Reliable Accuracy Research Articles

Predictive Factors for Tissue Inflammation in Patients with Benign Prostatic Hyperplasia: A Clinical Prediction Study

Introduction: Benign prostatic hyperplasia (BPH) is a common condition in older men, marked by the noncancerous enlargement of the prostate gland. Inflammation of the prostate plays a significant role in the progression of BPH and the symptoms it causes. The objective of this study was to create a predictive model for prostatic inflammation in men with BPH based on important clinical factors. Methods: A retrospective cohort study was conducted with 137 patients diagnosed with BPH. Data collected included various factors such as age, prostate volume (PV), preoperative international prostate symptom score, preoperative maximum urine flow rate (Qmax), preoperative post-void residue, weight of the excised tissue, body mass index, fasting blood glucose (FBG), cholesterol levels, prostate-specific antigen, blood calcium, blood phosphorus, blood uric acid, triglycerides, hypertension status, and presence of prostate calcifications. Multivariate logistic regression and LASSO regression analyses were performed to identify significant predictors and develop a nomogram. The model’s performance was evaluated using receiver operating characteristic curves, calibration plots, and decision curve analysis (DCA). Results: Among the patients, 9.49% showed no signs of prostatic inflammation, while 22.63% had mild, 47.45% had moderate, and 20.44% had severe inflammation. Factors such as PV, FBG, and prostate calcification were identified as important predictors of prostatic inflammation. The predictive model developed exhibited strong discrimination and calibration, as evidenced by a high area under the curve value, indicating reliable predictive accuracy. DCA further validated the clinical usefulness of the nomogram. Conclusion: The developed nomogram, incorporating PV, FBG, and prostate calcification, effectively predicts prostatic inflammation in men with BPH. This tool can aid in early intervention and targeted treatment, potentially improving patient outcomes. Further validation in diverse populations is recommended to enhance its generalizability and clinical applicability.

Rapid visual detection of Helicobacter pylori and vacA subtypes by Dual-Target RAA-LFD assay

BackgroundHelicobacter pylori (H. pylori) infects over 50% of the global population and is a significant risk factor for gastric cancer. The pathogenicity of H. pylori is primarily attributed to virulence factors such as vacA. Timely and accurate identification, along with genotyping of H. pylori virulence genes, are essential for effective clinical management and controlling its prevalence. MethodsIn this study, we developed a dual-target RAA-LFD assay for the rapid, visual detection of H. pylori genes (16s rRNA, ureA, vacA m1/m2), using recombinase aided amplification (RAA) combined with lateral flow dipstick (LFD) methods. Both 16s rRNA and ureA were selected as identification genes to ensure reliable detection accuracy. ResultsA RAA-LFD assay was developed to achieve dual-target amplification at a stable 37 °C within 20 min, followed by visualization using the lateral flow dipstick (LFD). The whole process, from amplification to results, took less than 30 min. The 95 % limit of detection (LOD) for 16 s rRNA and ureA, vacA m1, vacA m2 were determined as 3.8 × 10-2 ng/μL, 5.8 × 10-2 ng/μL and 1.4 × 10-2 ng/μL, respectively. No cross-reaction was observed in the detection of common pathogens including Escherichia coli, Klebsiella pneumoniae, Enterococcus faecalis, Staphylococcus aureus, Pseudomonas aeruginosa, and Bacillus subtilis, showing the assay’s high specificity. In the evaluation of the clinical performance of the RAA-LFD assay. A total of 44 gastric juice samples were analyzed, immunofluorescence staining (IFS) and quantitative polymerase chain reaction (qPCR) were used as reference methods. The RAA-LFD results for the 16s rRNA and ureA genes showed complete agreement with qPCR findings, accurately identifying H. pylori infection as confirmed by IFS in 10 out of the 44 patients. Furthermore, the assay successfully genotyped vacA m1/m2 among the positive samples, showing complete agreement with qPCR results and achieving a kappa (κ) value of 1.00. ConclusionThe dual-target RAA-LFD assay developed in this study provides a rapid and reliable method for detecting and genotyping H. pylori within 30 min, minimizing dependency on sophisticated laboratory equipment and specialized personnel. Clinical validation confirms its efficacy as a promising tool for effectively control of its prevalence and aiding in the precise treatment of H. pylori-associated diseases.

Assessing forest fire dynamics and risk zones in Central Indian forests: a comparative study of the Khandwa and North Betul forest divisions of Madhya Pradesh.

Forest fires pose significant environmental and socioeconomic threats, particularly in regions such as Central India, where forest ecosystems are vital for biodiversity and local livelihoods. Understanding forest fire dynamics and identifying fire risk zones are crucial for effective mitigation. The current study explores the spatiotemporal dynamics of forest fires in the Khandwa and North Betul forest divisions in the Central Indian region over 22years using Mann-Kendall and Sen's slope tests on MODIS (Moderate Resolution Imaging Spectroradiometer) fire point data. We found a nonsignificant increase in forest fires in both divisions. Khandwa showed a nonsignificant slope rise of more than three events per year, while North Betul revealed an increase of around one event per year. The lack of statistical significance suggests that upward trends of forest fire events may result from random fluctuations rather than consistent patterns. Spatial autocorrelation analysis revealed significant clustering of fire incidents in both regions. Khandwa confirmed moderate clustering (Moran's I = 0.043), whereas North Betul showed robust clustering (Moran's I = 0.096). Kernel density estimation further identified high-risk clusters in both divisions, necessitating zonal-wise targeted fire management strategies. Fire risk zonation was developed using the analytic hierarchy process (AHP), combining 10 environmental and socioeconomic factors. The AHP model, validated using MODIS fire data, showed reliable accuracy. The results revealed many of both divisions in the high- to very high-risk categories. Approximately, 45% of the area of the Khandwa and nearly 50% of the area of North Betul fall under high to very high fire risk zones. Khandwa's high-risk areas mainly lie in the northern and southeastern parts, while North Betul lies in the northwestern and north-eastern regions. The identified fire-prone areas indicate the pressing need for local or region-specific fire prevention and mitigation strategies. Thus, the findings of this study provide valuable insights into forest fire risk management and contribute to more focused research and methodological developments.

Clinical artificial intelligence: teaching a large language model to generate recommendations that align with guidelines for the surgical management of GERD.

Large Language Models (LLMs) provide clinical guidance with inconsistent accuracy due to limitations with their training dataset. LLMs are "teachable" through customization. We compared the ability of the generic ChatGPT-4 model and a customized version of ChatGPT-4 to provide recommendations for the surgical management of gastroesophageal reflux disease (GERD) to both surgeons and patients. Sixty patient cases were developed using eligibility criteria from the Society of American Gastrointestinal and Endoscopic Surgeons (SAGES) & United European Gastroenterology (UEG)-European Association of Endoscopic. Surgery (EAES) guidelines for the surgical management of GERD. Standardized prompts were engineered for physicians as the end-user, with separate layperson prompts for patients. A customized GPT was developed to generate recommendations based on guidelines, called the GERD Tool for Surgery (GTS). Both the GTS and generic ChatGPT-4 were queried July 21st, 2024. Model performance was evaluated by comparing responses to SAGES & UEG-EAES guideline recommendations. Outcome data was presented using descriptive statistics including counts and percentages. The GTS provided accurate recommendations for the surgical management of GERD for 60/60 (100.0%) surgeon inquiries and 40/40 (100.0%) patient inquiries based on guideline recommendations. The Generic ChatGPT-4 model generated accurate guidance for 40/60 (66.7%) surgeon inquiries and 19/40 (47.5%) patient inquiries. The GTS produced recommendations based on the 2021 SAGES & UEG-EAES guidelines on the surgical management of GERD, while the generic ChatGPT-4 model generated guidance without citing evidence to support its recommendations. ChatGPT-4 can be customized to overcome limitations with its training dataset to provide recommendations for the surgical management of GERD with reliable accuracy and consistency. The training of LLM models can be used to help integrate this efficient technology into the creation of robust and accurate information for both surgeons and patients. Prospective data is needed to assess its effectiveness in a pragmatic clinical environment.

KNNDM CV: k-fold nearest-neighbour distance matching cross-validation for map accuracy estimation

Abstract. Random and spatial cross-validation (CV) methods are commonly used to evaluate machine-learning-based spatial prediction models, and the performance values obtained are often interpreted as map accuracy estimates. However, the appropriateness of such approaches is currently the subject of controversy. For the common case where no probability sample for validation purposes is available, in Milà et al. (2022) we proposed the nearest-neighbour distance matching (NNDM) leave-one-out (LOO) CV method. This method produces a distribution of geographical nearest-neighbour distances (NNDs) between test and training locations during CV that matches the distribution of NNDs between prediction and training locations. Hence, it creates predictive conditions during CV that are comparable to what is required when predicting a defined area. Although NNDM LOO CV produced largely reliable map accuracy estimates in our analysis, as a LOO-based method, it cannot be applied to the large datasets found in many studies. Here, we propose a novel k-fold CV strategy for map accuracy estimation inspired by the concepts of NNDM LOO CV: the k-fold NNDM (kNNDM) CV. The kNNDM algorithm tries to find a k-fold configuration such that the empirical cumulative distribution function (ECDF) of NNDs between test and training locations during CV is matched to the ECDF of NNDs between prediction and training locations. We tested kNNDM CV in a simulation study with different sampling distributions and compared it to other CV methods including NNDM LOO CV. We found that kNNDM CV performed similarly to NNDM LOO CV and produced reasonably reliable map accuracy estimates across sampling patterns. However, compared to NNDM LOO CV, kNNDM resulted in significantly reduced computation times. In an experiment using 4000 strongly clustered training points, kNNDM CV reduced the time spent on fold assignment and model training from 4.8 d to 1.2 min. Furthermore, we found a positive association between the quality of the match of the two ECDFs in kNNDM and the reliability of the map accuracy estimates. kNNDM provided the advantages of our original NNDM LOO CV strategy while bypassing its sample size limitations.

Analysis of Precipitable Water Vapor, Liquid Water Path and Their Variations before Rainfall Event over Northeastern Tibetan Plateau

A ground-based microwave radiometer (MWR) provides continuous atmospheric profiles under various weather conditions. The change in total precipitable water vapor (PWV) and liquid water path (LWP) before rainfall events is particularly important for the improvement in the rainfall forecast. However, the analysis of the PWV and LWP before rainfall event on the plateau is especially worth exploring. In this study, the MWR installed at Xining, a city located over the northeastern Tibetan Plateau, was employed during September 2021 to August 2022. The results reveal that the MWR-retrieved temperature and vapor density demonstrate reliable accuracy, when compared with radiosonde observations; PWV and LWP values during the summer account for over 70% of the annual totals in the Xining area; both PWV and LWP at the initiating time of rainfall events are higher during summer, especially after sunset (during 20-00 local solar time); and notably, PWV and LWP anomalies are enhanced abruptly 8 and 28 min prior to the initiating time, respectively. Furthermore, the mean of LWP anomaly rises after the turning time (the moment rises abruptly) to the initiating time; as the intensity of rainfall events increases, the occurrence of the turning time is delayed, especially for PWV anomalies; while the occurrence of the turning time is similar for both convective cloud and stratiform cloud rainfall events, the PWV and LWP anomalies jump more the initiating time; as the intensity of rainfall events increases, the occurrence of the turning time is delayed, especially for PWV anomalies; while the occurrence of the turning time is similar for both convective cloud and stratiform cloud rainfall events, the PWV and LWP anomalies jump more dramatically after the turning time in convective cloud events. This study aims are to analyze the temporal characteristics of PWV and LWP, and assess their potential in predicting rainfall event.

Evaluating enhanced predictive modeling of foam concrete compressive strength using artificial intelligence algorithms

Artificial intelligence algorithms have recently demonstrated their efficacy in accurately predicting concrete properties by optimizing mixing proportions and overcoming design limitations. In this regard, foam concrete (FC) production presents a unique challenge, necessitating extensive experimental trials to attain specific properties such as compressive strength (CS). In this context, linear regression (LR), support vector regression (SVR), a multilayer-perceptron artificial neural network (MLP-ANN), and Gaussian process regression (GPR) algorithms, were used to predict the CS of FC. 261 experimental results were utilized, incorporating input variables such as density, water-to-cement ratio, and fine aggregate-to-cement ratio. During the training phase, 75 % of the experimental dataset was utilized. The experimental data is then validated using metrics such as coefficient of determination (R2), root mean square error, and root mean error. In comparison, the GPR algorithm reveals high-accuracy towards the estimation of CS, as proved by its high R2-value, which equals 0.98, while the R2 for ANN, SVR, and LR are 0.97, 0.90, and 0.89, respectively. Additionally, parametric and sensitivity analyses were used to assess the performance of the GPR and LR algorithms. Results revealed that density exerted the most significant influence on CS, with the GPR model showing a pronounced negative impact of fine aggregate-to-cement ratio on CS, particularly in low-density FC, contrasting with the LR model. This study confirmed that the GPR algorithm provided reliable accuracy in predicting the CS of FC. Therefore, it is recommended to utilize the prediction algorithms within the range of input variables employed in this investigation for optimal results.

A robust and real-time lane detection method in low-light scenarios to advanced driver assistance systems

Lane detection, which relies on front-view RGB cameras, is a crucial aspect of Advanced Driver Assistance Systems (ADAS), but its effectiveness is notably reduced in low-light conditions. This issue is exacerbated by the lack of specialized datasets and generalizable methods for such scenarios. To address this gap, we introduce NightLane, a comprehensive dataset tailored for low-light, multi-traffic lane detection. We adhere to stringent data annotation guidelines, ensuring reliable detection accuracy. Additionally, we propose the Fused Low-Light Enhancement Framework (FLLENet), which leverages modern detection networks and incorporates a low-light enhancement module and attention mechanisms. The enhancement module, based on zero-reference learning, improves image quality and channel richness, while the attention mechanisms effectively extract and utilize these features. Our extensive testing on NightLane and CULane datasets demonstrates superior performance in low-light lane detection, showcasing FLLENet’s robust generalizability and efficacy. Specifically, our approach achieves an F1 measure of 76.90 on CULane and 78.91 on NightLane, demonstrating its effectiveness against state-of-the-art methods. We also evaluate the real-time applicability of our framework on a low-power embedded lane detection system using NVIDIA Jetson AGX/Orin, achieving high accuracy and real-time performance. Our work offers a new approach and reference in the field of low-light lane detection, potentially aiding in the ongoing enhancement of ADAS (ADAS). Dateset are available at https://github.com/pengjingt/FLLENet.

Excellent performance of Ag6Si2O7 oxidase mimic endowed by self-released ions for rapid colorimetric determination with reduced operational interference

Increasing attention has been directed towards oxidase mimics due to their catalytic ability toward enzyme substrates in the absence of H2O2, offering great colorimetric sensing potential in assays and diagnostics. However, slow electron-transfer and unstable absorbance over time often lead to unsatisfactory enzymatic reaction rates and unreliable readouts, significantly reducing detection efficiency and accuracy. Herein, we report on an Ag6Si2O7 nanozyme utilizing 3,3′,5,5′-tetramethylbenzidine (TMB) as a chromogenic substrate, demonstrating excellent oxidase-like activity and long-term stable colorimetric signals. Experimental results reveal that the excellent catalytic kinetics of Ag6Si2O7 (Km = 0.197 mM, Vmax = 5.1 × 10−7 M/s) are attributed to ultrafast electron transfer between Ag+ and TMB, mediated by Ag2O intermediates formed from self-released alkaline ions. Additionally, self-released H2SiO42− improves the stability of the oxidized substrate, resulting in a long-term stable colorimetric signal (∼20 min), which exhibits reliable accuracy regardless of the time point at which analyte is added within 20 min, thus eliminating the interference of individual operation time errors. Ascorbic acid (AA) is selected as the target molecule to assess the performance of the Ag6Si2O7-TMB colorimetric sensing system. This approach demonstrates a wide detection range from 5 to 300 μM and a detection limit of 0.452 μM. The developed colorimetric sensing strategy exhibits good stability, specificity, rapidity, and potential application in real sample detection.

Monitoring and analysis of settlement and deformation status of high-rise buildings based on nonlinear regression

In order to solve the problems of low reliability and poor prediction accuracy in traditional building structure settlement monitoring, the author proposes a monitoring and analysis of high-rise building settlement deformation status based on nonlinear regression. The author collected and wirelessly transmitted building settlement information through various hardware devices such as sensors and GPRS communication modules. The monitoring data collected by sensors were compared and analyzed to determine the settlement situation of the building. An RBF neural network prediction model was constructed for possible settlement points. Then, the leapfrog algorithm is used to optimize the structural parameters of the RBF neural network. The experimental results show that this method can accurately evaluate the possible settlement of building structures in actual environments, and the prediction error is small, with a maximum relative error of 4.83 %, indicating good warning ability. This method achieved the best actual value fitting curve results, verifying its feasibility in settlement prediction. Subsequently, a more widely applicable settlement detection and prediction system for building complex structures will be established based on the proposed method, in order to promote its large-scale application.

Structure optimization of intercooler bionic fins based on artificial neural network and genetic algorithms

The bionic fins inspired by the shark are proposed to enhance the thermal-hydraulic performance of the intercoolers in this work. The geometric parameters of the fins are investigated to examine the effects on thermal-hydraulic performance. The height and width of protrusions are chosen as optimization parameters based on the results of the geometric parameter analysis. Non-dominated genetic algorithms are combined with artificial neural networks to obtain the optimal solution for the geometry parameters. The artificial neural networks used in this study exhibit a reliable accuracy with errors below 10 % (with mostly remaining below 5 %). The optimal values for the height and width of the protrusions are determined to be 1.01 mm and 0.82 mm, which results in a Colburn factor of 0.01923 and a comprehensive index of 0.04305. Compared with the original design, the optimized structure yields 17.69 % and 4.77 % increments for the Colburn factor and comprehensive index. Compared with the original model, the intercooler with the optimal structure exhibits a 9.9 % increase in entropy generation and a 20.2 % enhancement in the exergy difference between the inlet and outlet.

Smartphone videos-driven musculoskeletal multibody dynamics modelling workflow to estimate the lower limb joint contact forces and ground reaction forces.

The estimation of joint contact forces in musculoskeletal multibody dynamics models typically requires the use of expensive and time-consuming technologies, such as reflective marker-based motion capture (Mocap) system. In this study, we aim to propose a more accessible and cost-effective solution that utilizes the dual smartphone videos (SPV)-driven musculoskeletal multibody dynamics modeling workflow to estimate the lower limb mechanics. Twelve participants were recruited to collect marker trajectory data, force plate data, and motion videos during walking and running. The smartphone videos were initially analyzed using the OpenCap platform to identify key joint points and anatomical markers. The markers were used as inputs for the musculoskeletal multibody dynamics model to calculate the lower limb joint kinematics, joint contact forces, and ground reaction forces, which were then evaluated by the Mocap-based workflow. The root mean square error (RMSE), mean absolute deviation (MAD), and Pearson correlation coefficient (ρ) were adopted to evaluate the results. Excellent or strong Pearson correlations were observed in most lower limb joint angles (ρ = 0.74 ~ 0.94). The averaged MADs and RMSEs for the joint angles were 1.93 ~ 6.56° and 2.14 ~ 7.08°, respectively. Excellent or strong Pearson correlations were observed in most lower limb joint contact forces and ground reaction forces (ρ = 0.78 ~ 0.92). The averaged MADs and RMSEs for the joint lower limb joint contact forces were 0.18 ~ 1.07 bodyweight (BW) and 0.28 ~ 1.32 BW, respectively. Overall, the proposed smartphone video-driven musculoskeletal multibody dynamics simulation workflow demonstrated reliable accuracy in predicting lower limb mechanics and ground reaction forces, which has the potential to expedite gait dynamics analysis in a clinical setting.

Rewc-GNN Algorithm for the Property Prediction of Large-Scale Crystals.

The space group of a crystal describes the symmetry and periodic arrangement of its structure. As the fundamental element in the structure, it plays a vital role in determining the physical and chemical properties of crystals. The investigation of crystal space group information allows for the prediction of material properties, thereby providing guidance for material design and synthesis to enhance their performance or functionality. Currently prevalent first-principles-based computational methods exhibit good accuracy, but they rely heavily on computing resources, greatly limiting the efficiency of material screening. In this paper, our study is oriented toward the prediction the spatial group of crystals, and an algorithm named Rewc, based on graph neural networks (GNNs) is proposed. This algorithm encodes all atoms and the interactions between atoms in the crystal as features by combining Floyd algorithm and k-hop message passing and employs multilayer convolutional networks to extract connections between k layers. This allows for the automatic learning of more representative atomic vector representations through iterations of feature information for each atom and its neighbors. Experimental results demonstrate that the Rewc framework exhibits reliable accuracy and good generalization capabilities in predicting the crystal structure compared to previous GNN methods.

Investigation of a solar-assisted methanol steam reforming system: Operational factor screening and computational fluid dynamics data-driven prediction

The development of solar-to-fuel technologies has received significant attention while facing the growing interest in clean energy production. To accurately evaluate and optimize the solar-assisted thermochemical hydrogen production process, a reliable prediction method that ensures stable accuracy is essential. We utilized a gray correlation analysis (GRA) and a multi-objective genetic algorithm (GA) model to optimize the operating parameters of a methanol steam reforming system. Computational fluid dynamics simulations provided the response values for key parameters, including reactant conversion rate, syngas product yield, and CO selectivity. Additionally, the Taguchi’s method and analysis of variance (ANOVA) were employed to assess the impact of operating parameters on these target outputs. The results demonstrate that the proposed GA-Back propagation neural networks (GA-BPNN) model significantly outperforms traditional prediction models in accuracy, exhibiting robustness and generalization. The mean absolute percentage error (MAPE) of methanol conversion, hydrogen yield, and CO selectivity is 3.20 %, 4.69 % and 3.53 %. The GRA-GA-BPNN model shows a slight decline, while still maintains reliable prediction accuracy, with the MAPE value of 5.76 %, 5.11 %, and 10.4 %. This operational factor screening-based prediction model proves useful for large-scale data-driven predictions of solar thermochemical systems, especially under complex and variable external conditions and internal human interventions.

Bruxism treatment on Youtube: evaluating reliability and information accuracy

BackgroundThe aim of this study was to evaluate the content and quality of videos about bruxism treatments on YouTube, a platform frequently used by patients today to obtain information.MethodsA YouTube search was performed using the keywords “bruxism treatment” and “teeth grinding treatment”. “The sort by relevance” filter was used for both search terms and the first 150 videos were saved. A total of 139 videos that met the study criteria were included in the study. Videos were classified as poor, moderate or excellent based on a usefulness score that evaluated content quality. The modified DISCERN tool was also used to evaluate video quality. Additionally, videos were categorized according to the upload source, target audience and video type. The types of treatments mentioned in the videos and the demographic data of the videos were recorded.ResultsAccording to the usefulness score, 59% of the videos were poor-quality, 36.7% were moderate-quality and 4.3% were excellent-quality. Moderate-quality videos had a higher interaction index than excellent-quality videos (p = 0.039). The video duration of excellent-quality videos was longer than that of moderate and poor-quality videos (p = 0.024, p = 0.002). Videos with poor-quality content were found to have significantly lower DISCERN scores than videos with moderate (p < 0.001) and excellent-quality content (p = 0.008). Additionally, there was a significantly positive and moderate (r = 0.446) relationship between DISCERN scores and content usefulness scores (p < 0.001). There was only a weak positive correlation between DISCERN scores and video length (r = 0.359; p < 0.001). The videos uploaded by physiotherapists had significantly higher views per day and viewing rate than videos uploaded by medical doctors (p = 0.037), university-hospital-institute (p = 0.024) and dentists (p = 0.006). The videos uploaded by physiotherapists had notably higher number of likes and number of comments than videos uploaded by medical doctors (p = 0.023; p = 0.009, respectively), university-hospital-institute (p = 0.003; p = 0.008, respectively) and dentists (p = 0.002; p = 0.002, respectively).ConclusionsAlthough the majority of videos on YouTube about bruxism treatments are produced by professionals, most of the videos contain limited information, which may lead patients to debate treatment methods. Health professionals should warn patients against this potentially misleading content and direct them to reliable sources.

The Performance of ChatGPT-4 and Gemini Ultra 1.0 for Quality Assurance Review in Emergency Medical Services Chest Pain Calls

Objectives This study assesses the feasibility, inter-rater reliability, and accuracy of using OpenAI's ChatGPT-4 and Google’s Gemini Ultra large language models (LLMs), for Emergency Medical Services (EMS) quality assurance. The implementation of these LLMs for EMS quality assurance has the potential to significantly reduce the workload on medical directors and quality assurance staff by automating aspects of the processing and review of patient care reports. This offers the potential for more efficient and accurate identification of areas requiring improvement, thereby potentially enhancing patient care outcomes. Methods Two expert human reviewers, ChatGPT GPT-4, and Gemini Ultra assessed and rated 150 consecutively sampled and anonymized prehospital records from 2 large urban EMS agencies for adherence to 2020 National Association of State EMS metrics for cardiac care. We evaluated the accuracy of scoring, inter-rater reliability, and review efficiency. The inter-rater reliability for the dichotomous outcome of each EMS metric was measured using the kappa statistic. Results Human reviewers showed high interrater reliability, with 91.2% agreement and a kappa coefficient 0.782 (0.654-0.910). ChatGPT-4 achieved substantial agreement with human reviewers in EKG documentation and aspirin administration (76.2% agreement, kappa coefficient 0.401 (0.334-0.468), but performance varied across other metrics. Gemini Ultra’s evaluation was discontinued due to poor performance. No significant differences were observed in median review times: 01:28 min (IQR 1:12 − 1:51 min) per human chart review, 01:24 min (IQR 01:09 − 01:53 min) per ChatGPT-4 chart review (p = 0.46), and 01:50 min (IQR 01:10-03:34 min) per Gemini Ultra review (p = 0.06). Conclusions Large language models demonstrate potential in supporting quality assurance by effectively and objectively extracting data elements. However, their accuracy in interpreting non-standardized and time-sensitive details remains inferior to human evaluators. Our findings suggest that current LLMs may best offer supplemental support to the human review processes, but their current value remains limited. Enhancements in LLM training and integration are recommended for improved and more reliable performance in the quality assurance processes.

Autonomous and reliable fingerprint map maintenance for indoor positioning system

In WiFi-based crowdsourced fingerprinting indoor positioning systems (IPS), the signal space of WiFi APs changes over time. To autonomously maintain a highly reliable localization accuracy, the fingerprint database needs regular maintenance and updates. However, this process is labor-intensive and time-consuming due to the appearance of faulty access points (APs) in crowdsourced samples received from target clients, which are mainly used for autonomous maintenance and updates. Additionally, if some APs are relocated, removed, or replaced in the indoor environment after fingerprint map construction, it can severely impact IPS accuracy. In this paper, we present Dynamic Online Fingerprint Learning with Altered APs status-aware and updating (DOFLAAU) for IPS. Our systematic methodology involves several key steps. First, we employ the Modified Group Method of Data Handling (GMDH) neural network regression for autonomous AP status monitoring and alteration detection. Next, we perform autonomous APs subset sample selection using a modified Thomson model, followed by outlier feature detection and removal based on the weighted sample density rate. Thirdly, we propose a dynamic online fingerprint map updating model using the cosine similarity distance metric. Lastly, we adopted an effective signal distance-based weighted k-nearest neighbor algorithm to improve IPS accuracy. The experiment results validate the efficiency and effectiveness of our proposed algorithms in terms of better localization accuracy compared to peer algorithms.

Comprehensive Risk Assessment of Farmer Households in Flood and Earthquake Prone Areas Based on Multidimensional Information Diffusion Model

In recent years, the global practice of regional natural disaster reduction and comprehensive risk prevention has promoted the integration of multiple disciplines, and the theory and technology of comprehensive risk assessment for multiple natural disaster chains urgently need innovation. This article is based on multiple natural disaster chain scenarios and sets secondary indicators for multiple influencing factors based on the first level indicators composed of basic risk factors such as hazard factors, vulnerability of disaster bearing bodies, and disaster prevention and reduction capabilities. By using multidimensional information diffusion technology, multiple hazard factor hazard combination factors, vulnerability combination factors of disaster bearing bodies, and comprehensive disaster prevention and reduction capability combination factors reflecting various natural disaster scenarios are constructed, A household comprehensive risk assessment index system for multi-dimensional information diffusion assessment of natural disaster comprehensive risk was designed by quantifying risk factors such as the intensity of comprehensive disaster causing factors, vulnerability of disaster bearing bodies, and comprehensive disaster prevention and reduction capabilities in disaster scenarios. This paper expands the traditional information diffusion comprehensive risk assessment model, makes up for the lack of information on geographical units, establishes a multi impact factor multi dimension natural disaster risk comprehensive assessment model for multi risk factors of complex disaster scenarios with small samples, obtains the theoretical value of multi-dimensional information Diffusion model comprehensive risk assessment for complex disaster scenarios, breaks through the sample size limit of natural disaster risks, and makes up for the lack of information on small samples of small probability events, Improved the reliability and accuracy of comprehensive risk assessment for multiple natural disaster chains. Then, take the disaster scenario formed by the comprehensive risk of earthquake and flood in a place in the upper reaches of the Fujiang River basin as the analysis sample, calculate the comprehensive risk assessment value of flood and earthquake damage in the study area's micro samples (rural households in villages and towns). By comparison, it is found that the comprehensive risk value assessed by the multi-dimensional information Diffusion model has good reliability and high accuracy, which is significantly better than the traditional Kriging interpolation method and geographical weighted regression method. This article provides a comprehensive risk assessment of natural disasters at the micro household level, which can better reflect the diversity and regionality of risks, help clarify the hidden risks of rural natural disasters, and provide scientific basis for government emergency management decision-making.

P-049 Identification of human spermatozoa with zona pellucida-binding ability using deep learning

Abstract Study question Can a deep learning model be used for identification of fertilization-competent human spermatozoa based on their distinctive morphological features? Summary answer Our results validated the clinical significance of image analysis of sperm morphology using deep learning to identify high-quality spermatozoa with zona pellucida (ZP)-binding ability. What is known already Sperm morphology is manually evaluated as part of the conventional semen analysis in clinical settings. However, the clinical predictive power of sperm morphology remains debatable due to its lack of association with the fertilization potential of spermatozoa. Human zona pellucida (ZP)-binding ability is a measurable, independent sperm parameter associated with in vitro fertilization (IVF) and pregnancy outcome. Supervised deep learning is an advanced branch to systematically identify the underlying relationship between the input images and designated output. A well-trained model with high generalization ability can generate plausible predictions for unseen images collected under the same condition as the training datasets. Study design, size, duration Human spermatozoa and oocytes were obtained with written consents from the donors attending our assisted reproduction program. Acrosome intact, ZP-bound spermatozoa were recovered after 30 min of gamete coincubation. Unbound spermatozoa were collected from clinical samples of spermatozoa with defective ZP-binding ability leading to fertilization failure following conventional insemination. Sperm images of infertile men (n = 165) with fertilization rates including 0-40% (low), 41-70% (intermediate) and 71-100% (high) following conventional insemination were collected for validation. Participants/materials, setting, methods Diff-Quik stained images of spermatozoa were processed by the K-means clustering algorithm to generate grey-scaled images of individual sperm heads. All sperm images of clinical samples were subjected an additional image conversion step using Cycle Generative Adversarial Network (CycleGAN) to ensure that their microenvironments are similar to those of the laboratory samples. A VGG 13 model was fine-tuned to classify a total of 1,083 images of ZP-bound and unbound spermatozoa over 50 epochs. Main results and the role of chance The newly fine-tuned VGG-13 model demonstrated excellent performance in classifying the ZP-bound and unbound spermatozoa, as reflected by the high sensitivity of 97.6%, specificity of 96.0%, and accuracy of 96.4%. It had a high discriminative power to distinguish between ZP-bound and unbound spermatozoa with an area under the receiver operating characteristic (ROC) curve (AUC) of 0.992. Saliency maps indicated that the model focused on the sperm head and mid-pieces in all images, with a primary emphasis on the anterior regions (43.0%±5.0%). The model was further validated on a vast collection of over 40,000 sperm images collected from the aforementioned fertilization groups. Our results revealed that the high fertilization rate group had a significantly higher percentage of predicted ZP-binding ability than the low fertilization rate group, as determined by the model (16.8%±7.2 vs. 3.2%±1.4; p &amp;lt; 0.05). By analyzing sperm images from infertile men (n = 113) in the high and low fertilization rates groups, a clinical threshold of 4.8% was identified using ROS curve (AUC:0.970) and Youden’s index, which can be used to distinguish between ZP-bound and unbound spermatozoa of clinical samples with a specificity of 93.8% and a sensitivity of 90.9%. Limitations, reasons for caution Our deep learning model is only applicable to diff-quik stained images of spermatozoa captured at high magnification. Further investigation is needed to examine its classification performance on images captured by different platforms and settings, ensuring consistent and reliable prediction accuracy regardless of varying degrees of image quality. Wider implications of the findings Our newly fine-tuned model can be used to evaluate sperm fertilizing potential, irrespective of the parameters evaluated in conventional semen analysis and to identify normospermic patients with defective ZP-binding ability who may benefit from intracytoplasmic sperm injection (ICSI) to improve their fertilization outcome. Trial registration number not applicable

Thermal Effects on Monolithic 3D Ferroelectric Transistors for Deep Neural Networks Performance

Monolithic three‐dimensional (M3D) integration advances integrated circuits by enhancing density and energy efficiency. Ferroelectric thin‐film transistors (Fe‐TFTs) attract attention for neuromorphic computing and back‐end‐of‐the‐line (BEOL) compatibility. However, M3D faces challenges like increased runtime temperatures due to limited heat dissipation, impacting system reliability. This work demonstrates the effect of temperature impact on single‐gate (SG) Fe‐TFT reliability. SG Fe‐TFTs have limitations such as read‐disturbance and small memory windows, constraining their use. To mitigate these, dual‐gate (DG) Fe‐TFTs are modeled using technology computer‐aided design, comparing their performance. Compute‐in‐memory (CIM) architectures with SG and DG Fe‐TFTs are investigated for deep neural networks (DNN) accelerators, revealing heat's detrimental effect on reliability and inference accuracy. DG Fe‐TFTs exhibit about 4.6x higher throughput than SG Fe‐TFTs. Additionally, thermal effects within the simulated M3D architecture are analyzed, noting reduced DNN accuracy to 81.11% and 67.85% for SG and DG Fe‐TFTs, respectively. Furthermore, various cooling methods and their impact on CIM system temperature are demonstrated, offering insights for efficient thermal management strategies.