Nighttime features derived from topic models for classification of patients with COPD

Daily Posture Behavior Patterns Derived From Multitime-Scale Topic Models Using Wearable Triaxial Acceleration for Assessment of Concern About Falling

Concern about falling is prevalent in older population. This condition would cause a series of adverse physical and psychological consequences for older adults' health. Traditional assessment of concern about falling is relied on self-reported questionnaires and thus is too subjective. Therefore, we proposed a novel multi-time-scale topic modelling approach to quantitatively evaluate concern about falling by analyzing triaxial acceleration signals collected from a wearable pendent sensor. Different posture segments were firstly recognized to extract their corresponding feature subsets. Then, each selected feature related to concern about falling was clustered into discrete levels as feature letters of artificial words in different time scales. As a result, all older participants' signal recordings were converted to a collection of artificial documents, which can be processed by natural language processing methodologies. The topic modelling technique was used to discover daily posture behavior patterns from these documents as discriminants between older adults with different levels of concern about falling. The results indicated that there were significant differences in distributions of posture topics between groups of older adults with different levels of concern about falling. Additionally, the transitions of posture topics over daytime and nighttime revealed temporal regularities of posture behavior patterns of older adult's active and inactive status, which were substantially different for older adults with different levels of concern about falling. Finally, the level of concern about falling was accurately determined with accuracy of 71.2% based on the distributions of posture topics combined with the mobility performance metrics of walking behaviors and demographic information.

Lung Radiomics Features Selection for COPD Stage Classification Based on Auto-Metric Graph Neural Network

Chronic obstructive pulmonary disease (COPD) is a preventable, treatable, progressive chronic disease characterized by persistent airflow limitation. Patients with COPD deserve special consideration regarding treatment in this fragile population for preclinical health management. Therefore, this paper proposes a novel lung radiomics combination vector generated by a generalized linear model (GLM) and Lasso algorithm for COPD stage classification based on an auto-metric graph neural network (AMGNN) with a meta-learning strategy. Firstly, the parenchyma images were segmented from chest high-resolution computed tomography (HRCT) images by ResU-Net. Second, lung radiomics features are extracted from the parenchyma images by PyRadiomics. Third, a novel lung radiomics combination vector (3 + 106) is constructed by the GLM and Lasso algorithm for determining the radiomics risk factors (K = 3) and radiomics node features (d = 106). Last, the COPD stage is classified based on the AMGNN. The results show that compared with the convolutional neural networks and machine learning models, the AMGNN based on constructed novel lung radiomics combination vector performs best, achieving an accuracy of 0.943, precision of 0.946, recall of 0.943, F1-score of 0.943, and ACU of 0.984. Furthermore, it is found that our method is effective for COPD stage classification.

Topic2features: a novel framework to classify noisy and sparse textual data using LDA topic distributions

In supervised machine learning, specifically in classification tasks, selecting and analyzing the feature vector to achieve better results is one of the most important tasks. Traditional methods such as comparing the features' cosine similarity and exploring the datasets manually to check which feature vector is suitable is relatively time consuming. Many classification tasks failed to achieve better classification results because of poor feature vector selection and sparseness of data. In this paper, we proposed a novel framework, topic2features (T2F), to deal with short and sparse data using the topic distributions of hidden topics gathered from dataset and converting into feature vectors to build supervised classifier. For this we leveraged the unsupervised topic modelling LDA (latent dirichlet allocation) approach to retrieve the topic distributions employed in supervised learning algorithms. We made use of labelled data and topic distributions of hidden topics that were generated from that data. We explored how the representation based on topics affect the classification performance by applying supervised classification algorithms. Additionally, we did careful evaluation on two types of datasets and compared them with baseline approaches without topic distributions and other comparable methods. The results show that our framework performs significantly better in terms of classification performance compared to the baseline(without T2F) approaches and also yields improvement in terms of F1 score compared to other compared approaches.