RESUMEN

This work aims to explore the application of an improved convolutional neural network (CNN) combined with Internet of Things (IoT) technology in art design education and teaching. The development of IoT technology has created new opportunities for art design education, while deep learning and improved CNN models can provide more accurate and effective tools for image processing and analysis. In order to enhance the effectiveness of art design teaching and students' creative expression, this work proposes an improved CNN model. In model construction, it increases the number of convolutional layers and neurons, and incorporates the batch normalization layer and dropout layer to enhance feature extraction capabilities and reduce overfitting. Besides, this work creates an experimental environment using IoT technology, capturing art image samples and environmental data using cameras, sensors, and other devices. In the model application phase, image samples undergo preprocessing and are input into the CNN for feature extraction. Sensor data are concatenated with image feature vectors and input into the fully connected layers to comprehensively understand the artwork. Finally, this work trains the model using techniques such as cross-entropy loss functions and L2 regularization and adjusts hyperparameters to optimize model performance. The results indicate that the improved CNN model can effectively acquire art sample data and student creative expression data, providing accurate and timely feedback and guidance for art design education and teaching, with promising applications. This work offers new insights and methods for the development of art design education.

RESUMEN

PURPOSE: In vesicourethral anastomosis (VUA), which is part of robot-assisted radical prostatectomy, surgeons must proceed carefully to avoid urethral damage. We developed and evaluated a VUA bench-top model that can measure the traction force on the urethra during robotic surgery. MATERIALS AND METHODS: The VUA model included the urethra, bladder, pelvic bones, and a small force sensor that was capable of measuring the traction force on the urethra. Eight skilled and eight novice urologists performed a VUA task in robotic surgery. The skilled surgeons assessed the model's realism and usefulness as a training tool using a 5-point Likert scale. The evaluation items [task time, maximum force, force volume, and length of time that specific excessive forces were applied to the urethra (2, 3, 4, and ≥ 5 N)] were compared between the skilled and novice surgeons using the Mann-Whitney U test. Measurements were conducted in four directions with respect to the maximum force on the urethra: 11-1, 2-4, 5-7, and 8-10 o'clock. RESULTS: The quality of the model was scored 3.7 to 4.9 points for all 16 items in 4 domains except for "Usefulness compared with animal models." There were differences in the task time and almost all force parameters between the skilled and novice surgeons. CONCLUSION: We developed a relatively high-quality VUA bench-top model that measures traction force on the urethra, and we have revealed differences in the forces of action on the urethra in two groups of surgeons with different skill levels.

Asunto(s)

RESUMEN

INTRODUCTION: The integration of augmented reality (AR) in spine surgery marks a significant advancement, enhancing surgical precision and patient outcomes. AR provides immersive, three-dimensional visualizations of anatomical structures, facilitating meticulous planning and execution of spine surgeries. This technology not only improves spatial understanding and real-time navigation during procedures but also aims to reduce surgical invasiveness and operative times. Despite its potential, challenges such as model accuracy, user interface design, and the learning curve for new technology must be addressed. AR's application extends beyond the operating room, offering valuable tools for medical education and improving patient communication and satisfaction. MATERIAL AND METHODS: A literature review was conducted by searching PubMed and Scopus databases using keywords related to augmented reality in spine surgery, covering publications from January 2020 to January 2024. RESULTS: In total, 319 articles were identified through the initial search of the databases. After screening titles and abstracts, 11 articles in total were included in the qualitative synthesis. CONCLUSION: Augmented reality (AR) is becoming a transformative force in spine surgery, enhancing precision, education, and outcomes despite hurdles like technical limitations and integration challenges. AR's immersive visualizations and educational innovations, coupled with its potential synergy with AI and machine learning, indicate a bright future for surgical care. Despite the existing obstacles, AR's impact on improving surgical accuracy and safety marks a significant leap forward in patient treatment and care.

RESUMEN

Precision in grazing management is highly dependent on accurate pasture monitoring. Typically, this is often overlooked because existing approaches are labour-intensive, need calibration, and are commonly perceived as inaccurate. Machine-learning processes harnessing big data, including remote sensing, can offer a new era of decision-support tools (DST) for pasture monitoring. Its application on-farm remains poor because of a lack of evidence about its accuracy. This study aimed at evaluating and quantifying the minimum data required to train a machine-learning satellite-based DST focusing on accurate pasture biomass prediction using this approach. Management data from 14 farms in New South Wales, Australia and measured pasture biomass throughout 12 consecutive months using a calibrated rising plate meter (RPM) as well as pasture biomass estimated using a DST based on high temporal/spatial resolution satellite images were available. Data were balanced according to farm and week of each month and randomly allocated for model evaluation (20%) and for progressive training (80%) as follows: 25% training subset (1W: week 1 in each month); 50% (2W: week 1 and 3); 75% (3W: week 1, 3, and 4); and 100% (4W: week 1 to 4). Pasture biomass estimates using the DST across all training datasets were evaluated against a calibrated rising plate meter (RPM) using mean-absolute error (MAE, kg DM/ha) among other statistics. Tukey's HSD test was used to determine the differences between MAE across all training datasets. Relative to the control (no training, MAE: 498 kg DM ha-1) 1W did not improve the prediction accuracy of the DST (P > 0.05). With the 2W training dataset, the MAE decreased to 342 kg DM ha-1 (P < 0.001), while for the other training datasets, MAE decreased marginally (P > 0.05). This study accounts for minimal training data for a machine-learning DST to monitor pastures from satellites with comparable accuracy to a calibrated RPM which is considered the 'gold standard' for pasture biomass monitoring.

Asunto(s)

RESUMEN

RNA-dependent liquid-liquid phase separation (LLPS) proteins play critical roles in cellular processes such as stress granule formation, DNA repair, RNA metabolism, germ cell development, and protein translation regulation. The abnormal behavior of these proteins is associated with various diseases, particularly neurodegenerative disorders like amyotrophic lateral sclerosis and frontotemporal dementia, making their identification crucial. However, conventional biochemistry-based methods for identifying these proteins are time-consuming and costly. Addressing this challenge, our study developed a robust computational model for their identification. We constructed a comprehensive dataset containing 137 RNA-dependent and 606 non-RNA-dependent LLPS protein sequences, which were then encoded using amino acid composition, composition of K-spaced amino acid pairs, Geary autocorrelation, and conjoined triad methods. Through a combination of correlation analysis, mutual information scoring, and incremental feature selection, we identified an optimal feature subset. This subset was used to train a random forest model, which achieved an accuracy of 90% when tested against an independent dataset. This study demonstrates the potential of computational methods as efficient alternatives for the identification of RNA-dependent LLPS proteins. To enhance the accessibility of the model, a user-centric web server has been established and can be accessed via the link: http://rpp.lin-group.cn.

RESUMEN

BACKGROUND AND OBJECTIVES: Spinal surgery, particularly for cervical pathologies such as myelopathy and radiculopathy, requires a blend of theoretical knowledge and practical skill. The complexity of these conditions, often necessitating surgical intervention, underscores the need for intricate understanding and precision in execution. Advancements in neurosurgical training, especially with the use of low-cost 3D models for simulating cervical spine tumor removal, are revolutionizing this field. These models provide the realistic and hands-on experience crucial for mastering complex neurosurgical techniques, filling gaps left by traditional educational methods. MATERIALS AND METHODS: This study aimed to assess the effectiveness of 3D-printed cervical vertebrae models in enhancing surgical skills, focusing on tumor removal, and involving 20 young neurosurgery residents. These models, featuring silicone materials to simulate the spinal cord and tumor tissues, provided a realistic training experience. The training protocol included a laminectomy, dural incision, and tumor resection, using a range of microsurgical tools, focusing on steps usually performed by senior surgeons. RESULTS: The training program received high satisfaction rates, with 85% of participants extremely satisfied and 15% satisfied. The 3D models were deemed very realistic by 85% of participants, effectively replicating real-life scenarios. A total of 80% found that the simulated pathologies were varied and accurate, and 90% appreciated the models' accurate tactile feedback. The training was extremely useful for 85% of the participants in developing surgical skills, with significant post-training confidence boosts and a strong willingness to recommend the program to peers. CONCLUSIONS: Continuing laboratory training for residents is crucial. Our model offers essential, accessible training for all hospitals, regardless of their resources, promising improved surgical quality and patient outcomes across various pathologies.

RESUMEN

We present a novel set of quantitative measures for "likeness" (error function) designed to alleviate the time-consuming and subjective nature of manually comparing biological recordings from electrophysiological experiments with the outcomes of their mathematical models. Our innovative "blended" system approach offers an objective, high-throughput, and computationally efficient method for comparing biological and mathematical models. This approach involves using voltage recordings of biological neurons to drive and train mathematical models, facilitating the derivation of the error function for further parameter optimization. Our calibration process incorporates measurements such as action potential (AP) frequency, voltage moving average, voltage envelopes, and the probability of post-synaptic channels. To assess the effectiveness of our method, we utilized the sea slug Melibe leonina swim central pattern generator (CPG) as our model circuit and conducted electrophysiological experiments with TTX to isolate CPG interneurons. During the comparison of biological recordings and mathematically simulated neurons, we performed a grid search of inhibitory and excitatory synapse conductance. Our findings indicate that a weighted sum of simple functions is essential for comprehensively capturing a neuron's rhythmic activity. Overall, our study suggests that our blended system approach holds promise for enabling objective and high-throughput comparisons between biological and mathematical models, offering significant potential for advancing research in neural circuitry and related fields.

RESUMEN

Orientar la Estomatología hacia la promoción y prevención es una demanda actual de la Organización Mundial de la Salud. El objetivo de la investigación fue argumentar un modelo de formación del desempeño profesional en el estudiante de Estomatología que atendiera a esta demanda. Los métodos utilizados en la investigación fueron el analítico-sintético, el inductivo-deductivo, la modelación sistémico estructural funcional, y los talleres de reflexión crítica y construcción colectiva. El modelo parte de la asunción de que la práctica preprofesional es un ecosistema académico-laboral-investigativo idóneo para realizar la sistematización formativa del contenido. Se ha estructurado como un sistema compuesto por tres subsistemas que siguen la lógica del proceso de formación del desempeño profesional en promoción y prevención en la atención en pos de la salud bucal durante la práctica preprofesional: aprestamiento para la formación, sistematización formativa contextual y valoración de la transformación de este desempeño. Entre los subsistemas se establecen relaciones de coordinación y complementariedad, de estas relaciones surge la idoneidad formativa del desempeño profesional en promoción y prevención en salud bucal. El modelo fue valorado por especialistas en talleres de opinión crítica y construcción colectiva, los cuales confirmaron su pertinencia al considerarlo que responde a una problemática actual de la educación médica superior, en particular en el área de la Estomatología.

Orienting Stomatology towards the promotion and prevention is a current demand of the World Health Organization. The objective of the research was to argue a training model of professional performance in the Stomatology student that would meet this demand. The methods used in the research were analytical-synthetic, inductive-deductive, systemic-structural-functional modeling, and critical reflection and collective construction workshops. The model is based on the assumption that pre-professional practice is an ideal academic-labour-research ecosystem to carry out the formative systematization of content. It has been structured as a system made up of three subsystems that follow the logic of the training process of professional performance in promotion and prevention in care in pursuit of oral health during pre-professional practice: readiness for training, contextual training systematization and assessment of the transformation of this performance. Between the subsystems, coordination and complementarity relationships are established, from these relationships arises the formative suitability of professional performance in promotion and prevention in oral health. The model was evaluated by specialists in critical opinion and collective construction workshops, who confirmed its relevance by considering it to respond to a current problem in higher medical education, particularly in the area of Stomatology.

RESUMEN

Growing regulatory requirements set barriers around genetic data sharing and collaborations. Moreover, existing privacy-aware paradigms are challenging to deploy in collaborative settings. We present COLLAGENE, a tool base for building secure collaborative genomic data analysis methods. COLLAGENE protects data using shared-key homomorphic encryption and combines encryption with multiparty strategies for efficient privacy-aware collaborative method development. COLLAGENE provides ready-to-run tools for encryption/decryption, matrix processing, and network transfers, which can be immediately integrated into existing pipelines. We demonstrate the usage of COLLAGENE by building a practical federated GWAS protocol for binary phenotypes and a secure meta-analysis protocol. COLLAGENE is available at https://zenodo.org/record/8125935 .

Asunto(s)

RESUMEN

BACKGROUND: The reporting of machine learning (ML) prognostic and diagnostic modeling studies is often inadequate, making it difficult to understand and replicate such studies. To address this issue, multiple consensus and expert reporting guidelines for ML studies have been published. However, these guidelines cover different parts of the analytics lifecycle, and individually, none of them provide a complete set of reporting requirements. OBJECTIVE: We aimed to consolidate the ML reporting guidelines and checklists in the literature to provide reporting items for prognostic and diagnostic ML in in-silico and shadow mode studies. METHODS: We conducted a literature search that identified 192 unique peer-reviewed English articles that provide guidance and checklists for reporting ML studies. The articles were screened by their title and abstract against a set of 9 inclusion and exclusion criteria. Articles that were filtered through had their quality evaluated by 2 raters using a 9-point checklist constructed from guideline development good practices. The average κ was 0.71 across all quality criteria. The resulting 17 high-quality source papers were defined as having a quality score equal to or higher than the median. The reporting items in these 17 articles were consolidated and screened against a set of 6 inclusion and exclusion criteria. The resulting reporting items were sent to an external group of 11 ML experts for review and updated accordingly. The updated checklist was used to assess the reporting in 6 recent modeling papers in JMIR AI. Feedback from the external review and initial validation efforts was used to improve the reporting items. RESULTS: In total, 37 reporting items were identified and grouped into 5 categories based on the stage of the ML project: defining the study details, defining and collecting the data, modeling methodology, model evaluation, and explainability. None of the 17 source articles covered all the reporting items. The study details and data description reporting items were the most common in the source literature, with explainability and methodology guidance (ie, data preparation and model training) having the least coverage. For instance, a median of 75% of the data description reporting items appeared in each of the 17 high-quality source guidelines, but only a median of 33% of the data explainability reporting items appeared. The highest-quality source articles tended to have more items on reporting study details. Other categories of reporting items were not related to the source article quality. We converted the reporting items into a checklist to support more complete reporting. CONCLUSIONS: Our findings supported the need for a set of consolidated reporting items, given that existing high-quality guidelines and checklists do not individually provide complete coverage. The consolidated set of reporting items is expected to improve the quality and reproducibility of ML modeling studies.

Asunto(s)

RESUMEN

Background: Stratify new lung cancer patients based on the risk of in-hospital mortality rate after diagnosis. Methods: 522,941 lung cancer cases with available data on the Surveillance, Epidemiology, and End Results (SEER) were analyzed for the predicted probability based on six fundamental variables including age, gender, tumor size, T, N, and AJCC stages. The patients were randomly assigned to the training (n = 115,145) and validation datasets (n = 13,017). The remaining cohort with missing values (n = 394,779) was then combined with the primary lung tumour datasets (n = 1018) from The Cancer Genome Atlas, Lung Adenocarcinoma and Lung Squamous Cell Carcinoma projects (TCGA-LUAD & TCGA-LUSC) for external validation and sensitivity analysis. Results: Receiver Operating Characteristic (ROC) analyses showed high discriminatory power in the training and internal validation cohorts (Area under the curve [AUC] of 0.78 (95%CI = 0.78-0.79) and 0.78 (95%CI = 0.77-0.79), respectively), whereas that of the model on external validation data was 0.759 (95%CI = 0.757-0.761). We developed a static nomogram, a web app, and a risk table based on a logistic regression model using algorithm-selected variables. Conclusions: Our model can stratify lung cancer patients into high- and low-risk of in-hospital mortality to assist clinical further planning.

Asunto(s)

RESUMEN

This paper delves into image detection based on distributed deep-learning techniques for intelligent traffic systems or self-driving cars. The accuracy and precision of neural networks deployed on edge devices (e.g., CCTV (closed-circuit television) for road surveillance) with small datasets may be compromised, leading to the misjudgment of targets. To address this challenge, TensorFlow and PyTorch were used to initialize various distributed model parallel and data parallel techniques. Despite the success of these techniques, communication constraints were observed along with certain speed issues. As a result, a hybrid pipeline was proposed, combining both dataset and model distribution through an all-reduced algorithm and NVlinks to prevent miscommunication among gradients. The proposed approach was tested on both an edge cluster and Google cluster environment, demonstrating superior performance compared to other test settings, with the quality of the bounding box detection system meeting expectations with increased reliability. Performance metrics, including total training time, images/second, cross-entropy loss, and total loss against the number of the epoch, were evaluated, revealing a robust competition between TensorFlow and PyTorch. The PyTorch environment's hybrid pipeline outperformed other test settings.

RESUMEN

BACKGROUND: Artificial Intelligence (AI) has had an important impact on many industries as well as the field of medical diagnostics. In healthcare, AI techniques such as case-based reasoning and data driven machine learning (ML) algorithms have been used to support decision-making processes for complex tasks. This is used to assist medical professionals in making clinical decisions. A way of supporting clinicians is providing predicted prognoses of various ML models. OBJECTIVES: Training an ML model based on the data of a hospital and using it on another hospital have some challenges. METHODS: In this research, we applied data analysis to discover required data filters on a hospital's EHR data for training a model for another hospital. RESULTS: We applied experiments on real-world data of ELGA (Austrian health record system) and KAGes (a public healthcare provider of 20+ hospitals in Austria). In this scenario, we train the prediction model for ELGA- authorized health service providers using the KAGes data since we do not have access to the complete ELGA data. CONCLUSION: Finally, we observed that filtering the data with both feature and value selection increases the classification performance of the prediction model, which is trained for another system.

Asunto(s)

RESUMEN

Objective: To explore the potential application value of animal model training in improving the comprehensive clinical ability of postgraduate students of dentistry and to provide reference for new methods of preclinical skills teaching. Methods: A total of 40 postgraduate students of dentistry were assigned to two groups, an experimental group and a control group. The control group took the routine teaching course on root canal treatment for the right mandibular first molar, using a simulated model of human head. The experimental group also took a teaching course on root canal therapy for the right mandibular first molar, but an animal model was used for the group. After the course was completed, the instructor conducted comprehensive evaluation of the students' psychological quality, patient communication skills, diagnosis and treatment logic, speed of performing procedures, and treatment plan design. A questionnaire survey was conducted to examine the students' attitudes toward and evaluation of animal model training. Results: The scores for psychological quality (0.430±0.024 vs. 0.115±0.036), patient communication skills (0.878±0.065 vs. 0.115±0.036), diagnosis and treatment logic (0.630±0.066 vs. 0.372±0.033), speed of performing procedures (0.8975±0.019 vs. 0.055±0.080), and treatment plan design (0.539±0.036 vs. 0.396±0.017) of the experimental group were significantly higher than those of the control group ( P<0.0001). The total score of the experimental group (3.374±0.184) was significantly higher than that of the control group (1.053±0.082) and the difference was statistically significant ( P<0.001). 95% of the students in the control group and 100% of those in the experimental group were willing to participate in animal model training to improve their level of diagnosis and treatment skills for dental and endodontic diseases, showing no statistically significant difference ( χ 2=1.026, P=0.3112). In the experimental group, 30% of the students believed that their psychological qualities had been improved, 50% believed that their procedure skills had been improved, and 20% believed that animal model training had expanded the scope of their theoretical knowledge. Conclusion: Adding animal model training can improve dentistry graduate students' comprehensive abilities, including their psychological quality, patient communication skills, diagnosis and treatment logic, speed of performing procedures, and treatment plan design. In addition, it helps students familiarize themselves in advance with animal experimental operations for basic research, thus helping them acquire dual professional skills.

Asunto(s)

RESUMEN

The classification of time series is essential in many real-world applications like healthcare. The class of a time series is usually labeled at the final time, but more and more time-sensitive applications require classifying time series continuously. For example, the outcome of a critical patient is only determined at the end, but he should be diagnosed at all times for timely treatment. For this demand, we propose a new concept, Continuous Classification of Time Series (CCTS). Different from the existing single-shot classification, the key of CCTS is to model multiple distributions simultaneously due to the dynamic evolution of time series. But the deep learning model will encounter intertwined problems of catastrophic forgetting and over-fitting when learning multi-distribution. In this work, we found that the well-designed distribution division and replay strategies in the model training process can help to solve the problems. We propose a novel Adaptive model training strategy for CCTS (ACCTS). Its adaptability represents two aspects: (1) Adaptive multi-distribution extraction policy. Instead of the fixed rules and the prior knowledge, ACCTS extracts data distributions adaptive to the time series evolution and the model change; (2) Adaptive importance-based replay policy. Instead of reviewing all old distributions, ACCTS only replays important samples adaptive to their contribution to the model. Experiments on four real-world datasets show that our method outperforms all baselines.

RESUMEN

Introduction: Given the extensive training required for laparoscopic pyeloplasty and the difficulties achieving this training, there is a need to recreate the activity in a controlled environment, but high-fidelity models are unavailable or expensive. Our objective was to develop a model of pyeloureteral junction stenosis, resembling the anatomical details and consistency of natural tissue, for a replicable, cheaper, and realistic simulation model of laparoscopic pyeloplasty in children. Materials and Methods: A three-dimensional, printed synthetic model was created from magnetic resonance urography. The model comprises a plastic kidney as the reusable structure and a silicone renal pelvis and ureter as the interchangeable structure. We evaluated realism and performance with surgeons and residents at different levels of training, comparing operative time and complications of the procedure. Results: Twenty-four participants were recruited; 41.7% had previous experience in laparoscopic pyeloplasty, with 5.5 years of experience in laparoscopic surgery (interquartile range [IQR] 2-7.75). There were no cases of stenosis, but leaks accounted for 41.7%. The procedure lasted 72 minutes (IQR 55-90), with significant differences according to the level of training (85 minutes for residents, 68 minutes for pediatric surgeons and urologists, and 40 minutes for laparoscopic surgeons; P: .011) and years of previous experience in laparoscopic surgery (P: .003). Conclusions: A high-fidelity, replicable, and low-cost pyeloureteral stenosis model was developed to simulate laparoscopic pyeloplasty in pediatric patients.

Asunto(s)

RESUMEN

PURPOSE: Artificial intelligence (AI) has high diagnostic accuracy for coronary artery disease (CAD) from myocardial perfusion imaging (MPI). However, when trained using high-risk populations (such as patients with correlating invasive testing), the disease probability can be overestimated due to selection bias. We evaluated different strategies for training AI models to improve the calibration (accurate estimate of disease probability), using external testing. METHODS: Deep learning was trained using 828 patients from 3 sites, with MPI and invasive angiography within 6 months. Perfusion was assessed using upright (U-TPD) and supine total perfusion deficit (S-TPD). AI training without data augmentation (model 1) was compared to training with augmentation (increased sampling) of patients without obstructive CAD (model 2), and patients without CAD and TPD < 2% (model 3). All models were tested in an external population of patients with invasive angiography within 6 months (n = 332) or low likelihood of CAD (n = 179). RESULTS: Model 3 achieved the best calibration (Brier score 0.104 vs 0.121, p < 0.01). Improvement in calibration was particularly evident in women (Brier score 0.084 vs 0.124, p < 0.01). In external testing (n = 511), the area under the receiver operating characteristic curve (AUC) was higher for model 3 (0.930), compared to U-TPD (AUC 0.897) and S-TPD (AUC 0.900, p < 0.01 for both). CONCLUSION: Training AI models with augmentation of low-risk patients can improve calibration of AI models developed to identify patients with CAD, allowing more accurate assignment of disease probability. This is particularly important in lower-risk populations and in women, where overestimation of disease probability could significantly influence down-stream patient management.

Asunto(s)

RESUMEN

Simulation in veterinary education provides a safe and ethical alternative to using live animals, but most simulators are single purpose and unvalidated. In this study, canine training manikins were created using readily available materials to teach fine needle aspiration (FNA) of peripheral lymph nodes, jugular venipuncture, cephalic venipuncture, intravenous catheterization, and cystocentesis. Undergraduate subjects were prospectively enrolled and stratified by veterinary experience prior to randomization into two groups. Students were taught a new skill each week through a written description of the technique, video training, and hands-on practice (live animal vs. manikin). The following week, participants were scored on the performance of the previous week's skill on a live animal using a standardized rubric by reviewers blinded to the training group. Six weeks later, the assessment was repeated for all skills. Scores were compared between groups and time points using repeated-measures ANOVA after logarithmic transformation. p < .05 was significant. There were no significant differences in scores for any of the skills between the groups immediately following or 6 weeks after training. Initial proficiency and short-term retention of clinical skills do not differ for students trained using a manikin vs. a live dog.

RESUMEN

PURPOSE: The aim of this work was to demonstrate a practical and effective method to improve the performance of RapidPlan (RP) model. METHODS: 203 consecutive clinical VMAT plans (P0) for cervical and endometrial cancer were used to train an RP model (M0). The plans were then reoptimized by M0 to generate 203 new plans (P1). Compared with P0, 150 plans with a lower mean dose (MD) of bladder, rectum and PBM were selected from P1 to configure a new RP model (M1). A final RP model (M2) was trained using plans in M1 and the remaining 53 plans from P1 (excluding OARs with worse MD) and the corresponding plans from P0 (only including OARs with better MD). The models were validated on the mentioned 53 plans (closed-loop set) and 46 patient cohorts outside the training library (open-loop set). p < 0.05 was considered statistically significant. RESULTS: For closed-loop validation, the difference of D2%, D98% and CI95% between groups was of no statistical significance, the homogeneity index (HI) was lower in the groups of RP models (p < 0.05). The MD of all OARs decreased monotonically in the sequence of the clinical group, group M0, M1 and M2, except the MD of bowel in M1 and MD of LFH in M2. Similarly, for open-loop validation, there was no significant difference in D2%, D98% and HI between groups, but CI95% was larger in the clinical group (p < 0.05). The MD of all OARs decreased monotonically in the sequence of the clinical group, group M0, M1 and M2, with the exception of bowel in M1. CONCLUSION: The practical method of incorporating plan data of better-sparing OARs from both the clinical VMAT plans and the re-optimized plans could further improve the performance of the RP model.

Asunto(s)

RESUMEN

Monitoring dairy cattle behavior can improve the detection of health and welfare issues for early interventions. Often commercial sensors do not provide researchers with sufficient raw and open data; therefore, the aim of this study was to develop an open and customizable system to classify cattle behaviors. A 3D accelerometer device and host-board (i.e., sensor node) were embedded in a case and fixed on a dairy cow collar. It was developed to work in two modes: (1) acquisition mode, where a mobile application supported the raw data collection during observations; and (2) operating mode, where data was processed and sent to a gateway and on the cloud. Accelerations were sampled at 25 Hz and behaviors were classified in 10-min windows. Several algorithms were trained with the 108 h of behavioral data acquired from 32 cows on 3 farms, and after evaluating their computational/memory complexity and accuracy, the Decision Tree algorithm was selected. This model detected standing, lying, eating, and ruminating with an average accuracy of 85.12%. The open nature of this system enables for the addition of other functions (e.g., real-time localization of cows) and the integration with other information sources, e.g., microenvironment and air quality sensors, thereby enhancing data processing potential.