Monitoring Of Parameters Research Articles

Assessment of lipid peroxidation and total antioxidant capacity in patients with breast cancer.

Breast cancer (BC), a disease in which abnormal breast cells grow out of control and form tumors, is a prevalent life-threatening disease worldwide. Oxidative stress has been implicated in the development and progression of various cancers, including BC. Assessing lipid peroxidation and overall antioxidant status in BC offers valuable information on disease progression, patient prognosis, and the effectiveness of therapeutic options. A total of 150 women were categorized into three groups: normal, benign mass, and BC. Participants were selected and evaluated at the cancer clinic; fasting blood samples were collected, and total antioxidant capacity (TAC), oxidized low-density lipoprotein (Ox-LDL), cancer antigen (CA) 15-3, and carcinoembryonic antigen (CEA) were measured. Subsequently, statistical analysis was performed to compare the levels of these parameters in different groups and examine the analytical performance of TAC and Ox-LDL in BC. In patients with malignancy, the serum level of TAC was significantly decreased compared with the benign group (8.3 U/mL and 16.04 U/mL, respectively) (P < 0.001). Healthy controls exhibited higher levels of TAC (43.4 U/mL). The levels of Ox-LDL in BC were significantly increased in both malignant and benign groups (3,831 pg/mL and 1,234 pg/mL, respectively) compared with normal controls (682 pg/mL) (P < 0.001). CEA and CA15-3 were drastically increased in the BC groups compared with the control group. A significant area under the curve was observed in the receiver operating characteristic (ROC) curve analysis for TAC (0.975, P < 0.001) and Ox-LDL (0.986, P < 0.001). This study revealed that patients with BC had lower TAC and higher Ox-LDL serum levels, indicating elevated oxidative stress. These levels may serve as promising monitoring parameters in BC.

The relationship between body mass index changes and mortality in geriatric peritoneal dialysis patients: a case-control study.

The prevalence of chronic kidney disease (CKD) is increasing, reflecting the rising incidence of chronic diseases. With the continuous growth of the global geriatric population, a significant portion of individuals with CKD consists of those aged over 65. Regardless of the chosen treatment method, protein-energy loss in patients undergoing renal replacement therapy (RRT) has been associated with elevated morbidity and mortality rates. This is a retrospective, single-center study of incident adult PD patients on peritoneal dialysis (PD) from 1998 to 2022. We aimed to compare the survival outcomes of geriatric patients on PD with changing BMI measurements. In the geriatric patient group exhibiting a reduced BMI after dialysis initiation, BMI significantly and negatively influenced survival (p = 0.01). The negative effect of BMI on survival was independent of known risk factors such as diabetes mellitus, a history of cardiovascular disease, gender, residual renal function, and history of hemodialysis before peritoneal dialysis (HD before PD) (p = 0.04). Although BMI is easy and extensively measured, it is not considered the perfect monitoring parameter for dialysis patients. However, regular follow-up of BMI, especially in geriatric cases, can be a guiding tool for estimating patients' prognoses.

Monitoring spatiotemporal changes in global change drivers and their effects on semiarid woodlands and forests - fieldwork protocol

Training schools play a vital role in COST actions, particularly for young researchers, as they provide opportunities to visit international laboratories and learn new methodologies. In May 2024, CLEANFOREST organized its first training school, Monitoring Spatiotemporal Changes in Global Change Drivers and Their Effects on Semiarid Woodlands and Forests, held at the Faculty of Science of the Universidade de Lisboa. The training school included a field trip designed to explore global change drivers and their impacts on semiarid woodlands and forests. Participants engaged in hands-on activities to understand how forest ecosystems interact with key global change factors such as air quality and climate change. They were introduced to various monitoring techniques and parameters for assessing forest health, including ecosystem fluxes, tree physiology, mortality, and regeneration. Additionally, participants examined plant biodiversity and functional ecology, focusing on lichens and their connection to air quality. Soil-related topics, such as the characterization of forest soils and their physico-chemical properties, were also addressed. Participants applied these methodologies in real-world scenarios, conducting measurements in different grazing management settings to assess their effects on tree growth, biodiversity, and soil properties. They then processed and analyzed the collected data, synthesizing their results to develop recommendations for sustainable forest management in the context of global change. This paper presents the field trip protocol used at Companhia das Lezírias, where simplified versions of established methodologies for sampling various ecosystem components were employed. The protocol provides a valuable reference for replicating similar studies, ensuring consistency in methodologies for future training and monitoring efforts.

Natural gas production process fault localization based on direct transfer entropy with adaptive lag

Abstract Natural gas production equipment has complex structures, numerous monitoring parameters, and intricate correlation relationships, making it challenging to trace the source of faults for abnormal events. This paper proposes a fault localization method for natural gas production processes based on direct transfer entropy with adaptive lag (AL-DTE). Firstly, a variable set is screened based on the contribution plot. To enhance the adaptability to multiple operating conditions and reduce the reliance on experience, this paper integrates the adaptively to DTE and proposed AL-DTE. A causal analysis is then constructed and the causality graph is utilized to visualize the abnormal propagation path and identify the root cause of the fault. The proposed method can locate abnormal and faulty sub-equipment without relying on historical experience, enabling rapid localization of unknown faults. The effectiveness of the method is verified through simulation data and real faults of a triethylene glycol (TEG) dehydration equipment.&amp;#xD;

Bibliometric Analysis of the Zero Energy Neighborhood Concept: Developments and Key Trends in the Literature

This study presents a bibliometric analysis of 596 documents obtained through a literature search on the concept of "zero energy neighborhood" in the Web of Science (WoS) database in November 2024. The analysis was conducted using Vosviewer software, identifying two main clusters: Energy Efficiency and Monitoring Parameters, and Building Energy Consumption and Carbon Reduction. The first cluster encompasses key themes related to measuring energy efficiency and monitoring parameters, while the second highlights sustainable solutions aimed at reducing buildings' energy consumption, energy demand, and carbon emissions. The study analyzes collaboration networks among authors, institutions, and countries, identifying influential researchers and international partnerships in this field. Additionally, keyword and thematic analyses reveal that technological and conceptual focuses, such as energy monitoring, renewable energy integration, and carbon reduction, are increasingly prioritized in the development of zero energy neighborhoods. The study’s findings contribute to strategies that support the broader application of zero energy neighborhoods within urban planning and sustainable energy policies. It also concludes that further academic collaboration and exploration of new thematic areas on zero energy neighborhoods are needed. This study aims to make a valuable contribution to the knowledge base in sustainable urban planning

Optimizing tacrolimus therapeutic drug monitoring in Tunisian kidney transplant recipients: exploring the variability in bioavailability and the correlation between pharmacokinetic parameters.

While the existing literature extensively covers the topic of tacrolimus variability, it remains crucial to gather data that are tailored to the Tunisian population. Our primary goal was to assess the variability in tacrolimus bioavailability using the Cp(0)/weight dosage ratio in Tunisian kidney transplant patients. We also aimed to determine the correlations between blood trough level (Cp(0)) and the area under the concentration-time curve (AUC0-12 h) in this cohort. This retrospective study included patients treated with oral tacrolimus for the prevention of organ rejection between 2009 and 2023. The correlation between parameters was analyzed through a Pearson coefficient and a regression model. We assessed the inter- and intraindividual variability by calculating the coefficient of variation for patients with at least three samples. Analysis of 2,124 samples revealed a weak correlation (R=0.121) between Cp(0) and weight dosage. We found that 79.3 % of patients exhibited high variability in the Cp(0)/weight dosage ratio. A strong correlation (R=0.797) was found between Cp(0) and the AUC0-12 h. We also found that47.6 % of patients showed high variability in the AUC0-12 h/Cp(0) ratio. This study underscores the necessity for individualized therapeutic drug monitoring in Tunisian kidney transplant recipients due to the high variability in the Cp(0)/weight dosage ratio. The AUC0-12 h/Cp(0) ratio is proposed as a more consistent parameter for therapeutic drug monitoring, offering potential improvements in tacrolimus therapy management.

Feasibility of three dimensional and strain transthoracic echocardiography in a single-centre dedicated NHS cardio-oncology clinic

BackgroundFollowing the publication of international cardio-oncology (CO) imaging guidelines, standard echocardiographic monitoring parameters of left ventricular systolic function have been endorsed. Recommendations highlight that either two-dimensional (2D) or three-dimensional (3D) left ventricular ejection fraction (LVEF), alongside global longitudinal strain (GLS) should be routinely performed for surveillance of patients at risk of cancer therapy-related cardiac dysfunction (CTRCD). We studied the feasibility of 3D-LVEF, 2D-GLS and 2D-LVEF in a dedicated CO service.MethodsThis was a single-centre prospective analysis of consecutive all-comer patients (n = 105) referred to an NHS CO clinic. Using a dedicated Philips EPIQ CVx v7.0, with X5-1 3D-transducer and 3DQA software, we sought to acquire and analyse 2D- and 3D-LVEF and 2D-GLS, adhering to the British Society of Echocardiography (BSE) and British Cardio-Oncology Society (BCOS) transthoracic echocardiography protocol.ResultsA total of 105 patients were enrolled in the study; 5 were excluded due to carcinoid heart disease (n = 5). Calculation of 3D-LVEF was achieved in 40% (n = 40), 2D-GLS in 73% (n = 73), and 2D-LVEF in 81% (n = 81). LV quantification was not possible in 19% (n = 19) due to poor myocardial border definition. Strong correlation existed between 2D-LVEF and 3D-LVEF (r = 0.94, p < 0.0001). Bland–Altman plot demonstrated no statistical differences in that the mean deviation between 2D-LVEF and 3D-LVEF were consistent throughout a range of LVEF values. The most persistent obstacle to 3D-LVEF acquisition was insufficient myocardial border tracking (n = 30, 50%).ConclusionThis study demonstrates the high feasibility of 2D-GLS and 2D-LVEF, even in those with challenging echocardiographic windows. The lower feasibility of 3D-LVEF limits its real-world clinical application, even though only a small difference in agreement with 2D-LVEF calculation was found when successfully performed.

Identification of optimal Sentinel-1 SAR polarimetric parameters for forest monitoring in Czechia

Time series analysis of synthetic aperture radar data (SAR) offers a systematic, dynamic and comprehensive way to monitor forests. The main emphasis of this study is on the identification of the most suitable and best performing Sentinel-1 SAR polarimetric parameters for forest monitoring. This is accomplished through: 1) a pairwise correlation analysis of SAR polarimetric parameters, multispectral optical vegetation indices and ancillary data, 2) a univariate binary time series classification for differentiation between forest types and 3) a visual exploration of time series. For this purpose, 600 validated broad-leaved and 600 coniferous forest areas in Czechia were used. Nine different SAR polarimetric parameters were examined, including VH and VV polarizations, VV/VH and VH/VV polarization ratios, the Radar Vegetation Index, Radar Forest Degradation Index, polarimetric radar vegetation index and the original and modified versions of the dual polarimetric SAR vegetation index. The pairwise correlation analysis revealed that most of the derived SAR polarimetric parameters were functions of each other with nearly identical behavior (r &gt; |0.96|). The strongest correlation of r ~0.50 between SAR and optical features was found for broad-leaved forest for VV/VH and VH/VV. The highest overall accuracy in the time series classification of forest types was achieved by VH (76%), while for VV, VV/VH and VH/VV it was higher than 60%. Furthermore, the time series analysis of these parameters showed seasonal behaviors of the SAR features in both forest types. These results demonstrated the high relevance of using VH, VV, VV/VH and VH/VV time series in forest monitoring compared to other SAR polarimetric parameters. This study also introduces a novel pipeline to generate multi-modal time series datasets in Google Earth Engine (MMTS-GEE), used to generate data for the analysis. MMTS-GEE combines spatially and temporally aligned SAR and multispectral data, extended with topographic and weather data, and a land cover class label. Its high versatility enables its use in time series analyses, intercomparisons and in machine learning applications for tabular time series data. The GEE code for the proposed tool and analysis is freely available to the research community.

Association between chronic kidney disease stages and changes in ambulatory blood pressure monitoring parameters

Association between chronic kidney disease stages and changes in ambulatory blood pressure monitoring parameters

IoT based real-time water quality monitoring system in water treatment plants (WTPs)

This study presents the development and implementation of an Internet of Things (IoT)-based real-time water quality monitoring system tailored for water treatment plants (WTPs). The system integrates advanced sensor technologies to continuously monitor key water quality parameters such as pH, dissolved oxygen (DO), total dissolved solids (TDS), and temperature. Data collected by these sensors is transmitted through a robust communication network to a centralized monitoring platform that utilizes cloud-based storage and analytics. The system's design includes a PLC-based control mechanism, allowing for flexible setup modifications and the easy addition of new monitoring parameters. The IoT-based system, powered by a low-energy 29-W configuration, offers accurate and reliable data with a minimal error margin of 0.1–0.2 across various parameters. The research highlights the system's ability to provide real-time alerts, historical data logging, and remote monitoring, all of which contribute to enhanced operational efficiency, proactive maintenance, and informed decision-making. This innovative approach to water quality management not only improves the effectiveness of WTP operations but also ensures environmental sustainability and public health safety. The study underscores the significant potential of IoT technologies in revolutionizing water quality monitoring practices.

Moving Toward Meaningful Evaluations of Monitoring in e-Mental Health Based on the Case of a Web-Based Grief Service for Older Mourners: Mixed Methods Study.

Artificial intelligence (AI) tools hold much promise for mental health care by increasing the scalability and accessibility of care. However, current development and evaluation practices of AI tools limit their meaningfulness for health care contexts and therefore also the practical usefulness of such tools for professionals and clients alike. The aim of this study is to demonstrate the evaluation of an AI monitoring tool that detects the need for more intensive care in a web-based grief intervention for older mourners who have lost their spouse, with the goal of moving toward meaningful evaluation of AI tools in e-mental health. We leveraged the insights from three evaluation approaches: (1) the F1-score evaluated the tool's capacity to classify user monitoring parameters as either in need of more intensive support or recommendable to continue using the web-based grief intervention as is; (2) we used linear regression to assess the predictive value of users' monitoring parameters for clinical changes in grief, depression, and loneliness over the course of a 10-week intervention; and (3) we collected qualitative experience data from e-coaches (N=4) who incorporated the monitoring in their weekly email guidance during the 10-week intervention. Based on n=174 binary recommendation decisions, the F1-score of the monitoring tool was 0.91. Due to minimal change in depression and loneliness scores after the 10-week intervention, only 1 linear regression was conducted. The difference score in grief before and after the intervention was included as a dependent variable. Participants' (N=21) mean score on the self-report monitoring and the estimated slope of individually fitted growth curves and its standard error (ie, participants' response pattern to the monitoring questions) were used as predictors. Only the mean monitoring score exhibited predictive value for the observed change in grief (R2=1.19, SE 0.33; t16=3.58, P=.002). The e-coaches appreciated the monitoring tool as an opportunity to confirm their initial impression about intervention participants, personalize their email guidance, and detect when participants' mental health deteriorated during the intervention. The monitoring tool evaluated in this paper identified a need for more intensive support reasonably well in a nonclinical sample of older mourners, had some predictive value for the change in grief symptoms during a 10-week intervention, and was appreciated as an additional source of mental health information by e-coaches who supported mourners during the intervention. Each evaluation approach in this paper came with its own set of limitations, including (1) skewed class distributions in prediction tasks based on real-life health data and (2) choosing meaningful statistical analyses based on clinical trial designs that are not targeted at evaluating AI tools. However, combining multiple evaluation methods facilitates drawing meaningful conclusions about the clinical value of AI monitoring tools for their intended mental health context.

Heparan sulfate in cerebrospinal fluid as a biomarker to assess disease severity and for treatment monitoring in patients with Mucopolysaccharidosis Type II: a position statement.

Patients with mucopolysaccharidosis type II (MPS II) can present with a severe neuronopathic phenotype or an attenuated non-neuronopathic phenotype. In the light of the recent development of drugs that cross the blood-brain barrier for treatment of neurologic MPS II symptoms, it is critical to define biomarkers that objectively differentiate phenotypes and monitor therapeutic outcomes of advanced treatments. In December 2023, a panel of Brazilian experts discussed the potential of quantifying heparan sulfate (HS) in the cerebrospinal fluid (CSF) as a biomarker for assessing neurological impairment in patients with MPS II, as well as the potential of the molecule as an objective parameter for therapeutic monitoring. Based on scientific evidence, the experts concluded that HS in CSF is predominantly derived from the brain and reflects neurological impairment in patients with MPS II. CSF HS levels may help differentiate between neuronopathic and non-neuronopathic forms of MPS II, with preliminary observations suggesting a potential threshold around 4,000 ng/mL when HS quantification is performed using the same method described in clinical studies of pabinafusp alfa. According to the authors, monitoring HS levels in CSF can serve as an objective parameter for assessing the effectiveness of treatment with drugs that cross the blood-brain barrier. The recommended timing of HS evaluations in CSF of patients with the severe phenotype is: (i) before treatment; (ii) six months after starting treatment; and (iii) two years after starting treatment. The same monitoring scheme is recommended for patients with the attenuated MPS II phenotype, however, after two years of treatment, the physician may elect to perform regular neurocognitive evaluations instead of measuring HS in CSF. Lastly, the authors reinforced the importance of evaluating adherence to treatment, including interruptions, to provide a more meaningful assessment of the treatment's real-world impact and to determine the ideal timing of CSF collection for therapeutic monitoring.

Sensors for Inflatable Lunar Habitat Construction

Lunar habitat is necessary for human exploration, especially for long duration space missions. For lunar habitat consturction, there are several other environmental hurdles to overcome than earth and constant internal pressure of habitat is added if the structure is to be inflatable.Among these hurdles, high energetic ions and particles from solar radiation and consequence extreme temperature difference may be protected with higher priority at least to secure survival environment for humans.In Korea Institute of Civil engineering and building Technology, new research project was launched in 2023 to design basic plan of lunar habitat construction on the moon and one of research topics is how to secure indoor environment of inflatable lunar habitat under that harsh lunar environment.Multi layred shell structured wall was suggested from previous project and research results and was selected to the optimum initial structure to start. Multi layred shell is mainly consisted of several highly strong and heat resistant fabric such as Kevlar or Vectran in webbing with other ion or particle protective layers and thermal insulation.Key environmental parameters for monitoring are internal air pressure, oxygen cencentration, temperature, humidity, and high energy particles by secondary radiation. Therefore, it is essential how to design and configure total sensing and monitoring system for inflatable habitat for long duration human exploration. Environmental, radiation, and inflatable structure monitoring sensors are summarized and composed to secure indoor enviroment and provide environmental quality data to HVAC system in further.

Data Acquisition System on Cocoa Bean Fermenter Using ESP32 Based on MQQT Protocol

The fermentation process of cocoa beans is a critical stage in chocolate production that affects the final quality of the product. To ensure that fermentation takes place optimally, monitoring parameters such as temperature, humidity, and pH is necessary. This research aims to develop and validate an Internet of Things (IoT)-based data acquisition system that uses ESP32 and MQTT protocols to monitor the fermentation process of cocoa beans. The system consists of an ESP32 module connected to DHT22 sensors to measure temperature and humidity, and a pH meter to measure acidity. The data collected by the sensors is sent in real-time via a wireless connection to an MQTT broker, where it can be monitored continuously. System testing was conducted in a small-scale fermentation environment. Validation results show that the system is capable of providing accurate and consistent data when compared to manual measurements using standardized tools. The difference between the data collected by the system and manual measurements was within acceptable tolerance limits, indicating that the system is reliable enough to be used in small-scale applications. The system also demonstrated fast response to changes in fermentation conditions, and stable data connection with minimal latency via the MQTT protocol. The developed data acquisition system has successfully acquired data and validated it using standard measuring instruments. The average data error for the pH sensor is 2.78%, temperature sensor 1.41%, and humidity sensor 1.94%. These error values indicate that the performance of the sensors used is good.

Co-administration of dexmedetomidine with total intravenous anaesthesia in carotid endarterectomy reduces requirements for propofol and improves haemodynamic stability: A single-centre, prospective, randomised controlled trial.

Total intravenous anaesthesia guided by electroencephalography and neurophysiological monitoring may be used for carotid endarterectomy. Reduction of brain metabolic demand during cross-clamping of the internal carotid artery with propofol titrated to burst suppression requires effect-site concentrations that may delay emergence and interfere with intraoperative neurophysiological monitoring. To test the hypothesis that dexmedetomidine decreases the effect-site concentration of propofol required for burst-suppression in patients undergoing carotid endarterectomy. Randomised controlled trial. Patients undergoing carotid endarterectomy. University Hospital of Berne, Switzerland, from October 2018 to September 2024. Patients were randomised into a control (n = 23) and a dexmedetomidine groups (n = 22). Total intravenous anaesthesia was administered to both groups. Patients in the dexmedetomidine group received an intravenous bolus of dexmedetomidine (0.4 μg kg-1 over 10 min) before induction, followed by a continuous intravenous infusion (0.4 μg kg-1 h-1). The effect-site concentrations of propofol were titrated against frontal electroencephalography parameters. Burst suppression was induced with propofol during cross-clamping of the internal carotid artery. The primary outcome was the effect-site concentration of propofol required for burst-suppression. The secondary outcomes were the requirement for vasoactive substances, neurophysiological monitoring parameters, and postoperative delirium. The effect-site concentration of propofol required for burst suppression was 4.0 μg ml-1 [3.50 to 4.90] (median [interquartile range]) in the dexmedetomidine group compared with 6.0 μg ml-1 [5.5 to 7.3] in the control group (P < 0.001). Less norepinephrine was required in the dexmedetomidine group (total 454 μg [246 to 818] compared with 1000 μg [444 to 1326] (P = 0.015) in the control group). Dexmedetomidine did not affect intraoperative neurophysiological monitoring. Co-administration of dexmedetomidine to total intravenous anaesthesia for carotid endarterectomy decreased the effect-site concentrations of propofol required for burst suppression by 33%. The propofol-sparing effect and peripheral alpha-agonism of dexmedetomidine may explain the reduced requirement for vasopressors. Clinicaltrials.gov identifier: NCT04662177.

Hotelling T2 control chart based on minimum vector variance for monitoring high‐dimensional correlated multivariate process

AbstractMultivariate control charts are practical tools that simultaneously monitor several correlated quality characteristics in a process. Monitoring high‐dimensional data structures is challenging because, in most cases, the process sample size for monitoring parameters is greater than the number of process characteristics. Many researchers have used the multivariate Hotelling's T2 chart to monitor high‐dimensional data using the maximum‐likelihood methods (MLM) to estimate the covariance matrices. However, the multivariate Hotelling's T2chart based on MLM suffers from low statistical performance. In this paper, we proposed a multivariate Hotelling's T2 chart based on the minimum vector variance (MVV) and some regularized methods for monitoring high‐dimensional data structures. The performance of the proposed chart is evaluated in terms of the average run length (ARL). The results reveal the superiority of the proposed MVV Hotelling's T2 chart over the existing Hotelling's T2 charts for high‐dimensional correlated processes.

Evaluation of the effect of disposal of landfill leachate in a sewage treatment plant composed of stabilization ponds

This study aimed to evaluate the combined treatment system of domestic sewage and leachate by serial stabilization ponds in a Wastewater Treatment Plant (WWTP). The WWTP had two parallel pond modules, one receiving (module II—pond M10) and the other not receiving leachate (module I—pond M5). Physical, chemical, and biological monitoring parameters collected from January 2017 to December 2021 were evaluated. High reducing efficiency for ammonium nitrogen was found, with an average of 95.7 ± 2.5%. BOD5 and COD can be considered statistically different for a 95% confidence level in the two pond modules. The phytoplankton community was composed of 46 taxa distributed in four taxonomic classes: 6 belonging to the Cyanobacteria group (13%), 22 to the Green Algae group (48%), 4 to the Diatoms group (9%), and 14 to the Phytoflagellate group (30%). No ecotoxicity was detected for the evaluated pond effluent samples. Thus, although the insertion of leachate impacted the quality of the final effluent of the ponds and the organic matter, it may not have affected the effluents’ ecotoxicity. This research helps to understand the impacts of long-term leachate insertion in a real treatment system using stabilization ponds for combined treatment. In addition to the usual efficiency evaluation parameters, ecotoxicological tests and phytoplankton are also evaluated.

Development and external validation of an interpretable machine learning model for the prediction of intubation in the intensive care unit

Given the limited capacity to accurately determine the necessity for intubation in intensive care unit settings, this study aimed to develop and externally validate an interpretable machine learning model capable of predicting the need for intubation among ICU patients. Seven widely used machine learning (ML) algorithms were employed to construct the prediction models. Adult patients from the Medical Information Mart for Intensive Care IV database who stayed in the ICU for longer than 24 h were included in the development and internal validation. The model was subsequently externally validated using the eICU-CRD database. In addition, the SHapley Additive exPlanations method was employed to interpret the influence of individual parameters on the predictions made by the model. A total of 11,988 patients were included in the final cohort for this study. The CatBoost model demonstrated the best performance (AUC: 0.881). In the external validation set, the efficacy of our model was also confirmed (AUC: 0.750), which suggests robust generalization capabilities. The Glasgow Coma Scale (GCS), body mass index (BMI), arterial partial pressure of oxygen (PaO2), respiratory rate (RR) and length of stay (LOS) before ICU were the top 5 features of the CatBoost model with the greatest impact. We developed an externally validated CatBoost model that accurately predicts the need for intubation in ICU patients within 24 to 96 h of admission, facilitating clinical decision-making and has the potential to improve patient outcomes. The prediction model utilizes readily obtainable monitoring parameters and integrates the SHAP method to enhance interpretability, providing clinicians with clear insights into the factors influencing predictions.

Применение графов знаний для клинического мониторинга процесса лечения

Patient condition monitoring is essential at every stage of the treatment and diagnostic process. During treatment, the key tasks of monitoring include evaluating the effectiveness of treatment strategies and ensuring safety, specifically by avoiding complications and adverse effects from medications, procedures, or their combinations. To enhance doctor-patient interactions and improve treatment quality, intelligent monitoring tools are needed. These tools must use patient data and formalized knowledge of the subject area to identify which observations, at specific times, can indicate any deviation of the patient's condition from expected outcomes.This study aims to develop an ontology that formalizes the knowledge necessary for selecting and explaining monitoring parameters throughout treatment. Key concept rela-tionships that address the challenges of monitoring patient conditions during treatment are identified, leading to an on-tological graph for a specific class of medical monitoring issues. The study describes a method for building knowledge graphs applicable to various diseases and a reasoning process to identify unexpected conditions. A process of reasoning and the resulting recommendation is presented. This approach establishes a foundation for a decision support system tailored to this class of problems, where monitoring parameters can be adapted according to treatment stage, patient condition, and individual characteristics.

Localized topological states beyond Fano resonances via counter-propagating wave mode conversion in piezoelectric microelectromechanical devices

A variety of scientific fields like proteomics and spintronics have created a new demand for on-chip devices capable of sensing parameters localized within a few tens of micrometers. Nano and microelectromechanical systems (NEMS/MEMS) are extensively employed for monitoring parameters that exert uniform forces over hundreds of micrometers or more, such as acceleration, pressure, and magnetic fields. However, they can show significantly degraded sensing performance when targeting more localized parameters, like the mass of a single cell. To address this challenge, we present a MEMS device that leverages the destructive interference of two topological radiofrequency (RF) counter-propagating wave modes along a piezoelectric Aluminum Scandium Nitride (AlScN) Su-Schrieffer-Heeger (SSH) interface. The reported MEMS device opens up opportunities for further purposes, including achieving more stable frequency sources for communication and timing applications.