AI-powered COVID-19 forecasting: a comprehensive comparison of advanced deep learning methods.

Objectives: The coronavirus disease 2019 (COVID-19) pandemic continues to pose significant challenges to the public health sector, including that of the United Arab Emirates (UAE). The objective of this study was to assess the efficiency and accuracy of various deep-learning models in forecasting COVID-19 cases within the UAE, thereby aiding the nation's public health authorities in informed decision-making. Methods: This study utilized a comprehensive dataset encompassing confirmed COVID-19 cases, demographic statistics, and socioeconomic indicators. Several advanced deep learning models, including long short-term memory (LSTM), bidirectional LSTM, convolutional neural network (CNN), CNN-LSTM, multilayer perceptron, and recurrent neural network (RNN) models, were trained and evaluated. Bayesian optimization was also implemented to fine-tune these models. Results: The evaluation framework revealed that each model exhibited different levels of predictive accuracy and precision. Specifically, the RNN model outperformed the other architectures even without optimization. Comprehensive predictive and perspective analytics were conducted to scrutinize the COVID-19 dataset. Conclusion: This study transcends academic boundaries by offering critical insights that enable public health authorities in the UAE to deploy targeted data-driven interventions. The RNN model, which was identified as the most reliable and accurate for this specific context, can significantly influence public health decisions. Moreover, the broader implications of this research validate the capability of deep learning techniques in handling complex datasets, thus offering the transformative potential for predictive accuracy in the public health and healthcare sectors.

Polypharmacy and Drug Interactions in the COVID-19 Pandemic.

The COVID-19 pandemic generated a great impact on health systems. We compared evolution, polypharmacy, and potential drug-drug interactions (P-DDIs) in COVID-19 and non-COVID-19 hospitalizations during first wave of pandemic. Prescriptions for hospitalized patients ≥ 18 years (COVID-19 and non-COVID-19 rooms) between April and September 2020 were included. The computerized medical decision support system SIMDA and the physician order entry system Hdc.DrApp.la were used. Patients in COVID-19 rooms were divided into detectable and non-detectable, according to real-time reverse transcription polymerase chain reaction (RT-PCR). Number of drugs, prescribed on day 1, after day 1, and total; polypharmacy, excessive polypharmacy, and P-DDIs were compared. 1,623 admissions were evaluated: 881 COVID-19, 538 detectable and 343 non-detectable, and 742 non-COVID-19. Mortality was 15% in COVID-19 and 13% in non-COVID-19 (RR [non-COVID-19 vs. COVID-19]: 0.84 [95% CI] [0.66-1.07]). In COVID-19, mortality was 19% in detectable and 9% in non-detectable (RR: 2.07 [1.42-3.00]). Average number of drugs was 4.54/patient (SD ± 3.06) in COVID-19 and 5.92/patient (±3.24) in non-COVID-19 (p<0.001) on day 1 and 5.57/patient (±3.93) in COVID-19 and 9.17/patient (±5.27) in non-COVID-19 (p<0.001) throughout the hospitalization. 45% received polypharmacy in COVID-19 and 62% in non-COVID-19 (RR: 1.38 [1.25-1.51]) and excessive polypharmacy 7% in COVID-19 and 14% in non-COVID-19 (RR: 2.09 [1.54-2.83]). The frequency of total P-DDIs was 0.31/patient (±0.67) in COVID-19 and 0.40/patient (±0.94) in non-COVID-19 (p=0.022). Hospitalizations in the COVID-19 setting are associated with less use of drugs, less polypharmacy and less P-DDIs. Detectable patients had higher mortality.

The Statistics of Eye Movements and Binocular Disparities during VR Gaming: Implications for Headset Design.

The human visual system evolved in environments with statistical regularities. Binocular vision is adapted to these such that depth perception and eye movements are more precise, faster, and performed comfortably in environments consistent with the regularities. We measured the statistics of eye movements and binocular disparities in virtual-reality (VR) - gaming environments and found that they are quite different from those in the natural environment. Fixation distance and direction are more restricted in VR, and fixation distance is farther. The pattern of disparity across the visual field is less regular in VR and does not conform to a prominent property of naturally occurring disparities. From this we predict that double vision is more likely in VR than in the natural environment. We also determined the optimal screen distance to minimize discomfort due to the vergence-accommodation conflict, and the optimal nasal-temporal positioning of head-mounted display (HMD) screens to maximize binocular field of view. Finally, in a user study we investigated how VR content affects comfort and performance. Content that is more consistent with the statistics of the natural world yields less discomfort than content that is not. Furthermore, consistent content yields slightly better performance than inconsistent content.

LADER: Log-Augmented DEnse Retrieval for Biomedical Literature Search.

Queries with similar information needs tend to have similar document clicks, especially in biomedical literature search engines where queries are generally short and top documents account for most of the total clicks. Motivated by this, we present a novel architecture for biomedical literature search, namely Log-Augmented DEnse Retrieval (LADER), which is a simple plug-in module that augments a dense retriever with the click logs retrieved from similar training queries. Specifically, LADER finds both similar documents and queries to the given query by a dense retriever. Then, LADER scores relevant (clicked) documents of similar queries weighted by their similarity to the input query. The final document scores by LADER are the average of (1) the document similarity scores from the dense retriever and (2) the aggregated document scores from the click logs of similar queries. Despite its simplicity, LADER achieves new state-of-the-art (SOTA) performance on TripClick, a recently released benchmark for biomedical literature retrieval. On the frequent ("HEAD") queries, LADER largely outperforms the best retrieval model by 39% relative NDCG@10 (0.338 v.s. 0.243). LADER also achieves better performance on the less frequent ("TORSO") queries with 11% relative NDCG@10 improvement over the previous SOTA (0.303 v.s. 0.272). On the rare ("TAIL") queries where similar queries are scarce, LADER still compares favorably to the previous SOTA method (NDCG@10: 0.310 v.s. 0.295). On all queries, LADER can improve the performance of a dense retriever by 24%-37% relative NDCG@10 while not requiring additional training, and further performance improvement is expected from more logs. Our regression analysis has shown that queries that are more frequent, have higher entropy of query similarity and lower entropy of document similarity, tend to benefit more from log augmentation.

Development of a keyword library for capturing PRO-CTCAE-focused "symptom talk" in oncology conversations.

Objectives: As computational methods for detecting symptoms can help us better attend to patient suffering, the objectives of this study were to develop and evaluate the performance of a natural language processing keyword library for detecting symptom talk, and to describe symptom communication within our dataset to generate insights for future model building. Materials and Methods: This was a secondary analysis of 121 transcribed outpatient oncology conversations from the Communication in Oncologist-Patient Encounters trial. Through an iterative process of identifying symptom expressions via inductive and deductive techniques, we generated a library of keywords relevant to the Patient-Reported Outcome version of the Common Terminology Criteria for Adverse Events (PRO-CTCAE) framework from 90 conversations, and tested the library on 31 additional transcripts. To contextualize symptom expressions and the nature of misclassifications, we qualitatively analyzed 450 mislabeled and properly labeled symptom-positive turns. Results: The final library, comprising 1320 terms, identified symptom talk among conversation turns with an F1 of 0.82 against a PRO-CTCAE-focused gold standard, and an F1 of 0.61 against a broad gold standard. Qualitative observations suggest that physical symptoms are more easily detected than psychological symptoms (eg, anxiety), and ambiguity persists throughout symptom communication. Discussion: This rudimentary keyword library captures most PRO-CTCAE-focused symptom talk, but the ambiguity of symptom speech limits the utility of rule-based methods alone, and limits to generalizability must be considered. Conclusion: Our findings highlight opportunities for more advanced computational models to detect symptom expressions from transcribed clinical conversations. Future improvements in speech-to-text could enable real-time detection at scale.

Clinician and computer: a study on doctors' perceptions of artificial intelligence in skeletal radiography.

BACKGROUND: Traumatic musculoskeletal injuries are a common presentation to emergency care, the first-line investigation often being plain radiography. The interpretation of this imaging frequently falls to less experienced clinicians despite well-established challenges in reporting. This study presents novel data of clinicians' confidence in interpreting trauma radiographs, their perception of AI in healthcare, and their support for the development of systems applied to skeletal radiography. METHODS: A novel questionnaire was distributed through a network of collaborators to clinicians across the Southeast of England. Over a three-month period, responses were compiled into a database before undergoing statistical review. RESULTS: The responses of 297 participants were included. The mean self-assessed knowledge of AI in healthcare was 3.68 out of ten, with significantly higher knowledge reported by the most senior doctors (Specialty Trainee/Specialty Registrar or above = 4.88). 13.8% of participants reported an awareness of AI in their clinical practice. Overall, participants indicated substantial favourability towards AI in healthcare (7.87) and in AI applied to skeletal radiography (7.75). There was a preference for a hypothetical system indicating positive findings rather than ruling as negative (7.26 vs 6.20). CONCLUSIONS: This study identifies clear support, amongst a cross section of student and qualified doctors, for both the general use of AI technology in healthcare and in its application to skeletal radiography for trauma. The development of systems to address this demand appear well founded and popular. The engagement of a small but reticent minority should be sought, along with improving the wider education of doctors on AI.

Precomputed Radiative Heat Transport for Efficient Thermal Simulation.

Architectural design and urban planning are complex design tasks. Predicting the thermal impact of design choices at interactive rates enhances the ability of designers to improve energy efficiency and avoid problematic heat islands while maintaining design quality. We show how to use and adapt methods from computer graphics to efficiently simulate heat transfer via thermal radiation, thereby improving user guidance in the early design phase of large-scale construction projects and helping to increase energy efficiency and outdoor comfort. Our method combines a hardware-accelerated photon tracing approach with a carefully selected finite element discretization, inspired by precomputed radiance transfer. This combination allows us to precompute a radiative transport operator, which we then use to rapidly solve either steady-state or transient heat transport throughout the entire scene. Our formulation integrates time-dependent solar irradiation data without requiring changes in the transport operator, allowing us to quickly analyze many different scenarios such as common weather patterns, monthly or yearly averages, or transient simulations spanning multiple days or weeks. We show how our approach can be used for interactive design workflows such as city planning via fast feedback in the early design phase.

ParaDime: A Framework for Parametric Dimensionality Reduction.

ParaDime is a framework for parametric dimensionality reduction (DR). In parametric DR, neural networks are trained to embed high-dimensional data items in a low-dimensional space while minimizing an objective function. ParaDime builds on the idea that the objective functions of several modern DR techniques result from transformed inter-item relationships. It provides a common interface for specifying these relations and transformations and for defining how they are used within the losses that govern the training process. Through this interface, ParaDime unifies parametric versions of DR techniques such as metric MDS, t-SNE, and UMAP. It allows users to fully customize all aspects of the DR process. We show how this ease of customization makes ParaDime suitable for experimenting with interesting techniques such as hybrid classification/embedding models and supervised DR. This way, ParaDime opens up new possibilities for visualizing high-dimensional data.

Multimodal Fusion of Smart Home and Text-based Behavior Markers for Clinical Assessment Prediction.

New modes of technology are offering unprecedented opportunities to unobtrusively collect data about people's behavior. While there are many use cases for such information, we explore its utility for predicting multiple clinical assessment scores. Because clinical assessments are typically used as screening tools for impairment and disease, such as mild cognitive impairment (MCI), automatically mapping behavioral data to assessment scores can help detect changes in health and behavior across time. In this paper, we aim to extract behavior markers from two modalities, a smart home environment and a custom digital memory notebook app, for mapping to ten clinical assessments that are relevant for monitoring MCI onset and changes in cognitive health. Smart home-based behavior markers reflect hourly, daily, and weekly activity patterns, while app-based behavior markers reflect app usage and writing content/style derived from free-form journal entries. We describe machine learning techniques for fusing these multimodal behavior markers and utilizing joint prediction. We evaluate our approach using three regression algorithms and data from 14 participants with MCI living in a smart home environment. We observed moderate to large correlations between predicted and ground-truth assessment scores, ranging from r = 0.601 to r = 0.871 for each clinical assessment.

Reconstructing 3D Face of Infants in Social Interactions Using Morphable Models of Non-Infants.

3D morphable models (3DMMs) simultaneously reconstruct facial morphology, expression and pose from 2D images, and thus could be an invaluable tool for capturing and characterizing the face and facial behavior in early childhood. However, 3DMM fitting on infants is a largely unexplored problem. All publicly available 3DMMs are developed for adults, and it is unclear if and to what extent they can be used on videos of infants. In this paper, we compare five state-of-the-art 3DMM fitting methods on data from naturalistic infant-caregiver interactions. Results suggest that it is possible to produce consistent and subject-specific reconstructions of 3D shape identity from multiple frames, but not from a single frame. Qualitative evaluation highlights that facial regions with high texture variation, such as eyes, brows and mouth, are captured with higher accuracy compared to the rest of the face. Thus, even though a 3DMM developed for adults has significant limitations when reconstructing the morphology of the entire facial region of infants, applications that involve analysis of facial behavior can be feasible. Our encouraging results, combined with the unique ability of 3DMMs to disentangle two major sources of noise for expression analysis (i.e., identity bias and pose variations), motivate future research on using 3DMMs to measure the facial behavior of infants.

Bioengineering Tools Applied to Dentistry: Validation Methods for In Vitro and In Silico Analysis.

This study aimed to evaluate the use of bioengineering tools, finite element analysis, strain gauge analysis, photoelastic analysis, and digital image correlation, in computational studies with greater validity and reproducibility. A bibliographic search was performed in the main health databases PUBMED and Scholar Google, in which different studies, among them, laboratory studies, case reports, systematic reviews, and literature reviews, which were developed in living individuals, were included. Therefore, articles that did not deal with the use of finite element analysis, strain gauge analysis, photoelastic analysis, and digital image correlation were excluded, as well as their use in computational studies with greater validity and reproducibility. According to the methodological analysis, it is observed that the average publication of articles in the Pubmed database was 2.03 and with a standard deviation of 1.89. While in Google Scholar, the average was 0.78 and the standard deviation was 0.90. Thus, it is possible to verify that there was a significant variation in the number of articles in the two databases. Modern dentistry finds in finite element analysis, strain gauge, photoelastic and digital image correlation a way to analyze the biomechanical behavior in dental materials to obtain results that assist to obtain rehabilitations with favorable prognosis and patient satisfaction.

The Pitfalls of Using Open Data to Develop Deep Learning Solutions for COVID-19 Detection in Chest X-Rays.

Since the emergence of COVID-19, deep learning models have been developed to identify COVID-19 from chest X-rays. With little to no direct access to hospital data, the AI community relies heavily on public data comprising numerous data sources. Model performance results have been exceptional when training and testing on open-source data, surpassing the reported capabilities of AI in pneumonia-detection prior to the COVID-19 outbreak. In this study impactful models are trained on a widely used open-source data and tested on an external test set and a hospital dataset, for the task of classifying chest X-rays into one of three classes: COVID-19, non-COVID pneumonia and no-pneumonia. Classification performance of the models investigated is evaluated through ROC curves, confusion matrices and standard classification metrics. Explainability modules are implemented to explore the image features most important to classification. Data analysis and model evalutions show that the popular open-source dataset COVIDx is not representative of the real clinical problem and that results from testing on this are inflated. Dependence on open-source data can leave models vulnerable to bias and confounding variables, requiring careful analysis to develop clinically useful/viable AI tools for COVID-19 detection in chest X-rays.

Prediction of Breast Cancer using Machine Learning Approaches.

Background: Breast cancer is considered one of the most common cancers in women caused by various clinical, lifestyle, social, and economic factors. Machine learning has the potential to predict breast cancer based on features hidden in data. Objective: This study aimed to predict breast cancer using different machine-learning approaches applying demographic, laboratory, and mammographic data. Material and Methods: In this analytical study, the database, including 5,178 independent records, 25% of which belonged to breast cancer patients with 24 attributes in each record was obtained from Motamed cancer institute (ACECR), Tehran, Iran. The database contained 5,178 independent records, 25% of which belonged to breast cancer patients containing 24 attributes in each record. The random forest (RF), neural network (MLP), gradient boosting trees (GBT), and genetic algorithms (GA) were used in this study. Models were initially trained with demographic and laboratory features (20 features). The models were then trained with all demographic, laboratory, and mammographic features (24 features) to measure the effectiveness of mammography features in predicting breast cancer. Results: RF presented higher performance compared to other techniques (accuracy 80%, sensitivity 95%, specificity 80%, and the area under the curve (AUC) 0.56). Gradient boosting (AUC=0.59) showed a stronger performance compared to the neural network. Conclusion: Combining multiple risk factors in modeling for breast cancer prediction could help the early diagnosis of the disease with necessary care plans. Collection, storage, and management of different data and intelligent systems based on multiple factors for predicting breast cancer are effective in disease management.

Obesity Prediction with EHR Data: A deep learning approach with interpretable elements.

Childhood obesity is a major public health challenge. Early prediction and identification of the children at an elevated risk of developing childhood obesity may help in engaging earlier and more effective interventions to prevent and manage obesity. Most existing predictive tools for childhood obesity primarily rely on traditional regression-type methods using only a few hand-picked features and without exploiting longitudinal patterns of children's data. Deep learning methods allow the use of high-dimensional longitudinal datasets. In this paper, we present a deep learning model designed for predicting future obesity patterns from generally available items on children's medical history. To do this, we use a large unaugmented electronic health records dataset from a large pediatric health system in the US. We adopt a general LSTM network architecture and train our proposed model using both static and dynamic EHR data. To add interpretability, we have additionally included an attention layer to calculate the attention scores for the timestamps and rank features of each timestamp. Our model is used to predict obesity for ages between 3-20 years using the data from 1-3 years in advance. We compare the performance of our LSTM model with a series of existing studies in the literature and show it outperforms their performance in most age ranges.

Finding Primary Care-Repurposing Physician Registration Data to Generate a Regionally Accurate List of Primary Care Clinics: Development and Validation of an Open-Source Algorithm.

BACKGROUND: Some Canadians have limited access to longitudinal primary care, despite its known advantages for population health. Current initiatives to transform primary care aim to increase access to team-based primary care clinics. However, many regions lack a reliable method to enumerate clinics, limiting estimates of clinical capacity and ongoing access gaps. A region-based complete clinic list is needed to effectively describe clinic characteristics and to compare primary care outcomes at the clinic level. OBJECTIVE: The objective of this study is to show how publicly available data sources, including the provincial physician license registry, can be used to generate a verifiable, region-wide list of primary care clinics in British Columbia, Canada, using a process named the Clinic List Algorithm (CLA). METHODS: The CLA has 10 steps: (1) collect data sets, (2) develop clinic inclusion and exclusion criteria, (3) process data sets, (4) consolidate data sets, (5) transform from list of physicians to initial list of clinics, (6) add additional metadata, (7) create working lists, (8) verify working lists, (9) consolidate working lists, and (10) adjust processing steps based on learnings. RESULTS: The College of Physicians and Surgeons of British Columbia Registry contained 13,726 physicians, at 2915 unique addresses, 6942 (50.58%) of whom were family physicians (FPs) licensed to practice in British Columbia. The CLA identified 1239 addresses where primary care was delivered by 4262 (61.39%) FPs. Of the included addresses, 84.50% (n=1047) were in urban locations, and there was a median of 2 (IQR 2-4, range 1-23) FPs at each unique address. CONCLUSIONS: The CLA provides a region-wide description of primary care clinics that improves on simple counts of primary care providers or self-report lists. It identifies the number and location of primary care clinics and excludes primary care providers who are likely not providing community-based primary care. Such information may be useful for estimates of capacity of primary care, as well as for policy planning and research in regions engaged in primary care evaluation or transformation.

Predicting factors of clinically significant urological anomalies after initial urinary tract infection among 2- to 24-month-old children.

AIM: To find more effective criteria to identify clinically significant urological anomalies after initial urinary tract infection among children. METHODS: Children aged 2-24 months with an initial urinary tract infection were consecutively recruited in a Japanese hospital from 2013 to 2019. Voiding cystourethrography, 99mTc dimercaptosuccinic acid scan and ultrasound were intended to perform for all cases. Clinically significant urological anomalies were defined as high-grade vesicoureteral reflux, obstructive and abnormal urinary tract lesions, need for surgical intervention, renal hypoplasia and scarring. Using classification and regression tree analysis, we sought the associated factors. We developed new criteria with these factors, retrospectively applied them to the original data, and calculated the sensitivity and specificity. RESULTS: One hundred sixty-seven patients were eligible, and 39 had clinically significant urological anomalies. Classification and regression tree analysis showed that the associated factors were non-E. coli infections, serum creatinine levels and ultrasound abnormalities. When the gold standards were performed on children with non-E. coli infections or serum creatinine levels ≥0.21 mg/dl, sensitivity and specificity were 0.82 and 0.68, respectively. CONCLUSION: The criteria including non-E. coli infections and high-normal or higher serum creatinine levels may efficiently predict clinically significant urological anomalies after initial urinary tract infections.

Skill Characterisation of Sonographer Gaze Patterns during Second Trimester Clinical Fetal Ultrasounds using Time Curves.

We present a method for skill characterisation of sonographer gaze patterns while performing routine second trimester fetal anatomy ultrasound scans. The position and scale of fetal anatomical planes during each scan differ because of fetal position, movements and sonographer skill. A standardised reference is required to compare recorded eye-tracking data for skill characterisation. We propose using an affine transformer network to localise the anatomy circumference in video frames, for normalisation of eye-tracking data. We use an event-based data visualisation, time curves, to characterise sonographer scanning patterns. We chose brain and heart anatomical planes because they vary in levels of gaze complexity. Our results show that when sonographers search for the same anatomical plane, even though the landmarks visited are similar, their time curves display different visual patterns. Brain planes also, on average, have more events or landmarks occurring than the heart, which highlights anatomy-specific differences in searching approaches.

Hex Me If You Can.

HexMe consists of 189 tetrahedral meshes with tagged features and a workflow to generate them. The primary purpose of HexMe meshes is to enable consistent and practically meaningful evaluation of hexahedral meshing algorithms and related techniques, specifically regarding the correct meshing of specified feature points, curves, and surfaces. The tetrahedral meshes have been generated with Gmsh, starting from 63 computer-aided design (CAD) models from various databases. To highlight and label the diverse and challenging aspects of hexahedral mesh generation, the CAD models are classified into three categories: simple, nasty, and industrial. For each CAD model, we provide three kinds of tetrahedral meshes (uniform, curvature-adapted, and box-embedded). The mesh generation pipeline is defined with the help of Snakemake, a modern workflow management system, which allows us to specify a fully automated, extensible, and sustainable workflow. It is possible to download the whole dataset or select individual meshes by browsing the online catalog. The HexMe dataset is built with evolution in mind and prepared for future developments. A public GitHub repository hosts the HexMe workflow, where external contributions and future releases are possible and encouraged. We demonstrate the value of HexMe by exploring the robustness limitations of state-of-the-art frame-field-based hexahedral meshing algorithm. Only for 19 of 189 tagged tetrahedral inputs all feature entities are meshed correctly, while the average success rates are 70.9% / 48.5% / 34.6% for feature points/curves/surfaces.

Smooth Interpolating Curves with Local Control and Monotone Alternating Curvature.

We propose a method for the construction of a planar curve based on piecewise clothoids and straight lines that intuitively interpolates a given sequence of control points. Our method has several desirable properties that are not simultaneously fulfilled by previous approaches: Our interpolating curves are C2 continuous, their computation does not rely on global optimization and has local support, enabling fast evaluation for interactive modeling. Further, the sign of the curvature at control points is consistent with the control polygon; the curvature attains its extrema at control points and is monotone between consecutive control points of opposite curvature signs. In addition, we can ensure that the curve has self-intersections only when the control polygon also self-intersects between the same control points. For more fine-grained control, the user can specify the desired curvature and tangent values at certain control points, though it is not required by our method. Our local optimization can lead to discontinuity w.r.t. the locations of control points, although the problem is limited by its locality. We demonstrate the utility of our approach in generating various curves and provide a comparison with the state of the art.

Visualising Spatio-Temporal Gaze Characteristics for Exploratory Data Analysis in Clinical Fetal Ultrasound Scans.

Visualising patterns in clinicians' eye movements while interpreting fetal ultrasound imaging videos is challenging. Across and within videos, there are differences in size an d position of Areas-of-Interest (AOIs) due to fetal position, movement and sonographer skill. Currently, AOIs are manually labelled or identified using eye-tracker manufacturer specifications which are not study specific. We propose using unsupervised clustering to identify meaningful AOIs and bi-contour plots to visualise spatio-temporal gaze characteristics. We use Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) to identify the AOIs, and use their corresponding images to capture granular changes within each AOI. Then we visualise transitions within and between AOIs as read by the sonographer. We compare our method to a standardised eye-tracking manufacturer algorithm. Our method captures granular changes in gaze characteristics which are otherwise not shown. Our method is suitable for exploratory data analysis of eye-tracking data involving multiple participants and AOIs.