Evaluation de l’efficacité des logiciels de prédiction de mots sur la vitesse de saisie de texte sur l’outil informatique pour les personnes blessées médullaires cervicaux

摘要

The main objective of this work was to study the influence of key settings of word predictionsoftware as well as a training program on the use of word prediction, on text input speed in personswith cervical spinal cord injury.Study 1 determined text input speed in persons with cervical spinal cord injury and the influence ofpersonal characteristics and type of computer device on text input speed. Study 2 evaluated theeffect of a dynamic virtual keyboard coupled with word prediction software on text input speed inpersons with functional tetraplegia. Study 3 analysed the word prediction software settingscommonly prescribed by health-related professionals for people with cervical spinal cord injury.Studies 4 and 5 evaluated the influence of the number of words displayed in the prediction list andthe frequency of use setting on text input speed. Finally, study 6 evaluated the influence of a trainingprogram on the use of word prediction software for persons with cervical spinal cord injury on textinput speed.The results showed that only the type of computer device influenced text input speed; voicerecognition software increased the text input speed of persons with cervical spinal cord injury to thatof able-bodied people using a standard keyboard. The influence of the different word predictionsoftware settings (number of words displayed in the prediction list and the frequency of use) on textinput speed, the number of errors or comfort of use, differed depending on the level of injury. Wealso found differences between the perception of the importance of some settings by healthprofessionalsand data in the literature regarding the optimization of settings. Moreover, althoughsome parameters were considered as very important, they were rarely configured. Finally, trainingpersons with cervical spinal cord injury in the use of word prediction software increased text inputspeed.The results of this work highlighted that word prediction software settings influence text input speedin persons with cervical spinal cord injury, however not all professionals are aware of this.Information should therefore be disseminated through professional networks. Further studies shouldaim to improve word prediction software and should also focus on new devices such as tablets andvoice recognition software. Persons with cervical spinal cord injury training programs in the use ofword prediction software need to be developed and validated.