Mechanical behavior of full-thickness burn human skin is rate-independent.

Skin tissue is recognized to exhibit rate-dependent mechanical behavior under various loading conditions. Here, we report that the full-thickness burn human skin exhibits rate-independent behavior under uniaxial tensile loading conditions. Mechanical properties, namely, ultimate tensile stress, ultimate tensile strain, and toughness, and parameters of Veronda-Westmann hyperelastic material law were assessed via uniaxial tensile tests. Univariate hypothesis testing yielded no significant difference (p > 0.01) in the distributions of these properties for skin samples loaded at three different rates of 0.3 mm/s, 2 mm/s, and 8 mm/s. Multivariate multiclass classification, employing a logistic regression model, failed to effectively discriminate samples loaded at the aforementioned rates, with a classification accuracy of only 40%. The median values for ultimate tensile stress, ultimate tensile strain, and toughness are computed as 1.73 MPa, 1.69, and 1.38 MPa, respectively. The findings of this study hold considerable significance for the refinement of burn care training protocols and treatment planning, shedding new light on the unique, rate-independent behavior of burn skin.

Predicting Problematic Behavior in Autism Spectrum Disorder Using Medical History and Environmental Data.

Autism spectrum disorder (ASD), characterized by social, communication, and behavioral abnormalities, affects 1 in 36 children according to the CDC. Several co-occurring conditions are often associated with ASD, including sleep and immune disorders and gastrointestinal (GI) problems. ASD is also associated with sensory sensitivities. Some individuals with ASD exhibit episodes of challenging behaviors that can endanger themselves or others, including aggression and self-injurious behavior (SIB). In this work, we explored the use of artificial intelligence models to predict behavior episodes based on past data of co-occurring conditions and environmental factors for 80 individuals in a residential setting. We found that our models predict occurrences of behavior and non-behavior with accuracies as high as 90% for some individuals, and that environmental, as well as gastrointestinal, factors are notable predictors across the population examined. While more work is needed to examine the underlying connections between the factors and the behaviors, having reasonably accurate predictions for behaviors has the potential to improve the quality of life of some individuals with ASD.

Spatial topology of organelle is a new breast cancer cell classifier.

Genomics and proteomics have been central to identify tumor cell populations, but more accurate approaches to classify cell subtypes are still lacking. We propose a new methodology to accurately classify cancer cells based on their organelle spatial topology. Herein, we developed an organelle topology-based cell classification pipeline (OTCCP), which integrates artificial intelligence (AI) and imaging quantification to analyze organelle spatial distribution and inter-organelle topology. OTCCP was used to classify a panel of human breast cancer cells, grown as 2D monolayer or 3D tumor spheroids using early endosomes, mitochondria, and their inter-organelle contacts. Organelle topology allows for a highly precise differentiation between cell lines of different subtypes and aggressiveness. These findings lay the groundwork for using organelle topological profiling as a fast and efficient method for phenotyping breast cancer function as well as a discovery tool to advance our understanding of cancer cell biology at the subcellular level.

A statistical machine learning approach linking molecular conformational changes to altered mechanical characteristics of skin due to thermal injury.

This article develops statistical machine learning models to predict the mechanical properties of skin tissue subjected to thermal injury based on the Raman spectra associated with conformational changes of the molecules in the burned tissue. Ex vivo porcine skin tissue samples were exposed to controlled burn conditions at 200 °F for five different durations: (i) 10s, (ii) 20s, (iii) 30s, (iv) 40s, and (v) 50s. For each burn condition, Raman spectra of wavenumbers 500-2000 cm-1 were measured from the tissue samples, and tensile testing on the same samples yielded their material properties, including, ultimate tensile strain, ultimate tensile stress, and toughness. Partial least squares regression models were established such that the Raman spectra, describing conformational changes in the tissue, could accurately predict ultimate tensile stress, toughness, and ultimate tensile strain of the burned skin tissues with R2 values of 0.8, 0.8, and 0.7, respectively, using leave-two-out cross validation scheme. An independent assessment of the resultant models showed that amino acids, proteins & lipids, and amide III components of skin tissue significantly influence the prediction of the properties of the burned skin tissue. In contrast, amide I has a lesser but still noticeable effect. These results are consistent with similar observations found in the literature on the mechanical characterization of burned skin tissue.

Skill-level classification and performance evaluation for endoscopic sleeve gastroplasty.

BACKGROUND: We previously developed grading metrics for quantitative performance measurement for simulated endoscopic sleeve gastroplasty (ESG) to create a scalar reference to classify subjects into experts and novices. In this work, we used synthetic data generation and expanded our skill level analysis using machine learning techniques. METHODS: We used the synthetic data generation algorithm SMOTE to expand and balance our dataset of seven actual simulated ESG procedures using synthetic data. We performed optimization to seek optimum metrics to classify experts and novices by identifying the most critical and distinctive sub-tasks. We used support vector machine (SVM), AdaBoost, K-nearest neighbors (KNN) Kernel Fisher discriminant analysis (KFDA), random forest, and decision tree classifiers to classify surgeons as experts or novices after grading. Furthermore, we used an optimization model to create weights for each task and separate the clusters by maximizing the distance between the expert and novice scores. RESULTS: We split our dataset into a training set of 15 samples and a testing dataset of five samples. We put this dataset through six classifiers, SVM, KFDA, AdaBoost, KNN, random forest, and decision tree, resulting in 0.94, 0.94, 1.00, 1.00, 1.00, and 1.00 accuracy, respectively, for training and 1.00 accuracy for the testing results for SVM and AdaBoost. Our optimization model maximized the distance between the expert and novice groups from 2 to 53.72. CONCLUSION: This paper shows that feature reduction, in combination with classification algorithms such as SVM and KNN, can be used in tandem to classify endoscopists as experts or novices based on their results recorded using our grading metrics. Furthermore, this work introduces a non-linear constraint optimization to separate the two clusters and find the most important tasks using weights.

Video-based formative and summative assessment of surgical tasks using deep learning.

To ensure satisfactory clinical outcomes, surgical skill assessment must be objective, time-efficient, and preferentially automated-none of which is currently achievable. Video-based assessment (VBA) is being deployed in intraoperative and simulation settings to evaluate technical skill execution. However, VBA is manual, time-intensive, and prone to subjective interpretation and poor inter-rater reliability. Herein, we propose a deep learning (DL) model that can automatically and objectively provide a high-stakes summative assessment of surgical skill execution based on video feeds and low-stakes formative assessment to guide surgical skill acquisition. Formative assessment is generated using heatmaps of visual features that correlate with surgical performance. Hence, the DL model paves the way for the quantitative and reproducible evaluation of surgical tasks from videos with the potential for broad dissemination in surgical training, certification, and credentialing.

Objective metrics for hand-sewn bowel anastomoses can differentiate novice from expert surgeons.

BACKGROUND: Assessing performance automatically in a virtual reality trainer or from recorded videos is advantageous but needs validated objective metrics. The purpose of this study is to obtain expert consensus and validate task-specific metrics developed for assessing performance in double-layered end-to-end anastomosis. MATERIALS AND METHODS: Subjects were recruited into expert (PGY 4-5, colorectal surgery residents, and attendings) and novice (PGY 1-3) groups. Weighted average scores of experts for each metric item, completion time, and the total scores computed using global and task-specific metrics were computed for assessment. RESULTS: A total of 43 expert surgeons rated our task-specific metric items with weighted averages ranging from 3.33 to 4.5 on a 5-point Likert scale. A total of 20 subjects (10 novices and 10 experts) participated in validation study. The novice group completed the task significantly more slowly than the experienced group (37.67 ± 7.09 vs 25.47 ± 7.82 min, p = 0.001). In addition, both the global rating scale (23.47 ± 4.28 vs 28.3 ± 3.85, p = 0.016) and the task-specific metrics showed a significant difference in performance between the two groups (38.77 ± 2.83 vs 42.58 ± 4.56 p = 0.027) following partial least-squares (PLS) regression. Furthermore, PLS regression showed that only two metric items (Stay suture tension and Tool handling) could reliably differentiate the performance between the groups (20.41 ± 2.42 vs 24.28 ± 4.09 vs, p = 0.037). CONCLUSIONS: Our study shows that our task-specific metrics have significant discriminant validity and can be used to evaluate the technical skills for this procedure.

Synthetic tissues lack the fidelity for the use in burn care simulators.

This work compares the mechanical response of synthetic tissues used in burn care simulators from ten different manufacturers with that of ex vivo full thickness burned porcine skin as a surrogate for human skin tissues. This is of high practical importance since incorrect mechanical properties of synthetic tissues may introduce a negative bias during training due to the inaccurate haptic feedback from burn care simulator. A negative training may result in inadequately performed procedures, such as in escharotomy, which may lead to muscle necrosis endangering life and limb. Accurate haptic feedback in physical simulators is necessary to improve the practical training of non-expert providers for pre-deployment/pre-hospital burn care. With the U.S. Army's emerging doctrine of prolonged field care, non-expert providers must be trained to perform even invasive burn care surgical procedures when indicated. The comparison reported in this article is based on the ultimate tensile stress, ultimate tensile strain, and toughness that are measured at strain rates relevant to skin surgery. A multivariate analysis using logistic regression reveals significant differences in the mechanical properties of the synthetic and the porcine skin tissues. The synthetic and porcine skin tissues show a similar rate dependent behavior. The findings of this study are expected to guide the development of high-fidelity burn care simulators for the pre-deployment/pre-hospital burn care provider education.

Framework for Testing Robustness of Machine Learning-Based Classifiers.

There has been a rapid increase in the number of artificial intelligence (AI)/machine learning (ML)-based biomarker diagnostic classifiers in recent years. However, relatively little work has focused on assessing the robustness of these biomarkers, i.e., investigating the uncertainty of the AI/ML models that these biomarkers are based upon. This paper addresses this issue by proposing a framework to evaluate the already-developed classifiers with regard to their robustness by focusing on the variability of the classifiers' performance and changes in the classifiers' parameter values using factor analysis and Monte Carlo simulations. Specifically, this work evaluates (1) the importance of a classifier's input features and (2) the variability of a classifier's output and model parameter values in response to data perturbations. Additionally, it was found that one can estimate a priori how much replacement noise a classifier can tolerate while still meeting accuracy goals. To illustrate the evaluation framework, six different AI/ML-based biomarkers are developed using commonly used techniques (linear discriminant analysis, support vector machines, random forest, partial-least squares discriminant analysis, logistic regression, and multilayer perceptron) for a metabolomics dataset involving 24 measured metabolites taken from 159 study participants. The framework was able to correctly predict which of the classifiers should be less robust than others without recomputing the classifiers itself, and this prediction was then validated in a detailed analysis.

Multivariate analysis reveals topography dependent relationships amongst neurite morphological features from dorsal root ganglia neurons.

Objective.Nerve guidance scaffolds containing anisotropic architectures provide topographical cues to direct regenerating axons through an injury site to reconnect the proximal and distal end of an injured nerve or spinal cord. Previousin vitrocultures of individual neurons revealed that fiber characteristics such as fiber diameter and inter-fiber spacing alter neurite morphological features, such as total neurite length, the longest single neurite, branching density, and the number of primary neurites. However, the relationships amongst these four neurite morphological features have never been studied on fibrous topographies using multivariate analysis.Approach.In this study, we cultured dissociated dorsal root ganglia on aligned, fibrous scaffolds and flat, isotropic films and evaluated the univariate and multivariate differences amongst these four neurite morphological features.Main results.Univariate analysis showed that fibrous scaffolds increase the length of the longest neurite and decrease branching density compared to film controls. Further, multivariate analysis revealed that, regardless of scaffold type, overall neurite length increases due to a compromise between the longest extending neurite, branching density, and the number of primary neurites. Additionally, multivariate analysis indicated that neurite branching is more independent of the other neurite features when neurons were cultured on films but that branching is strongly related to the other neurite features when cultured on fibers.Significance.These findings are significant as they are the first evidence that aligned topographies affect the relationships between neurite morphological features. This study provides a foundation for analyzing how individual neurite morphology may relate to neural regeneration on a macroscopic scale and provide information that may be used to optimize nerve guidance scaffolds.

Deep learning-based motion artifact removal in functional near-infrared spectroscopy.

Significance: Functional near-infrared spectroscopy (fNIRS), a well-established neuroimaging technique, enables monitoring cortical activation while subjects are unconstrained. However, motion artifact is a common type of noise that can hamper the interpretation of fNIRS data. Current methods that have been proposed to mitigate motion artifacts in fNIRS data are still dependent on expert-based knowledge and the post hoc tuning of parameters. Aim: Here, we report a deep learning method that aims at motion artifact removal from fNIRS data while being assumption free. To the best of our knowledge, this is the first investigation to report on the use of a denoising autoencoder (DAE) architecture for motion artifact removal. Approach: To facilitate the training of this deep learning architecture, we (i) designed a specific loss function and (ii) generated data to mimic the properties of recorded fNIRS sequences. Results: The DAE model outperformed conventional methods in lowering residual motion artifacts, decreasing mean squared error, and increasing computational efficiency. Conclusion: Overall, this work demonstrates the potential of deep learning models for accurate and fast motion artifact removal in fNIRS data.

Thermally damaged porcine skin is not a surrogate mechanical model of human skin.

Porcine skin is considered a de facto surrogate for human skin. However, this study shows that the mechanical characteristics of full thickness burned human skin are different from those of porcine skin. The study relies on five mechanical properties obtained from uniaxial tensile tests at loading rates relevant to surgery: two parameters of the Veronda-Westmann hyperelastic material model, ultimate tensile stress, ultimate tensile strain, and toughness of the skin samples. Univariate statistical analyses show that human and porcine skin properties are dissimilar (p < 0.01) for each loading rate. Multivariate classification involving the five mechanical properties using logistic regression can successfully separate the two skin types with a classification accuracy exceeding 95% for each loading rate individually as well as combined. The findings of this study are expected to guide the development of effective training protocols and high-fidelity simulators to train burn care providers.

Prediction of Coronary Calcification and Stenosis: Role of Radiomics From Low-Dose CT.

RATIONALE AND OBJECTIVES: We aimed to assess relationship between single-click, whole heart radiomics from low-dose computed tomography (LDCT) for lung cancer screening with coronary artery calcification and stenosis. MATERIALS AND METHODS: The institutional review board-approved, retrospective study included all 106 patients (68 men, 38 women, mean age 64 ± 7 years) who underwent both LDCT for lung cancer screening and had calcium scoring and coronary computed tomography angiography in our institution. We recorded the clinical variables including patients' demographics, smoking history, family history, and lipid profiles. Coronary calcium scores and grading of coronary stenosis were recorded from the radiology information system. We calculated the multiethnic scores for atherosclerosis risk scores to obtain 10-year coronary heart disease (MESA 10-Y CHD) risk of cardiovascular disease for all patients. Deidentified LDCT exams were exported to a Radiomics prototype for automatic heart segmentation, and derivation of radiomics. Data were analyzed using multiple logistic regression and kernel Fisher discriminant analyses. RESULTS: Whole heart radiomics were better than the clinical variables for differentiating subjects with different Agatston scores (≤400 and >400) (area under the curve [AUC] 0.92 vs 0.69). Prediction of coronary stenosis and MESA 10-Y CHD risk was better on whole heart radiomics (AUC:0.86-0.87) than with clinical variables (AUC:0.69-0.79). Addition of clinical variables or visual assessment of coronary calcification from LDCT to whole heart radiomics resulted in a modest change in the AUC. CONCLUSION: Single-click, whole heart radiomics obtained from LDCT for lung cancer screening can differentiate patients with different Agatston and MESA risk scores for cardiovascular diseases.

Decreasing the Surgical Errors by Neurostimulation of Primary Motor Cortex and the Associated Brain Activation via Neuroimaging.

Acquisition of fine motor skills is a time-consuming process as it is based on learning via frequent repetitions. Transcranial electrical stimulation (tES) is a promising means of enhancing simple motor skill development via neuromodulatory mechanisms. Here, we report that non-invasive neurostimulation facilitates the learning of complex fine bimanual motor skills associated with a surgical task. During the training of 12 medical students on the Fundamentals of Laparoscopic Surgery (FLS) pattern cutting task over a period of 12 days, we observed that transcranial direct current stimulation (tDCS) decreased error level and the variability in performance, compared to the Sham group. Furthermore, by concurrently monitoring the cortical activations of the subjects via functional near-infrared spectroscopy (fNIRS), our study showed that the cortical activation patterns were significantly different between the tDCS and Sham group, with the activation of primary motor cortex (M1) and prefrontal cortex (PFC) contralateral to the anodal electrode significantly decreased while supplemental motor area (SMA) increased by tDCS. The lowered performance errors were retained after 1-month post-training. This work supports the use of tDCS to enhance performance accuracy in fine bimanual motor tasks.

Optimized collusion prevention for online exams during social distancing.

Online education is important in the COVID-19 pandemic, but online exam at individual homes invites students to cheat in various ways, especially collusion. While physical proctoring is impossible during social distancing, online proctoring is costly, compromises privacy, and can lead to prevailing collusion. Here we develop an optimization-based anti-collusion approach for distanced online testing (DOT) by minimizing the collusion gain, which can be coupled with other techniques for cheating prevention. With prior knowledge of student competences, our DOT technology optimizes sequences of questions and assigns them to students in synchronized time slots, reducing the collusion gain by 2-3 orders of magnitude relative to the conventional exam in which students receive their common questions simultaneously. Our DOT theory allows control of the collusion gain to a sufficiently low level. Our recent final exam in the DOT format has been successful, as evidenced by statistical tests and a post-exam survey.

Association of AI quantified COVID-19 chest CT and patient outcome.

PURPOSE: Severity scoring is a key step in managing patients with COVID-19 pneumonia. However, manual quantitative analysis by radiologists is a time-consuming task, while qualitative evaluation may be fast but highly subjective. This study aims to develop artificial intelligence (AI)-based methods to quantify disease severity and predict COVID-19 patient outcome. METHODS: We develop an AI-based framework that employs deep neural networks to efficiently segment lung lobes and pulmonary opacities. The volume ratio of pulmonary opacities inside each lung lobe gives the severity scores of the lobes, which are then used to predict ICU admission and mortality with three different machine learning methods. The developed methods were evaluated on datasets from two hospitals (site A: Firoozgar Hospital, Iran, 105 patients; site B: Massachusetts General Hospital, USA, 88 patients). RESULTS: AI-based severity scores are strongly associated with those evaluated by radiologists (Spearman's rank correlation 0.837, [Formula: see text]). Using AI-based scores produced significantly higher ([Formula: see text]) area under the ROC curve (AUC) values. The developed AI method achieved the best performance of AUC = 0.813 (95% CI [0.729, 0.886]) in predicting ICU admission and AUC = 0.741 (95% CI [0.640, 0.837]) in mortality estimation on the two datasets. CONCLUSIONS: Accurate severity scores can be obtained using the developed AI methods over chest CT images. The computed severity scores achieved better performance than radiologists in predicting COVID-19 patient outcome by consistently quantifying image features. Such developed techniques of severity assessment may be extended to other lung diseases beyond the current pandemic.

Raman spectroscopy accurately classifies burn severity in an ex vivo model.

Accurate classification of burn severities is of vital importance for proper burn treatments. A recent article reported that using the combination of Raman spectroscopy and optical coherence tomography (OCT) classifies different degrees of burns with an overall accuracy of 85% [1]. In this study, we demonstrate the feasibility of using Raman spectroscopy alone to classify burn severities on ex vivo porcine skin tissues. To create different levels of burns, four burn conditions were designed: (i) 200°F for 10s, (ii) 200°F for 30s, (iii) 450°F for 10s and (iv) 450°F for 30s. Raman spectra from 500-2000cm-1 were collected from samples of the four burn conditions as well as the unburnt condition. Classifications were performed using kernel support vector machine (KSVM) with features extracted from the spectra by principal component analysis (PCA), and partial least-square (PLS). Both techniques yielded an average accuracy of approximately 92%, which was independently evaluated by leave-one-out cross-validation (LOOCV). By comparison, PCA+KSVM provides higher accuracy in classifying severe burns, while PLS performs better in classifying mild burns. Variable importance in the projection (VIP) scores from the PLS models reveal that proteins and lipids, amide III, and amino acids are important indicators in separating unburnt or mild burns (200°F), while amide I has a more pronounced impact in separating severe burns (450°F).

Functional Brain Imaging Reliably Predicts Bimanual Motor Skill Performance in a Standardized Surgical Task.

Currently, there is a dearth of objective metrics for assessing bi-manual motor skills, which are critical for high-stakes professions such as surgery. Recently, functional near-infrared spectroscopy (fNIRS) has been shown to be effective at classifying motor task types, which can be potentially used for assessing motor performance level. In this work, we use fNIRS data for predicting the performance scores in a standardized bi-manual motor task used in surgical certification and propose a deep-learning framework 'Brain-NET' to extract features from the fNIRS data. Our results demonstrate that the Brain-NET is able to predict bi-manual surgical motor skills based on neuroimaging data accurately ( R2=0.73). Furthermore, the classification ability of the Brain-NET model is demonstrated based on receiver operating characteristic (ROC) curves and area under the curve (AUC) values of 0.91. Hence, these results establish that fNIRS associated with deep learning analysis is a promising method for a bedside, quick and cost-effective assessment of bi-manual skill levels.

Altered metabolism of mothers of young children with Autism Spectrum Disorder: a case control study.

BACKGROUND: Previous research studies have demonstrated abnormalities in the metabolism of mothers of young children with autism. METHODS: Metabolic analysis was performed on blood samples from 30 mothers of young children with Autism Spectrum Disorder (ASD-M) and from 29 mothers of young typically-developing children (TD-M). Targeted metabolic analysis focusing on the folate one-carbon metabolism (FOCM) and the transsulfuration pathway (TS) as well as broad metabolic analysis were performed. Statistical analysis of the data involved both univariate and multivariate statistical methods. RESULTS: Univariate analysis revealed significant differences in 5 metabolites from the folate one-carbon metabolism and the transsulfuration pathway and differences in an additional 48 metabolites identified by broad metabolic analysis, including lower levels of many carnitine-conjugated molecules. Multivariate analysis with leave-one-out cross-validation allowed classification of samples as belonging to one of the two groups of mothers with 93% sensitivity and 97% specificity with five metabolites. Furthermore, each of these five metabolites correlated with 8-15 other metabolites indicating that there are five clusters of correlated metabolites. In fact, all but 5 of the 50 metabolites with the highest area under the receiver operating characteristic curve were associated with the five identified groups. Many of the abnormalities appear linked to low levels of folate, vitamin B12, and carnitine-conjugated molecules. CONCLUSIONS: Mothers of children with ASD have many significantly different metabolite levels compared to mothers of typically developing children at 2-5 years after birth.

Modeling of moral decisions with deep learning.

One example of an artificial intelligence ethical dilemma is the autonomous vehicle situation presented by Massachusetts Institute of Technology researchers in the Moral Machine Experiment. To solve such dilemmas, the MIT researchers used a classic statistical method known as the hierarchical Bayesian (HB) model. This paper builds upon previous work for modeling moral decision making, applies a deep learning method to learn human ethics in this context, and compares it to the HB approach. These methods were tested to predict moral decisions of simulated populations of Moral Machine participants. Overall, test results indicate that deep neural networks can be effective in learning the group morality of a population through observation, and outperform the Bayesian model in the cases of model mismatches.