Bayesian Networks in Radiology.

A Bayesian network is a graphical model that uses probability theory to represent relationships among its variables. The model is a directed acyclic graph whose nodes represent variables, such as the presence of a disease or an imaging finding. Connections between nodes express causal influences between variables as probability values. Bayesian networks can learn their structure (nodes and connections) and/or conditional probability values from data. Bayesian networks offer several advantages: (a) they can efficiently perform complex inferences, (b) reason from cause to effect or vice versa, (c) assess counterfactual data, (d) integrate observations with canonical ("textbook") knowledge, and (e) explain their reasoning. Bayesian networks have been employed in a wide variety of applications in radiology, including diagnosis and treatment planning. Unlike deep learning approaches, Bayesian networks have not been applied to computer vision. However, hybrid artificial intelligence systems have combined deep learning models with Bayesian networks, where the deep learning model identifies findings in medical images and the Bayesian network formulates and explains a diagnosis from those findings. One can apply a Bayesian network's probabilistic knowledge to integrate clinical and imaging findings to support diagnosis, treatment planning, and clinical decision-making. This article reviews the fundamental principles of Bayesian networks and summarizes their applications in radiology. Keywords: Bayesian Network, Machine Learning, Abdominal Imaging, Musculoskeletal Imaging, Breast Imaging, Neurologic Imaging, Radiology Education Supplemental material is available for this article. © RSNA, 2023.

Assessment of malaria risk in Southeast Asia: a systematic review.

BACKGROUND: Several countries in Southeast Asia are nearing malaria elimination, yet eradication remains elusive. This is largely due to the challenge of focusing elimination efforts, an area where risk prediction can play an essential supporting role. Despite its importance, there is no standard numerical method to quantify the risk of malaria infection. Thus, there is a need for a consolidated view of existing definitions of risk and factors considered in assessing risk to analyse the merits of risk prediction models. This systematic review examines studies of the risk of malaria in Southeast Asia with regard to their suitability in addressing the challenges of malaria elimination in low transmission areas. METHODS: A search of four electronic databases over 2010-2020 retrieved 1297 articles, of which 25 met the inclusion and exclusion criteria. In each study, examined factors included the definition of the risk and indicators of malaria transmission used, the environmental and climatic factors associated with the risk, the statistical models used, the spatial and temporal granularity, and how the relationship between environment, climate, and risk is quantified. RESULTS: This review found variation in the definition of risk used, as well as the environmental and climatic factors in the reviewed articles. GLM was widely adopted as the analysis technique relating environmental and climatic factors to malaria risk. Most of the studies were carried out in either a cross-sectional design or case-control studies, and most utilized the odds ratio to report the relationship between exposure to risk and malaria prevalence. CONCLUSIONS: Adopting a standardized definition of malaria risk would help in comparing and sharing results, as would a clear description of the definition and method of collection of the environmental and climatic variables used. Further issues that need to be more fully addressed include detection of asymptomatic cases and considerations of human mobility. Many of the findings of this study are applicable to other low-transmission settings and could serve as a guideline for further studies of malaria in other regions.

The effect of 3D stereopsis and hand-tool alignment on learning effectiveness and skill transfer of a VR-based simulator for dental training.

Recent years have seen the proliferation of VR-based dental simulators using a wide variety of different VR configurations with varying degrees of realism. Important aspects distinguishing VR hardware configurations are 3D stereoscopic rendering and visual alignment of the user's hands with the virtual tools. New dental simulators are often evaluated without analysing the impact of these simulation aspects. In this paper, we seek to determine the impact of 3D stereoscopic rendering and of hand-tool alignment on the teaching effectiveness and skill assessment accuracy of a VR dental simulator. We developed a bimanual simulator using an HMD and two haptic devices that provides an immersive environment with both 3D stereoscopic rendering and hand-tool alignment. We then independently controlled for each of the two aspects of the simulation. We trained four groups of students in root canal access opening using the simulator and measured the virtual and real learning gains. We quantified the real learning gains by pre- and post-testing using realistic plastic teeth and the virtual learning gains by scoring the training outcomes inside the simulator. We developed a scoring metric to automatically score the training outcomes that strongly correlates with experts' scoring of those outcomes. We found that hand-tool alignment has a positive impact on virtual and real learning gains, and improves the accuracy of skill assessment. We found that stereoscopic 3D had a negative impact on virtual and real learning gains, however it improves the accuracy of skill assessment. This finding is counter-intuitive, and we found eye-tooth distance to be a confounding variable of stereoscopic 3D, as it was significantly lower for the monoscopic 3D condition and negatively correlates with real learning gain. The results of our study provide valuable information for the future design of dental simulators, as well as simulators for other high-precision psycho-motor tasks.

The IHI Rochester Report 2022 on Healthcare Informatics Research: Resuming After the CoViD-19.

In 2020, the CoViD-19 pandemic spread worldwide in an unexpected way and suddenly modified many life issues, including social habits, social relationships, teaching modalities, and more. Such changes were also observable in many different healthcare and medical contexts. Moreover, the CoViD-19 pandemic acted as a stress test for many research endeavors, and revealed some limitations, especially in contexts where research results had an immediate impact on the social and healthcare habits of millions of people. As a result, the research community is called to perform a deep analysis of the steps already taken, and to re-think steps for the near and far future to capitalize on the lessons learned due to the pandemic. In this direction, on June 09th-11th, 2022, a group of twelve healthcare informatics researchers met in Rochester, MN, USA. This meeting was initiated by the Institute for Healthcare Informatics-IHI, and hosted by the Mayo Clinic. The goal of the meeting was to discuss and propose a research agenda for biomedical and health informatics for the next decade, in light of the changes and the lessons learned from the CoViD-19 pandemic. This article reports the main topics discussed and the conclusions reached. The intended readers of this paper, besides the biomedical and health informatics research community, are all those stakeholders in academia, industry, and government, who could benefit from the new research findings in biomedical and health informatics research. Indeed, research directions and social and policy implications are the main focus of the research agenda we propose, according to three levels: the care of individuals, the healthcare system view, and the population view.

Quantifying the impact of data characteristics on the transferability of sleep stage scoring models.

Deep learning models for scoring sleep stages based on single-channel EEG have been proposed as a promising method for remote sleep monitoring. However, applying these models to new datasets, particularly from wearable devices, raises two questions. First, when annotations on a target dataset are unavailable, which different data characteristics affect the sleep stage scoring performance the most and by how much? Second, when annotations are available, which dataset should be used as the source of transfer learning to optimize performance? In this paper, we propose a novel method for computationally quantifying the impact of different data characteristics on the transferability of deep learning models. Quantification is accomplished by training and evaluating two models with significant architectural differences, TinySleepNet and U-Time, under various transfer configurations in which the source and target datasets have different recording channels, recording environments, and subject conditions. For the first question, the environment had the highest impact on sleep stage scoring performance, with performance degrading by over 14% when sleep annotations were unavailable. For the second question, the most useful transfer sources for TinySleepNet and the U-Time models were MASS-SS1 and ISRUC-SG1, containing a high percentage of N1 (the rarest sleep stage) relative to the others. The frontal and central EEGs were preferred for TinySleepNet. The proposed approach enables full utilization of existing sleep datasets for training and planning model transfer to maximize the sleep stage scoring performance on a target problem when sleep annotations are limited or unavailable, supporting the realization of remote sleep monitoring.

A retrospective study of 3D deep learning approach incorporating coordinate information to improve the segmentation of pre- and post-operative abdominal aortic aneurysm.

Abdominal aortic aneurysm (AAA) is one of the most common diseases worldwide. 3D segmentation of AAA provides useful information for surgical decisions and follow-up treatment. However, existing segmentation methods are time consuming and not practical in routine use. In this article, the segmentation task will be addressed automatically using a deep learning based approach which has been proved to successfully solve several medical imaging problems with excellent performances. This article therefore proposes a new solution of AAA segmentation using deep learning in a type of 3D convolutional neural network (CNN) architecture that also incorporates coordinate information. The tested CNNs are UNet, AG-DSV-UNet, VNet, ResNetMed and DenseVoxNet. The 3D-CNNs are trained with a dataset of high resolution (256 × 256) non-contrast and post-contrast CT images containing 64 slices from each of 200 patients. The dataset consists of contiguous CT slices without augmentation and no post-processing step. The experiments show that incorporation of coordinate information improves the segmentation results. The best accuracies on non-contrast and contrast-enhanced images have average dice scores of 97.13% and 96.74%, respectively. Transfer learning from a pre-trained network of a pre-operative dataset to post-operative endovascular aneurysm repair (EVAR) was also performed. The segmentation accuracy of post-operative EVAR using transfer learning on non-contrast and contrast-enhanced CT datasets achieved the best dice scores of 94.90% and 95.66%, respectively.

Added-value of mosquito vector breeding sites from street view images in the risk mapping of dengue incidence in Thailand.

Dengue is an emerging vector-borne viral disease across the world. The primary dengue mosquito vectors breed in containers with sufficient water and nutrition. Outdoor containers can be detected from geotagged images using state-of-the-art deep learning methods. In this study, we utilize such container information from street view images in developing a risk mapping model and determine the added value of including container information in predicting dengue risk. We developed seasonal-spatial models in which the target variable dengue incidence was explained using weather and container variable predictors. Linear mixed models with fixed and random effects are employed in our models to account for different characteristics of containers and weather variables. Using data from three provinces of Thailand between 2015 and 2018, the models are developed at the sub-district level resolution to facilitate the development of effective targeted intervention strategies. The performance of the models is evaluated with two baseline models: a classic linear model and a linear mixed model without container information. The performance evaluated with the correlation coefficients, R-squared, and AIC shows the proposed model with the container information outperforms both baseline models in all three provinces. Through sensitivity analysis, we investigate the containers that have a high impact on dengue risk. Our findings indicate that outdoor containers identified from street view images can be a useful data source in building effective dengue risk models and that the resulting models have potential in helping to target container elimination interventions.

Effects of COVID-19 government travel restrictions on mobility in a rural border area of Northern Thailand: A mobile phone tracking study.

BACKGROUND: Thailand is among the top five countries with effective COVID-19 transmission control. This study examines how news of presence of COVID-19 in Thailand, as well as varying levels of government restriction on movement, affected human mobility in a rural Thai population along the border with Myanmar. METHODS: This study makes use of mobility data collected using a smartphone app. Between November 2019 and June 2020, four major events concerning information dissemination or government intervention give rise to five time intervals of analysis. Radius of gyration is used to analyze movement in each interval, and movement during government-imposed curfew. Human mobility network visualization is used to identify changes in travel patterns between main geographic locations of activity. Cross-border mobility analysis highlights potential for intervillage and intercountry disease transmission. RESULTS: Inter-village and cross-border movement was common in the pre-COVID-19 period. Radius of gyration and cross-border trips decreased following news of the first imported cases. During the government lockdown period, radius of gyration was reduced by more than 90% and cross-border movement was mostly limited to short-distance trips. Human mobility was nearly back to normal after relaxation of the lockdown. CONCLUSIONS: This study provides insight into the impact of the government lockdown policy on an area with extremely low socio-economic status, poor healthcare resources, and highly active cross-border movement. The lockdown had a great impact on reducing individual mobility, including cross-border movement. The quick return to normal mobility after relaxation of the lockdown implies that close monitoring of disease should be continued to prevent a second wave.

Formative feedback generation in a VR-based dental surgical skill training simulator.

Fine motor skill is indispensable for a dentist. As in many other medical fields of study, the traditional surgical master-apprentice model is widely adopted in dental education. Recently, virtual reality (VR) simulators have been employed as supplementary components to the traditional skill-training curriculum, and numerous dental VR systems have been developed academically and commercially. However, the full promise of such systems has yet to be realized due to the lack of sufficient support for formative feedback. Without such a mechanism, evaluation still demands dedicated time of experts in scarce supply. To fill the gap of formative assessment using VR simulators in skill training in dentistry, we present a framework to objectively assess the surgical skill and generate formative feedback automatically. VR simulators enable collecting detailed data on relevant metrics throughout a procedure. Our approach to formative feedback is to correlate procedure metrics with the procedure outcome to identify the portions of a procedure that need to be improved. Specifically, for the errors in the outcome, the responsible portions of the procedure are identified by using the location of the error. Tutoring formative feedback is provided using the video modality. The effectiveness of the feedback system is evaluated with dental students using randomized controlled trials. The findings show the feedback mechanisms to be effective and to have the potential to be used as valuable supplemental training resources.

A 3D deep learning approach to epicardial fat segmentation in non-contrast and post-contrast cardiac CT images.

Epicardial fat (ECF) is localized fat surrounding the heart muscle or myocardium and enclosed by the thin-layer pericardium membrane. Segmenting the ECF is one of the most difficult medical image segmentation tasks. Since the epicardial fat is infiltrated into the groove between cardiac chambers and is contiguous with cardiac muscle, segmentation requires location and voxel intensity. Recently, deep learning methods have been effectively used to solve medical image segmentation problems in several domains with state-of-the-art performance. This paper presents a novel approach to 3D segmentation of ECF by integrating attention gates and deep supervision into the 3D U-Net deep learning architecture. The proposed method shows significant improvement of the segmentation performance, when compared with standard 3D U-Net. The experiments show excellent performance on non-contrast CT datasets with average Dice scores of 90.06%. Transfer learning from a pre-trained model of a non-contrast CT to contrast-enhanced CT dataset was also performed. The segmentation accuracy on the contrast-enhanced CT dataset achieved a Dice score of 88.16%.

Pyramid graph cut: Integrating intensity and gradient information for grayscale medical image segmentation.

Segmentation of grayscale medical images is challenging because of the similarity of pixel intensities and poor gradient strength between adjacent regions. The existing image segmentation approaches based on either intensity or gradient information alone often fail to produce accurate segmentation results. Previous approaches in the literature have approached the problem by embedded or sequential integration of different information types to improve the performance of the image segmentation on specific tasks. However, an effective combination or integration of such information is difficult to implement and not sufficiently generic for closely related tasks. Integration of the two information sources in a single graph structure is a potentially more effective way to solve the problem. In this paper we introduce a novel technique for grayscale medical image segmentation called pyramid graph cut, which combines intensity and gradient sources of information in a pyramid-shaped graph structure using a single source node and multiple sink nodes. The source node, which is the top of the pyramid graph, embeds intensity information into its linked edges. The sink nodes, which are the base of the pyramid graph, embed gradient information into their linked edges. The min-cut uses intensity information and gradient information, depending on which one is more useful or has a higher influence in each cutting location of each iteration. The experimental results demonstrate the effectiveness of the proposed method over intensity-based segmentation alone (i.e. Gaussian mixture model) and gradient-based segmentation alone (i.e. distance regularized level set evolution) on grayscale medical image datasets, including the public 3DIRCADb-01 dataset. The proposed method archives excellent segmentation results on the sample CT of abdominal aortic aneurysm, MRI of liver tumor and US of liver tumor, with dice scores of 90.49±5.23%, 88.86±11.77%, 90.68±2.45%, respectively.

Large scale detailed mapping of dengue vector breeding sites using street view images.

Targeted environmental and ecosystem management remain crucial in control of dengue. However, providing detailed environmental information on a large scale to effectively target dengue control efforts remains a challenge. An important piece of such information is the extent of the presence of potential dengue vector breeding sites, which consist primarily of open containers such as ceramic jars, buckets, old tires, and flowerpots. In this paper we present the design and implementation of a pipeline to detect outdoor open containers which constitute potential dengue vector breeding sites from geotagged images and to create highly detailed container density maps at unprecedented scale. We implement the approach using Google Street View images which have the advantage of broad coverage and of often being two to three years old which allows correlation analyses of container counts against historical data from manual surveys. Containers comprising eight of the most common breeding sites are detected in the images using convolutional neural network transfer learning. Over a test set of images the object recognition algorithm has an accuracy of 0.91 in terms of F-score. Container density counts are generated and displayed on a decision support dashboard. Analyses of the approach are carried out over three provinces in Thailand. The container counts obtained agree well with container counts from available manual surveys. Multi-variate linear regression relating densities of the eight container types to larval survey data shows good prediction of larval index values with an R-squared of 0.674. To delineate conditions under which the container density counts are indicative of larval counts, a number of factors affecting correlation with larval survey data are analyzed. We conclude that creation of container density maps from geotagged images is a promising approach to providing detailed risk maps at large scale.

3D segmentation of exterior wall surface of abdominal aortic aneurysm from CT images using variable neighborhood search.

A 3D model of abdominal aortic aneurysm (AAA) can provide useful anatomical information for clinical management and simulation. Thin-slice contiguous computed tomographic (CT) angiography is the best source of medical images for construction of 3D models, which requires segmentation of AAA in the images. Existing methods for segmentation of AAA rely on either manual process or 2D segmentation in each 2D CT slide. However, a traditional manual segmentation is a time consuming process which is not practical for routine use. The construction of a 3D model from 2D segmentation of each CT slice is not a fully satisfactory solution due to rough contours that can occur because of lack of constraints among segmented slices, as well as missed segmentation slices. To overcome such challenges, this paper proposes the 3D segmentation of AAA using the concept of variable neighborhood search by iteratively alternating between two different segmentation techniques in the two different 3D search spaces of voxel intensity and voxel gradient. The segmentation output of each method is used as the initial contour to the other method in each iteration. By alternating between search spaces, the technique can escape local minima that naturally occur in each search space. Also, the 3D search spaces provide more constraints across CT slices, when compared with the 2D search spaces in individual CT slices. The proposed method is evaluated with 10 easy and 10 difficult cases of AAA. The results show that the proposed 3D segmentation technique achieves the outstanding segmentation accuracy with an average dice similarity value (DSC) of 91.88%, when compared to the other methods using the same dataset, which are the 2D proposed method, classical graph cut, distance regularized level set evolution, and registration based geometric active contour with the DSCs of 87.57 ± 4.52%, 72.47 ± 8.11%, 58.50 ± 8.86% and 76.21 ± 10.49%, respectively.

Accuracy of dengue clinical diagnosis with and without NS1 antigen rapid test: Comparison between human and Bayesian network model decision.

Differentiating dengue patients from other acute febrile illness patients is a great challenge among physicians. Several dengue diagnosis methods are recommended by WHO. The application of specific laboratory tests is still limited due to high cost, lack of equipment, and uncertain validity. Therefore, clinical diagnosis remains a common practice especially in resource limited settings. Bayesian networks have been shown to be a useful tool for diagnostic decision support. This study aimed to construct Bayesian network models using basic demographic, clinical, and laboratory profiles of acute febrile illness patients to diagnose dengue. Data of 397 acute undifferentiated febrile illness patients who visited the fever clinic of the Bangkok Hospital for Tropical Diseases, Thailand, were used for model construction and validation. The two best final models were selected: one with and one without NS1 rapid test result. The diagnostic accuracy of the models was compared with that of physicians on the same set of patients. The Bayesian network models provided good diagnostic accuracy of dengue infection, with ROC AUC of 0.80 and 0.75 for models with and without NS1 rapid test result, respectively. The models had approximately 80% specificity and 70% sensitivity, similar to the diagnostic accuracy of the hospital's fellows in infectious disease. Including information on NS1 rapid test improved the specificity, but reduced the sensitivity, both in model and physician diagnoses. The Bayesian network model developed in this study could be useful to assist physicians in diagnosing dengue, particularly in regions where experienced physicians and laboratory confirmation tests are limited.

Outer Wall Segmentation of Abdominal Aortic Aneurysm by Variable Neighborhood Search Through Intensity and Gradient Spaces.

Aortic aneurysm segmentation remains a challenge. Manual segmentation is a time-consuming process which is not practical for routine use. To address this limitation, several automated segmentation techniques for aortic aneurysm have been developed, such as edge detection-based methods, partial differential equation methods, and graph partitioning methods. However, automatic segmentation of aortic aneurysm is difficult due to high pixel similarity to adjacent tissue and a lack of color information in the medical image, preventing previous work from being applicable to difficult cases. This paper uses uses a variable neighborhood search that alternates between intensity-based and gradient-based segmentation techniques. By alternating between intensity and gradient spaces, the search can escape from local optima of each space. The experimental results demonstrate that the proposed method outperforms the other existing segmentation methods in the literature, based on measurements of dice similarity coefficient and jaccard similarity coefficient at the pixel level. In addition, it is shown to perform well for cases that are difficult to segment.

Complexity-Based Spatial Hierarchical Clustering for Malaria Prediction.

Targeted intervention and resource allocation are essential in effective control of infectious diseases, particularly those like malaria that tend to occur in remote areas. Disease prediction models can help support targeted intervention, particularly if they have fine spatial resolution. But, choosing an appropriate resolution is a difficult problem since choice of spatial scale can have a significant impact on accuracy of predictive models. In this paper, we introduce a new approach to spatial clustering for disease prediction we call complexity-based spatial hierarchical clustering. The technique seeks to find spatially compact clusters that have time series that can be well characterized by models of low complexity. We evaluate our approach with 2 years of malaria case data from Tak Province in northern Thailand. We show that the technique's use of reduction in Akaike information criterion (AIC) and Bayesian information criterion (BIC) as clustering criteria leads to rapid improvement in predictability and significantly better predictability than clustering based only on minimizing spatial intra-cluster distance for the entire range of cluster sizes over a variety of predictive models and prediction horizons.

Automated outcome scoring in a virtual reality simulator for endodontic surgery.

BACKGROUND AND OBJECTIVE: We address the problem of automated outcome assessment in a virtual reality (VR) simulator for endodontic surgery. Outcome assessment is an essential component of any system that provides formative feedback, which requires assessing the outcome, relating it to the procedure, and communicating in a language natural to dental students. This study takes a first step toward automated generation of such comprehensive feedback. METHODS: Virtual reference templates are computed based on tooth anatomy and the outcome is assessed with a 3D score cube volume which consists of voxel-level non-linear weighted scores based on the templates. The detailed scores are transformed into standard scoring language used by dental schools. The system was evaluated on fifteen outcome samples that contained optimal results and those with errors including perforation of the walls, floor, and both, as well as various combinations of major and minor over and under drilling errors. Five endodontists who had professional training and varying levels of experiences in root canal treatment participated as raters in the experiment. RESULTS: Results from evaluation of our system with expert endodontists show a high degree of agreement with expert scores (information based measure of disagreement 0.04-0.21). At the same time they show some disagreement among human expert scores, reflecting the subjective nature of human outcome scoring. The discriminatory power of the AOS scores analyzed with three grade tiers (A, B, C) using the area under the receiver operating characteristic curve (AUC). The AUC values are generally highest for the {AB: C} cutoff which is cutoff at the boundary between clinically acceptable (B) and clinically unacceptable (C) grades. CONCLUSIONS: The objective consistency of computed scores and high degree of agreement with experts make the proposed system a promising addition to existing VR simulators. The translation of detailed level scores into terminology commonly used in dental surgery supports natural communication with students and instructors. With the reference virtual templates created automatically, the approach is robust and is applicable in scoring the outcome of any dental surgery procedure involving the act of drilling.

Spatiotemporal Bayesian networks for malaria prediction.

Targeted intervention and resource allocation are essential for effective malaria control, particularly in remote areas, with predictive models providing important information for decision making. While a diversity of modeling technique have been used to create predictive models of malaria, no work has made use of Bayesian networks. Bayes nets are attractive due to their ability to represent uncertainty, model time lagged and nonlinear relations, and provide explanations. This paper explores the use of Bayesian networks to model malaria, demonstrating the approach by creating village level models with weekly temporal resolution for Tha Song Yang district in northern Thailand. The networks are learned using data on cases and environmental covariates. Three types of networks are explored: networks for numeric prediction, networks for outbreak prediction, and networks that incorporate spatial autocorrelation. Evaluation of the numeric prediction network shows that the Bayes net has prediction accuracy in terms of mean absolute error of about 1.4 cases for 1 week prediction and 1.7 cases for 6 week prediction. The network for outbreak prediction has an ROC AUC above 0.9 for all prediction horizons. Comparison of prediction accuracy of both Bayes nets against several traditional modeling approaches shows the Bayes nets to outperform the other models for longer time horizon prediction of high incidence transmission. To model spread of malaria over space, we elaborate the models with links between the village networks. This results in some very large models which would be far too laborious to build by hand. So we represent the models as collections of probability logic rules and automatically generate the networks. Evaluation of the models shows that the autocorrelation links significantly improve prediction accuracy for some villages in regions of high incidence. We conclude that spatiotemporal Bayesian networks are a highly promising modeling alternative for prediction of malaria and other vector-borne diseases.

Spatiotemporal Bayesian Networks for Malaria Prediction: Case Study of Northern Thailand.

While a diversity of modeling technique have been used to create predictive models of malaria, no work has made use of Bayesian networks. Bayes nets are attractive due to their ability to represent uncertainty, model time lagged and nonlinear relations, and provide explanations of inferences. This paper explores the use of Bayesian networks to model malaria, demonstrating the approach by creating a village level model with weekly temporal resolution for Tha Song Yang district in northern Thailand. The network is learned using data on cases and environmental covariates. The network models incidence over time as well as evolution of the environmental variables, and captures time lagged and nonlinear effects. Out of sample evaluation shows the model to have high accuracy for one and two week predictions.

Recognizing Clinical Styles in a Dental Surgery Simulator.

Recognizing clinical style is essential for generating intelligent guidance in virtual reality simulators for dental skill acquisition. The aim of this study was to determine the potential of Dynamic Time Warping (DTW) in matching novices' tooth cutting sequences with those of experts. Forty dental students and four expert dentists were enrolled to perform access opening to the root canals with a simulator. Four experts performed in manners that differed widely in the tooth preparation sequence. Forty students were randomly allocated into four groups and were trained following each expert. DTW was performed between each student's sequence and all the expert sequences to determine the best match. Overall, the accuracy of the matching was high (95%). The current results suggest that the DTW is a useful technique to find the best matching expert for a student so that feedback based on that expert's performance can be given to the novice in clinical skill training.