Cloud Infrastructure for Creation of Interpretable Diagnostic Knowledge Bases of Diseases Regardless their Etiology

Abstract

The paper presents a cloud infrastructure for creation of interpretable diagnostic knowledge bases for intelligent decision support systems in medicine. An ontology of medical diagnostics allows us to form diseases regardless their etiology as a multivariate developing internal process. The relations types being defined in the ontology allow users to create a knowledge base sufficient for search of hypotheses of possible single diagnoses, for detection of combined and complicated pathologies, and for reduction of a set of hypotheses of diagnosis. The offered infrastructure includes the following tools: the knowledge base editor being generated on ontology, the terminology database editor, the tool for estimation of knowledge base quality and some instruments of automation of development and improvement of knowledge base. The infrastructure is implemented on the IACPaaS platform and used by experts to create knowledge bases in various fields of medicine. The article is useful for developers of medical diagnostics systems.

Ontology of anomalous processes diagnosis

“…43,44 Their long-term use in intelligent systems has led to the construction of a universal ontology of medical diagnosis and the creation of a task solver based on it. 45 Currently, the ontology is implemented on the IACPaaS platform 34 and is available upon request to all interested users. The presence of the KB editor control by the ontology (with several types of interfaces) makes the process of creating KBs simple and understandable for both knowledge engineers and domain experts.…”

“…So, diagnosis models of various diseases were developed by our team, 36‐42 then the developed models were generalized and the ontology of acute diseases and the ontology of chronicle diseases were developed on their basis 43,44 . Their long‐term use in intelligent systems has led to the construction of a universal ontology of medical diagnosis and the creation of a task solver based on it 45 …”

An Intelligent System for Medical Decision Support in Differential Diagnosis and Treatment of COVID-19

“…The "Knowledge Base of Viral Diseases" contains a description of COVID-19, influenza, parainfluenza, numerous infections (acute respiratory, adenovirus, rhinovirus, and others). It is formed in accordance with the ontology that determines the causal relationships of diseases used in medical diagnostics with the dynamics of external manifestations [23] and in accordance with clinical recommendations and methodological guidelines of the Russian Ministry of Health [5,14,24]. The description of each disease includes a code according to the International Classification of Diseases of the 10th revision (ICD-10), causes, risk factors, a necessary condition or event that led to the onset of the disease, a number of symptom complexes, and a detailed diagnosis.…”

“…Among them are key fields for prescribing treatment such as pharmacological properties, pharmacological action, contraindications, method of administration and doses, interaction with other drugs, etc. The developed ontology of the pharmacological guide is intended to describe in a formal, rather than textual form, all the necessary structural units of the drug [23]. The ontology made it possible to generate a knowledge base that includes 8000 concepts.…”