Predicting readmission risk from doctors' notes

11/29/2017

∙

We develop a model using deep learning techniques and natural language processing on unstructured text from medical records to predict hospital-wide 30-day unplanned readmission, with c-statistic .70. Our model is constructed to allow physicians to interpret the significant features for prediction.

READ FULL TEXT

Predicting readmission risk from doctors' notes

Natural Language Processing Methods to Identify Oncology Patients at High Risk for Acute Care with Clinical Notes

Smart Agriculture : A Novel Multilevel Approach for Agricultural Risk Assessment over Unstructured Data

Prediction Using Note Text: Synthetic Feature Creation with word2vec

Predicting Unplanned Readmissions with Highly Unstructured Data

Real-Time Prediction of the Duration of Distribution System Outages

Negation Detection for Clinical Text Mining in Russian

Deepr: A Convolutional Net for Medical Records

Predicting readmission risk from doctors' notes

Related Research

Natural Language Processing Methods to Identify Oncology Patients at High Risk for Acute Care with Clinical Notes

Smart Agriculture : A Novel Multilevel Approach for Agricultural Risk Assessment over Unstructured Data

Prediction Using Note Text: Synthetic Feature Creation with word2vec

Predicting Unplanned Readmissions with Highly Unstructured Data

Real-Time Prediction of the Duration of Distribution System Outages

Negation Detection for Clinical Text Mining in Russian

Deepr: A Convolutional Net for Medical Records