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

Opioid withdrawal's physiological effects are a major impediment to recovery from opioid use disorder (OUD). Prior work has demonstrated that transcutaneous cervical vagus nerve stimulation (tcVNS) can counteract some of opioid withdrawal's physiological effects by reducing heart rate and perceived symptoms. The purpose of this study was to assess the effects of tcVNS on respiratory manifestations of opioid withdrawal - specifically, respiratory timings and their variability. Patients with OUD (N = 21) underwent acute opioid withdrawal over the course of a two-hour protocol. The protocol involved opioid cues to induce opioid craving and neutral conditions for control purposes. Patients were randomly assigned to receive double-blind active tcVNS (n = 10) or sham stimulation (n = 11) throughout the protocol. Respiratory effort and electrocardiogram-derived respiration signals were used to estimate inspiration time (T_i), expiration time (T_e), and respiration rate (RR), along with each measure's variability quantified via interquartile range (IQR). Comparing the active and sham groups, active tcVNS significantly reduced IQR(T_i) - a variability measure - compared to sham stimulation (p = .02). Relative to baseline, the active group's median change in IQR(T_i) was 500 ms less than the sham group's median change in IQR(T_i). Notably, IQR(T_i) was found to be positively associated with post-traumatic stress disorder symptoms in prior work. Therefore, a reduction in IQR(T_i) suggests that tcVNS downregulates the respiratory stress response associated with opioid withdrawal. Although further investigations are necessary, these results promisingly suggest that tcVNS - a non-pharmacologic, non-invasive, readily implemented neuromodulation approach - can serve as a novel therapy to mitigate opioid withdrawal symptoms.

Parkinson's disease (PD) is the second most common neurodegenerative disease and presents a complex etiology with genomic and environmental factors and no recognized cures. Genotype data, such as single nucleotide polymorphisms (SNPs), could be used as a prodromal factor for early detection of PD. However, the polygenic nature of PD presents a challenge as the complex relationships between SNPs towards disease development are difficult to model. Traditional assessment methods such as polygenic risk scores and machine learning approaches struggle to capture the complex interactions present in the genotype data, thus limiting their discriminative capabilities in diagnosis. On the other hand, deep learning models are better suited for this task. Nevertheless, they encounter difficulties of their own such as a lack of interpretability. To overcome these limitations, in this work, a novel transformer encoder-based model is introduced to classify PD patients from healthy controls based on their genotype. This method is designed to effectively model complex global feature interactions and enable increased interpretability through the learned attention scores. The proposed framework outperformed traditional machine learning models and multilayer perceptron (MLP) baseline models. Moreover, visualization of the learned SNP-SNP associations provides not only interpretability to the model but also valuable insights into the biochemical pathways underlying PD development, which are corroborated by pathway enrichment analysis. Our results suggest novel SNP interactions to be further studied in wet lab and clinical settings.

To keep pace with the increased generation and digitization of documents, automated methods that can improve search, discovery and mining of the vast body of literature are essential. Keyphrases provide a concise representation by identifying salient concepts in a document. Various supervised approaches model keyphrase extraction using local context to predict the label for each token and perform much better than the unsupervised counterparts. However, existing supervised datasets have limited annotated examples to train better deep learning models. In contrast, many domains have large amount of un-annotated data that can be leveraged to improve model performance in keyphrase extraction. We introduce a self-learning based model that incorporates uncertainty estimates to select instances from large-scale unlabeled data to augment the small labeled training set. Performance evaluation on a publicly available biomedical dataset demonstrates that our method improves performance of keyphrase extraction over state of the art models.

High-throughput sequencing is widely used for strain detection and characterization of antibiotic resistance in microbial metagenomic samples. Current analytical tools use curated antibiotic resistance gene (ARG) databases to classify individual sequencing reads or assembled contigs. However, identifying ARGs from raw read data can be time consuming (especially if assembly or alignment is required) and challenging, due to genome rearrangements and mutations. Here, we present the k-mer-based antibiotic gene resistance analyzer (KARGA), a multi-platform Java toolkit for identifying ARGs from metagenomic short read data. KARGA does not perform alignment; it uses an efficient double-lookup strategy, statistical filtering on false positives, and provides individual read classification as well as covering of the database resistome. On simulated data, KARGA's antibiotic resistance class recall is 99.89% for error/mutation rates within 10%, and of 83.37% for error/mutation rates between 10% and 25%, while it is 99.92% on ARGs with rearrangements. On empirical data, KARGA provides higher hit score (≥1.5-fold) than AMRPlusPlus, DeepARG, and MetaMARC. KARGA has also faster runtimes than all other tools (2x faster than AMRPlusPlus, 7x than DeepARG, and over 100x than MetaMARC). KARGA is available under the MIT license at https://github.com/DataIntellSystLab/KARGA.

Mechanical thrombectomy (MTB) is one of the two standard treatment options for Acute Ischemic Stroke (AIS) patients. Current clinical guidelines instruct the use of pretreatment imaging to characterize a patient's cerebrovascular flow, as there are many factors that may underlie a patient's successful response to treatment. There is a critical need to leverage pretreatment imaging, taken at admission, to guide potential treatment avenues in an automated fashion. The aim of this study is to develop and validate a fully automated machine learning algorithm to predict the final modified thrombolysis in cerebral infarction (mTICI) score following MTB. A total 321 radiomics features were computed from segmented pretreatment MRI scans for 141 patients. Successful recanalization was defined as mTICI score >= 2c. Different feature selection methods and classification models were examined in this study. Our best performance model achieved 74.42±2.52% AUC, 75.56±4.44% sensitivity, and 76.75±4.55% specificity, showing a good prediction of reperfusion quality using pretreatment MRI. Results suggest that MR images can be informative to predicting patient response to MTB, and further validation with a larger cohort can determine the clinical utility.

Long-term endocrine therapy (e.g. Tamoxifen, aromatase inhibitors) is crucial to prevent breast cancer recurrence, yet rates of adherence to these medications are low. To develop, evaluate, and sustain future interventions, individual-level modeling can be used to understand breast cancer survivors' behavioral mechanisms of medication-taking. This paper presents interdisciplinary research, wherein a model employing randomized neural networks was developed to predict breast cancer survivors' daily medication-taking behavior based on their survey data over three time periods (baseline, 4 months, 8 months). The neural network structure was guided by random utility theory developed in psychology and behavioral economics. Comparative analysis indicates that the proposed model outperforms existing computational models in terms of prediction accuracy under conditions of randomness.

There are multiple study design choices to be selected in order to perform evaluations of predictive patient monitoring algorithms related to the event and true positive alarm definitions (e.g., how far ahead of the event is a true positive alarm). Often, passively collected patient monitoring datasets from clinical environments are available to perform these types of studies, so that the effects of different study design choices can be simulated to evaluate the robustness of an algorithm to those choices. Here, we simulate the effects of varying alarm and event definition criteria on the reported performance of the early warning score to predict hypotensive events. A total of 432 combinations of study design choices were simulated. Area under the receiver-operating characteristic curve varied from greater than 0.8 to less than 0.5 by adjusting alarm and event definition criteria. Traditional metrics for evaluating diagnostic systems were modulated across a wide range by adjusting study design choices for a predictive algorithm using a patient monitoring dataset. This highlights the importance of examining study design choices for new predictive patient monitoring algorithms and presents an approach to simulate different study designs with retrospective patient monitoring data as part of a robustness evaluation.