accuracy of counting Research Articles (Page 1)

Evaluation of large language models for carbohydrate counting in type 1 diabetes mellitus: a comparative study with patient estimations.

Reproducibility and standardization of methods are key approaches to microbiological research. However, laboratories differ widely in equipment, protocols, and operator expertise. These disparities are especially pronounced in fungal biology, since accurate spore counting and precise measurements of colony growth remain vulnerable to subjective bias and inconsistent technique. To standardize these foundational tasks, we developed two free, open-source image-analysis tools - SporeQuant and Orbisv2 - that automate hemocytometer spore counting and colony-area measurement, respectively. SporeQuant applies image thresholding and blob detection to identify individual spores and compute their concentration, while Orbisv2 segments colonies and calculates colony areas through thresholding and contour detection. Compared with manual analysis, SporeQuant and Orbis v2 markedly reduce analysis time by 63% and 76%, respectively, while achieving high measurement reliability, with MAE=0 for SporeQuant and R2>0.975 for Orbis v2. These tools reduce user-to-user variability, and achieve comparable or improved accuracy versus previously established methods. Furthermore, both tools can be accessed through a web page on both a computer or smartphone, requiring no specialized hardware, software, or prior knowledge. They provide accessible solutions for low-budget and high-throughput laboratories alike, enabling more consistent, scalable analysis of fungal growth and morphology in research and industrial settings.

This study aimed to (1) develop a novel method for fabricating simulated root canals, (2) introduce a reliable approach for detecting file fractures, and (3) establish a direct measurement technique for determining the number of cycles to failure (NCF) in bending fatigue tests of rotary files. Bending fatigue tests were conducted using a custom setup consisting of a simulated root canal, a handpiece-controller unit, and a signal extraction module for monitoring motor current and encoder signals. The simulated canals were fabricated to match the geometry of 25.06 ZenFlex rotary files, and included five configurations with varying radii (2, 5, and 8 mm) and angle of curvature (30°, 45°, and 60°). Tests were performed at room and body temperatures. File fracture was identified by an abrupt drop in motor current, and the NCF was directly determined from encoder-derived revolution counts. To verify accuracy, encoder-based revolution counts were compared with those measured with a mechanical counter. In addition, the proposed method was benchmarked against the conventional time-based calculation of NCF. The fabricated canals provided precise confinement of the files, ensuring reproducible curvature with negligible torsional distortion. Fractographic analysis revealed fatigue features, including striations radiating from the crack origin and dimples in the fast-fracture zone, confirming bending fatigue as the dominant failure mechanism. Encoder-based revolution counts closely matched those from the mechanical counter, with discrepancies of less than one revolution, and yielded slightly lower values than the conventional time-based method. Statistical analysis showed no significant difference between the proposed and conventional methods (p > 0.05). Fatigue life was significantly reduced at body temperature compared with room temperature (p < 0.05) and increased with larger radii of curvature (p < 0.05), while angle of curvature had no significant effect (p > 0.05). The proposed simulated root canals improved reproducibility and standardization of in vitro fatigue testing of files. The signal extraction method provided accurate revolution counts and a more realistic estimation of NCF than conventional time-to-failure methods, which overestimated actual values by 1.85 to 6.28% in this study.

Abstract Accurate counting of slender, densely stacked objects, such as welding wire stubs and welding electrode stubs, is crucial for the effective management of automated welding plants. However, the extreme aspect ratios and indistinct inter-object boundaries make the task highly challenging. To address these challenges, we propose a novel instance segmentation framework for accurately counting slender and dense objects, such as welding-wire stubs or welding electrode stubs. Specifically, its detection head adopts an instance-segmentation head with oriented bounding boxes (SegOBB), which adds an angular offset to the standard horizontal box, ensuring that each anchor tightly envelops the slender object. Subsequently, we propose an Edge feature fusion Feature Pyramid Network (EffFPN) as the neck to enhance boundary awareness. It fuses edge information of objects and boosts the network's capacity for extracting boundary features. During loss computation, we propose an Edge-guided cross-entropy loss (ECE loss). It combines the distance error between the edges of the predicted mask and the ground-truth mask with the binary cross-entropy loss, enabling the network to explicitly optimize mask boundaries and significantly improve both accuracy and convergence speed. Finally, comprehensive accuracy benchmarking and error evaluation conducted on both our self-collected dataset and established public datasets corroborate the proposed algorithm's validity and robustness, achieving an even more superior performance. We simultaneously developed an intelligent system for counting welding electrode stubs, demonstrating its practical applicability in welding workshops. These results demonstrate the effectiveness and robustness of the proposed novel instance-segmentation network.

Martian chronology is currently constrained using crater counting methodologies, in situ measurements onboard the Mars Science Laboratory (MSL) Curiosity rover, and significantly more precise radiometric isotope age measurements of meteorite samples. Each methodology has advantages and drawbacks. These include uncertainties surrounding crater counting accuracy and in situ ages from MSL, and the lack of field context and two age paradoxes associated with meteorite samples. Martian crater counting is calibrated to the less-than-certain lunar crater counting chronology, and in situ ages on Mars are difficult to calibrate to provide precise or accurate dates. The martian meteorite ‘surface age’ paradox details the observation that despite significant surface area on Mars with Hesperian ages (3.7–3.0 Ga), there are no meteorites with crystallization ages from this period. The other martian meteorite paradox, the ‘ancient Pb age’ paradox, is the discrepancy in relatively young shergottite crystallization ages (&lt;600 Ma) determined by 87 Rb– 87 Sr, 147 Sm– 143 Nd, 176 Lu– 176 Hf, 187 Re– 187 Os, 40 Ar/ 39 Ar and 40 K– 40 Ar isotope systematics compared with some relatively ancient apparent crystallization ages (&gt;4 Ga) from U–Th–Pb isotope systematics. The Mars Sample Return mission from Jezero crater holds great importance for the chronology of Mars, with its potential to elucidate the caveats within each of these chronology methods.

BackgroundArtificial intelligence (AI)–driven pose estimation (PE) offers a scalable and cost-effective solution to track exercises in mobile health apps. However, occlusion, influenced by camera angle and distance, can reduce detection accuracy and repetition counting precision. The influence of smartphone positioning on these performance metrics remains underexplored in controlled studies.ObjectiveThe study aimed to examine how smartphone camera angle (front, side, and diagonal) and distance (90 cm, 180 cm, 200 cm, and 360 cm) affect detection performance and repetition counting accuracy during push-ups and squats using AI-based PE.MethodsIn this cross-sectional, within-subject study, 44 healthy university students (9 [20.5%] female participants; mean age 20.3 y, SD 0.4 y; mean BMI 23.2, SD 0.6 kg/m²) were assigned to perform either squats or push-ups. Each participant completed their assigned exercise across 12 predefined smartphone camera configurations, yielding approximately 264 squat trials (n=22) and 264 push-up trials (n=22). Each trial consisted of an average of 5 repetitions, totaling approximately 1320 repetitions per exercise. PE performance was assessed using binary classification accuracy, detection rate, and mean absolute error (MAE) for repetition counting. Generalized linear mixed-effects models evaluated classification odds, linear mixed-effects models analyzed MAE, and Tukey-adjusted post hoc tests followed significant effects.ResultsThe mean detection rate was 61.1% (SD 48.8%) for push-ups and 61.5% (SD 48.7%) for squats, with MAEs of 1.08 (SD 1.78) and 1.11 (SD 1.82) repetitions, respectively. Push-ups were most accurately detected from diagonal views at 90 to 180 cm (up to 85.7% detection; MAE=0.28) and least accurately from the front at 360 cm (20%; MAE=2.70). Squats performed best from a diagonal view at 200 cm (95.5%; MAE=0.05) and worst from the side at 90 cm (0%; MAE=5). Generalized linear mixed models showed that for push-ups, the front 90 cm and diagonal 360 cm views significantly reduced classification odds compared to the side 90 cm view (P=.03 and P=.04, respectively), whereas for squats, diagonal and front views significantly outperformed side views across all distances (P<.001). Post hoc tests confirmed that for push-ups, diagonal close or mid-range views had significantly lower MAEs than far front views, and for squats, diagonal and front views at 180 to 200 cm achieved the highest accuracy and lowest MAEs (P<.05).ConclusionsAI-based PE effectiveness for exercise tracking is significantly affected by smartphone positioning. Diagonal and frontal views at mid-range distances (180‐200 cm) provided the highest detection accuracy and counting precision. These findings offer actionable guidance for developers, clinicians, coaches, and users optimizing mobile health exercise monitoring.

Small non-coding RNAs (sncRNA; < 200 nucleotide length) are of increasing research interest due to their key regulatory roles in a host of fundamental biological processes. For example, microRNAs (miRNAs), a specific class of sncRNAs, regulate gene expression through messenger RNA (mRNA) interactions, and their dysregulation is associated with disease. Classifying sncRNAs is an important bioinformatic task in small RNA-sequencing pipelines. Here we have developed an aligner called PymiRa, written in Python, to identify and quantify miRNAs from FASTA/FASTQ sequencing files. Unlike other approaches, PymiRa utilises a Burrows-Wheeler algorithm to align an input file against a reference hairpin precursor FASTA file derived from miRBase, the online miRNA registry, permitting up to two mismatches at the 3' end of a read. Previous tools used either a Burrows-Wheeler genome alignment or dynamic programming alignment to precursors; we demonstrate that combining both approaches yields improved results and efficiency. Importantly, the PymiRa aligner accounts for 3' post-transcriptional modifications to miRNAs that typically occur. PymiRa is a fast, accurate, and publicly accessible aligner available via GitHub and/or a webserver for sncRNA identification, including miRNAs, enabling accurate counts to be produced as part of a small RNA-sequencing pipeline. PymiRa will undergo relevant revisions over time e.g., with miRBase version updates. The PymiRa aligner will facilitate a deeper biological understanding of the landscape of sncRNA expression in normal physiological conditions and their dysregulation in disease states, including cancer.

Counterfeit and substandard pharmaceuticals represent a critical global health crisis, with the World Health Organisation (WHO) reporting that falsified medicines comprise 10% of the global pharmaceutical trade, constituting one of the fastest-growing grey economies worldwide. This illicit market affects all regions, including high-income countries, causing devastating health and economic consequences that contribute to increased mortality and morbidity rates. The problem is particularly severe in developing nations with inadequate regulatory systems. Mobile health (mHealth) technologies have emerged as promising solutions for enhancing pharmaceutical supply chain integrity. However, comprehensive frameworks that integrate multiple authentication mechanisms remain limited in addressing the growing counterfeit drug crisis. The primary objective of this study is to design and implement a novel mobile health framework that integrates innovative packaging technology and computer vision to enhance pharmaceutical integrity and patient safety. This innovative approach enables consumers to authenticate genuine drugs and detect counterfeit/spurious products through advanced Quick Response (QR) code verification systems and artificial intelligence- powered tablet recognition capabilities. The proposed system utilises individual strip QR codes that enable real-time scanning at the point of sale to verify drug authenticity, directly addressing critical gaps identified in current pharmaceutical authentication methods. To overcome the practical challenge of expiration date loss when medication strips are cut at pharmacies, we developed a computer vision-based Artificial Intelligence (AI) model that automatically recognises the number of tablets remaining in a strip and correlates this information with the unique Identifier (ID). This approach leverages recent advances in computer vision for pharmaceutical applications and automated packaging inspection technologies. Each medication strip is assigned to an individual customer at the time of purchase, with pharmacists recording detailed customer information to ensure comprehensive tracking and accountability throughout the pharmaceutical supply chain. The integrated mobile application creates a robust anti-counterfeiting ecosystem by combining secure QR code authentication with intelligent visual recognition capabilities. The computer vision model provides accurate tablet counting and strip identification, maintaining continuity of medication tracking even when packaging is modified during dispensing processes, thus significantly enhancing supply chain transparency. This dual-authentication approach builds consumer confidence in pharmaceutical authenticity while directly addressing critical vulnerabilities identified in current regulatory frameworks. This comprehensive mobile health solution provides a scalable, evidence-based approach to pharmaceutical authentication that can be readily implemented across diverse healthcare systems globally, offering substantial potential for reducing the circulation of falsified medicines and improving patient safety outcomes in the ongoing battle against the pandemic of counterfeit pharmaceuticals. To overcome the practical challenge of expiration date loss when medication strips are cut at pharmacies, we developed a computer vision-based Artificial Intelligence (AI) model that automatically recognises the number of tablets remaining in a strip and correlates this information with the unique Identifier (ID). This approach leverages recent advances in computer vision for pharmaceutical applications and automated packaging inspection technologies. Each medication strip is assigned to an individual customer at the time of purchase, with pharmacists recording detailed customer information to ensure comprehensive tracking and accountability throughout the pharmaceutical supply chain. The integrated mobile application creates a robust anti-counterfeiting ecosystem by combining secure QR code authentication with intelligent visual recognition capabilities. The computer vision model provides accurate tablet counting and strip identification, maintaining continuity of medication tracking even when packaging is modified during dispensing processes, thus significantly enhancing supply chain transparency. This dual-authentication approach builds consumer confidence in pharmaceutical authenticity while directly addressing critical vulnerabilities identified in current regulatory frameworks. This comprehensive mobile health solution provides a scalable, evidence-based approach to pharmaceutical authentication that can be readily implemented across diverse healthcare systems globally, offering substantial potential for reducing the circulation of falsified medicines and improving patient safety outcomes in the ongoing battle against the pandemic of counterfeit pharmaceuticals.

The increasing intensity of traffic object movement in urban areas has not been accompanied by adequate road infrastructure, resulting in traffic congestion, air pollution, and a higher risk of traffic accidents. One of the primary causes of accidents is traffic violations, particularly wrong-way driving behavior. This study develops a video-based automated traffic violation detection system using the YOLOv5 algorithm. A computer vision approach is employed to detect, classify traffic objects, and count wrong-way violations in real time. Due to limited access to real-world traffic violation footage, simulated traffic scenarios are used as testing data. The system is evaluated on four traffic object classes: motorcycles, cars, buses, and trucks. Experimental results demonstrate strong performance, achieving a precision of 90%, a recall of 92%, and an F1-score of 91%, while the traffic object counting accuracy reaches 89%. These findings indicate that the proposed system has significant potential to support traffic analysis and assist authorities in making more effective decisions to reduce congestion and traffic accidents.

Consumer Technology Association guidelines recommend two independent researchers review video recordings of treadmill bouts to verify accuracy of the number of steps taken. Performing multiple post hoc validation checks requires significant resources for personnel time and costs, but it is unknown if the burden is necessary. The purpose of this study was to evaluate accuracy and efficiency of step counts assessed during direct observation compared with multiple reviews of video recordings. Participants ages 18-20 years (n = 72) completed up to twelve 5-min, zero-incline treadmill bouts, speeds ranging 0.2-2.7 m/s (0.5-6.0 mph). Directly observed steps were counted and hand-tallied in real-time. A sex-age stratified random sample of 30 participants' bouts were selected for analysis. Two independent researchers recounted steps from video recordings, producing three independent counts. Intraclass correlation coefficient determined interrater reliability. Mean average percent deviation computed deviation magnitude among the three counts. Correlation tests determined the relationship between absolute count differences and average counts for each pairwise comparison. Interrater reliability was excellent with intraclass correlation coefficients ≥ .995 (p < .001) across all speeds. Average mean average percent deviation was 0.29% with bout-specific deviations ranging from 0.10% to 0.54%, indicating < 1% difference among the three counts for all bouts. A single real-time step count represents a sufficient and efficient approach to measure steps taken in a controlled treadmill setting, while video recounts serve as back-up to allay potential data loss concerns and/or for random selection verification. These data-driven findings are useful for optimizing personnel time and reducing costs associated with collecting quality data in large-scale treadmill-based step-counting studies.

Highlights This article proposes ISCF, a novel method for precise soybean pod and seed counting using a segmentation followed by a classification strategy. Compared to YOLO, ISCF offers faster inference, higher accuracy, and a more efficient pipeline for real-time applications. The proposed method focuses on the practical value of the lightweight design, making it deployable on edge devices for real-world use. The proposed method applies to the automated counting of seeds or fruits of various crops in controlled indoor environments, demonstrating strong generalizability and adaptability. Abstract. Accurate counting of soybean pods and seeds is essential for yield prediction, crop management, and variety improvement. However, existing automatic methods under controlled indoor conditions often exhibit limited computational efficiency, insufficient accuracy, and limited practical deployment for reducing manual workload. To address this, we propose an Indoor Soybean Counting Framework (ISCF), a lightweight deep learning framework that decouples localization and classification into two independent stages to count soybean pods and seeds. ISCF first performs precise segmentation of soybean pods using the proposed Indoor Soybean Segmentation Network (ISSN), followed by classification of the number of seeds per pod using a MobileNetV3-based architecture. Optimized for lightweight design, ISCF is well-suited to real-time deployment on edge devices. Experimental results demonstrate the superior performance of ISCF in soybean pod and seed counting tasks, achieving an AP 50 of 99.5% for pod segmentation, a mean absolute error (MAE) of merely 0.72, and an R 2 of 0.9942 for pod counting, and an MAE of 3.79 and an R 2 of 0.9573 for seed counting. Moreover, ISCF generalizes well to datasets from four additional crop species, underscoring its potential for a broad range of indoor crop counting and phenotyping applications. Keywords: Image classification, Image recognition, Instance segmentation, Lightweight network, Plant phenotyping, Soybean counting.

This study presents the development and implementation of a real-time human detection and counting system using the YOLOv11 deep learning algorithm. The system is designed to automatically monitor and analyze human flow within a campus environment as part of a Smart Campus initiative. A dataset of 1,000 human images obtained from Kaggle was used for model training, and data labeling was performed manually using the Roboflow platform. The YOLOv11 model was trained for 100 epochs with a batch size of 32 on a Google Colab T4 GPU. The proposed method integrates the YOLOv11 object detection framework with a centroid-based tracking algorithm and an in–out counting mechanism to determine directional human movement in real time. Experimental results show that the model achieved strong detection performance, with precision = 0.88, recall = 0.78, and mAP@0.5 = 0.87. The confusion matrix analysis demonstrated that 84% of actual human objects were correctly detected, while real-time video testing achieved stable tracking and reliable counting accuracy under different lighting and crowd conditions. Overall, the proposed YOLOv11-based system provides an effective, accurate, and robust solution for real-time human detection and flow monitoring, supporting the development of intelligent surveillance and Smart Campus applications.

Despite representing <1% of all musculoskeletal surgical pathology cases, primary musculoskeletal neoplasms are disproportionately emphasized in the surgical pathology literature, compared with non-neoplastic orthopedic pathology. Yet, there remains significant interest among practicing pathologists and their clinical colleagues to maintain expertise in the non-neoplastic arena, as evidenced by increasing volumes of non-neoplastic orthopedic diseases, often reflected in consult cases. Recent literature has renewed the discussion of arthroplasty, emphasized the clinical importance of pathologic examination, and provided updated diagnostic clarification for separating avascular necrosis from degenerative joint disease (DJD)/osteoarthritis (OA) with secondary osteonecrosis, acute infectious osteomyelitis from pseudoabscesses of DJD/OA, and revisited the diagnoses of subchondral insufficiency fracture and rapidly destructive arthropathy. Providing accurate neutrophil counts to help determine periprosthetic joint infection has rapidly become one of the most common sources of frozen section evaluation in the United States. Distinguishing periprosthetic joint infection from aseptic loosening has significant intraoperative implications. In addition to acute arthritis and mass effect, calcium pyrophosphate dihydrate (CPPD) deposition disease may lead to DJD/OA. However, most histologically confirmed examples of CPPD, involving the large extremity joints, are not identified preoperatively or radiologically, requiring pathologic evaluation to reliably establish the diagnosis. The incidence of CPPD deposits appears highest in the humeral head/shoulder, followed by the knees and hips/femoral head. Recent evidence has documented infrequent examples of combined gout and CPPD/pseudogout within the same tophi, associated with unique clinicopathologic features compared with those with gout alone. Carpal tunnel syndrome, trigger finger, and lumbar stenosis represent potential early red flags for the development of transthyretin (TR) cardiac amyloidosis. Although previously discarded at many institutions, excised tissue removed from such specimens, particularly tenosynovium from the carpal tunnel flexor retinaculum, are now routinely evaluated histologically with Congo red staining and, when positive, followed by mass spectrometry for confirmatory amyloid subtyping. With the use of a recently developed TR stabilizer, such as tafamidis, early histologic detection and treatment of TR cardiac amyloidosis has improved clinical outcomes. Herein is a summary of recent relevant developments in non-neoplastic orthopedic surgical pathology, updated diagnostic criteria and pitfalls, and the resulting clinical impact, where applicable.

RNA abundance quantification has become routine and affordable thanks to high-throughput "short-read" technologies that provide accurate molecule counts at the gene level. Similarly accurate and affordable quantification of definitive full-length, transcript isoforms has remained a stubborn challenge, despite its obvious biological significance across a wide range of problems. "Long-read" sequencing platforms now produce data-types that can, in principle, drive routine definitive isoform quantification. However some particulars of contemporary long-read datatypes, together with isoform complexity and genetic variation, present bioinformatic challenges. We show here, using ONT data, that fast and accurate quantification of long-read data is possible and that it is improved by exome capture. To perform quantifications we developed lr-kallisto, which adapts the kallisto bulk and single-cell RNA-seq quantification methods for long-read technologies.

Public land management relies on accurate visitor counts in order to understand and mitigate environmental impacts and to quantify the value of ecosystem services provided by natural areas. We build and test predictive visitation models suitable for publicly-managed parks, open space, and other protected lands based on multiple sources of digital mobility data including geotagged posts to social media platforms, community science observations, and a mobile device location dataset from a commercial vendor. Using observational visitation data series from the United States’ National Park Service, Forest Service, and Fish and Wildlife Service, we quantify the accuracy of statistical models to predict on-the-ground visitation using individual and combined sources of mobility data alongside other covariates. We find the predictive models performed best in settings where some on-site visitation data can be integrated into the models. On-site visitation data helps to account for meaningful differences in modeled relationships both within and across the three agencies considered. We find variation in the usefulness of the digital mobility data sources, with models combining multiple data sources outperforming those using a single source, including those based solely on mobile device locations. We discuss the practical implications of these findings as well as paths forward to improve visitation estimation on public lands.Supplementary InformationThe online version contains supplementary material available at 10.1038/s41598-025-26926-w.

Inventory management in warehouses faces challenges in terms of SKU (Stock Keeping Unit) counting accuracy, especially in the assembly process. The manual method used is not only time-consuming but also increases the risk of recording errors, which impacts overall operational performance. This study aims to design a technology-based SKU counter (Counting System) system to improve the efficiency and accuracy of assembly SKU counting. The system is designed with a warehouse technology approach that utilizes software to automatically count assembly SKUs and generate real-time inventory reports. Implementation is carried out through simulations in a warehouse environment to test aspects of speed and accuracy. The results show that the system is able to increase operational efficiency by up to 50%, optimize the inventory management process and significantly reduce recording errors in managing assembly SKUs in the warehouse.

Indoor residual spraying (IRS) is a vector control tool recommended by the WHO in areas of high malaria burden. Effective IRS implementation is complicated when up-to-date and accurate counts of structures eligible for IRS are unavailable; resultingly, programmatic spray coverage is typically calculated as the proportion of found structures that are sprayed. From 2016 – 2020 in Zambia, an open-source tool termed “Reveal,” was used to support digital mapping, microplanning, campaign monitoring and evaluation of IRS. Satellite imagery was used to enumerate structures and identify “spray areas,” clusters of structures for operational planning. Spray areas were visualized in the Reveal tool web-based planning module where campaign planners selected which would be sprayed and determined the resources required. Field teams used the Reveal tool mobile application to navigate and to record spray data against each structure. True coverage was calculated as the proportion of enumerated structures that were sprayed. Reveal was implemented in 21 districts across five years and coverage is reported for each district and year. Logistic regression models explored whether structures were more or less likely to be found and sprayed depending on a given calendar year’s targeting strategy, partner support level, and the year of Reveal implementation in a given district (first, second, third, or fourth). District-level programmatic IRS coverages overestimated the true adjusted coverages by an average 31.5 percentage points (range 2.8 - 69.4). The odds of finding and spraying structures increased with year of implementation; in the fourth year of implementation in a district, the odds of a household being sprayed and found were two times higher than in the first year of implementation. Digital tools improve structure and population estimates for planning and deployments in IRS campaigns, which may lead to more accurate coverage measurements and increased coverage over time.

Obesity prevalence continues to increase globally, with increased physical activity considered as the most effective intervention. Fitness activity tracker have been shown to assist people increase their physical activity level, with increasing number of features and affordability over the past decade. An affordable fitness tracker, Archon Alive 001 was compared to Actigraph wGT3x-BT, with participants walking on treadmill at three, four, five and eight kilometers per hour (kph) and hand tally used as criterion measurement. Mean Absolute Percentage Error (MAPE) of Archon and Actigraph relative to hand tally at varying speeds, and related bivariate correlation were calculated, along with multivariate analysis of variance to assess the effect of speed and participant demographics on tracker MAPE. Polar OH1 heart rate monitor synchronized with PNOĒ metabolic analyzer was used to monitor heart rate and calorie expenditure. MAPE and correlation between PNOĒ and Archon calorie expenditure was calculated. Bland-Altman analysis and Intraclass Correlation Coefficient (ICC) was used to compare heart rate measurement between Polar and Archon. Compared to hand tally calculations, Archon step count was accurate, with average MAPE of 3.46%, and average correlation of r = 0.986, p < 0.001, while Actigraph average MAPE was 31.46%, with average correlation of r = 0.513, p = 0.001 at various speed. Age and speed had small effect on Archon’s accuracy. Sex had small effect, while speed had a large effect on Actigraph accuracy. Archon heart rate had Intraclass Correlation Coefficient (ICC) of 75.8%, with mean difference of -3.33 beats per minute (bpm) and 95% Limit of Agreement at -31.55 bpm to 24.90 bpm relative to Polar OH1. Archon total calorie expenditure output had 29.3% MAPE, and correlation r = 0.629, p < 0.001 relative to PNOĒ. Archon Alive demonstrated high accuracy in step counting, along with acceptable reliability and accuracy for heart rate and calorie expenditure measurements, making it sufficient for monitoring exercise intensity. Heart rate and calorie expenditure outputs were insufficiently accurate for clinical assessment.

Temporomandibular disorders (TMDs) and orofacial pain (OFP) demand advanced diagnostic and clinical reasoning skills in dental education. Traditional simulations with real patients face limitations in availability and standardization. Generative artificial intelligence (GAI), such as ChatGPT-3.5, has emerged as a potential tool for clinical training. This blinded, cross-sectional, crossover study involved 30 undergraduate dental students, each completing two simulated cases: one with ChatGPT-3.5 and one with standardized real patients. Cases were developed and validated by TMD/OFP specialists via the Delphi method and incorporated into the AI through structured prompts. Quantitative parameters (such as responses, word count, follow-up questions, reformulations, and diagnostic accuracy) and qualitative aspects (such as empathy, clarity, and relevant information) were analyzed. GAI simulations provided higher information density (231vs.167 relevant units; p<0.001) and clearer reasoning flow. Students interacting with real patients asked more follow-up questions (p=0.004) and required more reformulations (p=0.011), indicating more adaptive communication. Diagnostic accuracy did not differ significantly (p>0.05). Relevant information correlated positively with diagnostic accuracy (r=0.484; p=0.007), whereas total word count correlated negatively (r=-0.386; p=0.035). ChatGPT-3.5 matched real patient simulations in diagnostic reasoning for TMD/OFP. Combining GAI's scalability and standardization with real patient variability may optimize clinical competency training.

Gastrointestinal (GI) parasites remain a significant global challenge to livestock health and farm productivity, particularly in resource-limited regions. Accurate and reliable fecal egg count (FEC) methods are essential for quantifying parasite burden and evaluating anthelmintic efficacy. This study compared the diagnostic performance of the Mini-FLOTAC and the modified McMaster techniques for detecting GI parasites in West African Long-legged (WALL) sheep under field conditions in southern Benin. A cross-sectional survey was conducted, during which 200 fresh fecal samples were collected from four-month-old lambs across five representative sheep farms. Each sample was divided and analyzed in parallel using the Mini-FLOTAC (using 2 g of feces diluted in a 1:10 ratio with saturated sodium chloride solution) and the modified McMaster technique (using 3 g of feces in a 1:15 dilution). Diagnostic parameters, including the intensity of infection expressed as eggs/oocysts per gram of feces (EPG/OPG, respectively), the prevalence, and the precision, were statistically analyzed and compared. Method agreement was assessed using Cohen’s kappa coefficient. The Mini-FLOTAC technique demonstrated superior performance, detecting a broader spectrum of parasites, including Nematodirus spp., Marshallagia spp., and Moniezia spp., which were frequently undetected by McMaster. Agreement between techniques was high for strongylids and Eimeria spp. (κ ≥ 0.76), but poor for other taxa (κ < 0.30). Mini-FLOTAC recorded significantly higher FECs and oocyst per gram of feces (OPG) values across farms (p < 0.05), and consistently exhibited greater diagnostic precision, with lower coefficients of variation (CVs ranging from 12.37% to 18.94%) and higher reproducibility (> 80% precision). Misclassification analysis revealed that the McMaster method underdiagnosed up to 12.5% of infections, especially for low-shedding species. These findings highlight Mini-FLOTAC as a more sensitive, precise, and operationally robust tool for GI parasite surveillance in small ruminants. Its adoption can improve the reliability of epidemiological monitoring and support sustainable parasite control programs in resource-limited settings.