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

TL;DR

This study develops and evaluates NLP algorithms, especially a CNN-LSTM model, to improve diagnosis accuracy from transcription reports, thereby enhancing clinical efficiency and reducing medical errors.

Contribution

Introduces a CNN-LSTM NLP model integrated into a web platform for accurate diagnosis from unstructured reports, advancing clinical decision support tools.

Findings

CNN-LSTM achieved 97.89% accuracy

Web platform facilitates accessible clinical assistance

Standardizing reports improves diagnostic consistency

Abstract

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