AUTOMATIC WRITING OF CARDIOLOGIC REPORTS BY A VOICE RECOGNITION SYSTEM

Computer systems that can convert spoken text into written text have r ecently become available, In one such system the phonetics of spoken w ords are compared with those of 32 000 stored words, with a statistica l program helping to choose the word with the highest probability of b eing correct. We evaluated the practicability of the IBM VoiceType sys tem for writing medical reports using a cardiologic vocabulary. A tota l of 200 medical documents were generated with a mean of 301 +/- 52 wo rds. In the mean, 12 +/- 5 words were falsely recognized in each docum ent, resulting in a rate of correct recognition of 95.1 +/- 2.5%. It i s possible to correct a falsely recognized word by choosing an alterna tive word from a provided list, which worked in our case in 51% (6.1 /- 2.8 words in each document), Correction of falsely recognized words had to be done by manual input 49%, of the time (5.9 +/- 2.9 words in each document). The mean time demand for word correction amounted to 57 +/- 15 s for each document, whereas correction by manual input need ed more time (37 +/- 14 s) than choosing from a list of alternative wo rds (20 +/- 4 s). A requirement for use of the Voice Type system is a reduced speech rate. Dictation of our documents took on average 260 s when done with a normal speech rate, and 400 s when done at a reduced speech rate. In conclusion, automatic writing of cardiologic reports c an be done easily and with a low failure rate using the IBM VoiceType system with a cardiologic vocabular. It takes about 3 min longer to cr eate a medical text 1 1/2, pages long which is free of mistakes by usi ng the VoiceType system than to simply dictate the text. Time can be s aved by eliminating the need to check a preliminary report. The major advantage of automated reporting is that the written report is immedia tely available. For each discipline, specific vocabularies should be v alidated.