Evaluating Embeddings for One-Shot Classification of Doctor-AI Consultations
This work addresses the challenge of enhancing doctor-AI communication in healthcare, but it is incremental as it applies existing embeddings to a new domain without introducing novel methods.
The paper tackled the problem of classifying doctor-written and AI-generated texts in healthcare consultations using various embeddings and one-shot classification systems, finding that Word2Vec, GloVe, character n-grams, and GPT2 embeddings performed well in capturing semantic features and improving communication quality when training data is scarce.
Effective communication between healthcare providers and patients is crucial to providing high-quality patient care. In this work, we investigate how Doctor-written and AI-generated texts in healthcare consultations can be classified using state-of-the-art embeddings and one-shot classification systems. By analyzing embeddings such as bag-of-words, character n-grams, Word2Vec, GloVe, fastText, and GPT2 embeddings, we examine how well our one-shot classification systems capture semantic information within medical consultations. Results show that the embeddings are capable of capturing semantic features from text in a reliable and adaptable manner. Overall, Word2Vec, GloVe and Character n-grams embeddings performed well, indicating their suitability for modeling targeted to this task. GPT2 embedding also shows notable performance, indicating its suitability for models tailored to this task as well. Our machine learning architectures significantly improved the quality of health conversations when training data are scarce, improving communication between patients and healthcare providers.