... IEEE-EMBS International Conference on Biomedical and Health Informatics. IEEE-EMBS International Conference on Biomedical and Health Informatics最新文献

Heart transplant rejection is one major threat for the survival of patients with a heart transplant. Endomyocardial biopsies are effective in showing signs of heart transplant rejection even before patients have any symptoms. Manually examining the tissue samples is costly, time-consuming and error-prone. With recent advances in deep learning (DL) based image processing methods, automatic training and prediction on heart transplant rejection using whole-slide images expect to be promising. This paper develops an advanced pipeline for quality control, feature extraction, clustering and classification. We first implement a stacked convolutional autoencoder to extract feature maps for each tile; we then incorporate multiple instance learning (MIL) with dimensionality reduction and unsupervised clustering prior to classification. Our results show that utilizing unsupervised clustering after feature extraction can achieve higher classification results while preserving the capability for multi-class classification.

In this study, we focus on the following question: do genomic regions enriched in cancer variant mutations have significantly different chromatin folding patterns? We utilize publicly available Hi-C data to characterize chromatin folding patterns in healthy (GM12878) and cancer (K562) cells based on status of A/B compartmentalization and random vs non-random chromatin physical interactions. We then perform statistical testing to assess if chromatin folding patterns in cancer variant-enriched loci are significantly different from non-enriched loci. Our results indicate that loci with cancer variant status have significantly altered (FDR < 0.05) chromatin folding patterns.

The complexity of the patterns associated with atrial fibrillation (AF) and the high level of noise affecting these patterns have significantly limited the application of current signal processing and shallow machine learning approaches to accurately detect this condition. Deep neural networks have shown to be very powerful to learn the non-linear patterns in various problems such as computer vision tasks. While deep learning approaches have been utilized to learn complex patterns related to the presence of AF in electrocardiogram (ECG) signals, they can considerably benefit from knowing which parts of the signal is more important to focus on during learning. In this paper, we introduce a two-channel deep neural network to more accurately detect the presence of AF in the ECG signals. The first channel takes in an ECG signal and automatically learns where to attend for detection of AF. The second channel simultaneously takes in the same ECG signal to consider all features of the entire signal. Besides improving detection accuracy, this model can guide the physicians via visualization that what parts of the given ECG signal are important to attend while trying to detect atrial fibrillation. The experimental results confirm that the proposed model significantly improves the performance of AF detection on well-known MIT-BIH AF database with 5-s ECG segments (achieved a sensitivity of 99.53%, specificity of 99.26% and accuracy of 99.40%).

We propose an innovative machine learning paradigm enabling precision medicine for prioritizing cognitive assessments according to their relevance to Alzheimer's disease at the individual patient level. The paradigm tailors the cognitive biomarker discovery and cognitive assessment selection process to the brain morphometric characteristics of each individual patient. We implement this paradigm using a newly developed learning-to-rank method PLTR. Our empirical study on the ADNI data yields promising results to identify and prioritize individual-specific cognitive biomarkers as well as cognitive assessment tasks based on the individual's structural MRI data. The resulting top ranked cognitive biomarkers and assessment tasks have the potential to aid personalized diagnosis and disease subtyping.

Oromotor dysfunction caused by neurological disorders can result in significant speech and swallowing impairments. Current diagnostic methods to assess oromotor function are subjective and rely on perceptual judgments by clinicians. In particular, the widely used oral-diadochokinesis (oral-DDK) test, which requires rapid, alternate repetitions of speech-based syllables, is conducted and interpreted differently among clinicians. It is therefore prone to inaccuracy, which results in poor test reliability and poor clinical application. In this paper, we present a deep learning based software to extract quantitative data from the oral DDK signal, thereby transforming it into an objective diagnostic and treatment monitoring tool. The proposed software consists of two main modules: a fully automated syllable detection module and an interactive visualization and editing module that allows inspection and correction of automated syllable units. The DeepDDK software was evaluated on speech files corresponding to 9 different DDK syllables (e.g., "Pa", "Ta", "Ka"). The experimental results show robustness of both syllable detection and localization across different types of DDK speech tasks.

Poor adherence to long-term therapies for chronic diseases, such as cancer, compromises effectiveness of treatment and increases the likelihood of disease progression, making medication adherence a critical issue in population health. While the field has documented many eers to adherence to medication, it has also come up with few efficacious solutions to medication adherence, indicating that new and innovative approaches are needed. In this paper, we evaluate medication-taking behaviors based on social cognitive theory (SCT), presenting patterns of adherence stratified across SCT constructs in 33 breast cancer survivors over an 8-month period. Findings indicate that medication adherence is a very personal experience influenced by many simultaneously interacting factors, and a deeper contextual understanding is needed to understand and develop interventions targeting non-adherence.

Successful translational studies within the field of Traumatic Brain Injury (TBI) are concerned with determining reliable markers of injury outcome at chronic time points. Determination of injury severity following Fluid Percussion Injury (FPI) has long been limited to the measured atmospheric pressure associated with the delivered pulse. Duration of unresponsiveness to toe pinch (unconsciousness) was next introduced as an extra marker of injury severity. The current study is an effort to assess the utilization of acute injury-induced biological responses (duration of toe pinch unresponsiveness, percent body weight change, quantification of brain edema, and apnea duration) to predict cognitive performance at a subacute time point following developmental brain injury. Cognitive performance, when measured at a subacute phase, after developmental FPI was negatively correlated with the following variables, duration of toe pinch unresponsiveness, percent weight change, and quantified level of brain edema. These finding suggest the potential utilization of reliable severity assessment of injury-induced biological responses in determining outcome measures at subacute time points.

Early mobilization of critically ill patients in the Intensive Care Unit (ICU) can prevent adverse outcomes such as delirium and post-discharge physical impairment. To date, no studies have characterized activity of sepsis patients in the ICU using granular actigraphy data. This study characterizes the activity of sepsis patients in the ICU to aid in future mobility interventions. We have compared the actigraphy features of 24 patients in four groups: Chronic Critical Illness (CCI) sepsis patients in the ICU, Rapid Recovery (RR) sepsis patients in the ICU, non-sepsis ICU patients (control-ICU), and healthy subjects. We used a total of 15 statistical and circadian rhythm features extracted from the patients' actigraphy data collected over a five-day period. Our results show that the four groups are significantly different in terms of activity features. In addition, we observed that the CCI and control-ICU patients show less regularity in their circadian rhythm compared to the RR patients. These results show the potential of using actigraphy data for guiding mobilization practices, classifying sepsis recovery subtype, as well as for tracking patients' recovery.

Geometric and topological features of proteins such as voids, pockets and channels are important for protein functions. We discuss a method for visualizing protein pockets and channels based on orthogonal spheres computed from alpha shapes of the protein structures, and how metric properties of channel surfaces can be mapped. In addition, we discuss how structurally prominent sites, such as constriction sties in channels, can be computed, which may help to understand protein functions and mutation effects, with implications in developing novel therapeutic interventions.

Information on protein hydrogen exchange can help delineate key regions involved in protein-protein interactions and provides important insight towards determining functional roles of genetic variants and their possible mechanisms in disease processes. Previous studies have shown that the degree of hydrogen exchange is affected by hydrogen bond formations, solvent accessibility, proximity to other residues, and experimental conditions. However, a general predictive method for identifying residues capable of hydrogen exchange transferable to a broad set of proteins is lacking. We have developed a machine learning method based on random forest that can predict whether a residue experiences hydrogen exchange. Using data from the Start2Fold database, which contains information on 13,306 residues (3,790 of which experience hydrogen exchange and 9,516 which do not exchange), our method achieves good performance. Specifically, we achieve an overall out-of-bag (OOB) error, an unbiased estimate of the test set error, of 20.3 percent. Using a randomly selected test data set consisting of 500 residues experiencing hydrogen exchange and 500 which do not, our method achieves an accuracy of 0.79, a recall of 0.74, a precision of 0.82, and an F1 score of 0.78.