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

General General

Interpretation of lung disease classification with light attention connected module.

In Biomedical signal processing and control

Lung diseases lead to complications from obstructive diseases, and the COVID-19 pandemic has increased lung disease-related deaths. Medical practitioners use stethoscopes to diagnose lung disease. However, an artificial intelligence model capable of objective judgment is required since the experience and diagnosis of respiratory sounds differ. Therefore, in this study, we propose a lung disease classification model that uses an attention module and deep learning. Respiratory sounds were extracted using log-Mel spectrogram MFCC. Normal and five types of adventitious sounds were effectively classified by improving VGGish and adding a light attention connected module to which the efficient channel attention module (ECA-Net) was applied. The performance of the model was evaluated for accuracy, precision, sensitivity, specificity, f1-score, and balanced accuracy, which were 92.56%, 92.81%, 92.22%, 98.50%, 92.29%, and 95.4%, respectively. We confirmed high performance according to the attention effect. The classification causes of lung diseases were analyzed using gradient-weighted class activation mapping (Grad-CAM), and the performances of their models were compared using open lung sounds measured using a Littmann 3200 stethoscope. The experts' opinions were also included. Our results will contribute to the early diagnosis and interpretation of diseases in patients with lung disease by utilizing algorithms in smart medical stethoscopes.

Choi Youngjin, Lee Hongchul

2023-Jul

Attention, ECA-Net, Grad-CAM, Lung disease, Respiratory sound, eXplainable AI

General General

Extracting Digital Biomarkers for Unobtrusive Stress State Screening from Multimodal Wearable Data

ArXiv Preprint

With the development of wearable technologies, a new kind of healthcare data has become valuable as medical information. These data provide meaningful information regarding an individual's physiological and psychological states, such as activity level, mood, stress, and cognitive health. These biomarkers are named digital since they are collected from digital devices integrated with various sensors. In this study, we explore digital biomarkers related to stress modality by examining data collected from mobile phones and smartwatches. We utilize machine learning techniques on the Tesserae dataset, precisely Random Forest, to extract stress biomarkers. Using feature selection techniques, we utilize weather, activity, heart rate (HR), stress, sleep, and location (work-home) measurements from wearables to determine the most important stress-related biomarkers. We believe we contribute to interpreting stress biomarkers with a high range of features from different devices. In addition, we classify the $5$ different stress levels with the most important features, and our results show that we can achieve $85\%$ overall class accuracy by adjusting class imbalance and adding extra features related to personality characteristics. We perform similar and even better results in recognizing stress states with digital biomarkers in a daily-life scenario targeting a higher number of classes compared to the related studies.

Berrenur Saylam, Özlem Durmaz İncel

2023-03-08

General General

Through the eyes into the brain, using artificial intelligence.

In Annals of the Academy of Medicine, Singapore

INTRODUCTION : Detection of neurological conditions is of high importance in the current context of increasingly ageing populations. Imaging of the retina and the optic nerve head represents a unique opportunity to detect brain diseases, but requires specific human expertise. We review the current outcomes of artificial intelligence (AI) methods applied to retinal imaging for the detection of neurological and neuro-ophthalmic conditions.

METHOD : Current and emerging concepts related to the detection of neurological conditions, using AI-based investigations of the retina in patients with brain disease were examined and summarised.

RESULTS : Papilloedema due to intracranial hypertension can be accurately identified with deep learning on standard retinal imaging at a human expert level. Emerging studies suggest that patients with Alzheimer's disease can be discriminated from cognitively normal individuals, using AI applied to retinal images.

CONCLUSION : Recent AI-based systems dedicated to scalable retinal imaging have opened new perspectives for the detection of brain conditions directly or indirectly affecting retinal structures. However, further validation and implementation studies are required to better understand their potential value in clinical practice.

Sathianvichitr Kanchalika, Lamoureux Oriana, Nakada Sakura, Tang Zhiqun, Schmetterer Leopold, Chen Christopher, Cheung Carol Y, Najjar Raymond P, Milea Dan

2023-Feb

General General

Deep learning techniques and mathematical modeling allow 3D analysis of mitotic spindle dynamics.

In The Journal of cell biology

Time-lapse microscopy movies have transformed the study of subcellular dynamics. However, manual analysis of movies can introduce bias and variability, obscuring important insights. While automation can overcome such limitations, spatial and temporal discontinuities in time-lapse movies render methods such as 3D object segmentation and tracking difficult. Here, we present SpinX, a framework for reconstructing gaps between successive image frames by combining deep learning and mathematical object modeling. By incorporating expert feedback through selective annotations, SpinX identifies subcellular structures, despite confounding neighbor-cell information, non-uniform illumination, and variable fluorophore marker intensities. The automation and continuity introduced here allows the precise 3D tracking and analysis of spindle movements with respect to the cell cortex for the first time. We demonstrate the utility of SpinX using distinct spindle markers, cell lines, microscopes, and drug treatments. In summary, SpinX provides an exciting opportunity to study spindle dynamics in a sophisticated way, creating a framework for step changes in studies using time-lapse microscopy.

Dang David, Efstathiou Christoforos, Sun Dijue, Yue Haoran, Sastry Nishanth R, Draviam Viji M

2023-May-01

General General

Flexible Quantum Dot Light-Emitting Device for Emerging Multifunctional and Smart Applications.

In Advanced materials (Deerfield Beach, Fla.)

Quantum dot light-emitting diodes (QLEDs), owing to their exceptional performances in device efficiency, color purity/tunability in the visible region, and solution-processing ability on various substrates, become a potential candidate for flexible and ultrathin electroluminescent (EL) lighting and display. Moreover, beyond the lighting and display, flexible QLEDs are enabled with endless possibilities in the era of the internet of things and artificial intelligence by acting as input/output ports in wearable integrated systems. Challenges remain in the development of flexible QLEDs with the goals for high performance, excellent flexibility/even stretchability, and emerging applications. In this paper, we review the recent developments of QLEDs including quantum dot materials, working mechanism, flexible/stretchable strategies, and patterning strategies, and highlight its emerging multifunctional integrations and smart applications covering wearable optical medical devices, pressure-sensing EL devices, and neural smart EL devices. We also summarize the remaining challenges and make an outlook on the future development of flexible QLEDs. The review is expected to offer a systematic understanding and valuable inspiration for flexible QLEDs to simultaneously satisfy optoelectronic and flexible properties for emerging applications. This article is protected by copyright. All rights reserved.

Lin Qinghong, Zhu Yangbin, Wang Yue, Li Deli, Zhao Yi, Liu Yang, Li Fushan, Huang Wei

2023-Mar-07

electroluminescent, flexible light emitting device, quantum dot, wearable devices

General General

Altitude-dependent Metabolite Biomarkers Reveal the Mechanism of Plateau Pika Adaptation to High Altitudes.

In Integrative zoology

The harsh environment in the Tibetan plateau, the highest place in the world, poses thermoregulatory challenges and hypoxic stress to animals. The impacts of plateau environment on animal physiology and reproduction include external factors such as strong ultraviolet radiation and low temperature, and internal factors such as animal metabolites and gut microbiota. However, it remains unclear how plateau pika adapt to high altitudes through the combination of serum metabolites and gut microbiota. To this end, we captured 24 wild plateau pikas at the altitudes of 3400 m, 3600 m, or 3800 m a.s.l. in a Tibetan alpine grassland. Using the machine learning algorithms (random forest), we identified five biomarkers of serum metabolites indicative of the altitudes, i.e., dihydrotestosterone, homo-L-arginine, alpha-ketoglutaric-acid, serotonin and threonine, which were related to body weight, reproduction, and energy metabolism of pika. Those metabolic biomarkers were positively correlated with Lachnospiraceae_ Agathobacter, Ruminococcaceae, or Prevotellaceae_Prevotella, suggesting the close relationship between metabolites and gut microbiota. By identifying the metabolic biomarkers and gut microbiota analysis, we reveal the mechanisms of adaptation to high altitudes in plateau pika. This article is protected by copyright. All rights reserved.

Chen Xi, Wang Zaiwei, Su Junhu, Li Huan, Xiong Jinbo, Fu Keyi, Wang Zilong, Yuan Xuefeng, Shi Ziyue, Miao Xiumei, Yang Mei, Yang Yunfeng, Shi Zunji

2023-Mar-07

Biomarkers, Gut microbiota, Machine, Metabolomics, Plateau pika, learning