Risk Early Detection Research Articles

Untargeted metabolomics to detect and identify plasma metabolic signatures associated with intracranial aneurysm and its rupture.

The biological basis for metabolic differences between unruptured and ruptured intracranial aneurysm (UIA and RIA) populations and their potential role in triggering IA rupture remain unclear. The aim of this study was to analyze the plasma metabolic profiles of patients with UIA and RIA using an untargeted metabolomic approach and to develop a model for early rupture classification. Plasma samples were analyzed using an ultra-high-performance liquid chromatography high-resolution tandem mass spectrometry-based platform. Least absolute shrinkage and selection operator regression and random forest machine learning methods were employed for metabolite feature selection and predictive model construction. Among 49 differential plasma metabolites identified, 31 were increased and 18 were decreased in the plasma of RIA patients. Five key metabolites-canrenone, piperine, 1-methyladenosine, betaine, and trigonelline-were identified as having strong potential to discriminate between UIA and RIA patients. This combination of metabolites demonstrated high diagnostic accuracy, with an area under the curve exceeding 0.95 in both the training and validation datasets. Our finding highlights the significance of plasma metabolites as potential biomarkers for early detection of IA rupture risk, offering new insights for clinical practice and future research on IA management.

PREDICTIVE MARKERS FOR ADVERSE PREGNANCY OUTCOMES: INSIGHTS FROM A PROSPECTIVE COHORT STUDY ON MATERNAL FACTORS, BIOMARKERS, AND UTERINE ARTERY DOPPLER RESULTS

Objective: Effective prediction tools are necessary for better outcomes when it comes to pregnancy-related complications such as intrauterine growth restriction (IUGR), pregnancy-induced hypertension (PIH), and premature birth. In order to improve early risk diagnosis and treatment, this study investigates relationships between maternal variables, first-trimester biomarkers, and second-trimester uterine artery Doppler findings. Methods: Correlations between demographic characteristics, maternal dual test indicators (serum beta-HCG, serum PAPPA), and uterine artery Doppler tests were examined in a prospective cohort study including 500 pregnant women. Statistical studies evaluated correlations with IUGR, PIH, and premature birth. Results: Serum beta-HCG levels below the 5th percentile correlated significantly with preterm birth (RR 2.3131, p = 0.0288). Low serum PAPP-A levels (<5th percentile) associated with PIH (RR 2.1447, p = 0.0204) and IUGR (RR 2.0953, p = 0.0002). Uterine artery Doppler indices (>0.58 RI) demonstrated associations with PIH (RR 2.2448) and IUGR (RR 1.6293). Diastolic notching correlated with preterm birth, PIH, and IUGR. Conclusion: The potential of serum beta-HCG, PAPP-A, and uterine artery Doppler indices as useful predictors of unfavorable pregnancy outcomes is highlighted by this study, which also highlights their use in early risk detection.

Application of artificial intelligence and machine learning for risk stratification acute kidney injury among hematopoietic stem cell transplantation patients: PCRRTICONIC AI Initiative Group Meeting Proceedings.

Acute kidney injury (AKI) is a frequent, severe complication of hematopoietic stem cell transplantation (HSCT) and is associated with an increased risk of morbidity and mortality. Recent advances in artificial intelligence (AI) and machine learning (ML) have showcased their proficiency in predicting AKI, projecting disease progression, and accurately identifying underlying etiologies. This review examines the central aspects of AKI post-HSCT, veno-occlusive disease (VOD) in HSCT recipients, discusses present-day applications of artificial intelligence in AKI, and introduces a proposed ML framework for the early detection of AKI risk.

Micro-Incubator Protocol for Testing a CO2 Sensor for Early Warning of Spontaneous Combustion

A protocol for detecting the potential occurrence of spontaneous combustion (SC) in stored cottonseeds and peanuts using a micro-incubator is described. The protocol indicates how to quantify CO2 production rates and final CO2 levels in wet versus dry cottonseed and peanut samples, which can provide crucial data for the early detection of SC risk in storage facilities. The experimental design utilizes a micro-incubator to simulate conditions found in large bulk crop storage. Parameters monitored include CO2 concentration, temperature, and relative humidity. The protocol includes preparation methods, experimental procedures for both control (dry) and wet seed tests, and test termination criteria that allow for safe experimentation of likely pathogenic fungi. The protocol has three replicates for wet and dry conditions. The protocol is intended to facilitate future experimental studies and ultimately contribute to the development of a consistently reliable early warning fire detection system for SC in cottonseed and peanut warehouse facilities. A consistently reliable fire detection system would address a critical need in the cotton and peanut industry for improved fire risk management and insurability of storage facilities.

Do sociodemographic and health predictors affect the non-insulin-based insulin resistance index? A cross-sectional study.

Insulin resistance (IR) is considered a risk factor for cardiovascular diseases (CVD). Therefore, early diagnosis of IR is clinically significant for primary and secondary CVD prevention initiatives. In addition, non-insulin metabolic indices may be useful for diagnosing IR. The first objective was to estimate the triglyceride and glucose (TyG) index and the metabolic score for insulin resistance (METS-IR) index values in a local community with high social deprivation and increased cardiovascular risk according to the Systematic Coronary Risk Evaluation scale. The second objective was to identify significant sociodemographic and health predictors for the TyG index and METS-IR index. This cross-sectional study was conducted in the local community of Janów district in eastern Poland and consisted of 2 stages. The 1st stage involved basic research (n = 4,040), while the 2nd stage involved enhanced diagnostics (n = 2,657). Data from the 2nd stage was used for the analyses. Anthropometric and physiological measurements were taken, blood was drawn for laboratory tests, selected sociodemographic and health variables were evaluated, and the TyG index and METS-IR index were calculated. The mean TyG index score in the study group was 8.65 (±0.58), and the mean METS-IR index score was 41.45 (±9.02). Both indices were significantly associated with age, male sex, smoking, and systolic blood pressure (SBP) in a multivariable model. In addition, alcohol consumption and body mass index (BMI) were significantly correlated with the TyG index, whereas education was significantly associated with the METS-IR index. Our results show the association between IR and sociodemographic and health variables in a group with a high social deprivation rate and increased cardiovascular risk. Early detection of cardiometabolic risk is important for both primary and secondary CVD prevention. In primary healthcare, this can be accomplished through surrogate markers of IR.

Explainable machine learning model for predicting the risk of significant liver fibrosis in patients with diabetic retinopathy.

Diabetic retinopathy (DR), a prevalent complication in patients with type 2 diabetes, has attracted increasing attention. Recent studies have explored a plausible association between retinopathy and significant liver fibrosis. The aim of this investigation was to develop a sophisticated machine learning (ML) model, leveraging comprehensive clinical datasets, to forecast the likelihood of significant liver fibrosis in patients with retinopathy and to interpret the ML model by applying the SHapley Additive exPlanations (SHAP) method. This inquiry was based on data from the National Health and Nutrition Examination Survey 2005-2008 cohort. Utilizing the Fibrosis-4 index (FIB-4), liver fibrosis was stratified across a spectrum of grades (F0-F4). The severity of retinopathy was determined using retinal imaging and segmented into four discrete gradations. A ten-fold cross-validation approach was used to gauge the propensity towards liver fibrosis. Eight ML methodologies were used: Extreme Gradient Boosting, Random Forest, multilayer perceptron, Support Vector Machines, Logistic Regression (LR), Plain Bayes, Decision Tree, and k-nearest neighbors. The efficacy of these models was gauged using metrics, such as the area under the curve (AUC). The SHAP method was deployed to unravel the intricacies of feature importance and explicate the inner workings of the ML model. The analysis included 5,364 participants, of whom 2,116 (39.45%) exhibited notable liver fibrosis. Following random allocation, 3,754 individuals were assigned to the training set and 1,610 were allocated to the validation cohort. Nine variables were curated for integration into the ML model. Among the eight ML models scrutinized, the LR model attained zenith in both AUC (0.867, 95% CI: 0.855-0.878) and F1 score (0.749, 95% CI: 0.732-0.767). In internal validation, this model sustained its superiority, with an AUC of 0.850 and an F1 score of 0.736, surpassing all other ML models. The SHAP methodology unveils the foremost factors through importance ranking. Sophisticated ML models were crafted using clinical data to discern the propensity for significant liver fibrosis in patients with retinopathy and to intervene early. Improved early detection of liver fibrosis risk in retinopathy patients enhances clinical intervention outcomes.

KEY STAGES AND INNOVATIVE APPROACHES IN RISK MANAGEMENT UNDER UNCERTAINTY

The purpose of the article is to analyze in detail the process of risk management at enterprises, in particular, its key stages. In addition, the article aims at studying the current instruments of bankruptcy risk management which can be implemented in the modern economy. The relevance of the article is stipulated by the need to improve approaches to risk management in today's dynamic business environment, where enterprises are constantly facing financial and operational threats. Of particular importance is bankruptcy risk management, since economic instability and high level of competition require effective mechanisms to protect financial stability. The following methods are used in the study: the method of analysis and synthesis - for a structured consideration of the stages of the risk management process, identifying the relationships between them and forming a holistic picture of management actions at each stage; the method of logical generalization - for formulating general conclusions and recommendations on the stages and tools of risk management based on the analysis of literature and practical examples. The result of the study is to determine the essential characteristics of the main stages of the enterprise risk management process and the relevant tools for managing the bankruptcy risk. This includes: a structured description of the key stages of risk management – from risk identification and assessment to monitoring and control, which ensures a systematic approach to responding to threats; analysis of current tools for managing bankruptcy risk – identification of tools that facilitate early detection of risks and support the financial stability of the enterprise. The practical value of the article lies in providing enterprises with a clear description of the risk management process, which includes the main stages from identification to monitoring and control, allowing companies to take a more systematic approach to risk management and reducing the likelihood of negative financial consequences. The use of the current tools for managing bankruptcy risk described in the article provides an opportunity to quickly identify early signs of financial instability, which helps to maintain their financial stability. In addition, the proposed recommendations can be integrated into the enterprise management system, creating a flexible and adaptive model to maintain stable development in the face of economic uncertainty.

The Genetic Basis of Sudden Cardiac Death: From Diagnosis to Emerging Genetic Therapies.

Sudden cardiac death (SCD) is an abrupt, tragic manifestation of a number of cardiovascular diseases, primarily ion channelopathies and heritable cardiomyopathies. Because these diseases are heritable, genetics play a key role in the diagnosis and management of SCD-predisposing diseases. Historically, genetics have been used to confirm a diagnosis and identify at-risk family members, but a deeper understanding of the genetic causes of SCD could pave the way for individualized therapy, early risk detection, and a transformative shift toward genetically informed therapies. This review focuses on the evolving genetic landscape of SCD-predisposing diseases, the current state of gene therapy and therapeutic development, and the promise of using predictive genetics to identify individuals at risk of SCD.

Improving health awareness with real-time monitoring through a three-dimensional visualized digital health avatar

IntroductionThe use of modern technologies has become crucial for enhancing people's awareness of health problems. By early health risk detection, there will be better treatment outcomes, the severity of illness will decrease, and costs for treatment will also reduce. Performing routine checkups could help patients feel less anxious about their health in the future. In this study, the innovation of "Digital Health Avatar" enables users to monitor physical changes, raise awareness of medical conditions, and encourage healthy behaviors by visualizing health status as a 3D figure. MethodsHealth data were collected using medical devices like blood test strips, body composition meters, and automatic blood pressure monitors. Advanced algorithms, such as computer vision and natural language processing (NLP), were used to process these collected data and produced a three-dimensional avatar that indicated the user's health status. User satisfaction survey on using the health avatar system was assessed through a survey of 61 participants. ResultsHealth avatar system successfully generate the data and display the measurement results on the health report page of the system. Users can easily check and record their physiological conditions through the avatar. Moreover, users showed satisfaction on the use of the health avatar system and its effectiveness in health check-ups in the survey. ConclusionsThe 'Digital Health Avatar' has the potential to significantly promote individual well-being and health awareness. Its development will be improved by user feedback and continued study, ensuring it becomes an efficient tool for promoting healthier lifestyles.

Quantitative biomechanical analysis in validating a video-based model to remotely assess physical frailty: a potential solution to telehealth and globalized remote-patient monitoring.

Assessing physical frailty (PF) is vital for early risk detection, tailored interventions, preventive care, and efficient healthcare planning. However, traditional PF assessments are often impractical, requiring clinic visits and significant resources. We introduce a video-based frailty meter (vFM) that utilizes machine learning (ML) to assess PF indicators from a 20s exercise, facilitating remote and efficient healthcare planning. This study validates the vFM against a sensor-based frailty meter (sFM) through elbow flexion and extension exercises recorded via webcam and video conferencing app. We developed the vFM using Google's MediaPipe ML model to track elbow motion during a 20s elbow flexion and extension exercise, recorded via a standard webcam. To validate vFM, 65 participants aged 20-85 performed the exercise under single-task and dual-task conditions, the latter including counting backward from a random two-digit number. We analyzed elbow angular velocity to extract frailty indicators-slowness, weakness, rigidity, exhaustion, and unsteadiness-and compared these with sFM results using intraclass correlation coefficient analysis and Bland-Altman plots. The vFM results demonstrated high precision (0.00-7.14%) and low bias (0.00-0.09%), showing excellent agreement with sFM outcomes (ICC(2,1): 0.973-0.999), unaffected by clothing color or environmental factors. The vFM offers a quick, accurate method for remote PF assessment, surpassing previous video-based frailty assessments in accuracy and environmental robustness, particularly in estimating elbow motion as a surrogate for the 'rigidity' phenotype. This innovation simplifies PF assessments for telehealth applications, promising advancements in preventive care and healthcare planning without the need for sensors or specialized infrastructure.

Relationship between autonomic and peripheral neuropathies and cardiovascular outcomes in diabetes

This review explores the complex relationship between diabetic neuropathy and cardiovascular disease (CVD). Neuropathy, a common complication of type 1 and type 2 diabetes, is divided into autonomic and peripheral types, each impacting cardiovascular health. Cardiovascular autonomic neuropathy, a form of autonomic neuropathy, is associated with various CVD complications, including arrhythmias, impaired nocturnal blood pressure regulation, and increased mortality. The prevalence of cardiovascular autonomic neuropathy varies depending on the type and duration of diabetes and is influenced by factors like glycemic control and metabolic stress. Peripheral polyneuropathy, which is often linked to diabetic foot disease, is also correlated with elevated CVD risk; research suggests shared pathophysiological mechanisms between peripheral neuropathy and cardiovascular conditions. Screening for neuropathies using tools like the Michigan Neuropathy Screening Instrument and heart rate variability analyses can facilitate early detection of CVD risk. Additionally, emerging technologies, like deep learning models, have demonstrated promise in detecting early cardiovascular patterns associated with autonomic neuropathy through electrocardiogram analysis. These findings underscore the value of integrating novel diagnostic approaches for early intervention. As CVD represents a leading cause of death among patients with diabetes, this article emphasizes the need for thorough assessment and proactive management of neuropathy to mitigate cardiovascular risk. The review recommends a multidisciplinary approach to diabetes care, including early screening, accurate risk stratification, and targeted therapeutic strategies to prevent or slow the progression of CVD in patients with autonomic and peripheral neuropathies. Further research is warranted to clarify the optimal intervention strategies for reducing CVD risk in these populations.

Next-generation public health surveillance: extreme heat event prediction and monitoring system

Abstract Background Extreme Heat Events (EHEs) are a growing threat to public health. The increase in the frequency of occurrence of once rarer EHEs and the rise in their average temperatures are dangerously drastic for public health outcomes. Despite this, existing public health surveillance (PHS) systems fail to leverage IoT and AI technologies to facilitate real-time, continuous monitoring of EHE indicators and its associated health risks. This study closes this gap by proposing a comprehensive PHS system that can, in real-time monitor and predict EHE indicators to provide timely alerts to public health authorities. Methods The EHE PHS system collects EHE detection metrics, including indoor temperature and humidity levels, from IoT sensors and thermostats to map them across Canada, primarily focusing on low-income communities. The system also integrates historical climate data (surface temperature, humidity, wind speed and direction, and air quality indicators) from Environment Canada. The system uses the data to train initial prediction models including CNN, LSTM and GNN. The validated model will be integrated into the system, enabling real-time EHE prediction. The output will be displayed in user-friendly visualizations on the EHE PHS system’s dashboard capabilities. Results The system allows for the analysis of real-time data through dashboards and provides alerts when certain indicators (e.g. excessive or prolonged heat) detrimental to public health outcomes are detected. The alerts enable valuable lead time for public health authorities to implement proactive measures, such as issuing heat advisories and deploying resources to vulnerable areas. Conclusions The EHE PHS system will serve as a blueprint for global public health researchers, utilizing IoT and AI technologies for proactive crisis prevention. This knowledge will inform the development of heat-resilient policies and set a precedent for global public health crisis prevention. Key messages • The proposed EHE PHS system uses AI and IoT technologies, to enhance EHE prediction, risk identification, and real-time monitoring for effective public health interventions. • By integrating advanced predictive models and environmental data, the system facilitates early detection of EHE risk, which can significantly mitigate the health impact on vulnerable populations.

Improving early mortality risk detection in light-chain cardiac amyloidosis patients with routine echocardiographic indicators and mayo staging

Abstract Background Light-chain cardiac amyloidosis (AL-CA) is a fatal cardiomyopathy caused by the deposition of monoclonal immunoglobulin light-chain in the cardiac fibers, conduction system, valves, and other parts of the heart. The Mayo 2004 staging system is widely used to assess the prognosis of AL-CA. Those in the highest-risk categories, Mayo 2004 stage IIIb, exhibit extremely poor responses to conventional treatment regimens, resulting in high early mortality rates. However, within the same stage, prognostic outcomes among patients can still vary significantly. Hence, a more detailed stratification of high-risk patients is crucial for pinpointing those at extreme risk. Objective To investigate whether conventional echocardiographic measurements can enhance the identification of high-risk patients with early mortality in AL-CA on the basis of existing risk stratification. Methods Continuous enrollment of patients diagnosed with AL-CA at our center from May 2020 to December 2022. Clinical data, echocardiography, and follow-up results of the patients were collected. Logistic regression analyses were used to identify risk factors for early mortality, with risk factor thresholds calculated using Receiver Operating Characteristic (ROC) curves. Kaplan-Meier survival analysis was employed to assess endpoint events. The diagnostic efficacy of the model was evaluated using the area under the ROC curve and the Integrated Discrimination Improvement (IDI). Results A total of 76 patients were included with an average age of 59±10 years. Among them, 51 were male (67.1%). The median follow-up duration was 10 months (ranging from 5 to 20 months). Early mortality, defined as death within 6 months, occurred in 20 patients (26.3%). Twenty-three patients were categorized under the Mayo 2004 stage IIIb (30.3%). The 6-month mortality rate for patients in the Mayo 2004 stage IIIb was 56.5%. The sensitivity of early diastolic transmitral flow velocity to early diastolic mitral annular tissue velocity ratio divided left ventricular ejection fraction [(E/e’) /LVEF] in predicting early mortality in patients with AL-CA is 63%, and the specificity is 92%.When compared to the Mayo 2004 stage IIIb alone, (E/e')/LVEF≥0.5 combined with the Mayo 2004 stage IIIb had an area under the curve of 0.731 and 0.824, respectively, in the ROC curve. The IDI was 0.113 (95% CI: 0.013-0.213, P=0.026), representing an 11.3% enhancement in the predictive value of early mortality in AL-CA patients. Conclusion Routine echocardiography derived E/e' to LVEF ratio offered added prognostic value for early mortality beyond Mayo staging.Kaplan-Meier survival curve

Prediction of gastrointestinal bleeding hospitalization risk in hemodialysis using machine learning

BackgroundGastrointestinal bleeding (GIB) is a clinical challenge in kidney failure. INSPIRE group assessed if machine learning could determine a hemodialysis (HD) patient’s 180-day GIB hospitalization risk.MethodsAn eXtreme Gradient Boosting (XGBoost) and logistic regression model were developed using an HD dataset in United States (2017–2020). Patient data was randomly split (50% training, 30% validation, and 20% testing). HD treatments ≤ 180 days before GIB hospitalization were classified as positive observations; others were negative. Models considered 1,303 exposures/covariates. Performance was measured using unseen testing data.ResultsIncidence of 180-day GIB hospitalization was 1.18% in HD population (n = 451,579), and 1.12% in testing dataset (n = 38,853). XGBoost showed area under the receiver operating curve (AUROC) = 0.74 (95% confidence interval (CI) 0.72, 0.76) versus logistic regression showed AUROC = 0.68 (95% CI 0.66, 0.71). Sensitivity and specificity were 65.3% (60.9, 69.7) and 68.0% (67.6, 68.5) for XGBoost versus 68.9% (64.7, 73.0) and 57.0% (56.5, 57.5) for logistic regression, respectively. Associations in exposures were consistent for many factors. Both models showed GIB hospitalization risk was associated with older age, disturbances in anemia/iron indices, recent all-cause hospitalizations, and bone mineral metabolism markers. XGBoost showed high importance on outcome prediction for serum 25 hydroxy (25OH) vitamin D levels, while logistic regression showed high importance for parathyroid hormone (PTH) levels.ConclusionsMachine learning can be considered for early detection of GIB event risk in HD. XGBoost outperforms logistic regression, yet both appear suitable. External and prospective validation of these models is needed. Association between bone mineral metabolism markers and GIB events was unexpected and warrants investigation.Trial registrationThis retrospective analysis of real-world data was not a prospective clinical trial and registration is not applicable.Graphical

Research on Electric Vehicle Powertrain Systems Based on Digital Twin Technology

As a critical component of electric vehicles, the powertrain has a significant impact on the overall performance of vehicles. In addressing the challenge of lengthy testing cycles, this study develops a para model of the powertrain, utilizing digital twin (DT) technology, thereby establishing a framework for simulation testing of multi-controller intermodulation. We establish functional definition coverage testing by designing specific functional requirement use cases, and we validate the failure mechanism via fault injection use cases. The results indicate that the DT testing platform can effectively simulate the operational interactions among various controllers within the powertrain system. In comparison to traditional field testing, the digital twin-based testing methodology offers enhanced operational efficiency and allows for the examination of testing conditions that are impractical to implement in real vehicles, particularly in the context of fault injection testing, thus facilitating the early detection of potential safety risks within the system. The advancement of this technical solution holds significant practical implications for the future mass production and development of electric vehicles.

Clinical Features and Risk Factors for Outcome in Hemodialysis Patients with COVID-19 after Complete Liberalization of Epidemic Control in China

Introduction: Patients undergoing hemodialysis (HD) are highly vulnerable during the COVID-19 pandemic. We aimed to investigate the risk factors associated with the severity of COVID-19 and death after the complete liberalization of epidemic control in China. Methods: We followed the outcomes of the HD patients of Central Hospital of Dalian University of Technology, from December 6, 2022, to January 8, 2023. The non-contrast-enhanced chest computed tomography (CT) was performed on all COVID-19-infected hospitalized patients. We recorded the patient’s clinical characteristics, demographic features, vaccination history, treatments, and lung lesions. Odds ratios and 95% confidence intervals were calculated using logistic regression models to identify independent risk factors for COVID-19-related severity and mortality. Results: This study included a total of 858 HD patients, of which 660 were infected with COVID-19. The mean age was (55.61 ± 14.61) years, with a median (interquartile range) dialysis duration of 44.5 (69.5) months. Over half (60%) of the study participants were male, and the majority had hypertension as a comorbidity. Multivariable analysis revealed that age, pre-dialysis diastolic pressure, fever, white blood cell (WBC) count, potassium, β2-microglobulin level, and calcium were independent risk factors for disease severity, while platelets, urea nitrogen, serum chlorine and creatinine were identified as independent protective factors. Furthermore, total iron-binding capacity and vaccination were found to be independent protective factors against mortality, and WBC count was an independent risk factor for in-hospital mortality (p < 0.05). The most frequent CT finding among hospitalized patients with chest symptoms was patchy shadow or pleural effusion, observed in 64.8% of cases. More than half of the patients exhibited bilateral lung lesions, and over 60% involved two or more lobes. Conclusion: The majority of HD patients are susceptible to COVID-19. Demographic, clinical features, and laboratory indicators can be used to predict the severity and mortality associated with COVID-19. Our findings will assist clinicians in identifying markers for the early detection of high mortality risk in HD patients with COVID-19.

AI driven interpretable deep learning based fetal health classification

In this study, a deep learning model is proposed for the classification of fetal health into 3 categories: Normal, suspect, and pathological. The primary objective is to utilize the power of deep learning to improve the efficiency and effectiveness of diagnostic processes. A deep neural network (DNN) model is proposed for fetal health analysis using data obtained from Cardiotocography (CTG). A dataset containing 21 attributes is used to carry out this work. The model incorporates multiple hidden layers, augmented with batch normalization and dropout layers for improved generalization. This study assesses the model's interpretation ability in fetal health classification using explainable deep learning. This enhances transparency in decision-making of the classifier model by leveraging feature importance and feature saliency analysis, fostering trust and facilitating the clinical adoption of fetal health assessments. Our proposed model demonstrates a remarkable performance with 0.99 accuracy, 0.93 sensitivity, 0.93 specificity, 0.96 AUC, 0.93 precision, and 0.93 F1 scores in classifying fetal health. We also performed comparative analysis with six other models including Logistic Regression, KNN, SVM, Naive Bayes, Random Forest, and Gradient Boosting to assess and compare the effectiveness of our model and the accuracies of 0.89, 0.88, 0.90, 081, 0.93, and 0.93 were achieved respectively by these baseline models. The results revealed that our proposed model outperformed all the baseline models in terms of accuracy. This indicates the potential of deep learning in improving fetal health assessment and contributing to the field of obstetrics by providing a robust tool for early risk detection.

Prediction of adolescent depression from prenatal and childhood data from ALSPAC using machine learning

Depression is a major cause of disability and mortality for young people worldwide and is typically first diagnosed during adolescence. In this work, we present a machine learning framework to predict adolescent depression occurring between ages 12 and 18 years using environmental, biological, and lifestyle features of the child, mother, and partner from the child’s prenatal period to age 10 years using data from 8467 participants enrolled in the Avon Longitudinal Study of Parents and Children (ALSPAC). We trained and compared several cross-sectional and longitudinal machine learning techniques and found the resulting models predicted adolescent depression with recall (0.59 ± 0.20), specificity (0.61 ± 0.17), and accuracy (0.64 ± 0.13), using on average 39 out of the 885 total features (4.4%) included in the models. The leading informative features in our predictive models of adolescent depression were female sex, parental depression and anxiety, and exposure to stressful events or environments. This work demonstrates how using a broad array of evidence-driven predictors from early in life can inform the development of preventative decision support tools to assist in the early detection of risk for mental illness.

Identifying food safety risks with a novel digitally-driven food safety early warning tool – A retrospective study on the pesticide ethylene oxide

Foodborne diseases present a major global health challenge, with 600 million annual cases and 420,000 deaths worldwide in 2023 reported by the World Health Organization, underscoring the critical need for early risk detection and swift measures. Novel solutions for early risk detection in food are emerging due to artificial intelligence-based data models. By applying diverse algorithms and ontologies in data processing, the continually expanding amount of available data can be harnessed in a precise manner. To assess the efficacy of such technologies in early risk detection, we evaluated whether the risk to exceed a legal limit for ethylene oxide – specifically in sesame seeds – could have been identified sooner with the assistance of a commercially available Artificial Intelligence (AI)-based platform. The non-compliance of sesame seeds led to various product recalls in the year 2020. The result of this retrospective case study shows that the first indirect indications of the issue started to emerge from the year 2018 with initial Rapid Alert System for Food and Feed (RASFF) notification of ethylene oxide limit value exceedances in black pepper powder. Based on these promising findings, the subsequent challenge is to develop a methodology for systematically categorizing and evaluating similar risks in the light of the exponentially growing volume of accessible data.

An Ensemble Learning Algorithm with Hyperparameter Optimization (ELAHO) Model for Early Detection of Maternal Health Risk (MHR) Level Using Machine Learning

Despite the advancement in the healthcare system, maternal health risk remains high, which is the most challenging aspect nowadays. There is a need to develop an effective model for early detection, monitoring, and prediction of maternal health risk levels during pregnancy. The machine learning intelligence model has proven its effectiveness and robustness in providing accurate and reliable prediction, analysis, and interpretation of medical data, reducing several risk factors for early diagnosis in healthcare. In this research work, we proposed an ensemble learning algorithm with a hyperparameter optimization (ELAHO) model using machine learning algorithms to improve its robustness, effectiveness, and model performance. The proposed method uses a hybrid model of logistic regression and support vector machines (LG-SVM) to predict maternal health risk levels during pregnancy. The method utilized Python software for training, testing, and validation. We evaluated the performance of our proposed model using accuracy, precision, sensitivity, f1-score, and ROC-AUC score. The proposed models outperformed the conventional models and achieved 100% predictive accuracy. The proposed approach has the potential to be adapted as an intelligence-monitoring system for early medical diagnosis during pregnancy. The proposed techniques will help medical professionals make quick decisions accurately and enhance monitoring to improve the level of care offered to pregnant mothers and their unborn children.