Cardiac auscultation (CA), the act of listening to the heart's sound, is a critical skill that provides valuable information for identifying serious heart diseases. Proficiency in cardiac auscultation requires repeated stethoscope practice and experience in identifying abnormal or irregular cardiac rhythms. However, nowadays, most hospital admissions are short and intensely focused, with fewer opportunities for medical trainees to learn and practice bedside examination skills. It is common practice in many institutions to incorporate standardized patients (SPs) into CA training because these actors are able to represent the patient and convey the symptoms. However, SPs are typically healthy individuals, limiting the kinds of abnormalities that students can hear. In this work, we develop a novel real-time simulation-based method for virtual pathology stethoscope (VPS) detection. The VPS system uses augmented reality (AR) to teach medical students how to perform cardiac examinations by listening to abnormal heart sounds in SPs who are otherwise healthy. A digital stethoscope with two electrodes on the chest piece collects electrocardiogram (ECG) signal data sets from SPs at the four primary auscultation sites. Next, different deep-learning methods are evaluated for classifying the location of the stethoscope by taking advantage of subtle differences in the ECG signals. This study would significantly extend the simulation capabilities of SPs by allowing medical students and trainees to perform realistic CA and hear CA in a clinical environment.

OBJECTIVE:This work presents the development and validation of an interactive simulation training platform for the minimally invasive repair of pectus excavatum, otherwise known as the Nuss procedure.METHODS:The challenges and implications of developing both an all-virtual and an all-physical version of the simulator are investigated in a training context. A hybrid system is then developed that integrates virtual and physical constituents and a haptic interface to reproduce the primary steps of the procedure and to satisfy clinically relevant prerequisites for its training system. Furthermore, this work carries out a study to investigate the system's face, content, and construct validity.RESULTS:Objective and subjective evaluations of the system demonstrate its utility for surgical training and establish various levels of its validity.CONCLUSION:A hybrid virtual/physical configuration of the trainer can efficiently and realistically reproduce the primary steps of the procedure.SIGNIFICANCE:Outside of this work, a simulation and training platform for the Nuss procedure is not available. This system was developed in close collaboration with the pioneers of this surgical technique.

Standardized Patient (SP) based medical simulation is commonly used to teach bedside skills. However, SPs are typically healthy individuals, and the number and range of conditions they can portray are limited. Our research aims to improve the cardiac auscultation (CA) skills of medical students by utilizing a modified stethoscope in tandem with SP. This technology introduces the potential to augment virtual pathology sounds on otherwise healthy SP. In this study, CNN models, previously trained on large-scale image datasets, are transferred to identify the four CA sites. We applied the pre-trained CNN models of ResNet50, InceptionV3, and Alexnet, to the ECG recordings from the CA regions, which are converted to images using a wavelet scalogram. Moreover, data augmentation is performed to supplement limited labeled data. Experimental results illustrate data augmentation with InceptionV3 and Resnet50 models leads to a better performance than our previously reported methods, between 93% and 95% F1 score.

Monitoring the progress of medical treatment is paramount to its success and the patient's quality-of-life. An efficient, cost-effective, and accurate assessment of the treatment's progress that illustrates its tangible impact can motivate patients and guide the procedure. This work discusses such an assessment tool for both surgical and nonsurgical interventions to correct Pectus Excavatum(PE) - a chest wall deformity characterized by depression of the sternum. We previously proposed a novel approach for measuring and evaluating the severity of pectus deformities. Our method uses 3-D optical scans which are analyzed to compute surface deformation via registration-based point comparisons, and a distance map is generated, providing a quantitative representation of chest wall improvements. The work presented in this paper expands on this effort by adding a module to objectively evaluate the aesthetic outcomes. In this study, we developed a statistical 3D chest model based on the Gaussian Process Morphable Model (GPMM) using a limited number of optical surface scans (n=20) of healthy male subjects. The model builds an average chest shape which can be used to evaluate the aesthetic results of PE treatment. We analyzed the impact of different kernel functions in the modeling of the chest variation and report on the models generalization, specificity, and compactness.

Monitoring the progress of therapeutic treatment is paramount to its success and to the patient's quality-of-life. An efficient, cost-effective, and accurate assessment of the treatment's progress that illustrates its tangible impact can motivate patients and guide the procedure. This work discusses such an assessment tool for both surgical and nonsurgical interventions to correct pectus excavatum - the most common chest wall deformity. The developed instrument utilizes optical scanning and registration techniques to provide an accurate evaluation of the improvement over the course of treatment. In this paper, a prospective study is conducted to report on and establish the validity of the instrument after deploying it for clinical use. Statistical tests are used to study the utility of the system in a clinical setting.

"Optical scanning has proven to be advantageous to objectively assess the severity of chest wall deformities and the effectiveness of its treatment. By potentially eliminating the need for computed tomography (CT) scanning and superseding manual measurements that are subject to errors, a system that utilizes optical scanning presents great value to patients and practitioners. This work aims to investigate and evaluate the performance of two off-the-shelf optical scanning sensors in the context of their utility and accuracy to measure the severity of chest wall deformities. An in-vitro experiment and a human study are conducted utilizing both sensors to collect data and report the findings."

Chest wall deformities are congenital chest wall malformations that become more pronounced during early adolescence. Pectus Excavatum (PE) and Pectus Carinatum (PC) account for over 90% of these deformities and are often accompanied by other problems such as fatigue, depression, breathing issues, heart palpitations, and even scoliosis [Williams 2003]. Surgical intervention may or may not be indicated largely depending upon the gold standard measurement index, the Haller index (HI) [Haller 1987], evaluated for PE and PC using computed tomography (CT). There are many other indices that are also used. However, all of these objective approaches have attempted solely a quantification of the severity and not a qualification of the deformity that might not only determine surgical candidacy but also may identify more clearly the best course of treatment for a particular individual.

Cardiac auscultation (CA) is the auditory detection of heart sounds to diagnose abnormalities, a crucial skill that is both efficient and cost-effective in medical practice. However, due to increased prevalence and usage of expensive cardiac technologies, many new physicians and trainees have difficulty performing essential cardiac examinations on their patients, particularly diagnosing abnormalities through auscultation using a stethoscope. A virtual pathology stethoscope is a simulation-based solution that train students to perform cardiac examinations by listening to abnormal heart sounds in otherwise healthy standardized patients (SPs). This study reports the accuracy of an electrocardiogram (ECG)-based stethoscope tracking method for placing virtual symptoms in correct auscultation regions. A modified stethoscope head with two electrodes was used to pick up ECG signals at the four primary auscultation sites. A one-dimensional convolutional neural network (CNN) is then modeled to classify the location of the stethoscope by taking advantage of subtle differences in the ECG signals. A 91% accuracy was obtained, showing promising performance gain over our previous methods. This finding would significantly extend the simulation capabilities of SPs by allowing trainees to perform realistic CA and hear CA in clinical environment.

BACKGROUND:The nonsurgical treatment of chest wall deformity by a vacuum bell or external brace is gradual, with correction taking place over months. Monitoring the progress of nonsurgical treatment of chest wall deformity has relied on the ancient methods of measuring the depth of the excavatum and the protrusion of the carinatum. Patients, who are often adolescent, may become discouraged and abandon treatment.METHODS:Optical scanning was utilized before and after the intervention to assess the effectiveness of treatment. The device measured the change in chest shape at each visit. In this pilot study, patients were included if they were willing to undergo scanning before and after treatment. Both surgical and nonsurgical treatment results were assessed.RESULTS:Scanning was successful in 7 patients. Optical scanning allowed a visually clear, precise assessment of treatment, whether by operation, vacuum bell (for pectus excavatum), or external compression brace (for pectus carinatum). Millimeter-scale differences were identified and presented graphically to patients and families.CONCLUSION:Optical scanning with the digital subtraction of images obtained months apart allows a comparison of chest shape before and after treatment. For nonsurgical, gradual methods, this allows the patient to more easily appreciate progress. We speculate that this will increase adherence to these methods in adolescent patients.

Food security and sustainable agriculture are two of the challenges faced by nations globally. As a population grows, the demand for food rises. To keep up with the demand without compromising the environment, sustainable agriculture techniques are significantly being studied and advocated by concerned organizations like the United Nations (UN). The UN furthers sustainable agriculture through its Sustainable Development Goal 2 (SDG 2) which aspires to double the agricultural productivity and incomes of small-scale food producers and ensure sustainable food production systems and implement resilient agricultural practices. Smallholder farming households, which has an estimated global population of 500 million (around 2 billion people), rely on small-scale agriculture for their livelihoods. They are considered as the backbone of agricultural production in developing countries and they play a key role in upholding sustainability. Having a crop rotation sustainability assessment tool for smallholder farmers can aid them accordingly in their crop production planning and abet the advocacy of agriculture sustainability. Our research aims to develop a model-driven decision support tool for smallholder farmers to promote sustainability in their crop production practices. In this paper, we investigate the integration of crop simulation model and multicriteria decision analysis as an approach for a dynamic and multi-criteria sustainability assessment of crop rotation alternatives.

In this paper, a flexible microfluidic-based sensor is investigated for monitoring the bending and tilting of a metal bar for miniature access pectus excavatum repair (MAPER). Built on a polyethylene terephthalate (PET) substrate, the sensor contains a polydimethylsiloxane (PDMS) microstructure embedded with an electrolyte-enabled 5x1 resistive transducer array. One end of the metal bar is fixed and the sensor is attached to different locations of the bar. The other end of the metal bar is connected to a 5-1b weight for controlling the bending of the bar. Manually holding and releasing the weight bends the metal bar, which translates to strain in the PET substrate and consequently causes resistance changes in the transducer array. Upon the same amount of bending, resistance change of the sensor varies with the location of the sensor on the metal bar, due to the bending (or strain) variation along its length. Tilting of the metal bar relative to a rigid object (i.e., sternum) introduces force acting on the microstructure of the sensor, and thus gives rise to resistance changes in the transducer array. As a result, this sensor shows the potential of being used in MAPER to minimize tissue injury in vivo application.

With the food security challenge faced by nations globally, agriculture sustainability has been a significant consideration for concerned agencies. Sustainability assessments are significant tools in providing support to stakeholders in their crop production planning. Agricultural sustainability assessment, however, is complex and it involves numerous criteria that can be conflicting. In this study we investigated the use Analytical Hierarchy Process, a multi-criteria decision analysis method, in assessing the sustainability of crop rotation alternatives and its applicability to address the multiple criteria of sustainability and the diverse preferences of stakeholders. The comparable results of the model with a sustainability assessment of cropping systems reported in the literature, validates AHP as an apt method for sustainability assessment of crop rotation alternatives and handling the complex criteria of sustainability and preferences of stakeholders. The model results, when well presented, can be utilized to support stakeholders in their decision making and in evaluating their crop rotation choices.

INTRODUCTION:Patient-centered simulation for nonhealthcare providers is an emerging and innovative application for healthcare simulation. Currently, no consensus exists on what patient-centered simulation encompasses and outcomes research in this area is limited. Conceptually, patient-centered simulation aligns with the principles of patient- and family-centered care bringing this educational tool directly to patients and caregivers with the potential to improve patient care and outcomes.METHODS:This descriptive article is a summary of findings presented at the 2nd International Meeting for Simulation in Healthcare Research Summit. Experts in the field delineated a categorization for better describing patient-centered simulation and reviewed the literature to identify a research agenda.RESULTS:Three types of patient-centered simulation patient-directed, patient-driven, and patient-specific are presented with research priorities identified for each.CONCLUSIONS:Patient-centered simulation has been shown to be an effective educational tool and has the potential to directly improve patient care outcomes. Presenting a typology for patient-centered simulation provides direction for future research.

Stress can impose negative impact on the health and well-being of a person. People who do not have tools to manage their stress are more likely to acquire cardiovascular disease (CVD) - the leading cause of death in the USA. For affected individuals, it not only implies health risks but also increased medical expenditures which can lead to financial issues - the top stressor in the USA. Research studies reveal that yoga reduces the stress perceived and modulates stress response systems. In this study, an agent-based model was developed to simulate the impact of adopting a yogic breathing technique, particularly on managing stress, preventing CVD and reducing the associated medical expenses. The simulation results show that people who practice SKY have generally lower and normal SBP, BMI and stress levels while those who don't, have generally higher levels and fall into the high-risk category.

Rising stress levels is a significant problem in the USA. The average stress levels increased to 5.1 in 2015 compared to 4.9 in 2014 (American Psychological Association, 2016). People who do not have tools to manage their stress are more likely to acquire cardiovascular disease (CVD) – the leading cause of death in the USA. In Hampton Roads, an average of 23% of Medicare beneficiaries were treated for heart disease (Greater Hampton Roads, 2014). For affected individuals, it not only implies health risks but also increased medical expenditures which can lead to financial issues – the top stressor in the USA. Therefore, interventions are needed to manage the risk of CVD. Harvard Health Publications (2009) indicates that yoga reduces the stress perceived and modulates stress response systems. Sudarshan KriyaYoga (SKY), a form of yogic breathing, is unique method for balancing the autonomic nervous system and influencing psychologic and stress related disorders (Brown & Gerbarg, 2005). An agent-based model was developed in this study to simulate the micro and macro-level impact of adopting SKY in Hampton Roads, particularly on managing stress, preventing CVD and reducing the associated medical expenses. The validation results indicate that the difference between the published results of research studies on SKY and the simulation results are not statistically significant. Simulation results show that people who practice SKY have generally lower and normal SBP, BMI and stress level while those who don’t, have generally higher and falls on the high-risk category. The analysis of variance suggests that the increase in SKY population in Hampton Roads provides an extremely significant effect in decreasing the percentage of CVD high risk population, associated expenses and the overall stress level in the region. In addition, advertising SKY offers greater impact on improving the risk factors and reducing the expenses associated to CVD in Hampton Roads.

Task engagement is defined as loadings on energetic arousal (affect), task motivation, and concentration (cognition) [1]. It is usually challenging and expensive to label cognitive state data, and traditional computational models trained with limited label information for engagement assessment do not perform well because of overfitting. In this paper, we proposed two deep models (i.e., a deep classifier and a deep autoencoder) for engagement assessment with scarce label information. We recruited 15 pilots to conduct a 4-h flight simulation from Seattle to Chicago and recorded their electroencephalograph (EEG) signals during the simulation. Experts carefully examined the EEG signals and labeled 20 min of the EEG data for each pilot. The EEG signals were preprocessed and power spectral features were extracted. The deep models were pretrained by the unlabeled data and were fine-tuned by a different proportion of the labeled data (top 1%, 3%, 5%, 10%, 15%, and 20%) to learn new representations for engagement assessment. The models were then tested on the remaining labeled data. We compared performances of the new data representations with the original EEG features for engagement assessment. Experimental results show that the representations learned by the deep models yielded better accuracies for the six scenarios (77.09%, 80.45%, 83.32%, 85.74%, 85.78%, and 86.52%), based on different proportions of the labeled data for training, as compared with the corresponding accuracies (62.73%, 67.19%, 73.38%, 79.18%, 81.47%, and 84.92%) achieved by the original EEG features. Deep models are effective for engagement assessment especially when less label information was used for training.

An instrument that objectively quantifies a condition's severity and its improvement after treatment is of great use. This is also the case for pectus excavatum (PE), a congenital chest wall deformity, for which several severity indices have been introduced. This work describes a system that utilizes chest surface scans generated from CT-data or optical scanning to provide a gauge and visualization of chest wall deviations. A validation experiment is conducted to evaluate the fidelity of such an instrument utilizing pre-and postoperative CT scans. Statistical analysis shows the ability of the instrument to accurately recognize changes in the chest surface profile.

Depending on the severity of the condition and associated risk, surgical intervention may not always be the first choice. This is true for treating chest wall deformities such as pectus excavatum and pectus carinatum. For both conditions, novel non-surgical treatments have been developed to gradually alleviate the malformation making use of the elastic nature of the costal cartilages at an early age of the patient. To quantify the performance of such treatments, this paper introduces and discusses the development of a software-based instrument that utilizes 3D chest optical images (surface scans) as input and uses registration techniques to produce an objective gauge of a patient's physical improvement after undergoing treatments. Further discussed is an experiment designed to investigate the construct validity of the developed instrument.

The severity of the condition and associated risk usually steer the choice for either a surgical or conservative intervention. This is also the case for treating chest wall deformities such as pectus excavatum where novel non-surgical treatments have been developed to gradually alleviate the condition making use of the elastic nature of the costal cartilages in pediatric patients. An instrument for quantifying the improvement after such treatments has been developed to produce a numerical and visual gauge of the change. In this research, a validation experiment is conducted to assess the fidelity of the developed instrument utilizing real patients' data after undergoing a single treatment session. Patients are scanned using the constructed apparatus before and after treatment and manual hand-measurements are recorded to be used as a frame of reference. We report on the statistical results of these measurements in the validation of the scanning and comparison apparatus.

We review the state of the art of process modeling for discrete event simulation, make a number of observations and identify a number of issues that have to be tackled for promoting the use of process modeling in simulation. Process models are of particular interest in model-based simulation engineering approaches where the executable simulation model (code) is obtained with the help of textual or visual models. We present an illustrative example of model-based simulation development.