PC-based medical transcription verification system

Date of Publication

2006

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Electronics and Communications Engineering

Subject Categories

Engineering

College

Gokongwei College of Engineering

Department/Unit

Electronics and Communications Engineering

Thesis Adviser

Edwin Sybingco

Defense Panel Member


Enrique M. Manzano
Leonard U. Ambata
Emmanuel A. Gonzalez

Abstract/Summary

Medical Transcription is a process in which a doctor hires a transcriptionist to transcribe the recorded audio of his patients' medical history, records, and diagnosis. However, due to several factors such as noisy recording environment, unclear pronunciation of words, and the complexity of the medical lexicon, the transcriptionists have difficulty in understanding and transcribing the audio. It is imperative that the transcriptions are error-free but doctors are too busy to check the work of the transcriptionists thus quality control poses as a problem in manual transcription.

The aim of this research is to utilize speech recognition techniques to create a software that would aid transcriptionists in transcribing medical audio. Based on the knowledge that phonemes are characterized by their unique features, the system used several algorithms including a phoneme recognition, statistical algorithm, and artificial intelligence to recognize indecipherable audio selected by the user on the assumption that the word is included in the system's database. Audio samples are acquired using a digital audio recorder that is connected to the computer via the USB port and are saved in .way format. Text files, on the other hand, are saved in .txt format. The GUI allows the user to view the audio's waveform, playback the audio, open and edit a text file, and select parts of the audio segment for recognition. Another aspect of the GUI scans the text file and verifies the medical terms in the file if they are also present in the system's database.

Abstract Format

html

Language

English

Format

Print

Accession Number

TU13797

Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

Physical Description

1 v. (various foliations) : ill. (some col.) ; 28 cm.

Keywords

Medical transcription--Technological innovations; Medical technology; Medical records--Data processing; Automatic speech recognition

This document is currently not available here.

Share

COinS