1. Detecting conversation topics in primary care office visits from transcripts of patient-provider interactions
- Author
-
Park, Jihyun, Kotzias, Dimitrios, Kuo, Patty, Logan, Robert L, Merced, Kritzia, Singh, Sameer, Tanana, Michael, Taniskidou, Efi Karra, Lafata, Jennifer Elston, Atkins, David C, Tai-Seale, Ming, Imel, Zac E, and Smyth, Padhraic
- Subjects
Clinical Research ,Bioengineering ,Health Services ,Generic health relevance ,Good Health and Well Being ,Aged ,Communication ,Datasets as Topic ,Humans ,Machine Learning ,Medical Records ,Middle Aged ,Natural Language Processing ,Neural Networks ,Computer ,Office Visits ,Physician-Patient Relations ,Primary Health Care ,Tape Recording ,classification ,supervised machine learning ,patient care ,communication ,Information and Computing Sciences ,Engineering ,Medical and Health Sciences ,Medical Informatics - Abstract
ObjectiveAmid electronic health records, laboratory tests, and other technology, office-based patient and provider communication is still the heart of primary medical care. Patients typically present multiple complaints, requiring physicians to decide how to balance competing demands. How this time is allocated has implications for patient satisfaction, payments, and quality of care. We investigate the effectiveness of machine learning methods for automated annotation of medical topics in patient-provider dialog transcripts.Materials and methodsWe used dialog transcripts from 279 primary care visits to predict talk-turn topic labels. Different machine learning models were trained to operate on single or multiple local talk-turns (logistic classifiers, support vector machines, gated recurrent units) as well as sequential models that integrate information across talk-turn sequences (conditional random fields, hidden Markov models, and hierarchical gated recurrent units).ResultsEvaluation was performed using cross-validation to measure 1) classification accuracy for talk-turns and 2) precision, recall, and F1 scores at the visit level. Experimental results showed that sequential models had higher classification accuracy at the talk-turn level and higher precision at the visit level. Independent models had higher recall scores at the visit level compared with sequential models.ConclusionsIncorporating sequential information across talk-turns improves the accuracy of topic prediction in patient-provider dialog by smoothing out noisy information from talk-turns. Although the results are promising, more advanced prediction techniques and larger labeled datasets will likely be required to achieve prediction performance appropriate for real-world clinical applications.
- Published
- 2019