IDDAT: An Ontology-Driven Decision Support System for Infectious Disease Diagnosis and Therapy

Shen, Ying; Deng, Yang; Zhang, Jin; Li, Yaliang; Du, Nan; Fan, Wei; Yang, Min; Lei, Kai

doi:10.1109/icdmw.2018.00201

Cited by 4 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent years have witnessed many successful real-world applications of Knowledge Graph (KG) in the medical and health domain, such as medical diagnosis [24,26], disease classification [8] and drug-drug interaction learning [10,32]. A medical KG is composed of medical knowledge triples containing a head entity, a tail entity and the relation between them, and plays an indispensable role in medical knowledge representation and storage.…”

Section: Introductionmentioning

confidence: 99%

MedTruth: A Semi-supervised Approach to Discovering Knowledge Condition Information from Multi-Source Medical Data

Deng

Shen

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Knowledge Graph (KG) contains entities and the relations between entities. Due to its representation ability, KG has been successfully applied to support many medical/healthcare tasks. However, in the medical domain, knowledge holds under certain conditions. For example, symptom runny nose highly indicates the existence of disease whooping cough when the patient is a baby rather than the people at other ages. Such conditions for medical knowledge are crucial for decision-making in various medical applications, which is missing in existing medical KGs. In this paper, we aim to discovery medical knowledge conditions from texts to enrich KGs.Electronic Medical Records (EMRs) are systematized collection of clinical data and contain detailed information about patients, thus EMRs can be a good resource to discover medical knowledge conditions. Unfortunately, the amount of available EMRs is limited due to reasons such as regularization. Meanwhile, a large amount of medical question answering (QA) data is available, which can greatly help the studied task. However, the quality of medical QA data is quite diverse, which may degrade the quality of the discovered medical knowledge conditions. In the light of these challenges, we propose a new truth discovery method, MedTruth, for medical knowledge condition discovery, which incorporates prior source quality information into the source reliability estimation procedure, and also utilizes the knowledge triple information for trustworthy information computation. We conduct series of experiments on realworld medical datasets to demonstrate that the proposed method can discover meaningful and accurate conditions for medical knowledge by leveraging both EMR and QA data. Further, the proposed method is tested on synthetic datasets to validate its effectiveness under various scenarios.

show abstract

Section: Introductionmentioning

confidence: 99%

MedTruth: A Semi-supervised Approach to Discovering Knowledge Condition Information from Multi-Source Medical Data

Deng

Shen

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Survey of Various Statistical Numerical and Machine Learning Ontological Models on Infectious Disease Ontology

Natarajan¹,

Kannan²,

Mohanty

2021

Data Analytics in Bioinformatics

View full text Add to dashboard Cite

Design of a blockchain-based secure and efficient ontology generation model for multiple data genres using augmented stratification in the healthcare industry

Purbey

Khandelwal

Choudhary³

2023

SIViP

View full text Add to dashboard Cite

Ontology generation is a process of relationship analysis, and representation for multiple data categories using automatic or semi-automatic approaches. This process requires a domain knowledgebase that describes given input data using entity-to-entity relations. A wide variety of approaches are proposed for this purpose, and each of them processes & converts input data using multiple relationship evaluation stages. These stages include data-preprocessing, correlation analysis, entity mapping, and ontology generation. A very few of these approaches are dataset independent, and most of them do not implement security measures during ontology generation, which limits their security, scalability & deployment capabilities during real-time implementation. Thus, in this text a blockchain based secure & e cient ontology generation model for multiple data genres using augmented strati cation (BOGMAS) is described. The BOGMAS model uses a semi-supervised approach for ontology generation from almost any structured or unstructured dataset. It uses a variance-based method (VBM) for reduction of redundant numerical features from the dataset, while textual features are converted to numerical values via standard word2vec model, and then processed using VBM. This model uses a combination of linear support vector machine (LSVM), and extra trees (ET) strati ers for variance estimation, which makes the model highly e cient, and reduces redundant features from the output ontology. These feature sets & their variances are given to a correlation engine for relationship estimation, and ontology generation.Each ontology record is secured using a mutable proof-of-work (PoW) based blockchain model, which assists in imbibing transparency, traceability, and distributed peer-to-peer processing capabilities. The generated ontology is represented using an incremental OWL (W3C Web Ontology Language) format, which assists in dynamically sizing the ontology depending upon incoming data. Performance of the proposed BOGMAS model is evaluated in terms of precision & recall of representation, memory usage, computational complexity, and accuracy of attack detection. It is observed that the proposed model is highly e cient in terms of precision, recall & accuracy performance, but has incrementally higher computational complexity & delay of ontology formation when compared with existing approaches. Due to this incremental increase in delay, the proposed model is observed to be applicable for a wide variety of real-time scenarios, which include but are not limited to, medical ontology generation, sports ontology generation, and internet of things (IoT) ontology generation with high security levels.

show abstract

IDDAT: An Ontology-Driven Decision Support System for Infectious Disease Diagnosis and Therapy

Cited by 4 publications

References 12 publications

MedTruth: A Semi-supervised Approach to Discovering Knowledge Condition Information from Multi-Source Medical Data

MedTruth: A Semi-supervised Approach to Discovering Knowledge Condition Information from Multi-Source Medical Data

Survey of Various Statistical Numerical and Machine Learning Ontological Models on Infectious Disease Ontology

Design of a blockchain-based secure and efficient ontology generation model for multiple data genres using augmented stratification in the healthcare industry

Contact Info

Product

Resources

About