[Medical thyreological documentation adapted to computer data processing].

The PAPNET-system is a current example of automated technological progress in the pathological laboratory field. As the first Department of Pathology in Denmark, we have tested the applicability of this semi-automatical screening system in screening against cervical cancer. 3000 prospectively selected cervical smears were entered into the project. 1500 of these were first prescreened by the use of PAPNET and the negative slides were then manually rescreened. The remaining 1500 slides consisted of manually screened smears diagnosed as negative or inadequate. They were subsequently rescreened by the use of PAPNET. We only found one false negative smear in each group. Compared with histological follow-up the diagnoses CIN 1-3 were histologically confirmed in both groups. The PAPNET-assisted screening of cervical smears is faster, more valid and less fatiguing than the conventional screening method. Nevertheless, our results show no diagnostic quality improvement by the use of PAPNET. This is probably due to a strict screening procedure and a limited work load of a maximum of about 40-50 slides per cytotechnologist a day in our laboratory.

Diagnosis, Computer-Assisted↗

PubMed1998

[Computerized speech recognition-based endoscopic findings].

Discrete, Hidden Markov model based speech recognition and phoneme based speech synthesis techniques were applied for gastroscopy reporting and machine control. The authors developed a special program for grammatical analysis of the sentences. Altogether 100 patient findings were grammatically analysed. The sentences were grouped according to the topographical order of the investigation: oesophagus, cardia, fundus, corpus, antrum, pylorus, bulbus, postbulbar section, and the pathological findings: erosion, ulceration, malignancy. Speech samples from 3 deep voiced male investigators were collected. The recognition rate was above 95%. A simulation program was also developed for dictation and controlling of the different equipment (monitor, printer, video, endoscope) in the gastroscopy laboratory by speech recognition. Speech synthesis was applied for the evaluation of understanding. This module artificially synthesizes the answer of the system giving backup for the understood information. With additional developments the discrete word speech 'recognition' achieved the level of routine application in medical reporting. However, ready-to-use developments need the joint activity of speech technology and endoscopy industry with end-user teams.

Diagnosis, Computer-Assisted↗

PubMed1998

Spiral analysis: a new technique for measuring tremor with a digitizing tablet.

A new computational method for quantification of tremor and other aspects of motor dysfunction is described. By using a digitizing tablet connected to a microcomputer, this analysis is derived from the handwritten Archimedean spiral. This technique extends the standard clinical neurologic test of spiral drawing into an objective and accurate measure that can automatically detect, characterize, and quantify motor dysfunction in patients with movement disorders. Further, it is safe, inexpensive, fast, portable, noninvasive, and can be administered to a large cohort of patients without the need for wires or other attachments. Spiral data are collected in the X, Y, and pressure axes, providing virtual "triaxial" recordings. Spiral analysis is shown to be capable of assessing subtle motor abnormalities potentially indicative of clinical problems in their earliest stages, and thus allow the most rational forms of genetic testing, treatment, or prevention. Spiral analysis may be useful as an initial marker of clinical involvement or serve as an objective gauge of change after therapeutic intervention.

Diagnosis, Computer-Assisted↗