Urgent.News

What's breaking now, across thousands of outlets.

AI

ChatGPT's translation of mental health questionnaires into Mandarin reveals inconsistent results

As more Asian New Zealanders report experiencing mental health challenges, a Te Whare Wānanga o Waitaha | University of Canterbury (UC) researcher is asking a critical question: Can artificial intelligence (AI) help bridge language barriers when human translation resources are limited?

ChatGPT's translation of mental health questionnaires into Mandarin reveals inconsistent results

A University of Canterbury researcher is investigating whether artificial intelligence (AI) can assist in translating mental health questionnaires into Mandarin Chinese for use in Aotearoa New Zealand. Dr. Wei Teng's study examined the effectiveness of ChatGPT in translating two widely used mental health screening instruments—the Kessler Psychological Distress Scale (K10) and the Patient Health Questionnaire-9 (PHQ-9)—into Mandarin.

These tools determine if someone is experiencing distress or depression, so inaccurate translations could impact clinical decisions. Teng, an accessibility advocate, conducted the research after discussions with community leaders who raised concerns about language barriers preventing Mandarin-speaking migrants from receiving adequate mental health support.

Teng found that while some existing Mandarin translations of these screening tools were available, they often felt overly formal or unnatural. To test if AI could produce more natural, empathetic translations, Teng provided ChatGPT with structured prompts that assigned it a professional role and specified tone requirements like being caring and clinically appropriate.

One particular prompt yielded more favorable results, indicating that AI could enhance translation quality when properly guided. However, the study also revealed a significant issue: inconsistency in the translations generated by ChatGPT. When different users ran the same prompt through their own free accounts, the outputs varied in tone and naturalness, highlighting the potential unreliability of AI-generated translations in clinical settings.

Since consistency is crucial in mental health screenings, Teng is now collaborating with AI researchers to explore ways to improve consistency through more deterministic prompting or customized models. While AI shows promise in this field, Teng emphasizes the importance of clinical oversight and interdisciplinary collaboration to ensure trust and cultural sensitivity are prioritized, especially when people's well-being is at stake.

Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at medicalxpress.com →

More in AI

More from Friday 20 November →