Automatic speech recognition (ASR) systems often exhibit uneven performance across accents, raising concerns about fairness and bias. This study investigates the impact of model fine-tuning strategies on ASR performance and accent-related disparities. We conduct a controlled empirical evaluation of two adaptation approaches—single-step and two-step fine-tuning—using pretrained Whisper (small) and Wav2Vec2-XLSR-53 models on African-accented English speech from the AfriSpeech-200 dataset, covering Yoruba, Igbo, Swahili, and Hausa accents. Both fine-tuning strategies substantially reduced mean word error rate (WER) for all models. However, these improvements did not translate into consistent reductions in accent-related performance gaps. When analysed separately across general and clinical subsets, WER gaps often increased due to uneven gains across accents. Although two-step fine-tuning provided modest improvements over single-step adaptation, its impact on reducing disparities remained limited. These findings indicate that fine-tuning primarily optimises performance without effectively addressing systematic bias across speaker groups, even when models are specialised for individual accents. This highlights the limitations of per-accent specialisation as a practical bias mitigation strategy.

Understanding medical terminology is critical for effective patient-doctor communication, yet many patients struggle with complex jargon. This study compares Machine Learning (ML) models and Large Language Models (LLMs) in predicting medical term complexity as a means of improving doctor-patient communication. Using survey data from 252 participants rating 1,000 words along with various lexical features, we measured the accuracy of both model types. The results show that LLMs outperform traditional lexical-feature-based models, suggesting their potential to identify complex medical terms and lay the groundwork for personalised patient-doctor communication.