Transcribed Medical Records datasets for Machine Learning

Transcription of 257,977 hours of Real-world Physician Dictation from 31 specialties to train Healthcare Speech models. Transcribed medical records refers to transcription of physician and patient conversation, transcription of medical reports and medical assessment. It helps in mapping the medical history of the patient for future visits and also acts as a refence point for the doctors. It helps the doctor to evaluate the present condition of the patient and suggest a suitable treatment.

本数据集由257,977小时的现实世界医师语音记录构成，涵盖31个专业领域，旨在训练医疗语音模型。所转录的医疗记录包括医师与患者之间的对话、医学报告及医学评估的转录。该数据集有助于对患者病史进行映射，以备未来就诊之需，并作为医生诊疗的参考依据。此外，它还有助于医生评估患者的当前状况，并提出适宜的治疗建议。