ABSTRACT
BACKGROUND: Automatic speech recognition (ASR) technology is increasingly being used for transcription in clinical contexts. Although there are numerous transcription services using ASR, few studies have compared the word error rate (WER) between different transcription services among different diagnostic groups in a mental health setting. There has also been little research into the types of words ASR transcriptions mistakenly generate or omit. OBJECTIVE: This study compared the WER of 3 ASR transcription services (Amazon Transcribe [Amazon.com, Inc], Zoom-Otter AI [Zoom Video Communications, Inc], and Whisper [OpenAI Inc]) in interviews across 2 different clinical categories (controls and participants experiencing a variety of mental health conditions). These ASR transcription services were also compared with a commercial human transcription service, Rev (Rev.Com, Inc). Words that were either included or excluded by the error in the transcripts were systematically analyzed by their Linguistic Inquiry and Word Count categories. METHODS: Participants completed a 1-time research psychiatric interview, which was recorded on a secure server. Transcriptions created by the research team were used as the gold standard from which WER was calculated. The interviewees were categorized into either the control group (n=18) or the mental health condition group (n=47) using the Mini-International Neuropsychiatric Interview. The total sample included 65 participants. Brunner-Munzel tests were used for comparing independent sets, such as the diagnostic groupings, and Wilcoxon signed rank tests were used for correlated samples when comparing the total sample between different transcription services. RESULTS: There were significant differences between each ASR transcription service's WER (P<.001). Amazon Transcribe's output exhibited significantly lower WERs compared with the Zoom-Otter AI's and Whisper's ASR. ASR performances did not significantly differ across the 2 different clinical categories within each service (P>.05). A comparison between the human transcription service output from Rev and the best-performing ASR (Amazon Transcribe) demonstrated a significant difference (P<.001), with Rev having a slightly lower median WER (7.6%, IQR 5.4%-11.35 vs 8.9%, IQR 6.9%-11.6%). Heat maps and spider plots were used to visualize the most common errors in Linguistic Inquiry and Word Count categories, which were found to be within 3 overarching categories: Conversation, Cognition, and Function. CONCLUSIONS: Overall, consistent with previous literature, our results suggest that the WER between manual and automated transcription services may be narrowing as ASR services advance. These advances, coupled with decreased cost and time in receiving transcriptions, may make ASR transcriptions a more viable option within health care settings. However, more research is required to determine if errors in specific types of words impact the analysis and usability of these transcriptions, particularly for specific applications and in a variety of populations in terms of clinical diagnosis, literacy level, accent, and cultural origin.
ABSTRACT
PURPOSE: To evaluate visual acuity and contrast sensitivity after bilateral implantation of AcrySof® IQ ReSTOR® +2.50 D or +3.00 D. METHODS: A total of 56 eyes with cataract had bilateral implantation of a multifocal IOL. Inclusion criteria were corneal astigmatism less than 1.0 diopters, axial length between 22.0 and 24.0 mm, and no associated ocular disease. Outcome measures recorded 12 months postoperatively were binocular uncorrected and corrected distance, intermediate and near visual acuities, and contrast sensitivity. Postoperative quality of life and patient satisfaction were assessed with the VF-14 Questionnaire. RESULTS: Twenty months postoperatively, the mean uncorrected and best-corrected distance visual acuities, UCIVA at 60 cm, and contrast sensitivity were similar in all two groups. UCNVA were better in the +3.00 IOL group than in the +2.50 D group. Patients reported good performance for visual tasks. CONCLUSION: Apodized multifocal IOLs seem a good compromise for non-spectacles life in elderly patients; our study indicates that this solution has a good long-term stability on patients' visual function.
Subject(s)
Cataract/physiopathology , Contrast Sensitivity/physiology , Lens Implantation, Intraocular , Multifocal Intraocular Lenses , Phacoemulsification , Visual Acuity/physiology , Aged , Female , Follow-Up Studies , Humans , Male , Middle Aged , Patient Satisfaction , Quality of LifeABSTRACT
PURPOSE: To compare the visual acuity and contrast sensitivity in eyes with the AcrySof ReSTOR multifocal intraocular lens (IOL) (Alcon) and eyes with the monofocal AcrySof SA60AT IOL. SETTING: Policlinico Umberto I, Department of Ophthalmology, Rome, and private clinical practice, Rome, Italy. METHODS: One hundred eyes had phacoemulsification cataract extraction and implantation of a ReSTOR multifocal IOL in the capsular bag. Inclusion criteria were corneal astigmatism less than 1.5 diopters (D), myopia less than 4.0 D, and no associated ocular disease. A complete ophthalmic examination, including uncorrected visual acuity, best spectacle-corrected visual acuity, and contrast sensitivity, was performed 6 months postoperatively. Results were compared with those in 40 eyes with the AcrySof monofocal IOL single-piece IOL. RESULTS: In the multifocal group, 90 eyes (90%) had an uncorrected distance visual acuity of 20/25 or better (logMAR<0.10) and an uncorrected near visual acuity at 35 cm of J3 or better (logMAR 0.14). The multifocal group and monofocal group had similar distance uncorrected and best corrected visual acuities; however, the multifocal group had significantly better near uncorrected acuity. The mean contrast sensitivity values were 18.28 dB (static program) and 17.95 dB (dynamic program) in the multifocal group and 19.18 dB (static program) and 21.2 dB (dynamic program) in the monofocal group. CONCLUSIONS: The ReSTOR multifocal IOL provided a satisfactory full range of vision; 92% of the patients achieved total spectacle independence. Contrast sensitivity was lower than with the SA60AT monofocal IOL.
