Natural language processing and machine learning to enable automatic extraction and classification of patients’ smoking status from electronic medical records

  • Andrea Caccamisi Department of Learning, Informatics, Management and Ethics, Karolinska Institutet, Stockholm, Sweden; Department of Computer and Systems Sciences (DSV), Stockholm University, Stockholm, Sweden
  • Leif Jørgensen IQVIA Solutions Sweden AB, Solna, Sweden
  • Hercules Dalianis Department of Computer and Systems Sciences (DSV), Stockholm University, Stockholm, Sweden
  • Mats Rosenlund Department of Learning, Informatics, Management and Ethics, Karolinska Institutet, Stockholm, Sweden; IQVIA Solutions Sweden AB, Solna, Sweden
Keywords: Clinical informatics, electronic medical records, machine learning, natural language processing, smoking, text mining

Abstract

Background: The electronic medical record (EMR) offers unique possibilities for clinical research, but some important patient attributes are not readily available due to its unstructured properties. We applied text mining using machine learning to enable automatic classification of unstructured information on smoking status from Swedish EMR data.

Methods: Data on patients’ smoking status from EMRs were used to develop 32 different predictive models that were trained using Weka, changing sentence frequency, classifier type, tokenization, and attribute selection in a database of 85,000 classified sentences. The models were evaluated using F-score and accuracy based on out-of-sample test data including 8500 sentences. The error weight matrix was used to select the best model, assigning a weight to each type of misclassification and applying it to the model confusion matrices. The best performing model was then compared to a rule-based method.

Results: The best performing model was based on the Support Vector Machine (SVM) Sequential Minimal Optimization (SMO) classifier using a combination of unigrams and bigrams as tokens. Sentence frequency and attributes selection did not improve model performance. SMO achieved 98.14% accuracy and 0.981 F-score versus 79.32% and 0.756 for the rule-based model.

Conclusions: A model using machine-learning algorithms to automatically classify patients’ smoking status was successfully developed. Such algorithms may enable automatic assessment of smoking status and other unstructured data directly from EMRs without manual classification of complete case notes.

Downloads

Download data is not yet available.
Published
2020-07-22
How to Cite
Caccamisi, A., Jørgensen, L., Dalianis, H., & Rosenlund, M. (2020). Natural language processing and machine learning to enable automatic extraction and classification of patients’ smoking status from electronic medical records. Upsala Journal of Medical Sciences, 125(4), 316–324. https://doi.org/10.1080/03009734.2020.1792010
Section
Original Articles