ABSTRACT
OBJECTIVE: To evaluate the performance of commercial automatic speech recognition (ASR) systems on d/Deaf and hard-of-hearing (d/Dhh) speech. METHODS: A corpus containing 850 audio files of d/Dhh and normal hearing (NH) speech from the University of Memphis Speech Perception Assessment Laboratory was tested on four speech-to-text application program interfaces (APIs): Amazon Web Services, Microsoft Azure, Google Chirp, and OpenAI Whisper. We quantified the Word Error Rate (WER) of API transcriptions for 24 d/Dhh and nine NH participants and performed subgroup analysis by speech intelligibility classification (SIC), hearing loss (HL) onset, and primary communication mode. RESULTS: Mean WER averaged across APIs was 10 times higher for the d/Dhh group (52.6%) than the NH group (5.0%). APIs performed significantly worse for "low" and "medium" SIC (85.9% and 46.6% WER, respectively) as compared to "high" SIC group (9.5% WER, comparable to NH group). APIs performed significantly worse for speakers with prelingual HL relative to postlingual HL (80.5% and 37.1% WER, respectively). APIs performed significantly worse for speakers primarily communicating with sign language (70.2% WER) relative to speakers with both oral and sign language communication (51.5%) or oral communication only (19.7%). CONCLUSION: Commercial ASR systems underperform for d/Dhh individuals, especially those with "low" and "medium" SIC, prelingual onset of HL, and sign language as primary communication mode. This contrasts with Big Tech companies' promises of accessibility, indicating the need for ASR systems ethically trained on heterogeneous d/Dhh speech data. LEVEL OF EVIDENCE: 3 Laryngoscope, 2024.
ABSTRACT
To fuel artificial intelligence (AI) potential in clinical practice in otolaryngology, researchers must understand its epistemic limitations, which are tightly linked to ethical dilemmas requiring careful consideration. AI tools are fundamentally opaque systems, though there are methods to increase explainability and transparency. Reproducibility and replicability limitations can be overcomed by sharing computing code, raw data, and data processing methodology. The risk of bias can be mitigated via algorithmic auditing, careful consideration of the training data, and advocating for a diverse AI workforce to promote algorithmic pluralism, reflecting our population's diverse values and preferences.
ABSTRACT
BACKGROUND: Inflammation may promote atrial fibrillation (AF) recurrence after catheter ablation. This study aimed to evaluate a short-term anti-inflammatory treatment with colchicine following ablation of AF. METHODS: Patients scheduled for ablation were randomized to receive colchicine 0.6 mg twice daily or placebo for 10 days. The first dose of the study drug was administered within 4 hours before ablation. Atrial arrhythmia recurrence was defined as AF, atrial flutter, or atrial tachycardia >30 s on two 14-day Holters performed immediately and at 3 months following ablation. RESULTS: The modified intention-to-treat population included 199 patients (median age, 61 years; 22% female; 70% first procedure) who underwent radiofrequency (79%) or cryoballoon ablation (21%) of AF. Antiarrhythmic drugs were prescribed at discharge in 149 (75%) patients. Colchicine did not prevent atrial arrhythmia recurrence at 2 weeks (31% versus 32%; hazard ratio [HR], 0.98 [95% CI, 0.59-1.61]; P=0.92) or at 3 months following ablation (14% versus 15%; HR, 0.95 [95% CI, 0.45-2.02]; P=0.89). Postablation chest pain consistent with pericarditis was reduced with colchicine (4% versus 15%; HR, 0.26 [95% CI, 0.09-0.77]; P=0.02) and colchicine increased diarrhea (26% versus 7%; HR, 4.74 [95% CI, 1.95-11.53]; P<0.001). During a median follow-up of 1.3 years, colchicine did not reduce a composite of emergency department visit, cardiovascular hospitalization, cardioversion, or repeat ablation (29 versus 25 per 100 patient-years; HR, 1.18 [95% CI, 0.69-1.99]; P=0.55). CONCLUSIONS: Colchicine administered for 10 days following catheter ablation did not reduce atrial arrhythmia recurrence or AF-associated clinical events, but did reduce postablation chest pain and increase diarrhea.