Diagnostic Prediction Using Discomfort Drawings with IBTM

Cheng Zhang, Hedvig Kjellström, Carl Henrik Ek, Bo Bertilson
Proceedings of the 1st Machine Learning for Healthcare Conference, PMLR 56:226-238, 2016.

Abstract

In this paper, we explore the possibility to apply machine learning to make diagnostic predictions using discomfort drawings. Discomfort drawings have proven to be an effective method to collect patient data and make diagnostic decisions in real-life practice. A dataset from relevant patient cases is collected for which medical experts provide diagnostic labels. Next, we use a factorized multimodal topic model, Inter-Battery Topic Model (IBTM), to train a system that can make diagnostic predictions given an unseen discomfort drawing. Experimental results show reasonable predictions of diagnostic labels given an unseen discomfort drawing. Additionally, we generate synthetic discomfort drawings with IBTM given a diagnostic label, which results in typical cases of symptoms. The positive result indicates a significant potential of machine learning to be used for parts of the pain diagnostic process and to be a decision support system for physicians and other health care personnel.

Cite this Paper

BibTeX
@InProceedings{pmlr-v56-Zhang16, title = {Diagnostic Prediction Using Discomfort Drawings with IBTM}, author = {Zhang, Cheng and Kjellström, Hedvig and Ek, Carl Henrik and Bertilson, Bo}, booktitle = {Proceedings of the 1st Machine Learning for Healthcare Conference}, pages = {226--238}, year = {2016}, editor = {Doshi-Velez, Finale and Fackler, Jim and Kale, David and Wallace, Byron and Wiens, Jenna}, volume = {56}, series = {Proceedings of Machine Learning Research}, address = {Northeastern University, Boston, MA, USA}, month = {18--19 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v56/Zhang16.pdf}, url = {https://proceedings.mlr.press/v56/Zhang16.html}, abstract = {In this paper, we explore the possibility to apply machine learning to make diagnostic predictions using discomfort drawings. Discomfort drawings have proven to be an effective method to collect patient data and make diagnostic decisions in real-life practice. A dataset from relevant patient cases is collected for which medical experts provide diagnostic labels. Next, we use a factorized multimodal topic model, Inter-Battery Topic Model (IBTM), to train a system that can make diagnostic predictions given an unseen discomfort drawing. Experimental results show reasonable predictions of diagnostic labels given an unseen discomfort drawing. Additionally, we generate synthetic discomfort drawings with IBTM given a diagnostic label, which results in typical cases of symptoms. The positive result indicates a significant potential of machine learning to be used for parts of the pain diagnostic process and to be a decision support system for physicians and other health care personnel.} }
Endnote
%0 Conference Paper %T Diagnostic Prediction Using Discomfort Drawings with IBTM %A Cheng Zhang %A Hedvig Kjellström %A Carl Henrik Ek %A Bo Bertilson %B Proceedings of the 1st Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2016 %E Finale Doshi-Velez %E Jim Fackler %E David Kale %E Byron Wallace %E Jenna Wiens %F pmlr-v56-Zhang16 %I PMLR %P 226--238 %U https://proceedings.mlr.press/v56/Zhang16.html %V 56 %X In this paper, we explore the possibility to apply machine learning to make diagnostic predictions using discomfort drawings. Discomfort drawings have proven to be an effective method to collect patient data and make diagnostic decisions in real-life practice. A dataset from relevant patient cases is collected for which medical experts provide diagnostic labels. Next, we use a factorized multimodal topic model, Inter-Battery Topic Model (IBTM), to train a system that can make diagnostic predictions given an unseen discomfort drawing. Experimental results show reasonable predictions of diagnostic labels given an unseen discomfort drawing. Additionally, we generate synthetic discomfort drawings with IBTM given a diagnostic label, which results in typical cases of symptoms. The positive result indicates a significant potential of machine learning to be used for parts of the pain diagnostic process and to be a decision support system for physicians and other health care personnel.
RIS
TY - CPAPER TI - Diagnostic Prediction Using Discomfort Drawings with IBTM AU - Cheng Zhang AU - Hedvig Kjellström AU - Carl Henrik Ek AU - Bo Bertilson BT - Proceedings of the 1st Machine Learning for Healthcare Conference DA - 2016/12/10 ED - Finale Doshi-Velez ED - Jim Fackler ED - David Kale ED - Byron Wallace ED - Jenna Wiens ID - pmlr-v56-Zhang16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 56 SP - 226 EP - 238 L1 - http://proceedings.mlr.press/v56/Zhang16.pdf UR - https://proceedings.mlr.press/v56/Zhang16.html AB - In this paper, we explore the possibility to apply machine learning to make diagnostic predictions using discomfort drawings. Discomfort drawings have proven to be an effective method to collect patient data and make diagnostic decisions in real-life practice. A dataset from relevant patient cases is collected for which medical experts provide diagnostic labels. Next, we use a factorized multimodal topic model, Inter-Battery Topic Model (IBTM), to train a system that can make diagnostic predictions given an unseen discomfort drawing. Experimental results show reasonable predictions of diagnostic labels given an unseen discomfort drawing. Additionally, we generate synthetic discomfort drawings with IBTM given a diagnostic label, which results in typical cases of symptoms. The positive result indicates a significant potential of machine learning to be used for parts of the pain diagnostic process and to be a decision support system for physicians and other health care personnel. ER -
APA
Zhang, C., Kjellström, H., Ek, C.H. & Bertilson, B.. (2016). Diagnostic Prediction Using Discomfort Drawings with IBTM. Proceedings of the 1st Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 56:226-238 Available from https://proceedings.mlr.press/v56/Zhang16.html.

Related Material