (CI) 0.004 – 0.022), continuous net reclassification improvement (NRI) = 0.287 (95% CI 0.200 – 0.367), relative integrated discrimination improvement (IDI): 17.47 % (95% CI 9.463 - 27.825)). Simplified models only including age, sex and metabolomics performed almost as well as the PCP-HF model (Harrel’s C: 0.745 vs. 0.755, ΔC = 0.010 (95% CI -0.004 - 0.027), continuous NRI: 0.097 (95% CI -0.025 - 0.217), relative IDI: 13.445 % (95% CI -10.608 - 41.454)). Risk and survival stratification was improved by integrating metabolomics. External validation within FINRISK revealed similar patterns using the original model coefficients. Conclusions Serum metabolomics improve the prediction of incident HF risk. Scores obtained from the combination of age, sex and metabolomics exhibit similar predictive power as clinical risk models. Offering serum metabolomics to a middle-aged cohort might significantly improve HF risk stratification, thus facilitating preventive efforts. Via a single blood draw, serum metabolomics displays a highly cost- and time-effective, standardizable, and scalable alternative to clinical risk scores involving physical measurements and history taking in addition to clinical chemistry.Relative performance (test split)ROC & DCA plots (test split)

Contribution to Conditional Maintenance by Vibration Analysis of Rotating Machine Mechanical Failures and Proposed Solutions

Objective: The aim of this study is to analyze the Cement Separator machine and identify potential condition indicators through vibration measurements and analysis. The goal is to diagnose and repair the machine before any material damage occurs. Background: Maintenance Technology: Modern maintenance technologies are crucial for monitoring equipment performance and planning timely maintenance interventions. Vibration Monitoring: As a key component in maintenance programs, especially for mechanical systems, vibration monitoring provides early warnings of faults based on the actual state of the machine. Cement Separator Machine: Issue: The cement separator exhibits significant vibrations despite its low operating speed. Data Sources: The construction and operational details of the machine are available from its operating manual and vibration measurements. Methodology: Practical Vibration Measurements: Extensive measurements are performed in a research laboratory and on-site to monitor the machine's condition. Vibration measuring devices are used to monitor rotating machines at specified intervals according to their condition and international standards. Condition Indicators: Various condition indicators are monitored to detect possible deterioration and the onset of mechanical or electrical failures during the machine's operation. Experimental Studies: Practical experiments validate the theoretical and numerical findings and refine the vibration analysis approach. Strategy: Adequate scheduling of interventions and repairs based on the machine's condition. Continuous monitoring through vibration analysis devices. Expected Outcomes: Early detection of potential mechanical or electrical failures. Sustainable solutions to reduce vibrations and enhance the machine's performance. Improved maintenance scheduling to prevent material damage and extend the machine's lifespan. By integrating vibration monitoring and analysis with practical studies, this research aims to provide a comprehensive diagnosis and repair strategy for the cement separator machine.

Early diagnosis and revision repair of lesser tuberosity osteotomy failure after anatomic total shoulder arthroplasty

BackgroundLesser tuberosity osteotomy (LTO) in total shoulder arthroplasty (TSA) has a relatively high success rate owing to bone-to-bone healing and modern repair techniques. Failure of the LTO repair has been associated with poorer outcomes, decreased patient satisfaction, and the potential need for revision arthroplasty. Despite this, few studies closely examined outcomes for revision LTO repair in the setting of prior TSA. MethodsA retrospective review of all TSAs performed by a single surgeon from 2016 until 2023 was performed to identify all cases with LTO failure who underwent acute revision LTO repair. Baseline characteristics, postoperative complications including infection, need for revision surgery, and time to revision surgery were collected and reported on all TSA patients. All patients were followed for a minimum of 1 year after their TSA and revision LTO fixation if required. Subgroup analysis was performed on the LTO revision cohort to evaluate for potential risk factors. ResultsA total of 166 patients underwent TSA with LTO. Of these, eight patients were diagnosed with an acute LTO failure at a mean of 5.7 weeks after surgery and underwent revision LTO fixation at a mean of 6.3 weeks after surgery. At a mean follow-up of 147.9 weeks (standard deviation: 90.3; range: 52.1-284.9), seven of eight patients (87.5%) demonstrated healing of their LTO and had no complaints, complications, or reoperations at the latest follow-up. One patient developed a periprosthetic infection requiring two-stage revision. No patients in the overall cohort underwent revision shoulder arthroplasty due to subscapularis failure. ConclusionEarly identification of subscapularis failure is important to optimize outcomes of revision fixation. Use of LTO for subscapularis repair is beneficial by allowing early radiographic detection of subscapularis failure. Revision LTO repair can be successful when performed acutely and appears to minimize the need for revision shoulder arthroplasty due to subscapularis failure.

Detectable Adhesives: Nondestructive Detection of Adhesion

AbstractMetal‐to‐metal adhesives are vital across diverse sectors including automotive, aerospace, and industrial assembly. However, traditional adhesion detection methods are mainly based on the fracture mechanism, posing challenges for nondestructive detection. Here, a nondestructive method that leverages electrical signals to monitor the adhesion state of metal interfaces in real‐time is presented. The approach utilizes detectable adhesives (DA) synthesized from poly(ionic liquid) (PIL), which not only exhibit robust adhesion properties (4.9 MPa) but also function as ionic conductors. By correlating changes in capacitance and resistance with the adhesive state, the method allows for in situ monitoring of the curing process, prediction of adhesion strength, and early detection of potential failures. This dual‐sensing capability, combining electrical and mechanical aspects, enhances understanding of adhesive behavior in diverse conditions, presenting a fresh approach for digitally transforming adhesive technologies.

Automated Crack Detection in Monolithic Zirconia Crowns Using Acoustic Emission and Deep Learning Techniques.

Monolithic zirconia (MZ) crowns are widely utilized in dental restorations, particularly for substantial tooth structure loss. Inspection, tactile, and radiographic examinations can be time-consuming and error-prone, which may delay diagnosis. Consequently, an objective, automatic, and reliable process is required for identifying dental crown defects. This study aimed to explore the potential of transforming acoustic emission (AE) signals to continuous wavelet transform (CWT), combined with Conventional Neural Network (CNN) to assist in crack detection. A new CNN image segmentation model, based on multi-class semantic segmentation using Inception-ResNet-v2, was developed. Real-time detection of AE signals under loads, which induce cracking, provided significant insights into crack formation in MZ crowns. Pencil lead breaking (PLB) was used to simulate crack propagation. The CWT and CNN models were used to automate the crack classification process. The Inception-ResNet-v2 architecture with transfer learning categorized the cracks in MZ crowns into five groups: labial, palatal, incisal, left, and right. After 2000 epochs, with a learning rate of 0.0001, the model achieved an accuracy of 99.4667%, demonstrating that deep learning significantly improved the localization of cracks in MZ crowns. This development can potentially aid dentists in clinical decision-making by facilitating the early detection and prevention of crack failures.

T2-LSTM-Based AI System for Early Detection of Motor Failure in Chemical Plants

In the chemical industry, stable reactor operation is essential for consistent production. Motor failures can disrupt operations, resulting in economic losses and safety risks. Traditional monitoring methods, based on human experience and simple current monitoring, often need to be faster and more accurate. The rapid development of artificial intelligence provides powerful tools for early fault detection and maintenance. In this study, the Hotelling T2 index is used to calculate the root mean square values of the normal motor’s x, y, and z axes. A long short-term memory (LSTM) model creates a trend model for the Hotelling T2 index, determining an early warning threshold. Current anomaly detection follows the ISO 10816-1 standard, while future anomaly prediction uses the T2-LSTM trend model. Validated at a chemical plant in Southern Taiwan, the method shows 98% agreement between the predicted and actual anomalies over three months, demonstrating its effectiveness. The T2-LSTM model significantly improves the accuracy of motor fault detection, potentially reducing economic losses and improving safety in the chemical industry. Future research will focus on reducing false alarms and integrating more sensor data.

Enhanced algorithm for predictive maintenance to detect turbocharger overspeed in diesel engine rail vehicles

The reliability and safety of locomotives is crucial for efficient train operation. Repeated turbocharger failures in Israel Railways locomotive fleet have raised serious safety concerns. An investigation into the failures revealed that the uncontrolled acceleration and overspeed transients of the turbocharger shaft occurred before the failure. Early detection of potential turbocharger failures by predicting overspeed conditions is critical to the safety and reliability of locomotives. In this study, an enhanced novel algorithm for estimating the Instantaneous Angular Speed (IAS) of the turbocharger and diesel engines is presented to overcome the challenges of transient operating conditions of diesel engines. Using adaptive dephasing, the algorithm effectively isolates critical asynchronous vibration components that are crucial for the early detection of turbocharger failures. This algorithm is suitable for non-stationary speeds and is applicable to any range of rotational speed and rate of change. The algorithm requires the input of the basic parameters of the system, while all other parameters that control the process are determined automatically. The algorithm was developed specifically for the special operating conditions of diesel engines and improves predictive maintenance and operational reliability. The method is robust as it correlates between several characteristic frequencies of the rotating parts of the system. The algorithm was verified and validated with simulated and experimental data.

Machine Learning Models for Predicting Heart Failure: Unveiling Patterns and Enhancing Precision in Cardiac Risk Assessment

Purpose This study aims to evaluate the efficacy of various machine learning models in predicting heart failure incidence using medical data, focusing on the innovative aspect of a novel dataset. Unlike previous studies that predominantly examined features such as smoking status or age, this research explores novel features. The primary challenge addressed is the utilization of these new features, coupled with machine learning techniques, to accurately diagnose heart failure. Methods Five machine learning models, including logistic regression, support vector classifier, decision tree classifier, random forest classifier, and K-nearest neighbors, were applied to analyze medical data from a dataset comprising over 900 individuals. The dataset encompasses diverse parameters such as age, sex, chest pain severity, blood pressure, cholesterol levels, blood sugar levels, and electrocardiogram results, introducing a novel approach to feature selection. Results The evaluation of machine learning models unveiled varying performances in predicting heart failure. Logistic regression and support vector classifier exhibited the highest accuracy of 88%, followed by the decision tree classifier (below 85%), random forest classifier (84%), and K-nearest neighbors (82%). Additionally, the analysis revealed a balanced dataset distribution and highlighted sex-based disparities in heart failure incidence, along with significant correlations with factors such as age, chest pain severity, blood glucose levels, and physical activity. Conclusions The findings underscore the potential of integrating multiple machine learning models for early detection of heart failure, leveraging the inclusion of novel features in the dataset. However, careful model selection is crucial to account for discrepancies in accuracy among different models, emphasizing the importance of tailoring approaches based on specific project requirements.

COMPARISON OF CORONA DISCHARGE IDENTIFICATION IN 20 kV CUBICLES BASED ON VOLTAGE AND NOISE USING ED, HMM, AND FCM

Phenomena such as corona discharge (CD) still occurs in many electrical systems in Indonesia. As a first step for early detection of insulation failure. Identification of CD acoustic in this study namely clustering based on voltage and based on noise. So that the CD acoustic classification is set into 3 clusters. In addition, this study also classifies CD acoustic based on noise with three clusters, namely pure CD, CD with noise, and pure noise. Clustering was performed using the linear predictive coding (LPC) method as feature extraction, then a comparison of pattern matching results of feature extraction was performed using Euclidean distance (ED), hidden Markov model (HMM) and fuzzy cluster mean (FCM). The temperature in the cubical is between 27.5 ℃ - 35.3 ℃ and humidity ranges from 70% - 95%. The results of clustering accuracy on the average base voltage using the ED, HMM and FCM methods were obtained respectively 100%, 100% 93.93% for training data and 80.74%, 84.44%, 80.55% for testing data. While the results of the average base noise clustering accuracy using the ED, HMM and FCM methods were obtained respectively 100%, 100%, 94.69% for training data and 100%, 100%, 100% for testing data.