Identification of Cirrhosis Subtypes Through Heterogeneous Medical Information Network

Background:Liver cirrhosis is a complex and heterogeneous disease,with a mortality rate of up to 57%,resulting in 1.03 million deaths per year.The prevalence of liver cirrhosis is on the rise.Patients with liver cirrhosis have a variety of clinical phenotypes and are prone to various complications related to liver cirrhosis.Therefore,there is an urgent need to improve the early prevention and clinical management of cirrhosis and its complications.Methods:We use a precise medical approach to analyze and characterize the complex manifestations of cirrhotic patient populations,and we propose a Heterogeneous Medical Record Network(HEMnet)that includes electronic medical records,molecular interaction networks,and domain knowledge.We train the network embedding vector on HEMnet to obtain the low-dimensional vector representation of each node.With these vectors,we enriched the original medical record and identified six subtypes of cirrhosis.Results:Subtype 1 is characterized by heart disease,and subtype 2 has the strongest association with metabolic-related diseases.Subtype 3 was characterized by Chronic gastritis diseases.Subtype 4 was characterized by Liver cirrhosis-related complications-serous effusion.Subtype 5 had the strongest association with hepatitis-cirrhosis-related complications diseases and gallbladder disease.Subtype 6 was most strongly associated with Liver cirrhosis-related complications and hepatic carcinoma.By assessing the human disease-gene association of each subtype,the rich phenotype and biological functions of each subtype at the gene level were matched to the disease comorbidities and clinical differences we identified through EHR.Conclusion:Our approach demonstrates the utility of applying a precision medicine paradigm to cirrhosis and the prospect of extending this approach to other complexes,multifactorial diseases.

Classification of metabolic-associated fatty liver disease subtypes based on TCM clinical phenotype

Objective:To classify the subtypes of metabolic-associated fatty liver disease(MAFLD)and provide new insights into the heterogeneity of MAFLD.Methods:Electronic medical records(EMR)of MAFLD diagnosed in accordance with the diagnostic criteria of Hubei Provincial Hospital of Traditional Chinese Medicine from 2016-2020 were included in the study.for physical annotation,and the data on each clinical phenotype was normalized according to corresponding aspirational standards.The MAFLD heterogeneous medical record network(HEMnet)was constructed using sex,age,disease diagnosis,symptoms,and Western medicine prescriptions as nodes and the co-occurrence times between phenotypes as edges.K-means clustering was used for disease classification.Relative risk(RR)was used to assess the specificity of each phenotype.Statistical methods were used to compare differences in laboratory indicators among subtypes.Results:A total of patients(12,626)with a mean age of 55.02(±14.21)years were included in the study.MAFLD can be divided into five subtypes:digestive diseases(C0),mental disorders and gynecological diseases(C1),chronic liver diseases and decompensated complications(C2),diabetes mellitus and its complications(C3),and immune joint system diseases(C4).Conclusions:Patients with MAFLD experience various symptoms and complications.The classification of MAFLD based on the HEMnet method is highly reliable.

iBole： A Hybrid Multi-Layer Architecture for Doctor Recommendation in Medical Social Networks

In this paper, we try to systematically study how to perform doctor recommendation in medical social net- works （MSNs）. Specifically, employing a real-world medical dataset as the source in our work, we propose iBole, a novel hybrid multi-layer architecture, to solve this problem. First, we mine doctor-patient relationships/ties via a time-constraint probability factor graph model （TPFG）. Second, we extract network features for ranking nodes. Finally, we propose RWR- Model, a doctor recommendation model via the random walk with restart method. Our real-world experiments validate the effectiveness of the proposed methods. Experimental results show that we obtain good accuracy in mining doctor-patient relationships from the network, and the doctor recommendation performance is better than that of the baseline algorithms： traditional Ranking SVM （RSVM） and the individual doctor recommendation model （IDR-Model）. The results of our RWR-Model are more reasonable and satisfactory than those of the baseline approaches.

An End-to-End Authentication Scheme for Healthcare IoT Systems Using WMSN

The healthcare internet of things(IoT)system has dramatically reshaped this important industry sector.This system employs the latest technology of IoT and wireless medical sensor networks to support the reliable connection of patients and healthcare providers.The goal is the remote monitoring of a patient’s physiological data by physicians.Moreover,this system can reduce the number and expenses of healthcare centers,make up for the shortage of healthcare centers in remote areas,enable consultation with expert physicians around the world,and increase the health awareness of communities.The major challenges that affect the rapid deployment and widespread acceptance of such a system are the weaknesses in the authentication process,which should maintain the privacy of patients,and the integrity of remote medical instructions.Current research results indicate the need of a flexible authentication scheme.This study proposes a scheme with enhanced security for healthcare IoT systems,called an end-to-end authentication scheme for healthcare IoT systems,that is,an E2EA.The proposed scheme supports security services such as a strong and flexible authentication process,simultaneous anonymity of the patient and physician,and perfect forward secrecy services.A security analysis based on formal and informal methods demonstrates that the proposed scheme can resist numerous security-related attacks.A comparison with related authentication schemes shows that the proposed scheme is efficient in terms of communication,computation,and storage,and therefore cannot only offer attractive security services but can reasonably be applied to healthcare IoT systems.