Medical information extraction with deep neural networks
Background. Electronic Health Records (EHRs) are the databases used by hospital and general practitioners to daily log all the information they record from patients (i.e. disorders, taken medications, symptoms, medical testsâ€¦). Most of the information held in EHRs is in the form of natural language text (written by the physician during each session with each patient), making it inaccessible for research. Unlocking all this information would bring a very significant advancement to biomedical research, multiplying the quantity and variety of scientifically usable data, which is the reason why major efforts have been relatively recently initiated towards this aim (e.g. I2B2 challenges https://www.i2b2.org/NLP/ or the UK-CRIS network of EHRs https://crisnetwork.co/uk-cris-programme)
Project. Recent Deep Neural Networks (DNN) architectures have shown remarkable results in traditionally unsolved NLP problems, including some Information Extraction tasks such as Slot Filling [Mesnil et al] and Relation Classification [dos Santos et al]. When transferring this success to EHRs, DNNs offer the advantage of not requiring well formatted text, while the problem remains of labelled data being scarce (ranging on the hundreds for EHRs, rather than the tens of thousands used in typical DNN studies). However, ongoing work in our lab has shown that certain extensions of recent NLP-DNN architectures can reproduce the typical remarkable success of DNNs in situations with limited labelled data (paper in preparation). Namely, incorporating interaction terms to feed forwards DNN architectures [Denil et al] can rise the performance of relation classification in I2B2 datasets from 0.65 F1 score to 0.90, while the highest performance previously reported with the same dataset was 0.74.
We therefore propose to apply DNNs to the problem of information extraction in EHRs, using I2B2 and UK-CRIS data as a testbed. More specifically, the DNNs designed and implemented by the student should be able to extract medically relevant information, such as prescribed drugs or diagnoses given to patients. This corresponds to some of the challenges proposed by I2B2 during recent years (https://www.i2b2.org/NLP/Medication/), and are objectives of high interest in UK-CRIS which have sometimes been addressed with older techniques such as rules [Iqbal et al, Jackson et al]. The student is free to use the extension of the feed forward DNN developed in our lab, or to explore other feed forwards or recurrent (e.g. RNN, LSTM or GRU) alternatives. The DNN should be implemented in Pythonâ€™s Keras, Theano, Tensorflow, or PyTorch.
G. Mesnil et al., Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding, IEEEACM Trans. Audio Speech Lang. Process. 23 (2015) 530â€“539. doi:10.1109/TASLP.2014.2383614.
C.N. dos Santos, B. Xiang, B. Zhou, Classifying Relations by Ranking with Convolutional Neural Networks, CoRR. abs/1504.06580 (2015). http://arxiv.org/abs/1504.06580.
M. Denil, A. Demiraj, N. Kalchbrenner, P. Blunsom, N. de Freitas, Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network, CoRR. abs/1406.3830 (2014). http://arxiv.org/abs/1406.3830.
E. Iqbal, R. Mallah, R.G. Jackson, M. Ball, Z.M. Ibrahim, M. Broadbent, O. Dzahini, R. Stewart, C. Johnston, R.J.B. Dobson, Identification of Adverse Drug Events from Free Text Electronic Patient Records and Information in a Large Mental Health Case Register, PLOS ONE. 10 (2015) e0134208. doi:10.1371/journal.pone.0134208.
R.G. Jackson MSc, M. Ball, R. Patel, R.D. Hayes, R.J. Dobson, R. Stewart, TextHunter â€“ A User Friendly Tool for Extracting Generic Concepts from Free Text in Clinical Research, AMIA. Ann. Symp. Proc. 2014 (2014) 729â€“738.