Using a Cellular Automaton to Extract Medical Information from Clinical Reports

Abstract

Abstract-An important amount of clinical data concerning the medical history of a patient is in the form of clinical reports that are written by doctors. They describe patients, their pathologies, their personal and medical histories, findings made during interviews or during procedures, and so forth. They represent a source of precious information that can be used in several applications such as research information to diagnose new patients, epidemiological studies, decision support, statistical analysis, and data mining. But this information is difficult to access, as it is often in unstructured text form. To make access to patient data easy, our research aims to develop a system for extracting information from unstructured text. In a previous work, a rule-based approach is applied to a clinical reports corpus of infectious diseases to extract structured data in the form of named entities and properties. In this paper, we propose the use of a Boolean inference engine, which is based on a cellular automaton, to do extraction. Our motivation to adopt this Boolean modeling approach is twofold: first optimize storage, and second reduce the response time of the entities extraction.

Lattice-Cell : Hybrid Approach for Text Categorization

“…Once the preprocessing step completed we obtain a vector representation with binary weighting for the 9 documents presented in table 1, which will represent the formal context. [18,19] is a cellular Automaton that is made of two finite arbitrary long layers of finite state machines (cells) that are all identical. The operation of the system is synchronous, and the state of each cell at time t+1 depends only on the state of its vicinity cells, and on its own state at time t. This automaton, simulates the functioning of the basic cycle of an inference engine by using two finite layers of finite automata.…”

Planning by Case-Based Reasoning Based on Fuzzy Logic

“…The dynamics of the cellular automaton BIG [1,23], to simulate the operation of an Inference engine uses two functions of transitions δ fact and δ rule , where δ fact corresponds to the phase of assessment, selection and filtering, and δ rule corresponds to the execution phase [1,24]. To set the two functions of transition we will adopt the following notation: EF, IF and SF to designate CELFACT_E, _I and _S; Respectively ER, IR and SR to designate CELRULE_E, _I and _S.…”

“…Suppose that G = {G0, G1,..., Gq} is the set of Boolean PLC configurations. Discrete developments plc, from one generation to another, is defined by the sequence G0, G1,..., Gq, where Gi+1=∆(Gi) [1,23,24].…”

“…In this section, we present the principles of construction, by Boolean modelling [1,5,9,23,24], of induction graphs in the problems of discrimination and classification [1,2] : we want to explain the class taken by one variable to predict categorical Y, attribute class or endogenous variable; from a series of variables X 1 , X 2 ,..., X p , say variable predictive (descriptors) or exogenous, discrete or continuous. According to the terminology of machine learning, we are therefore in the context of supervised learning.…”

Using Local Grammar for Entity Extraction from Clinical Reports

“…Secondly, most existing medical entities extraction systems are devoted to English. Research in the French language is still at its initial stages [2].…”