Accuracy Assessment Research Articles

Preliminary assessment of the diagnostic accuracy of cutaneous T-cell lymphoma through deep sequencing of T-cell receptor gamma gene

Abstract Background The diagnostic challenges in early mycosis fungoides (MF) and other cutaneous T-cell lymphomas (CTCL) persist despite advancements in molecular methods. Aim The study aims to provide a preliminary assessment of next-generation sequencing in analyzing T-cell receptor gamma (TRG) sequences for distinguishing CTCL from benign inflammatory disorders. Methods Skin samples from CTCL and benign inflammatory skin disorders proven clinicopathologically were assessed for TRG by NGS. Results Our study analyzed skin samples from a total of 36 subjects, comprising 22 cases of CTCL, including 14 MF and 8 other CTCLs, alongside 14 cases of benign inflammatory skin disorders. According to the LymphoTrack criteria, monoclonality was detected in 75.0 % of the overall 24 CTCL patients. Specifically, in MF cases, 10 out of 14 were identified as monoclonality, with all four non-monoclonal cases being in the patch stage. For the other CTCL, 6 out of 8 cases displayed monoclonality. Among the overall 22 CTCL patients, 11 had multiple biopsies, with 9 displaying the same dominant clone across different sites. Among the 14 benign cases, only the case with erythrodermic psoriasis exhibited monoclonality. Our decision tree analysis suggests that a high frequency of the most abundant clone, its ratio to the third most abundant clone, and TRG V-I segment usage are effective markers aiding in diagnosing CTCL. Conclusion Combination of the clone frequencies, and TRG V segment usage may enhance diagnosis for MF and other CTCLs, aiding in differentiating them from benign conditions. However, molecular diagnosis for patch-stage MF remains challenging.

Potential of the upcoming Biomass P-band radar mission for digital terrain modelling beneath dense tropical forests: first accuracy assessment

Abstract. P-band radar surveys can be used to produce digital elevation models (DEMs) at ground level in dense tropical forest areas. However, the previous performance studies were carried out on DEMs derived from high-resolution synthetic aperture radar (SAR) acquisitions, while the upcoming Biomass space mission should provide DEMs at a coarser resolution due to a frequency bandwidth of 6 MHz in range. The aim of this study is to predict the quality of the DEM products derived from Biomass data through dense forest. A DEM was produced in a slant range geometry at a 15-m mesh size using SAR tomography. It was compared to the reference LiDAR survey in terms of elevation and slope, and the statistical distribution of the corresponding error was analysed with regards to the radar off-nadir angle and to the local slope and aspect. The results show that the DEM elevation has no systematic error despite the presence of forest, and it has an RMS error of 3 meters. The DEM slope has a mean error of 2° and an RMS error of 6°. The behaviour of these errors for different terrain slopes and aspects will allow to predict the quality of Biomass DEMs on a variety of terrestrial landscapes.

Prediction and assessment of meteorological drought in southwest China using long short-term memory model

Abstract Drought prediction is crucial for mitigating risks and designing measures to alleviate its impact. Machine learning models have been widely applied in the field of drought prediction in recent years. This study concentrated on predicting meteorological droughts in southwest China, a region prone to frequent and severe droughts, particularly in areas with sparse meteorological station coverage. The long short-term memory (LSTM) predictive model, which is a deep learning model, was constructed by calculating standardized precipitation evapotranspiration index (SPEI) values based on 144 weather station observations from 1980 to 2020. The 5-fold cross-validation method was used for the hyperparameter optimization of the model. The LSTM model underwent comprehensive assessment and validation through multiple methods. This included the use of several accuracy assessment indicators and a comparison of results. The comparison covered different drought characteristics among the LSTM predictive model, the benchmark random forest (RF) predictive model, the historical drought situations, and the calculated SPEI values based on observations from 144 weather stations. The results showed that the training results of the LSTM predictive model basically agreed with the SPEI values calculated from weather station observations. The model-predicted variation trend of SPEI values for 2020 was similar to the variation in SPEI values calculated based on weather station observations. On the test set, the coefficient of determination (R 2), the root mean square error, the explained variance score, the Nash–Sutcliffe efficiency, and the Kling–Gupta efficiency were 0.757, 0.210, 0.802, 0.761, and 0.212, respectively. The total consistency rate of the drought grade was 59.26%. The spatial correlation distribution of SPEI values between LSTM model prediction and calculation from meteorological stations in 2020 was more than 0.5 for most regions. The correlation coefficients exceeded 0.6 in western Tibet and Chengdu Plains. Compared to the RF model, the LSTM model excelled in all five performance evaluation metrics and demonstrated a higher overall consistency rate for drought categories. The Kruskal–Wallis test for both the LSTM and RF models all indicated no significant difference in the distributions between the predicted and observed data. Scatter plots revealed that the prediction accuracy for both models in 2020 was suboptimal, with the SPEI showing a comparatively narrow range of values. Nonetheless, the LSTM model significantly outperformed the RF model in terms of prediction accuracy. In summary, the LSTM model demonstrated good overall performance, accuracy, and applicability. It has the potential to enhance dynamic drought prediction in regions with complex terrain, diverse climatic factors, and sparse weather station networks.

Automated identification of earthen berms in Western US rangelands from LiDAR‐based digital elevation models

AbstractEarthworks such as earthen berms have been constructed across the western US since the late 1800s to mitigate erosion in landscapes where water is both the dominant driver of erosion and the limiting resource for biota. Berms alter hydrologic, geomorphic and ecologic processes by intercepting runoff and altering patterns of water availability in the landscape. Understanding site‐specific changes in process dynamics requires accurate mapping of berm locations and knowledge of their condition. This paper presents an automated, object‐based framework for identifying earthen berms from 1 m LiDAR‐derived digital elevation models in the western US rangelands. Geomorphon, a computer vision tool, was used to classify landforms and identify berm‐like landforms, including summits and ridges. Ten geomorphic and geometric attributes associated with each potential berm object were used to develop a machine‐learning model for distinguishing berms from natural summits and ridges. The model was trained and applied to independent test sites to identify and map berms. The mapped berms were compared with manually identified reference berms for accuracy assessment. The identification results achieved 79% to 87% recall, 82% to 92% precision and 81% to 89% F‐measure. We also explored the influence of training sample selection on model performance and conducted an analysis of attribute relative importance. The automated framework has the potential to be scaled up to larger areas in semi‐arid environments.

Ultrasound-guided percutaneous biopsy for challenging perihilar focal liver lesions: diagnostic accuracy and safety assessment.

In cases of perihilar focal liver lesions, distinguishing between benign strictures and malignancies is critical to prevent unnecessary surgery. Although the use of contrast-enhanced CT or MRI in combination with clinical and laboratory findings can aid in diagnosis, histologic examination is often necessary. Histologic specimens can be obtained through various techniques, including ERCP-guided brush cytology or intraductal biopsy, cholangioscopy-directed biopsy or endoscopic ultrasound (EUS). However, these methods have been associated with suboptimal sensitivity and specificity, sometimes leading to inconclusive results. Therefore, ultrasound-guided percutaneous biopsy (US-guided PB) may play a crucial role, but data is lacking for perihilar lesions. The objective of our study was to assess the technical feasibility and safety of US-guided PB for perihilar lesions. We included 20 consecutive patients who underwent US-guided PB of perihilar liver lesions that were not suitable for surgery between June 2018 and October 2023. All samples were obtained using a Menghini needle 20G and were adequate for histological examination, with a mean diameter of 12.3 mm (range 3-40 mm). Out of the 20 patients, 11 were diagnosed with malignancy while the remaining 9 had inflammatory or fibrotic tissue samples. No adverse events related to the procedure were reported. US-guided PB of perihilar liver lesions is a valuable and safe diagnostic approach to consider for patients who are not suitable for surgery.

A Comprehensive Evaluation of Machine Learning Algorithms for Digital Soil Organic Carbon Mapping on a National Scale

The aim of this study was to narrow the research gap of ambiguity in which machine learning algorithms should be selected for evaluation in digital soil organic carbon (SOC) mapping. This was performed by providing a comprehensive assessment of prediction accuracy for 15 frequently used machine learning algorithms in digital SOC mapping based on studies indexed in the Web of Science Core Collection (WoSCC), providing a basis for algorithm selection in future studies. Two study areas, including mainland France and the Czech Republic, were used in the study based on 2514 and 400 soil samples from the LUCAS 2018 dataset. Random Forest was first ranked for France (mainland) and then ranked for the Czech Republic regarding prediction accuracy; the coefficients of determination were 0.411 and 0.249, respectively, which was in accordance with its dominant appearance in previous studies indexed in the WoSCC. Additionally, the K-Nearest Neighbors and Gradient Boosting Machine regression algorithms indicated, relative to their frequency in studies indexed in the WoSCC, that they are underrated and should be more frequently considered in future digital SOC studies. Future studies should consider study areas not strictly related to human-made administrative borders, as well as more interpretable machine learning and ensemble machine learning approaches.

Assessment of pencil beam scanning proton therapy beam delivery accuracy through machine learning and log file analysis.

Comprehensive Quality Assurance (QA) protocols are necessary for complex beam delivery systems like Pencil Beam Scanning (PBS) proton therapy. This study focuses on automating the evaluation of beam delivery accuracy using irradiation log files and machine learning (ML) models. Irradiation log files of 935 clinical treatment fields and routine QA beams were analysed to evaluate spot parameters and Monitor Unit (MU) accuracy. ML models predicted spot size along theX,Y, major, and minor axes. In-house scripts automated log file analysis and spot size predictions. Predicted spot sizes were compared with expected baselines, and the accuracy of spot position, symmetry, and MU for each spot in the beam was evaluated. More than 99.5% of spot positions were accurate within a 1mm. The mean and Standard Deviation (SD) ofXpositional error were -0.021mm (SD: 0.181mm), and for Y positional error, they were -0.002mm (SD: 0.132mm). ML models accurately predicted spot sizes, with over 95% of spots demonstrating size variations within 10% of the baseline. The Root Mean Squared Error (RMSE) ofXand Y spot size differences were 0.15mm and 0.16mm, respectively. Spot symmetry was within 10%, and MU accuracy showed 95% of spots with MU per spot variation less than 2%. This method can validate the vendor's beam delivery safety interlock system and serve as a quick alternative to patient-specific QA in adaptive treatment, where time is limited, as well as for routine QA spot parameter evaluations.

Integrating Multisource Data and Machine Learning for Supraglacial Lake Detection: Implications for Environmental Management and Sustainable Development Goals in High Mountainous Regions

The accurate detection and monitoring of supraglacial lakes in high mountainous regions are crucial for understanding their dynamic nature and implications for environmental management and sustainable development goals. In this study, we propose a novel approach that integrates multisource data and machine learning techniques for supra-glacial lake detection in the Passu Batura glacier of the Hunza Basin, Pakistan. We extract pertinent features or parameters by leveraging multisource datasets such as radar backscatter intensity VH and VV parameters from Sentinel-1 Ground Range Detected (GRD) data, near-infrared (NIR), NDWI_green, NDWI_blue parameters from Sentinel-2 Multi-spectral Instrument(MSI) data, and surface slope, aspect, and elevation parameters from topographic data. The entire dataset is partitioned into training and testing sets, with machine learning models including the artificial neural network (ANN), the support vector machine (SVM), logistic regression (LR), random forest (RF), and K-nearest neighbour (KNN) trained on the training data (70%). Accuracy assessment employs testing data and involves the evaluation of metrics such as ROC curves and confusion matrices. The best-performing model, ANN, is validated against manually digitized lake polygons derived from Sentinel-2 and Google Earth Pro imagery. Furthermore, the digitized lake polygons are used to analyze glacial lake dynamics from 2016 to 2022. Key findings of this research presented that the NDWI_green, Sigma0_VH, and elevation are the most significant predictors in detecting supra-glacial lakes. Among the various trained and evaluated models, the Artificial Neural Network (ANN) achieved the highest performance (accuracy: 95%, AUC: 0.99) and accurately mapped supra-glacial lakes regardless of their small size. The findings have significant implications for understanding glacial lake behavior in the context of climate change and informing future research and monitoring efforts.

Accuracy assessment of offshore wind measurements partially compensated by MCP method considering data availability

Abstract In Japan, most offshore promotion areas for bottom-fixed wind turbines are in near-shore areas, where offshore wind speeds are not uniform. The dual-scanning LiDAR system (DSL), which is a remote-sensing technology, is widely used to measure the mean wind speed, wind direction, and turbulence for resource and site assessments. However, the availability of DSL data tends to be lower than the key performance indicators proposed in the Carbon Trust in Offshore Wind Accelerator project owing to the characteristics of DSL. Missing observed data can be predicted using the measure–correlate–predict (MCP) method, and the uncertainty of the MCP method can be examined using a prediction function. However, a method to evaluate the accuracy of the final dataset comprising observed data and data predicted by the MCP method is yet to be devised. In this study, a set of formulas is proposed to evaluate the accuracy of indices, such as the coefficient of determination, slope, and offset of linear regression, for a partially complemented dataset using the MCP method. The proposed formulas are validated against on-site measurements.

Accuracy assessment of LAI, PAI and FCOVER from Sentinel-2 and GEDI for monitoring forests and their disturbance in Central Germany

ABSTRACT Forest monitoring benefits from biophysical parameters such as Leaf Area Index (LAI), Plant Area Index (PAI) and fractional vegetation cover (FCOVER) and can be obtained from optical and LiDAR remote sensing, such as Sentinel-2 (S2) and the Global Ecosystem Dynamics Investigation (GEDI). While GEDI-derived products consider all phyto-elements, those from S2 refer to green elements only. Apart from individual accuracies, systemic deviations among products are thus expectable. However, products from S2 and GEDI lack inter-comparison. We evaluated S2 and GEDI-derived LAI, PAI and FCOVER with digital hemispherical photography observations (DHP) in a forest disturbance hotspot in Germany across various forest conditions, including vital stands, standing deadwood and clearings. We found moderate to high agreement with in-situ data, with highest accuracy for S2-derived LAI (R2 = 0.54) and GEDI-derived FCOVER (R2 = 0.73). Agreements between S2 and GEDI products were low, which we attribute to systematic influences of woody components, GEDI’s limitations in sloped terrain, and saturation of optical signals in dense canopy. In conclusion, findings suggest that while GEDI is effective in dense canopies, S2 products are beneficial for monitoring forest recovery. We also see potential for synergistic use in monitoring standing deadwood for habitat mapping and fire risk assessment.

Assessing the potential accuracy of a small-sized goniometer with extended dynamic range based on nuclear magnetic resonance

This paper evaluates potential accuracy characteristics of a small-sized goniometer based on nuclear magnetic resonance with an extended dynamic range. This required constructing a model of goniometer errors, estimating its accuracy based on this model, and formulating practical recommendations for the design of such a device based on the accuracy assessment. To evaluate the accuracy of a nuclear goniometer, a theoretical model was built that makes it possible to determine the optimal operating parameters of the cell gas mixture, the ranges of their permissible changes, the sensitivity of the goniometer, and the dependence of its characteristics on external and internal factors. In particular, the dependence of output signal of the device on the parameters of gas mixture and optical pumping has been determined. For a goniometer with a cell volume of 8 cm3, the optimum temperature is 130 °C, and the optimum intensity of the pumping radiation is 5 mW. The dependence of output signal on the measured angle of rotation was also established, as well as the noise and error dependence of the device on the permissible values of its parameters. Based on the model built, parameters of a goniometer with a cell volume of 8 cm3 were determined; the maximum angular sensitivity of such a goniometer with complete suppression of technical noise is δφsen=1.0 arcsec. The greatest contribution to the angle measurement error is from the instability of pumping power Ip (ΔIp/Ip=0.05) – 85 %, magnetic field B0 (ΔB0/B0=10-8) – 13 %, temperature T (ΔT/T=0,1) – 2 %. The goniometer under consideration corresponds to the medium accuracy class, δφtot≥10 arcsec. It could be used in optical manufacturing for operational control, calibration, and certification of optical products. To improve the angular accuracy of the goniometer, it is necessary to increase the stability of the laser pumping intensity

Planning Accuracy and Stem Offset Assessment in Digital Two-Dimensional Versus Three-Dimensional Planning in Cementless Hip Arthroplasty: A Systematic Review and Meta-Analysis

Background/Objectives: Total hip arthroplasty (THA) planning is crucial for restoring hip function and minimizing complications. The present systematic review and meta-analysis aimed to assess and compare the accuracy of 2D versus 3D preoperative planning in THA. Methods: The inclusion criteria were randomized controlled trials (RCTs) and observational studies (ROSs) published in English comparing the accuracy of 2D and 3D preoperative planning for total hip arthroplasty. We excluded review articles, registers, studies not written in English, studies that did not report the cup sizing accuracy or stem sizing accuracy or give a description of the preoperative planning method used, and non-comparative studies. In June 2024, following the PRISMA 2020 statement, a systematic review and a meta-analysis of the literature were conducted in PubMed, Scopus, and the Cochrane Library. The statistical analysis software Review Manager (RevMan) version 5.4 was used to perform the meta-analysis to compare the accuracy of 2D and 3D planning, and to assess the risk of bias, the ROBINS-I tool was used. Results: The analysis included 777 patients from six studies. The analysis showed that 3D planning offers superior precision compared to 2D planning, both for the cup (96.92% vs. 87.14%) and the stem (94.72% vs. 86.28%). The forest plots assessed a better trend for 3D planning in terms of exact size prediction and accuracy within ±1 size. Conclusions: The three-dimensional method was more precise and accurate than two-dimensional planning, both for the stem and the cup. It offered a detailed three-dimensional view of the patient’s anatomy. The main limitation was the challenge in finding homogeneous data regarding biomechanical parameters, surgical approaches, and different planning systems for both three-dimensional and two-dimensional methods.

Accuracy Assessment of Coastal Aquaculture Facility Detection Using Deep Learning Techniques

Accuracy Assessment of Coastal Aquaculture Facility Detection Using Deep Learning Techniques

Establishing a plastic waste map using remote sensing data in the coastal area of Thanh Hoa province (Vietnam)

Plastic pollution, particularly in oceans, is a growing environmental threat. Monitoring this pollution is challenging due to the shortage of data and tools. Remote sensing offers a promising solution by using various types of satellite and aerial images to detect and track plastic waste movement. Purpose. The study aims to establish a plastic waste map using remote sensing technology, focusing on the case study of the coastal area of Thanh Hoa province, Vietnam. Methodology. The study involves several steps, including the collection of plastic waste data (samples in the case study and indices from remote sensing images) as well as topographic and base map collection, statistics of plastic samples, grid design, calculation, interpolation, accuracy assessment, and mapping. Field surveys involved taking pictures of plastic debris along designated routes and a grid system was used to classify and calculate waste samples. Satellite images, especially Sentinel-2 MSI optical satellite imagery, are utilized to identify water areas of high plastic concentration. Findings. A map of plastic wastes in coastal areas of Thanh Hoa was created, with indices like NDWI (Normalized Difference Water Index) and FDI (Floating Debris Index) helping identify potential plastic waste signals. The resulting map reveals high concentrations of plastic waste in sea areas near the major river mouths of the Ma River basin and tourist areas, which aligns with areas of high human activity. Originality. This is the first study of plastic waste in the coastal area using remote sensing data in Thanh Hoa province, Vietnam. Practical value. This study can contribute to the effective management of marine plastic waste in Thanh Hoa while opening up opportunities for applying the method to create marine plastic waste maps throughout Vietnam and foster long-term monitoring and management.

Assessment of digital elevation models accuracy for local geoid modeling

One of the critical factors influencing the accuracy of a local geoid model is the quality of the digital elevation model (DEM). A properly selected high-resolution DEM can significantly mitigate errors in geoid modeling, gravity anomaly processing, and topography and downward continuation correction. Purpose. Evaluating the accuracy of five global DEMs obtained from open sources to identify the most suitable model for creating a local geoid. Methodology. The vertical accuracy of the DEMs was assessed by comparing the heights between the DEM and control points across different types of terrain. The reference values are based on 344 ground benchmarks, where GNSS observations were performed with subsequent adjustment of coordinates and heights. The accuracy analysis involved calculating statistical indicators of the height differences between the GNSS data and the DEM data. Findings. The standard deviation assessment showed favorable values for the COPERNICUS and ALOS DEMs, followed by SRTM, ASTER, and ETOPO. In the mean absolute error calculations for mountainous areas, the ALOS model performed best, followed by COPERNICUS, SRTM, ASTER, and ETOPO. For other types of terrain, COPERNICUS demonstrated the best results in mean absolute error. Originality. This study distinguishes itself through the incorporation of advanced high-resolution DEMs, such as GLO30, providing a modern and thorough evaluation of DEM accuracy specifically for Kazakhstan. What is new is a detailed analysis of the impact of terrain features (plain, hilly, mountainous) on modeling accuracy. This approach advances beyond previous assessments, delivering new and significant insights into the performance of contemporary DEMs. Practice value. The practical value of the results obtained consists in issuing recommendations regarding the possibility of using the studied DEM for the regions of Kazakhstan which differ among themselves in terms of landscape characteristics. The findings indicate that COPERNICUS and ALOS DEMs are highly suitable for precise geoid modeling in southern Kazakhstan. These models can significantly improve the accuracy of local geoid models, benefiting applications in geospatial science and engineering.

Accuracy assessment of global vertical displacement loading tide models for the equatorial and Indian Ocean

Accuracy assessment of global vertical displacement loading tide models for the equatorial and Indian Ocean

Development of Konseling-Ku.id website to improve Islamic guidance and counseling services

In the current era of the industrial revolution 4.0, digital technology-based innovations are urgently needed and are growing rapidly. The development method in this study is the Borg and Gall development model. The researcher made a development in the form of a website media named "konseling-ku.id". The purpose of research and development is to produce "Website Development "konseling-ku.id" to improve Islamic counseling guidance services. Based on the analysis of data from the development research results regarding konseling-ku.id websites in avery clear category, based on an assessment of usefulness, convenience, accuracy, attractiveness, and clarity that have been validated by two expert validators. The results of the qualitative analysis data are used as input to revise the product until the final product is produced on the konseling-ku.id website to improve the Islamic guidance and counseling services that have been theoretically accepted. The results of research and development show the effectiveness of counseling services through the https://konseling-ku.id/ website because it can provide convenience and benefits for peer counselors, professional counselors and counselors to conduct counseling that is not limited by distance and time.

The Evidence Base for Circulating Tumor DNA-Methylation in Non-Small Cell Lung Cancer: A Systematic Review and Meta-Analysis

Background: Non-Small Cell Lung Cancer (NSCLC) remains a challenging disease to manage with effectiveness. Early detection and precise monitoring are crucial for improving patient outcomes. Circulating tumor DNA (ctDNA) offers a non-invasive cancer detection and monitoring method. Emerging biomarkers, such as ctDNA methylation, have shown promise in enhancing diagnostic accuracy and prognostic assessment in NSCLC. In this review, we examined the current evidence regarding ctDNA methylation’s role in NSCLC detection through a systematic review of the existing literature and meta-analysis. Methods: We systematically searched PubMed, Medline, Embase, and Web of Science databases up to 26 June 2024 for studies on the role of ctDNA methylation analysis in NSCLC patients. We included studies from 2010 to 2024 on NSCLC patients. We excluded case reports, non-English articles, studies on cell lines or artificial samples, those without cfDNA detection, prognostic studies, and studies with non-extractable data or mixed cancer types. Funnel plots were visually examined for potential publication bias, with a p value < 0.05 indicating bias. Meta-analysis was conducted using R packages (meta, forestplot, and mada). Combined sensitivity, specificity, positive likelihood ratio (LR+), negative likelihood ratio (LR−), positive and negative predictive values, diagnostic odds ratio (DOR), and 95% confidence intervals (95% CI) were calculated. A summary receiver operating characteristic curve (SROC) and area under the curve (AUC) with related Standard Error (SE) were used to evaluate the overall diagnostic performance. Additionally, RASSF1A, APC, SOX17, SEPT9, and RARβ2 were analyzed, since their methylation was assessed in two or more studies. Results: From 38 candidate papers, we finally identified 12 studies, including 472 NSCLC patients. The pooled sensitivity was 0.62 (0.47–0.77) and the specificity was 0.90 (0.85–0.94). The diagnostic odds ratio was 15.6 (95% CI 9.36–26.09) and the area under the curve was 0.249 (SE = 0.138). The positive and negative predictive values were 5.38 (95% CI 3.89–7.44) and 0.34 (95% CI 0.22–0.54), respectively. For single genes, the specificity reached 0.83~0.96, except for RARβ2, but the sensitivity was relatively low for each gene. Significant heterogeneity across the included studies, the potential publication bias for specificity (p = 0.0231), and the need to validate the clinical utility of ctDNA methylation for monitoring treatment response and predicting outcomes in NSCLC patients represent the main limitations of this study. Conclusions: These results provide evidence of the significant potential of ctDNA methylation as a valuable biomarker for improving the diagnosis of NSCLC, advocating for its integration into clinical practice to enhance patient management.

Deep learning-based algorithm for staging secondary caries in bitewings.

Despite the notable progress in developing artificial intelligence (AI)-based tools for caries detection in bitewings, limited research has addressed the detection and staging of secondary caries. Therefore, we aimed to develop a Convolutional neural network (CNN)-based algorithm for these purposes using a novel approach for determining lesion severity. We used a dataset from a Dutch dental practice-based research network containing 2,612 restored teeth in 413 bitewings from 383 patients aged 15 to 88 years and trained the Mask R-CNN architecture with a Swin Transformer backbone. Two-stage training fine-tuned caries detection accuracy and severity assessment. Annotations of caries around restorations were made by two evaluators and checked by two other experts. Aggregated accuracy metrics (mean ± Standard Deviation - SD) in detecting teeth with secondary caries were calculated considering two thresholds: detecting all lesions and dentine lesions. The correlation between the lesion severity scores obtained with the algorithm and the annotators' consensus was determined using the Pearson correlation coefficient and Bland-Altman plots. Our refined algorithm showed high specificity in detecting all lesions (0.966 ± 0.025) and dentine lesions (0.964 ± 0.019). Sensitivity values were lower: 0.737 ± 0.079 for all lesions and 0.808 ± 0.083 for dentine lesions. The areas under ROC curves (SD) were 0.940 (0.025) for all lesions and 0.946 (0.023) for dentine lesions. The correlation coefficient for severity scores was 0.802. We developed an improved algorithm to support clinicians in detecting and staging secondary caries in bitewing, incorporating an innovative approach for annotation, considering the lesion severity as a continuous outcome.

Evaluating Accuracy of AI-Generated Travel Vaccine Recommendations: GPTs in Public Health

Abstract Introduction Artificial intelligence (AI), particularly generative pre-trained transformers (GPTs), holds promise for enhancing public health strategies like travel vaccine recommendations. This pilot study evaluated GPTs’ accuracy in delivering tailored vaccine advisories compared to standards set by public health professionals. Integrating AI’s data analysis capabilities into healthcare decision-making could improve recommendation precision and personalization. Methods This retrospective study analyzed GPT travel vaccine recommendation accuracy against a gold standard from health professionals for 90 travelers visiting various countries. Sociodemographic data and vaccine recommendation outcomes were examined. Accuracy assessments were stratified by age, sex, country of travel, duration of travel, type of travel, and specific vaccines. Results Preliminary results showed an 77.43% overall accuracy across all vaccine recommendations. Specific vaccine accuracies varied, with 97.78% alignment for hepatitis A, 93.51% for typhoid fever and 89.36% for rabies. However, lower accuracies were observed for cholera (33.33%) and encephalitis (56.25%). Moderate accuracies were noted for yellow fever (75%), 74.07% for malaria prophylaxis, diphtheria and tetanus (63.33%), and dengue (57.58%). Stratified analyses are expected to provide more realistic results and highlight discrepancies in certain groups. Conclusions This pilot demonstrates GPTs can be a valuable tool for supporting international vaccination professionals, but they are still not a substitute for these professionals, achieving 77.43% overall accuracy. Recommendations include: a) Educate health professionals in the use of GPTs, b) Developing guidelines for ethical and accurate AI use in public health, c) Using AI to strengthen surveillance and response systems. Combining AI with traditional strategies aims to optimize international traveler health outcomes. Key messages • Using artificial intelligence can optimize and facilitate the task of clinical consultancy in traveler’s advice. • It is necessary to establish guidelines for AI use to ensure ethical and accurate applications.