An analysis model of diagnosis and treatment for COVID-19 pandemic based on medical information fusion

Exploring the complicated relationships underlying the clinical information is essential for the diagnosis and treatment of the Coronavirus Disease 2019 (COVID-19). Currently, few approaches are mature enough to show operational impact. Based on electronic medical records (EMRs) of 570 COVID-19 inpatients, we proposed an analysis model of diagnosis and treatment for COVID-19 based on the machine learning algorithms and complex networks. Introducing the medical information fusion, we constructed the heterogeneous information network to discover the complex relationships among the syndromes, symptoms, and medicines. We generated the numerical symptom (medicine) embeddings and divided them into seven communities (syndromes) using the combination of Skip-Gram model and Spectral Clustering (SC) algorithm. After analyzing the symptoms and medicine networks, we identified the key factors using six evaluation metrics of node centrality. The experimental results indicate that the proposed analysis model is capable of discovering the critical symptoms and symptom distribution for diagnosis; the key medicines and medicine combinations for treatment. Based on the latest COVID-19 clinical guidelines, this model could result in the higher accuracy results than the other representative clustering algorithms. Furthermore, the proposed model is able to provide tremendously valuable guidance and help the physicians to combat the COVID-19.

Comparative study of heat transfer and thermal damage assessment models for hyperthermia treatment

Appropriate heating of the tumor can ablate tumor cells with minimal damage to healthy tissue and low side effects to the patient. Therefore, it is important to estimate power dissipation requirement and predict thermal damage in tumor before hyperthermia treatment. This work applied a mathematical model on heat transfer in two-layered spherical tissue to predict the temperature profile within hyperthermia domain. The present bioheat transfer problem was analyzed based on the Pennes equation, the thermal wave and dual-phase lag modes in order to explore the effect of analysis mode on the power dissipation requirement. The Arrenius equation, the modified thermal damage model with regeneration term, and the equivalent thermal dose equation were used to evaluate the thermal damage and discuss their effects on thermal damage prediction. The computation results show that the model of bioheat transfer and the non-Fourier effect significantly affects the power dissipation requirement. The damage parameter value predicted by the modified thermal damage model with regeneration term seems to have a limit value of Ω = 1. The results imply that the regeneration of biological tissue can prevent the tissue from thermal damage, the equivalent thermal dose equation is more related to heating time, and the Arrenius equation is more related to heating temperature.

Compressed sensing of large-scale local field potentials using adaptive sparsity analysis and Non-convex Optimization

OBJECTIVE

Energy consumption is a critical issue in resource-constrained wireless neural recording applications with limited data bandwidth. Compressed sensing (CS) has emerged as a powerful framework in addressing this issue owing to its highly efficient data compression procedure. In this paper, a CS-based approach termed Simultaneous Analysis Non-Convex Optimization (SANCO) is proposed for large-scale, multi-channel local field potentials (LFPs) recording.

APPROACH

The SANCO method consists of three parts: (1) the analysis model is adopted to reinforce sparsity of the multi-channel LFPs, therefore overcoming the drawbacks of conventional synthesis models. (2) An optimal continuous order difference matrix is constructed as the analysis operator, enhancing the recovery performance while saving both computational resources and data storage space. (3) A non-convex optimizer that can by efficiently solved with alternating direction method of multipliers (ADMM) is developed for multi-channel LFPs reconstruction.

MAIN RESULTS

Experimental results on real datasets reveal that the proposed approach outperforms state-of-the-art CS methods in terms of both recovery quality and computational efficiency.

SIGNIFICANCE

Energy efficiency of the SANCO make it an ideal candidate for resource-constrained, large scale wireless neural recording. Particularly, the proposed method ensures that the key features of LFPs had little degradation even when data are compressed by 16x, making it very suitable for long term wireless neural recording applications.