A computer-assisted radiologic reporting system

A Radiologic Reporting System for Computer-Aided Diagnosis with Associated Database

A reporting system which assists radiologists reporting on medical images and calculates alternatives of probable diseases was developed with proven applicability for CT and ultrasonography. The diagnostic information found by radiologists in various types of images is managed as a database in the reporting system and is also transferred to a medical record database, the HIS (Hospital Information System) of Hokkaido University Hospital. The reporting system supports both data conversion and transfer to the host computer of the HIS. The system has processed about 20 000 reports over the last 5 years. Here we present the efficiency of producing reports, the structure of the database, and the hit ratio of calculated diagnoses in this system.

A framework for improving radiology reporting

The interpretative reports rendered by radiologists are the only tangible manifestation of their expertise, training, and experience. These documents are very often the primary means by which radiologists provide patient care. Radiology reports are extremely variable in form, content, and quality. The authors propose a framework for conceptualizing the reporting process and how it might be improved. This consists of standard language, a structured format, and consistent content. These attributes will be realized by modifying the clinical reporting process, including the creation, storage, transmission, and review of interpretative documents. The authors also point out that changes in training and evaluation must be a part of the process, because they are complementary to purely technical solutions.

A human friendly reporting and database system for brain PET analysis

We have developed a human friendly reporting and database system for clinical brain PET (Positron Emission Tomography) scans, which enables statistical data analysis on qualitative information obtained from image interpretation. Our system consists of a Brain PET Data (Input) Tool and Report Writing Tool. In the Brain PET Data Tool, findings and interpretations are input by selecting menu icons in a window panel instead of writing a free text. This method of input enables on-line data entry into and update of the database by means of pre-defined consistent words, which facilitates statistical data analysis. The Report Writing Tool generates a one page report of natural English sentences semi-automatically by using the above input information and the patient information obtained from our PET center's main database. It also has a keyword selection function from the report text so that we can save a set of keywords on the database for further analysis. By means of this system, we can store the data related to patient information and visual interpretation of the PET examination while writing clinical reports in daily work. The database files in our system can be accessed by means of commercially available databases. We have used the 4th Dimension database that runs on a Macintosh computer and analyzed 95 cases of 18F-FDG brain PET studies. The results showed high specificity of parietal hypometabolism for Alzheimer's patients.

Speech interfacing for diagnosis reporting systems: an overview

Automatic speech recognition has since long been seen as an ideal method for innovation in diagnosis reporting. Speech technology now seems on the verge of introducing (commercially) attractive systems. The selection of a good speech recogniser is only one consideration in system design. Interface aspects, error handling, reporting method and implementation in the daily working routine are interwoven with the selection of an appropriate speech recognition technique, and should therefore be determined first.

Explaining variation in radiologists' reporting times

This paper describes an investigation into the reasons for variation in the time taken by senior radiologists to complete radiological reports. An observational study of the reporting process at one UK hospital was undertaken for a 25 day period. An independent health service researcher observed the radiology reporting process and collected data on a variety of factors including the time taken to produce the report, the number and nature of all images viewed, the experience of the radiologist, and the number of disturbances that occurred. The nature of the variation in reporting time was explored using both simple comparative statistics and more sophisticated multiple regression techniques. Data were collected on 2345 report observations and the median report time was 117 s. This research provides the first empirical evidence for systematic variation in reporting time. The results confirm the importance of certain factors that were expected to explain report time variation. For example, the results indicate that report time tended to be significantly shorter in reporting sessions that were busy, and significantly longer when the radiologist was disturbed during the reporting process or was training juniors during a reporting session. More surprising were the results indicating that there was no significant difference in report time for reports categorized as urgent or "hot" and those categorized as less urgent or "cold", and that report time appeared to vary systematically depending on the day of the week and on the time of day.

RGSS-ID: an approach to new radiologic reporting system

RGSS-ID is a developmental computer system that applies artificial intelligence (AI) methods to a reporting system. The representation scheme called Generalized Finding Representation (GFR) is proposed to bridge the gap between natural language expressions in the radiology report and AI methods. The entry process of RGSS-ID is made mainly by selecting items; our system allows a radiologist to compose a sentence which can be completely parsed by the computer. Further RGSS-ID encodes findings into the expression corresponding to GFR, and stores this expression into the knowledge data base. The final printed report is made in the natural language.

Development and evaluation of a radiological reporting system for use with a personal computer

A computer-assisted radiological reporting system (CRRS) was developed for the efficient management and effective use of a database of radiological information. The system consists of a computer terminal linked to an HIS, a reporting console and a personal computer in the local area network of the radiology department, and a radiography care reader which transfers basic data on the patient from the HIS to the CRRS. The patient's name, hospital ID number, sex and date of birth, the department from which the patient has been referred, in-patient/out-patient status and the procedure needed are recorded on magnetic cards (radiography cards) issued to radiology patients. The system has been successfully used in all diagnostic procedures for 8 months: 16,300 reports have been printed out and stored. The system has made it possible to implement the complete radiological reporting procedure for clinical applications, and the required data can easily be retrieved and used. It has proved to be quite easy to use CRRS to obtain diagnostic histories, and the improved efficiency of the reporting procedure has enabled the cost of a clerk typist to be eliminated.

The use of microcomputers for data management in a large epidemiological survey

A data management system designed around microcomputers and commercial software packages was employed for a large epidemiological study. Management involved the tracking of subjects through several stages of the study and the generation of subject listings, personalized letters of invitation, daily worklists for the field teams, and a checklist for the laboratories. These processes were controlled using a continually updated subject data base which in final form provided the core of the management system for the collected data. Data management presented major problems because of the volume of data which were received from several sources over a period of months. A key feature to emerge was the importance of an accurate serial number on all items for which a check digit was employed. The system had a short development time and was found to be inexpensive and flexible and to cope easily with the demands made of it.

Application of microcomputers in the emergency department: experience with a computerized logbook

The regulations of the Joint Commission on Accreditation of Hospitals stipulate that every emergency department must maintain a control register or logbook of patients seen. The retrieval of handwritten logbook data characteristically is a slow and tedious task that is prone to error. A computerized logbook has been developed for use on personal microcomputers using an economical database management system. Each patient record consists of 16 fields, including basic identifying data, chief complaint, diagnosis, physicians involved, and disposition. The daily log of patients seen is a computer-generated printout containing nearly four times the number of patients per printed page as our handwritten log system. It is now possible to obtain listings of admissions, mortalities, daily radiographs, laboratory cultures, and physicians patient lists 24 hours a day. The system is a valuable resource in an emergency medicine residency, and allows our program to generate interesting case and radiograph listings. Research data can be obtained in a fraction of the time and with a fraction of the effort usually required by manual methods.