Wyniki wyszukiwania - BazTech

1

Medical prescription classification: a NLP-based approach

Carchiolo Vincenza, Longheu Alessandro, Reitano Giuseppa, Zagarella Luca

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

605--609

EN

The digitization of healthcare data has been consolidated in the last decade as a must to manage the vast amount of data generated by healthcare organizations. Carrying out this process effectively represents an enabling resource that will improve healthcare services provision, as well as on-the-edge related applications, ranging from clinical text mining to predictive modelling, survival analysis, patient similarity, genetic data analysis and many others. The application presented in this work concerns the digitization of medical prescriptions, both to provide authorization for healthcare services or to grant reimbursement for medical expenses. The proposed system first extract text from scanned medical prescription, then Natural Language Processing and machine learning techniques provide effective classification exploiting embedded terms and categories about patient/- doctor personal data, symptoms, pathology, diagnosis and suggested treatments. A REST ful Web Service is introduced, together with results of prescription classification over a set of 800K+ of diagnostic statements.

2

Building compact language models for medical speech recognition in mobile devices with limited amount of memory

Sas J.

Journal of Medical Informatics & Technologies

|

2012

|

Vol. 20

111--119

EN

The article presents the method of building compact language model for speech recognition in devices with limited amount of memory. Most popularly used bigram word-based language models allow for highly accurate speech recognition but need large amount of memory to store, mainly due to the big number of word bigrams. The method proposed here ranks bigrams according to their importance in speech recognition and replaces explicit estimation of less important bigrams probabilities by probabilities derived from the class-based model. The class-based model is created by assigning words appearing in the corpus to classes corresponding to syntactic properties of words. The classes represent various combinations of part of speech inflectional features like number, case, tense, person etc. In order to maximally reduce the amount of memory necessary to store class-based model, a method that reduces the number of part-of-speech classes has been applied, that merges the classes appearing in stochastically similar contexts in the corpus. The experiments carried out with selected domains of medical speech show that the method allows for 75% reduction of model size without significant loss of speech recognition accuracy.

3

Metody analizy kognitywnej w medycznych systemach informacyjnych typu DSS

Ogiela L.D.

Computer Science

|

2005

|

Vol. 7

105-114

PL

W pracy wykazano, że metody sztucznej inteligencji, a w szczególnosci mechanizmy lingwistyczne semantycznego wnioskowania znaczeniowego są możliwe do wykorzystania przy tworzeniu inteligentnych systemów informacyjnych, a także umożliwiają prowadzenie wnikliwej analizy znaczeniowej w prezentowanych systemach informacyjnych typu DSS. W pracy zostały przedstawione informatyczne mechanizmy opisu znaczeniowego obiektów na wybranych przykładach analizy obrazów rdzenia kręgowego. Procedury takiego wnioskowania semantycznego oparte są o model rezonansu kognitywnego i zostały zaaplikowane do zadania znaczeniowej interpretacji wybranego rodzaju zobrazowań diagnostycznych centralnego układu nerwowego jako modułu inteligentnej analizy w systemach informacyjnych. Prezentowana w pracy aplikacja ma charakter badawczy i służy opracowaniu skutecznych metod wykrywania poszukiwanych zmian na pewnym zbiorze danych pochodzących z badań magnetycznorezonansowych struktur rdzenia kręgowego.

EN

This paper demonstrates that AI methods, in particular linguistic mechanisms of semantic meaning reasoning can be applied to the development of intelligent IT systems. They enable also conducting an in-depth meaning analysis in the presented DDS information systems. This paper presents also IT mechanisms of object meaning description on selected examples of spinal cord image analysis. The procedures for such semantic reasoning are based on the model of cognitive resonance. They have been applied to the task of meaning interpretation of a selected type of central nervous system diagnostic images, as an intelligent analysis module in IT systems. The application presented in this paper is of research character and it serves the preparation of efficient lesion detection methods applied to a dataset originating from magnetic and resonance examinations of the spinal cord structures.