Innovative AI methods for monitoring front-of-package information: A case study on infant foods

Front-of-package (FOP) is one of the most direct communication channels connecting manufacturers and consumers, as it displays crucial information such as certification, nutrition, and health. Traditional methods for obtaining information from FOPs often involved manual collection and analysis. To overcome these labor-intensive characteristics, new methods using two artificial intelligence (AI) approaches were applied for information monitoring of FOPs. In order to provide practical implementations, a case study was conducted on infant food products. First, FOP images were collected from Amazon.com. Then, from the FOP images, 1) the certification usage status of the infant food group was obtained by recognizing the certification marks using object detection. Moreover, 2) the nutrition and health-related texts written on the images were automatically extracted based on optical character recognition (OCR), and the associations between health-related texts were identified by network analysis. The model attained a 94.9% accuracy in identifying certification marks, unveiling prevalent certifications like Kosher. Frequency and network analysis revealed common nutrients and health associations, providing valuable insights into consumer perception. These methods enable fast and efficient monitoring capabilities, which can significantly benefit various food industries. Moreover, the AI-based approaches used in the study are believed to offer insights for related industries regarding the swift transformations in product information status.

Prediction of treatment response after stereotactic radiosurgery of brain metastasis using deep learning and radiomics on longitudinal MRI data

We developed artificial intelligence models to predict the brain metastasis (BM) treatment response after stereotactic radiosurgery (SRS) using longitudinal magnetic resonance imaging (MRI) data and evaluated prediction accuracy changes according to the number of sequential MRI scans. We included four sequential MRI scans for 194 patients with BM and 369 target lesions for the Developmental dataset. The data were randomly split (8:2 ratio) for training and testing. For external validation, 172 MRI scans from 43 patients with BM and 62 target lesions were additionally enrolled. The maximum axial diameter (Dmax), radiomics, and deep learning (DL) models were generated for comparison. We evaluated the simple convolutional neural network (CNN) model and a gated recurrent unit (Conv-GRU)-based CNN model in the DL arm. The Conv-GRU model performed superior to the simple CNN models. For both datasets, the area under the curve (AUC) was significantly higher for the two-dimensional (2D) Conv-GRU model than for the 3D Conv-GRU, Dmax, and radiomics models. The accuracy of the 2D Conv-GRU model increased with the number of follow-up studies. In conclusion, using longitudinal MRI data, the 2D Conv-GRU model outperformed all other models in predicting the treatment response after SRS of BM.

Apoptosis-modulatory miR-361-3p as a novel treatment target in endocrine-responsive and endocrine-resistant breast cancer

Breast cancer (BC) is the most diagnosed cancer in women worldwide. In estrogen receptor (ER)-positive disease, anti-estrogens and aromatase inhibitors (AI) improve patient survival; however, many patients develop resistance. Dysregulation of apoptosis is a common resistance mechanism; thus, agents that can reinstate the activity of apoptotic pathways represent promising therapeutics for advanced drug-resistant disease. Emerging targets in this scenario include microRNAs (miRs). To identify miRs modulating apoptosis in drug-responsive and -resistant BC, a high-throughput miR inhibitor screen was performed, followed by high-content screening microscopy for apoptotic markers. Validation demonstrated that miR-361-3p inhibitor significantly increases early apoptosis and reduces proliferation of drug-responsive (MCF7), plus AI-/antiestrogen-resistant derivatives (LTED, TamR, FulvR), and ER- cells (MDA-MB-231). Importantly, proliferation-inhibitory effects were observed in vivo in a xenograft model, indicating the potential clinical application of miR-361-3p inhibition. RNA-seq of tumour xenografts identified FANCA as a direct miR-361-3p target, and validation suggested miR-361-3p inhibitor effects might be mediated in part through FANCA modulation. Moreover, miR-361-3p inhibition resulted in p53-mediated G1 cell cycle arrest through activation of p21 and reduced BC invasion. Analysis of publicly available datasets showed miR-361-3p expression is significantly higher in primary breast tumours vspaired normal tissue and is associated with decreased overall survival. In addition, miR-361-3p inhibitor treatment of BC patient explants decreased levels of miR-361-3p and proliferation marker, Ki67. Finally, miR-361-3p inhibitor showed synergistic effects on BC growth when combined with PARP inhibitor, Olaparib. Together, these studies identify miR-361-3p inhibitor as a potential new treatment for drug-responsive and -resistant advanced BC.

A Visual Analytics System for Improving Attention-based Traffic Forecasting Models

With deep learning (DL) outperforming conventional methods for different tasks, much effort has been devoted to utilizing DL in various domains. Researchers and developers in the traffic domain have also designed and improved DL models for forecasting tasks such as estimation of traffic speed and time of arrival. However, there exist many challenges in analyzing DL models due to the black-box property of DL models and complexity of traffic data (i.e., spatio-temporal dependencies). Collaborating with domain experts, we design a visual analytics system, AttnAnalyzer, that enables users to explore how DL models make predictions by allowing effective spatio-temporal dependency analysis. The system incorporates dynamic time warping (DTW) and Granger causality tests for computational spatio-temporal dependency analysis while providing map, table, line chart, and pixel views to assist user to perform dependency and model behavior analysis. For the evaluation, we present three case studies showing how AttnAnalyzer can effectively explore model behaviors and improve model performance in two different road networks. We also provide domain expert feedback.

Intravenous epoprostenol therapy in the treatment of pulmonary arterial hypertension: the Singapore experience

Funding Acknowledgements

Type of funding sources: None.

Background

Pulmonary arterial hypertension (PAH) is a progressive disease with significant morbidity and mortality. While intravenous (IV) Epoprostenol, a prostacyclin analogue, has been shown to improve exercise tolerance, symptoms, hemodynamics and survival, there are challenges with initiation and maintenance of this IV therapy.

Purpose

We aim to describe our local experience of the use of IV Epoprostenol in the treatment of PAH patients in Singapore, highlighting various issues and challenges.

Methods

From 2016, patients at a tertiary cardiac institution diagnosed with Group 1 PAH and remaining in intermediate to high risk class with progressive symptoms (despite being on maximum tolerable doses of PhosphoDiEsterase-5 inhibitors and Endothelin-1 receptor antagonists) were assessed and counselled for initiation of Epoprostenol therapy. With a fixed set of local protocols, comprehensive assessment and support of a multi-disciplinary team including physicians, specialist nurses and pharmacists, suitable patients were started on this treatment.

Results

A total of 12 patients (11 female, mean age 42.8 +/- 11.0 years) were included. The average New York Heart Association class of the patients initiated on Epoprostenol was II-III. The pulmonary artery pressures and pulmonary vascular resistance on right heart catheterization prior to initiation was 52.5 (IQR 47.0-54.0) mmHg and 12.6 (IQR 10.0-14.2) Woods respectively. The duration from diagnosis to time of initiating Epoprostenol was 89 (IQR 62-140) months. Epoprostenol was generally well tolerated. The most common side effect experienced was diarrhea (5/12 patients) followed by headache and musculoskeletal complains (3/12 patients each). Of the 12 patients, 6 passed away after 12 (IQR 10-16) months of Epoprostenol therapy. Of the remaining 6, PAH was diagnosed 110 (IQR 104-136) months ago and Epoprostenol therapy has been continued for 17 (IQR 14-27) months. Of those who survived, right ventricle size and PA pressures on echocardiography remained relatively stable as compared to those who passed on. 2 patients had line related infections requiring a line change 1 and 2 times respectively.

Conclusion

While not without its challenges, the establishment of concrete protocols with the support of a multidisciplinary team allows for the introduction of IV Epoprostenol as an additional potential line of effective therapy for PAH patients in Singapore.

Missing Value Imputation of Time-Series Air-Quality Data via Deep Neural Networks

To prevent severe air pollution, it is important to analyze time-series air quality data, but this is often challenging as the time-series data is usually partially missing, especially when it is collected from multiple locations simultaneously. To solve this problem, various deep-learning-based missing value imputation models have been proposed. However, often they are barely interpretable, which makes it difficult to analyze the imputed data. Thus, we propose a novel deep learning-based imputation model that achieves high interpretability as well as shows great performance in missing value imputation for spatio-temporal data. We verify the effectiveness of our method through quantitative and qualitative results on a publicly available air-quality dataset.

Prediction of hand-wrist maturation stages based on cervical vertebrae images using artificial intelligence

OBJECTIVE

To predict the hand-wrist maturation stages based on the cervical vertebrae (CV) images, and to analyse the accuracy of the proposed algorithms.

SETTINGS AND POPULATION

A total of 499 pairs of hand-wrist radiographs and lateral cephalograms of 455 orthodontic patients aged 6-18 years were used for developing the prediction model for hand-wrist skeletal maturation stages.

MATERIALS AND METHODS

The hand-wrist radiographs and the lateral cephalograms were collected from two university hospitals and a paediatric dental clinic. After identifying the 13 anatomic landmarks of the CV, the width-height ratio, width-perpendicular height ratio and concavity ratio of the CV were used as the morphometric features of the CV. Patients' chronological age and sex were also included as input data. The ground truth data were the Fishman SMI based on the hand-wrist radiographs. Three specialists determined the ground truth SMI. An ensemble machine learning methods were used to predict the Fishman SMI. Five-fold cross-validation was performed. The mean absolute error (MAE), round MAE and root mean square error (RMSE) values were used to assess the performance of the final ensemble model.

RESULTS

The final ensemble model consisted of eight machine learning models. The MAE, round MAE and RMSE were 0.90, 0.87 and 1.20, respectively.

CONCLUSION

Prediction of hand-wrist SMI based on CV images is possible using machine learning methods. Chronological age and sex increased the prediction accuracy. An automated diagnosis of the skeletal maturation may aid as a decision-supporting tool for evaluating the optimal treatment timing for growing patients.

Development of Deep Learning-Based Automatic Detection Algorithm for Adrenal Nodules on Contrast-Enhanced Abdominal CT Scans

Objective: Adrenal nodules are often incidentally detected on abdominal computed tomography (CT) scans due to their asymptomatic nature. We aimed to develop an automatic detection program for adrenal nodules on abdominal CT scans using deep learning algorithms. Methods: We retrospectively analyzed abdominal CT scans performed at two university-affiliated hospitals (n = 483 and n = 514, respectively) from 2006 to 2019. This dataset was randomly divided into training set (181 CTs without adrenal nodule and 362 CTs with adrenal nodule) and test set (291 CTs without adrenal nodule and 163 CTs with adrenal nodule). All CT scans were contrast-enhanced and the phase with the highest contrast between adrenal gland and adjacent normal tissues was selected for multi-phase CT. The core algorithm of our deep learning algorithm for adrenal nodule (DLAAN) was MULAN (Multitask Universal Lesion Analysis Network) algorithm whose backbone was a convolutional neural network. DLAAN was composed of two stages. The first stage was to detect the CT slice where normal adrenal gland or adrenal nodule were located. The second stage was for fine localization of adrenal nodule on the corresponding CT slice. The performance of DLAAN was evaluated using the area under the receiver operating characteristic curve (AUROC) for patient-level classification and free-response ROC for nodule-level localization. The figure of merit for free-response ROC was calculated as an average sensitivity when 0.5, 1, 2, and 4 false positives per slice were allowed. Results: The AUROC of DLAAN was 0.927 (95% confidence interval: 0.900–0.955). With a threshold probability of 0.9, the sensitivity and specificity were 86.5% and 89.0%, respectively. When left and right adrenal nodules were analyzed separately, the AUROC was 0.910 for left adrenal nodule and 0.957 for right adrenal nodule, respectively. The accuracy of DLAAN according to the size of adrenal nodule was 0.890, 0.734, 0.981, 1.00 and 1.00 for no adrenal nodule, adrenal nodule sized 1–2 cm, 2–3 cm, 3–4 cm and > 4 cm, respectively. The performance of DLAAN for the localization of adrenal nodule which was estimated by average sensitivity was 0.812. The number of CTs with at least one false positive nodule was 93/454 (20.5%). Conclusion: Our proof of concept study of deep learning-based automatic detection of adrenal nodule on contrast-enhanced abdominal CT scans showed high accuracy for both the classification of patients with or without adrenal nodule and the localization of adrenal nodule, although the performance of the algorithm decreased for small sized adrenal nodules. External validation with different CT settings and patient population is needed to assess the generalizability of our algorithm.

Artificial intelligence-assisted analysis of endoscopic retrograde cholangiopancreatography image for identifying ampulla and difficulty of selective cannulation

The advancement of artificial intelligence (AI) has facilitated its application in medical fields. However, there has been little research for AI-assisted endoscopy, despite the clinical significance of the efficiency and safety of cannulation in the endoscopic retrograde cholangiopancreatography (ERCP). In this study, we aim to assist endoscopists performing ERCP through automatic detection of the ampulla and the identification of cannulation difficulty. We developed a novel AI-assisted system based on convolutional neural networks that predict the location of the ampulla and the difficulty of cannulation to the ampulla. ERCP data of 531 and 451 patients were utilized in the evaluation of our model for each task. Our model detected the ampulla with mean intersection-over-union 64.1%, precision 76.2%, recall 78.4%, and centroid distance 0.021. In classifying the cannulation difficulty, it achieved the recall of 71.9% for the class of easy cases and that of 61.1% for that of difficult cases. Remarkably, our model accurately detected AOV with varying morphological shape, size, and texture on par with the level of a human expert and showed promising results for recognizing cannulation difficulty. It demonstrated its potential to improve the quality of ERCP by assisting endoscopists.

HyperTendril: Visual Analytics for User-Driven Hyperparameter Optimization of Deep Neural Networks

To mitigate the pain of manually tuning hyperparameters of deep neural networks, automated machine learning (AutoML) methods have been developed to search for an optimal set of hyperparameters in large combinatorial search spaces. However, the search results of AutoML methods significantly depend on initial configurations, making it a non-trivial task to find a proper configuration. Therefore, human intervention via a visual analytic approach bears huge potential in this task. In response, we propose HyperTendril, a web-based visual analytics system that supports user-driven hyperparameter tuning processes in a model-agnostic environment. HyperTendril takes a novel approach to effectively steering hyperparameter optimization through an iterative, interactive tuning procedure that allows users to refine the search spaces and the configuration of the AutoML method based on their own insights from given results. Using HyperTendril, users can obtain insights into the complex behaviors of various hyperparameter search algorithms and diagnose their configurations. In addition, HyperTendril supports variable importance analysis to help the users refine their search spaces based on the analysis of relative importance of different hyperparameters and their interaction effects. We present the evaluation demonstrating how HyperTendril helps users steer their tuning processes via a longitudinal user study based on the analysis of interaction logs and in-depth interviews while we deploy our system in a professional industrial environment.

Development of artificial intelligence system for quality control of photo documentation in esophagogastroduodenoscopy

BACKGROUND

Esophagogastroduodenoscopy (EGD) is generally a safe procedure, but adverse events often occur. This highlights the necessity of the quality control of EGD. Complete visualization and photo documentation of upper gastrointestinal (UGI) tracts are important measures in quality control of EGD. To evaluate these measures in large scale, we developed an AI-driven quality control system for EGD through convolutional neural networks (CNNs) using archived endoscopic images.

METHODS

We retrospectively collected and labeled images from 250 EGD procedures, a total of 2599 images from eight locations of the UGI tract, using the European Society of Gastrointestinal Endoscopy (ESGE) photo documentation methods. The label confirmed by five experts was considered the gold standard. We developed a CNN model for multi-class classification of EGD images to one of the eight locations and binary classification of each EGD procedure based on its completeness.

RESULTS

Our CNN model successfully classified the EGD images into one of the eight regions of UGI tracts with 97.58% accuracy, 97.42% sensitivity, 99.66% specificity, 97.50% positive predictive value (PPV), and 99.66% negative predictive value (NPV). Our model classified the completeness of EGD with 89.20% accuracy, 89.20% sensitivity, 100.00% specificity, 100.00% PPV, and 64.94% NPV. We analyzed the credibility of our model using a probability heatmap.

CONCLUSIONS

We constructed a CNN model that could be used in the quality control of photo documentation in EGD. Our model needs further validation with a large dataset, and we expect our model to help both endoscopists and patients by improving the quality of EGD procedures.

A Multi-Organ Nucleus Segmentation Challenge

Generalized nucleus segmentation techniques can contribute greatly to reducing the time to develop and validate visual biomarkers for new digital pathology datasets. We summarize the results of MoNuSeg 2018 Challenge whose objective was to develop generalizable nuclei segmentation techniques in digital pathology. The challenge was an official satellite event of the MICCAI 2018 conference in which 32 teams with more than 80 participants from geographically diverse institutes participated. Contestants were given a training set with 30 images from seven organs with annotations of 21,623 individual nuclei. A test dataset with 14 images taken from seven organs, including two organs that did not appear in the training set was released without annotations. Entries were evaluated based on average aggregated Jaccard index (AJI) on the test set to prioritize accurate instance segmentation as opposed to mere semantic segmentation. More than half the teams that completed the challenge outperformed a previous baseline. Among the trends observed that contributed to increased accuracy were the use of color normalization as well as heavy data augmentation. Additionally, fully convolutional networks inspired by variants of U-Net, FCN, and Mask-RCNN were popularly used, typically based on ResNet or VGG base architectures. Watershed segmentation on predicted semantic segmentation maps was a popular post-processing strategy. Several of the top techniques compared favorably to an individual human annotator and can be used with confidence for nuclear morphometrics.

Automatic detection of tympanic membrane and middle ear infection from oto-endoscopic images via convolutional neural networks

Convolutional neural networks (CNNs), a popular type of deep neural network, have been actively applied to image recognition, object detection, object localization, semantic segmentation, and object instance segmentation. Accordingly, the applicability of deep learning to the analysis of medical images has increased. This paper presents a novel application of state-of-the-art CNN models, such as DenseNet, to the automatic detection of the tympanic membrane (TM) and middle ear (ME) infection. We collected 2,484 oto-endoscopic images (OEIs) and classified them into one of three categories: normal, chronic otitis media (COM) with TM perforation, and otitis media with effusion (OME). Our results indicate that CNN models have significant potential for the automatic recognition of TM and ME infections, demonstrating a competitive accuracy of 95% in classifying TM and middle ear effusion (MEE) from OEIs. In addition to accuracy measurement, our approach achieves nearly perfect measures of 0.99 in terms of the average area under the receiver operating characteristics curve (AUROC). All these results indicate robust performance when recognizing TM and ME effusions in OEIs. Visualization through a class activation mapping (CAM) heatmap demonstrates that our proposed model performs prediction based on the correct region of OEIs. All these outcomes ensure the reliability of our method; hence, the study can aid otolaryngologists and primary care physicians in real-world scenarios.

6074Cardiorespiratory fitness, socioeconomic status and mortality in middle-aged men: a population-based prospective cohort study

Background

Although both low socioeconomic status (SES) and poor cardiorespiratory fitness (CRF) are associated with increased chronic disease and a heightened risk of death, it remains unclear whether moderate-to-high levels of CRF confer survival benefits in low SES populations.

Purpose

The present study evaluated the hypothesis that SES and CRF predict all-cause mortality (ACM), cardiovascular disease (CVD) mortality and sudden cardiac death (SCD), and that moderate-to-high levels of CRF may attenuate the associations between low SES and adverse cardiovascular outcomes.

Methods

This prospective study was based on a population-based sample of 2,368 men aged 42 to 61 years, who were followed in the Kuopio Ischemic Heart Disease cohort. CRF was directly measured by peak oxygen uptake (VO2peak) during progressive exercise testing to volitional fatigue. SES was characterized using self-reported questionnaires via combined measures of income, education, occupation, occupational prestige, material standard of living, and housing conditions. CRF and SES were divided into tertiles, and 4 combined groups (Fit-high SES, Fit-low SES, Unfit-high SES, and Unfit-low SES) based on the median values of CRF and SES.

Results

During a 25 year median follow-up (interquartile ranges: 18–27 years), 1116 ACM, 512 CVD mortality and 221 SCD events occurred. After adjusting for potential confounders (age, smoking, alcohol, body mass index, systolic blood pressure, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, glucose, diabetes, hypertensive medication, family history of coronary heart disease, and physical activity), the lowest levels of SES were at significantly increased risk for ACM (hazard ratio (HR) 1.49, 95% Confidence Interval (CI): 1.30–1.71), CVD mortality (HR 1.38, 1.13–1.69) and SCD (HR 1.34, 0.97–1.84). In contrast, higher levels of CRF were associated with lower risks of ACM (HR 0.56, 0.46–0.67), CVD mortality (HR 0.53, 0.40–0.71) and SCD (HR 0.53, 0.34–0.83). In combined associations of SES and CRF with mortality, unfit-low SES had significantly higher risks of ACM (HR 2.12, 1.75–2.57), CVD mortality (HR 2.20, 1.64–2.94) and SCD (HR 2.95, 1.79–4.86), but fit-low SES was not associated with a heightened risk of cardiovascular mortality or SCD (CVD mortality, 1.03, 0.73–1.46; SCD, 1.54, 0.87–2.72) as compared with their fit-high SES counterparts (reference).

Conclusion

Our findings indicate that both SES and CRF are independently associated with the risk of death; however, moderate-to-high levels of CRF appear to attenuate the risk of CVD mortality and SCD in low SES men. These unique data have important implications for public health interventions designed to enhance survival in underserved population cohorts.

RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records

We have recently seen many successful applications of recurrent neural networks (RNNs) on electronic medical records (EMRs), which contain histories of patients' diagnoses, medications, and other various events, in order to predict the current and future states of patients. Despite the strong performance of RNNs, it is often challenging for users to understand why the model makes a particular prediction. Such black-box nature of RNNs can impede its wide adoption in clinical practice. Furthermore, we have no established methods to interactively leverage users' domain expertise and prior knowledge as inputs for steering the model. Therefore, our design study aims to provide a visual analytics solution to increase interpretability and interactivity of RNNs via a joint effort of medical experts, artificial intelligence scientists, and visual analytics researchers. Following the iterative design process between the experts, we design, implement, and evaluate a visual analytics tool called RetainVis, which couples a newly improved, interpretable, and interactive RNN-based model called RetainEX and visualizations for users' exploration of EMR data in the context of prediction tasks. Our study shows the effective use of RetainVis for gaining insights into how individual medical codes contribute to making risk predictions, using EMRs of patients with heart failure and cataract symptoms. Our study also demonstrates how we made substantial changes to the state-of-the-art RNN model called RETAIN in order to make use of temporal information and increase interactivity. This study will provide a useful guideline for researchers that aim to design an interpretable and interactive visual analytics tool for RNNs.

ConceptVector: Text Visual Analytics via Interactive Lexicon Building Using Word Embedding

Central to many text analysis methods is the notion of a concept: a set of semantically related keywords characterizing a specific object, phenomenon, or theme. Advances in word embedding allow building a concept from a small set of seed terms. However, naive application of such techniques may result in false positive errors because of the polysemy of natural language. To mitigate this problem, we present a visual analytics system called ConceptVector that guides a user in building such concepts and then using them to analyze documents. Document-analysis case studies with real-world datasets demonstrate the fine-grained analysis provided by ConceptVector. To support the elaborate modeling of concepts, we introduce a bipolar concept model and support for specifying irrelevant words. We validate the interactive lexicon building interface by a user study and expert reviews. Quantitative evaluation shows that the bipolar lexicon generated with our methods is comparable to human-generated ones.

Visual Analytics for Explainable Deep Learning

Recently, deep learning has been advancing the state of the art in artificial intelligence to a new level, and humans rely on artificial intelligence techniques more than ever. However, even with such unprecedented advancements, the lack of explanation regarding the decisions made by deep learning models and absence of control over their internal processes act as major drawbacks in critical decision-making processes, such as precision medicine and law enforcement. In response, efforts are being made to make deep learning interpretable and controllable by humans. This article reviews visual analytics, information visualization, and machine learning perspectives relevant to this aim, and discusses potential challenges and future research directions.

Toward Predicting Social Support Needs in Online Health Social Networks

Background

While online health social networks (OHSNs) serve as an effective platform for patients to fulfill their various social support needs, predicting the needs of users and providing tailored information remains a challenge.

Objective

The objective of this study was to discriminate important features for identifying users’ social support needs based on knowledge gathered from survey data. This study also provides guidelines for a technical framework, which can be used to predict users’ social support needs based on raw data collected from OHSNs.

Methods

We initially conducted a Web-based survey with 184 OHSN users. From this survey data, we extracted 34 features based on 5 categories: (1) demographics, (2) reading behavior, (3) posting behavior, (4) perceived roles in OHSNs, and (5) values sought in OHSNs. Features from the first 4 categories were used as variables for binary classification. For the prediction outcomes, we used features from the last category: the needs for emotional support, experience-based information, unconventional information, and medical facts. We compared 5 binary classifier algorithms: gradient boosting tree, random forest, decision tree, support vector machines, and logistic regression. We then calculated the scores of the area under the receiver operating characteristic (ROC) curve (AUC) to understand the comparative effectiveness of the used features.

Results

The best performance was AUC scores of 0.89 for predicting users seeking emotional support, 0.86 for experience-based information, 0.80 for unconventional information, and 0.83 for medical facts. With the gradient boosting tree as our best performing model, we analyzed the strength of individual features in predicting one’s social support need. Among other discoveries, we found that users seeking emotional support tend to post more in OHSNs compared with others.

Conclusions

We developed an initial framework for automatically predicting social support needs in OHSNs using survey data. Future work should involve nonsurvey data to evaluate the feasibility of the framework. Our study contributes to providing personalized social support in OHSNs.

Cryoneurolysis to treat the pain and symptoms of knee osteoarthritis: a multicenter, randomized, double-blind, sham-controlled trial

OBJECTIVE

Evaluate the efficacy and safety/tolerability of cryoneurolysis for reduction of pain and symptoms associated with knee osteoarthritis (OA).

DESIGN

Randomized, double-blind, sham-controlled, multicenter trial with a 6-month follow-up in patients with mild-to-moderate knee OA. Patients were randomized 2:1 to cryoneurolysis targeting the infrapatellar branch of the saphenous nerve (IPBSN) or sham treatment. The primary endpoint was the change from baseline to Day 30 in the Western Ontario and McMaster Osteoarthritis Index (WOMAC) pain score adjusted by the baseline score and site. Secondary endpoints, including visual analogue scale (VAS) pain score and total WOMAC score, were tested in a pre-defined order.

RESULTS

The intent-to-treat (ITT) population consisted of 180 patients (n = 121 active treatment, n = 59 sham treatment). Compared to the sham group, patients who received active treatment had a statistically significant greater change from baseline in the WOMAC pain subscale score at Day 30 (P = 0.0004), Day 60 (P = 0.0176), and Day 90 (P = 0.0061). Patients deemed WOMAC pain responders at Day 120 continued to experience a statistically significant treatment effect at Day 150. Most expected side effects were mild in severity and resolved within 30 days. The incidence of device- or procedure-related adverse events was similar in the two treatment groups with no occurrence of serious or unanticipated adverse device effects (ADE).

CONCLUSIONS

Cryoneurolysis of the IPBSN resulted in statistically significant decreased knee pain and improved symptoms compared to sham treatment for up to 150 days, and appeared safe and well tolerated.

AxiSketcher: Interactive Nonlinear Axis Mapping of Visualizations through User Drawings

Visual analytics techniques help users explore high-dimensional data. However, it is often challenging for users to express their domain knowledge in order to steer the underlying data model, especially when they have little attribute-level knowledge. Furthermore, users' complex, high-level domain knowledge, compared to low-level attributes, posits even greater challenges. To overcome these challenges, we introduce a technique to interpret a user's drawings with an interactive, nonlinear axis mapping approach called AxiSketcher. This technique enables users to impose their domain knowledge on a visualization by allowing interaction with data entries rather than with data attributes. The proposed interaction is performed through directly sketching lines over the visualization. Using this technique, users can draw lines over selected data points, and the system forms the axes that represent a nonlinear, weighted combination of multidimensional attributes. In this paper, we describe our techniques in three areas: 1) the design space of sketching methods for eliciting users' nonlinear domain knowledge; 2) the underlying model that translates users' input, extracts patterns behind the selected data points, and results in nonlinear axes reflecting users' complex intent; and 3) the interactive visualization for viewing, assessing, and reconstructing the newly formed, nonlinear axes.

TopicLens: Efficient Multi-Level Visual Topic Exploration of Large-Scale Document Collections

Topic modeling, which reveals underlying topics of a document corpus, has been actively adopted in visual analytics for large-scale document collections. However, due to its significant processing time and non-interactive nature, topic modeling has so far not been tightly integrated into a visual analytics workflow. Instead, most such systems are limited to utilizing a fixed, initial set of topics. Motivated by this gap in the literature, we propose a novel interaction technique called TopicLens that allows a user to dynamically explore data through a lens interface where topic modeling and the corresponding 2D embedding are efficiently computed on the fly. To support this interaction in real time while maintaining view consistency, we propose a novel efficient topic modeling method and a semi-supervised 2D embedding algorithm. Our work is based on improving state-of-the-art methods such as nonnegative matrix factorization and t-distributed stochastic neighbor embedding. Furthermore, we have built a web-based visual analytics system integrated with TopicLens. We use this system to measure the performance and the visualization quality of our proposed methods. We provide several scenarios showcasing the capability of TopicLens using real-world datasets.

Personas in online health communities

Many researchers and practitioners use online health communities (OHCs) to influence health behavior and provide patients with social support. One of the biggest challenges in this approach, however, is the rate of attrition. OHCs face similar problems as other social media platforms where user migration happens unless tailored content and appropriate socialization is supported. To provide tailored support for each OHC user, we developed personas in OHCs illustrating users' needs and requirements in OHC use. To develop OHC personas, we first interviewed 16 OHC users and administrators to qualitatively understand varying user needs in OHC. Based on their responses, we developed an online survey to systematically investigate OHC personas. We received 184 survey responses from OHC users, which informed their values and their OHC use patterns. We performed open coding analysis with the interview data and cluster analysis with the survey data and consolidated the analyses of the two datasets. Four personas emerged-Caretakers, Opportunists, Scientists, and Adventurers. The results inform users' interaction behavior and attitude patterns with OHCs. We discuss implications for how these personas inform OHCs in delivering personalized informational and emotional support.

Inflammasome signaling affects anxiety- and depressive-like behavior and gut microbiome composition

The inflammasome is hypothesized to be a key mediator of the response to physiological and psychological stressors, and its dysregulation may be implicated in major depressive disorder. Inflammasome activation causes the maturation of caspase-1 and activation of interleukin (IL)-1β and IL-18, two proinflammatory cytokines involved in neuroimmunomodulation, neuroinflammation and neurodegeneration. In this study, C57BL/6 mice with genetic deficiency or pharmacological inhibition of caspase-1 were screened for anxiety- and depressive-like behaviors, and locomotion at baseline and after chronic stress. We found that genetic deficiency of caspase-1 decreased depressive- and anxiety-like behaviors, and conversely increased locomotor activity and skills. Caspase-1 deficiency also prevented the exacerbation of depressive-like behaviors following chronic stress. Furthermore, pharmacological caspase-1 antagonism with minocycline ameliorated stress-induced depressive-like behavior in wild-type mice. Interestingly, chronic stress or pharmacological inhibition of caspase-1 per se altered the fecal microbiome in a very similar manner. When stressed mice were treated with minocycline, the observed gut microbiota changes included increase in relative abundance of Akkermansia spp. and Blautia spp., which are compatible with beneficial effects of attenuated inflammation and rebalance of gut microbiota, respectively, and the increment in Lachnospiracea abundance was consistent with microbiota changes of caspase-1 deficiency. Our results suggest that the protective effect of caspase-1 inhibition involves the modulation of the relationship between stress and gut microbiota composition, and establishes the basis for a gut microbiota-inflammasome-brain axis, whereby the gut microbiota via inflammasome signaling modulate pathways that will alter brain function, and affect depressive- and anxiety-like behaviors. Our data also suggest that further elucidation of the gut microbiota-inflammasome-brain axis may offer novel therapeutic targets for psychiatric disorders.

VisOHC: Designing Visual Analytics for Online Health Communities

Through online health communities (OHCs), patients and caregivers exchange their illness experiences and strategies for overcoming the illness, and provide emotional support. To facilitate healthy and lively conversations in these communities, their members should be continuously monitored and nurtured by OHC administrators. The main challenge of OHC administrators' tasks lies in understanding the diverse dimensions of conversation threads that lead to productive discussions in their communities. In this paper, we present a design study in which three domain expert groups participated, an OHC researcher and two OHC administrators of online health communities, which was conducted to find with a visual analytic solution. Through our design study, we characterized the domain goals of OHC administrators and derived tasks to achieve these goals. As a result of this study, we propose a system called VisOHC, which visualizes individual OHC conversation threads as collapsed boxes-a visual metaphor of conversation threads. In addition, we augmented the posters' reply authorship network with marks and/or beams to show conversation dynamics within threads. We also developed unique measures tailored to the characteristics of OHCs, which can be encoded for thread visualizations at the users' requests. Our observation of the two administrators while using VisOHC showed that it supports their tasks and reveals interesting insights into online health communities. Finally, we share our methodological lessons on probing visual designs together with domain experts by allowing them to freely encode measurements into visual variables.

The Associations of C-Reactive Protein with Serum Levels of Polyunsaturated Fatty Acids and Trans Fatty Acids Among Middle-Aged Men from Three Populations

BACKGROUND

C-reactive protein (CRP) and many fatty acids (FAs) have been linked to cardiovascular disease. Associations of serum CRP with FAs in different populations have not been established.

METHODS

Participants were 926 men aged 40-49 (2002-2006) from a population-based sample; 310 Whites from Pennsylvania, U.S., 313 Japanese from Shiga, Japan, and 303 Japanese Americans from Hawaii, U.S. Serum CRP (mg/L) was measured using immunosorbent assay while serum FAs (%) were measured using capillary-gas-liquid chromatography.

RESULTS

Whites had CRP (mg/L) levels higher than Japanese with Japanese Americans in-between (age-adjusted geometric mean "GM" 0.96, 0.38, 0.66, respectively). Whites had also higher levels of total n-6 FAs (%) and trans fatty acids (TFAs) but lower levels of marine-derived n-3 FAs compared to Japanese (41.78 vs. 35.05, 1.04 vs. 0.58, and 3.85 vs. 9.29, respectively). Japanese Americans had FAs levels in-between the other two populations. Whites had significant inverse trends between CRP and tertiles of total n-6 FAs (GM 1.20, 0.91 and 0.80; p=0.002) and marine-derived n-3 FAs (GM 1.22, 1.00 and 0.72; p<0.001) but a significant positive trend with TFAs (GM 0.80, 0.95 and 1.15; p=0.007). Japanese had a significant inverse trend between CRP and only total n-6 FAs (GM 0.50, 0.35 and 0.31; p<0.001). Japanese Americans had CRP associations with n-3 FAs, n-6 FAs, and TFAs similar to but weaker than Whites.

CONCLUSIONS

With the exception of consistent inverse association of CRP with total n-6 FAs, there are considerable variations across the three populations in the associations of CRP with different FAs.

InterAxis: Steering Scatterplot Axes via Observation-Level Interaction

Scatterplots are effective visualization techniques for multidimensional data that use two (or three) axes to visualize data items as a point at its corresponding x and y Cartesian coordinates. Typically, each axis is bound to a single data attribute. Interactive exploration occurs by changing the data attributes bound to each of these axes. In the case of using scatterplots to visualize the outputs of dimension reduction techniques, the x and y axes are combinations of the true, high-dimensional data. For these spatializations, the axes present usability challenges in terms of interpretability and interactivity. That is, understanding the axes and interacting with them to make adjustments can be challenging. In this paper, we present InterAxis, a visual analytics technique to properly interpret, define, and change an axis in a user-driven manner. Users are given the ability to define and modify axes by dragging data items to either side of the x or y axes. from which the system computes a linear combination of data attributes and binds it to the axis. Further, users can directly tune the positive and negative contribution to these complex axes by using the visualization of data attributes that correspond to each axis. We describe the details of our technique and demonstrate the intended usage through two scenarios.

Anatomic Landmarks of the Distal Radioulnar Joint

HYPOTHESIS

Using Lister's tubercle and the ulnar styloid as landmarks, accurate localization of the distal radioulnar joint can be achieved without the need for an image-guided approach.

METHODS

Cadaveric dissection of 16 upper extremities was performed to measure the relationships between the ulnar styloid, Lister's tubercle, and the distal radioulnar joint. In each specimen, the location of the distal radioulnar joint (point A) in relation to Lister's tubercle and the ulnar styloid was determined as follows: (1) the perpendicular distance between the distal radioulnar joint and ulnar styloid-Lister's tubercle was measured; (2) with A' marking the intersection of this distance and the ulnar styloid-Lister's tubercle line, the location of the distal radioulnar joint along the ulnar styloid-Lister's tubercle axis was determined by comparing ulnar styloid-A' and A'-Lister's tubercle with ulnar styloid-Lister's tubercle.

RESULTS

The mean distance between ulnar styloid-Lister's tubercle was 4.3 ± 0.4 cm. The mean perpendicular distance between the distal radioulnar joint and the ulnar styloid-Lister's tubercle line was 0.2 ± 0.1 cm proximal to the ulnar styloid-Lister's tubercle line. The ratio of ulnar styloid-A' and A'-Lister's tubercle to ulnar styloid-Lister's tubercle was 0.5 ± 0.03 and 0.5 ± 0.03, respectively.

CONCLUSIONS

Simple relationships between the ulnar styloid and Lister's tubercle serve as reliable landmarks for locating the distal radioulnar joint. The distal radioulnar joint is centered about the midpoint of the ulnar styloid-Lister's tubercle axis and slightly proximal to it. This may improve the accuracy and efficacy of corticosteroid injections in the treatment of distal radioulnar joint arthritis without the need for image guidance.

Safe Tummy Tuck: Anatomy and Strategy to Avoid Injury to the Lateral Femoral Cutaneous Nerve During Abdominoplasty

BACKGROUND

Abdominoplasty is one of the most common aesthetic procedures performed in the United States. While poor contour and unsatisfactory cosmetic result have been recognized, neuropathic pain from lateral femoral cutaneous nerve injury has been poorly described. We aim to improve outcomes by using an anatomical study to develop a strategy to avoid injury to the lateral femoral cutaneous nerve in abdominoplasty.

METHODS

Twenty-three fresh cadaver abdomens were dissected to evaluate the course of the lateral femoral cutaneous nerve, using 2.5× loupe magnification. Measurements were taken from the nerve to the anterior superior iliac spine and from the pubic symphysis to the lateral femoral cutaneous nerve. Recordings of the relationship of the nerve to the inguinal ligament and depth at scarpa's fascia were also made. Statistical analysis was performed to find average distances with a standard deviation.

RESULTS

On average, the distance from the lateral femoral cutaneous nerve to the anterior superior iliac spine was 3.62 (SD = 1.32) cm and 13.58 (SD = 2.41) cm from the pubic symphysis in line with the inguinal ligament. The lateral femoral cutaneous nerve was found at the inguinal ligament 80% of the time and 20% of the time superior to the ligament and always deep to scarpa's fascia.

CONCLUSION

Abdominoplasty carries a high patient and surgeon satisfaction rate. The plastic surgeon is continuously challenged to identify ways to improve outcomes, efficiency, and morbidity. Minimal and careful dissection in the area around 4 cm of the anterior superior iliac spine in addition to preserving scarpa's fascia near the inguinal ligament may serve as key strategies to avoiding lateral femoral cutaneous nerve injury.

Composite grafting of a distal thumb amputation: a case report and review of literature

OBJECTIVE

We report a case in which an avulsion-amputation of the thumb proximal to the lunula was repaired by reattaching the amputated segment as a composite graft. The graft demonstrated complete survival with only a minimal sacrifice in length.

METHODS

A 23-year-old man presented 4 hours after an avulsion injury of the thumb with associated distal and proximal phalanx fractures. The amputated segment included the sterile and germinal matrix. He underwent defatting and composite grafting of the amputated segment followed by K-wire fixation of his proximal phalanx fracture.

RESULTS

In his 1-week follow-up, the patient's composite graft-including his nail bed-demonstrated complete survival. At one month, the composite graft maintained stable soft tissue coverage and showed signs of nail plate regrowth. Four months after repair, he was able to return to light duty and was advanced to full duty within 5 months. He continued to report gradually improving hypersensitivity at the margins of the graft and stiffness of the interphalangeal joint. At five months he regained full mobility of his carpometacarpal joint. The range of motion of his interphalangeal and metacarpophalangeal joint were 0 to 10 degrees and 0 to 25 degrees, respectively. He was able to oppose his thumb to all 4 digits. Six months after repair, he demonstrated protective sensation of the tip of the thumb.

CONCLUSION

Composite grafting of the thumb, even in less than ideal cases, can still provide useful length for function as a opposable post and can be considered in reconstruction of thumb amputations at or proximal to the lunula.

Continuous and low error-rate passive synchronization of pre-formed droplets

A microfluidic droplet-handling architecture for the synchronization of asynchronous, mis-matched, pre-formed droplet streams is demonstrated.

UTOPIAN: user-driven topic modeling based on interactive nonnegative matrix factorization

Topic modeling has been widely used for analyzing text document collections. Recently, there have been significant advancements in various topic modeling techniques, particularly in the form of probabilistic graphical modeling. State-of-the-art techniques such as Latent Dirichlet Allocation (LDA) have been successfully applied in visual text analytics. However, most of the widely-used methods based on probabilistic modeling have drawbacks in terms of consistency from multiple runs and empirical convergence. Furthermore, due to the complicatedness in the formulation and the algorithm, LDA cannot easily incorporate various types of user feedback. To tackle this problem, we propose a reliable and flexible visual analytics system for topic modeling called UTOPIAN (User-driven Topic modeling based on Interactive Nonnegative Matrix Factorization). Centered around its semi-supervised formulation, UTOPIAN enables users to interact with the topic modeling method and steer the result in a user-driven manner. We demonstrate the capability of UTOPIAN via several usage scenarios with real-world document corpuses such as InfoVis/VAST paper data set and product review data sets.

Combining computational analyses and interactive visualization for document exploration and sensemaking in jigsaw

Investigators across many disciplines and organizations must sift through large collections of text documents to understand and piece together information. Whether they are fighting crime, curing diseases, deciding what car to buy, or researching a new field, inevitably investigators will encounter text documents. Taking a visual analytics approach, we integrate multiple text analysis algorithms with a suite of interactive visualizations to provide a flexible and powerful environment that allows analysts to explore collections of documents while sensemaking. Our particular focus is on the process of integrating automated analyses with interactive visualizations in a smooth and fluid manner. We illustrate this integration through two example scenarios: an academic researcher examining InfoVis and VAST conference papers and a consumer exploring car reviews while pondering a purchase decision. Finally, we provide lessons learned toward the design and implementation of visual analytics systems for document exploration and understanding.

Customizing computational methods for visual analytics with big data

The volume of available data has been growing exponentially, increasing data problem's complexity and obscurity. In response, visual analytics (VA) has gained attention, yet its solutions haven't scaled well for big data. Computational methods can improve VA's scalability by giving users compact, meaningful information about the input data. However, the significant computation time these methods require hinders real-time interactive visualization of big data. By addressing crucial discrepancies between these methods and VA regarding precision and convergence, researchers have proposed ways to customize them for VA. These approaches, which include low-precision computation and iteration-level interactive visualization, ensure real-time interactive VA for big data.

Myocardial stunning in hyperthyroidism

The cases of two patients with hyperthyroidism and acute left ventricular (LV) dysfunction with segmental wall motion abnormalities resulting in heart failure are reported. Both had electrocardiographic changes mimicking ischemic coronary artery disease. Treatment with antithyroid medications, beta blockers, and angiotensin-converting enzyme inhibitors rapidly restored LV function. The rapid reversibility suggests a role for myocardial stunning, an important entity to recognize in hyperthyroidism since this form of LV dysfunction can be reversed with appropriate treatment.

Early prediction of response in patients with advanced/metastatic non-small cell lung cancer during chemotherapy with FDG-PET-CT

13154

Background: To evaluate the use of 18-fluorodeoxyglucose positron emission tomography-computed tomography (PET-CT) for prediction of response and survival early during the course of treatment in patients with advanced/metastatic NSCLC. Methods: Between May 2004 and November 2005, 31 patients (gender, 23M, 8F; stage, 2IIIB/29IV, histology, 6 squamous cell ca, 22 adenoca, 3 NOS; age median 57 (30–73 y)) with histopathologically proven NSCLC stage IIIB/IV were enrolled into this study. PET-CT was performed prior to and after one cycle of treatment. Early changes of primary tumor FDG-uptake measured by standardized uptake values (SUV) were correlated with best response to therapy as assessed by CT scan according to WHO response criteria. Results: Patients underwent standard treatment with gemcitabine/vinorelbine (15), gemcitabine/cisplatin (1) gemcitabine/vinorelbine/cisplatin (1), irinotecan/cisplatin (9) or gefitinib (5). In the 25 patients evaluable for response, other 6 patients ongoing, 9 patients achieved a partial response (36%), 5 showed stable diseases and 11 were progressive. Using a cut-off value of 20% reduction of FDG-uptake as a criterion for a response in PET-CT, subsequent best response was predicted with a sensitivity of 88.9% and a specificity of 87.5%. The positive predictive value of a metabolic response was 80.0% and the negative predictive value 93.3%, respectively. There was a significant correlation between the decrease of tumor metabolic activity and subsequent best response (p< 0.001). The median time to progression for PET-CT responder was 10.1 months when compared with that of non-responders with 2.6 months (log-rank p=0.009). Conclusions: Using FDG-PET best response to standard treatment and patient outcome can be predicted very early and therefore, the use of PET-CT may allow to reduce side effects and costs of ineffective therapy in non-responding patients

No significant financial relationships to disclose.

Activation of NF-κB transcription factor in the preterm ovine brain and placenta after acute LPS exposure

Intrauterine infection may be causally related to inflammation and injury of the fetal brain, however the mechanisms by which this occurs are unclear. We have investigated whether nuclear factor (NF)-kappaB, a transcription factor for proinflammatory cytokines, is activated in the fetal brain after acute LPS-exposure. At 95 days of gestation (term = approximately 147 days), 5 fetuses received a single intravenous bolus dose of LPS (1 microg/kg); 6 fetuses served as controls. Fetal blood samples were taken hourly for 6 hr post LPS-exposure to assess physiological status. Ewes and fetuses were then euthanased, placental and brain tissue examined histologically, and NF-kappaB activation assessed in several regions of the fetal brain using an electromobility shift assay (EMSA). Oxidative stress was measured using lipid peroxidation and 8-isoprostane biochemical assays and brain cytokine concentrations analysed by enzyme linked immunosorbent assay (ELISA). LPS-exposed fetuses (relative to controls) were hypoxemic and the haematocrit and lactate levels had increased. In the brains of LPS-exposed fetuses compared to controls, NF-kappaB binding activity was elevated in the hippocampus and the thalamus/basal ganglia; 8-isoprostane levels were elevated overall (P < 0.05) in the parietal/occipital/temporal lobes and thalamus/basal ganglia. TNF-alpha and IL-6 concentrations were not elevated, however, there was a tendency for an elevation of IFN-gamma concentrations in the thalamus/basal ganglia. IFN-gamma concentration was elevated (P < 0.05) in the plasma 4 hr after LPS-exposure. In the placenta, NF-kappaB binding activity was increased (P < 0.05). We conclude that acute systemic administration of LPS leads to increased binding activity of NF-kappaB subunits in specific regions of the fetal brain and in the placenta, but that there is no clear-cut relationship between this elevation and vulnerability to endotoxic damage.