Accurate ICD-11 coding is critical for billing, medical studies, and software communications and documentation in a clinical environment. Manual coding is not reliable and consumes a lot of time. There is limited data in the Persian language for training a language model. As such, a language model with an English dataset and a pre-trained model has been used to map sentences in Persian to model language for predicting ICD-11 codes. This reduces the reliance on Persian language datasets and greatly improves prediction accuracy for Persian. In this paper, a technique utilizing pre-trained large language models (LLMs) for ICD-11 automation in terms of patient grievances extracted from the MIMIC-IV corpus is proposed. Prompt-based training is adopted in our model, and it obtains satisfactory performance with an average F1-score of 0.90 for ICD-11 prediction. We also demonstrate the usability of our model through output in JSON format for integration into medical tools.