Improving Clinical Efficiency and Reducing Medical Errors through NLP-enabled Diagnosis of Health Conditions from Transcription Reports

Misdiagnosis rates are one of the leading causes medical errors in hospitals, affecting over 12 million adults across US. To address high rate misdiagnosis, this study utilizes 4 NLP-based algorithms to determine appropriate health condition based on an unstructured transcription report. From Logistic Regression, Random Forest, LSTM, and CNNLSTM models, CNN-LSTM model performed best with accuracy 97.89%. We packaged into a authenticated web platform for accessible assistance clinicians. Overall, by standardizing care diagnosis structuring reports, our NLP drastically improves clinical efficiency hospitals worldwide.