Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Internal Medicine Internal Medicine

Acute and chronic stress alter behavioral laterality in dogs.

In Scientific reports ; h5-index 158.0

Dogs are one of the key animal species in investigating the biological mechanisms of behavioral laterality. Cerebral asymmetries are assumed to be influenced by stress, but this subject has not yet been studied in dogs. This study aims to investigate the effect of stress on laterality in dogs by using two different motor laterality tests: the Kong™ Test and a Food-Reaching Test (FRT). Motor laterality of chronically stressed (n = 28) and emotionally/physically healthy dogs (n = 32) were determined in two different environments, i.e., a home environment and a stressful open field test (OFT) environment. Physiological parameters including salivary cortisol, respiratory rate, and heart rate were measured for each dog, under both conditions. Cortisol results showed that acute stress induction by OFT was successful. A shift towards ambilaterality was detected in dogs after acute stress. Results also showed a significantly lower absolute laterality index in the chronically stressed dogs. Moreover, the direction of the first paw used in FRT was a good predictor of the general paw preference of an animal. Overall, these results provide evidence that both acute and chronic stress exposure can change behavioral asymmetries in dogs.

Salgirli Demirbas Yasemin, Isparta Sevim, Saral Begum, Keskin Yılmaz Nevra, Adıay Deniz, Matsui Hiroshi, Töre-Yargın Gülşen, Musa Saad Adam, Atilgan Durmus, Öztürk Hakan, Kul Bengi Cinar, Şafak C Etkin, Ocklenburg Sebastian, Güntürkün Onur

2023-Mar-11

General General

Predicting Potential Drug-Disease Associations Based on Hypergraph Learning with Subgraph Matching.

In Interdisciplinary sciences, computational life sciences

The search for potential drug-disease associations (DDA) can speed up drug development cycles, reduce costly wasted resources, and accelerate disease treatment by repurposing existing drugs that can control further disease progression. As technologies such as deep learning continue to mature, many researchers tend to use emerging technologies to predict potential DDA. The performance of DDA prediction is still challenging and there is some space for improvement due to issues such as the small number of existing associations and possible noise in the data. To better predict DDA, we propose a computational approach based on hypergraph learning with subgraph matching (HGDDA). In particular, HGDDA first extracts feature subgraph information in the validated drug-disease association network and proposes a negative sampling strategy based on similarity network to reduce the data imbalance. Second, the hypergraph Unet module is used by extracting Finally, the potential DDA is predicted by designing a hypergraph combination module to convolution and pooling the two constructed hypergraphs separately, and calculating the difference information between the subgraphs using cosine similarity for node matching. The performance of HGDDA is verified under two standard datasets by 10-fold cross-validation (10-CV), and the results outperform existing drug-disease prediction methods. In addition, to validate the overall utility of the model, the top 10 drugs for the specific disease are predicted through the case study and validated using the CTD database.

Wang Yuanxu, Song Jinmiao, Wei Mingjie, Duan Xiaodong

2023-Mar-11

Drug–disease associations, Hypergraph Unet, Hypergraph convolutional neural network, Subgraph matching

Radiology Radiology

Optimizing Convolutional Neural Networks for Chronic Obstructive Pulmonary Disease Detection in Clinical Computed Tomography Imaging

ArXiv Preprint

Chronic Obstructive Pulmonary Disease (COPD) is a leading cause of death worldwide, yet early detection and treatment can prevent the progression of the disease. In contrast to the conventional method of detecting COPD with spirometry tests, X-ray Computed Tomography (CT) scans of the chest provide a measure of morphological changes in the lung. It has been shown that automated detection of COPD can be performed with deep learning models. However, the potential of incorporating optimal window setting selection, typically carried out by clinicians during examination of CT scans for COPD, is generally overlooked in deep learning approaches. We aim to optimize the binary classification of COPD with densely connected convolutional neural networks (DenseNets) through implementation of manual and automated Window-Setting Optimization (WSO) steps. Our dataset consisted of 78 CT scans from the Klinikum rechts der Isar research hospital. Repeated inference on the test set showed that without WSO, the plain DenseNet resulted in a mean slice-level AUC of 0.80$\pm$0.05. With input images manually adjusted to the emphysema window setting, the plain DenseNet model predicted COPD with a mean AUC of 0.86$\pm$0.04. By automating the WSO through addition of a customized layer to the DenseNet, an optimal window setting in the proximity of the emphysema window setting was learned and a mean AUC of 0.82$\pm$0.04 was achieved. Detection of COPD with DenseNet models was optimized by WSO of CT data to the emphysema window setting range, demonstrating the importance of implementing optimal window setting selection in the deep learning pipeline.

Tina Dorosti, Manuel Schultheiss, Felix Hofmann, Luisa Kirchner, Theresa Urban, Franz Pfeiffer, Johannes Thalhammer, Florian Schaff, Tobias Lasser, Daniela Pfeiffer

2023-03-13

General General

Occupant privacy perception, awareness, and preferences in smart office environments.

In Scientific reports ; h5-index 158.0

Building management systems tout numerous benefits, such as energy efficiency and occupant comfort but rely on vast amounts of data from various sensors. Advancements in machine learning algorithms make it possible to extract personal information about occupants and their activities beyond the intended design of a non-intrusive sensor. However, occupants are not informed of data collection and possess different privacy preferences and thresholds for privacy loss. While privacy perceptions and preferences are most understood in smart homes, limited studies have evaluated these factors in smart office buildings, where there are more users and different privacy risks. To better understand occupants' perceptions and privacy preferences, we conducted twenty-four semi-structured interviews between April 2022 and May 2022 on occupants of a smart office building. We found that data modality features and personal features contribute to people's privacy preferences. The features of the collected modality define data modality features - spatial, security, and temporal context. In contrast, personal features consist of one's awareness of data modality features and data inferences, definitions of privacy and security, and the available rewards and utility. Our proposed model of people's privacy preferences in smart office buildings helps design more effective measures to improve people's privacy.

Li Beatrice, Tavakoli Arash, Heydarian Arsalan

2023-Mar-11

Pathology Pathology

Learning Reduced-Order Models for Cardiovascular Simulations with Graph Neural Networks

ArXiv Preprint

Reduced-order models based on physics are a popular choice in cardiovascular modeling due to their efficiency, but they may experience reduced accuracy when working with anatomies that contain numerous junctions or pathological conditions. We develop one-dimensional reduced-order models that simulate blood flow dynamics using a graph neural network trained on three-dimensional hemodynamic simulation data. Given the initial condition of the system, the network iteratively predicts the pressure and flow rate at the vessel centerline nodes. Our numerical results demonstrate the accuracy and generalizability of our method in physiological geometries comprising a variety of anatomies and boundary conditions. Our findings demonstrate that our approach can achieve errors below 2% and 3% for pressure and flow rate, respectively, provided there is adequate training data. As a result, our method exhibits superior performance compared to physics-based one-dimensional models, while maintaining high efficiency at inference time.

Luca Pegolotti, Martin R. Pfaller, Natalia L. Rubio, Ke Ding, Rita Brugarolas Brufau, Eric Darve, Alison L. Marsden

2023-03-13

General General

Novel architecture for gated recurrent unit autoencoder trained on time series from electronic health records enables detection of ICU patient subgroups.

In Scientific reports ; h5-index 158.0

Electronic health records (EHRs) are used in hospitals to store diagnoses, clinician notes, examinations, lab results, and interventions for each patient. Grouping patients into distinct subsets, for example, via clustering, may enable the discovery of unknown disease patterns or comorbidities, which could eventually lead to better treatment through personalized medicine. Patient data derived from EHRs is heterogeneous and temporally irregular. Therefore, traditional machine learning methods like PCA are ill-suited for analysis of EHR-derived patient data. We propose to address these issues with a new methodology based on training a gated recurrent unit (GRU) autoencoder directly on health record data. Our method learns a low-dimensional feature space by training on patient data time series, where the time of each data point is expressed explicitly. We use positional encodings for time, allowing our model to better handle the temporal irregularity of the data. We apply our method to data from the Medical Information Mart for Intensive Care (MIMIC-III). Using our data-derived feature space, we can cluster patients into groups representing major classes of disease patterns. Additionally, we show that our feature space exhibits a rich substructure at multiple scales.

Merkelbach Kilian, Schaper Steffen, Diedrich Christian, Fritsch Sebastian Johannes, Schuppert Andreas

2023-Mar-11