Marianna Kong

Rationale: Socioeconomically disadvantaged patients with asthma and/or chronic obstructive pulmonary disease (COPD) face barriers to evidence-based care that are difficult to overcome in health care settings with limited resources. Objectives: Evaluate the efficacy of a pulmonary-specialist-health coach consultation model (intervention) for patients with asthma and/or COPD, relative to usual care (control). Methods: Randomized-controlled trial of 16 weeks of intervention versus control for adult English- or Spanish-speaking, low-income patients. Intervention: a lay health coach gathered information from the patient and medical record for remote review by a pulmonary specialist, who provided general recommendations to the primary care clinician. The coach supported implementation of recommendations. Measurements: Primary outcomes were receipt of guideline-based care and medications. Secondary outcomes were receipt of chronic lung disease education, breathing-related quality of life and symptoms, patient-rated quality of care, and adherence to inhaler therapy. Longitudinal models for count data were used to estimate Intervention: Control relative rates. Parallel models for continuous data estimated relative means. Main results: 165 intervention participants received 1.61-fold more guideline-based care than 163 control participants (relative ratio; CI: 1.37-1.90). They were not more likely to receive guideline-based medications in planned analysis using a pooled baseline rate, although post-hoc analysis using arm-specific baseline rates found significant improvement. Intervention patients received more chronic lung disease education and reported greater improvements in breathing-related quality of life, symptoms, and patient-reported quality of care. Conclusions: This intervention offers a scalable approach to improve uptake of clinical guidelines in resource-limited primary care practices managing most asthma and COPD care.

Introduction Machine translation of patient-specific information could mitigate language barriers if sufficiently accurate and non-harmful and may be particularly useful in healthcare encounters when professional translators are not readily available. We evaluated the translation accuracy and potential for harm of ChatGPT-4 and Google Translate in translating from English to Spanish, Chinese and Russian. Methods We used ChatGPT-4 and Google Translate to translate 50 sets (316 sentences) of deidentified, patient-specific, clinician free-text emergency department instructions into Spanish, Chinese and Russian. These were then back-translated into English by professional translators and double-coded by physicians for accuracy and potential for clinical harm. Results At the sentence level, we found that both tools were ≥90% accurate in translating English to Spanish (accuracy: GPT 97%, Google Translate 96%) and English to Chinese (accuracy: GPT 95%; Google Translate 90%); neither tool performed as well in translating English to Russian (accuracy: GPT 89%; Google Translate 80%). At the instruction set level, 16%, 24% and 56% of Spanish, Chinese and Russian GPT-translated instruction sets contained at least one inaccuracy. For Google Translate, 24%, 56% and 66% of Spanish, Chinese and Russian translations contained at least one inaccuracy. The potential for harm due to inaccurate translations was ≤1% for both tools in all languages at the sentence level and ≤6% at the instruction set level. GPT was significantly more accurate than Google Translate in Chinese and Russian at the sentence level; the potential for harm was similar. Conclusion These results support the potential of machine translation tools to mitigate gaps in translation services for low-stakes written communication from English to Spanish, while also strengthening the case for caution and for professional oversight in non-low-risk communication. Further research is needed to evaluate machine translation for other languages and more technical content.