Diagnostic Prediction Using Discomfort Drawings with IBTM

In this paper, we explore the possibility to apply machine learning to make diagnostic predictions using discomfort drawings. A discomfort drawing is an intuitive way for patients to express discomfort and pain related symptoms. These drawings have proven to be an effective method to collect patient data and make diagnostic decisions in real-life practice. A dataset from real-world 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. The number of output diagnostic labels is determined by using mean-shift clustering on the 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.

[1]  Roger Luckmann,et al.  "They don't want anything to do with you": patient views of primary care management of chronic pain. , 2010, Pain medicine.

[2]  Igor Kononenko,et al.  Analysing and improving the diagnosis of ischaemic heart disease with machine learning , 1999, Artif. Intell. Medicine.

[3]  Yang Wang,et al.  Max-margin Latent Dirichlet Allocation for Image Classification and Annotation , 2011, BMVC.

[4]  Michael I. Jordan,et al.  Modeling annotated data , 2003, SIGIR.

[5]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[6]  Hedvig Kjellström,et al.  How to Supervise Topic Models , 2014, ECCV Workshops.

[7]  Yasuhisa Tanaka,et al.  Cervical Roots as Origin of Pain in the Neck or Scapular Regions , 2006, Spine.

[8]  Shaogang Gong,et al.  Learning Tags from Unsegmented Videos of Multiple Human Actions , 2011, 2011 IEEE 11th International Conference on Data Mining.

[9]  Padhraic Smyth,et al.  Statistical entity-topic models , 2006, KDD '06.

[10]  L. Strender,et al.  Reliability of Clinical Tests in the Assessment of Patients With Neck/Shoulder Problems—Impact of History , 2003, Spine.

[11]  Chong Wang,et al.  Online Variational Inference for the Hierarchical Dirichlet Process , 2011, AISTATS.

[12]  L. Strender,et al.  Assessment of nerve involvement in the lumbar spine: agreement between magnetic resonance imaging, physical examination and pain drawing findings , 2010, BMC musculoskeletal disorders.

[13]  Dan Song,et al.  Contextual modeling with labeled multi-LDA , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Hedvig Kjellström,et al.  Inter-battery Topic Representation Learning , 2016, ECCV.

[15]  Pain and pathology in lumbar disc hernia. , 1995, Clinical orthopaedics and related research.

[16]  J. Ekholm,et al.  Relation between pain location and disc pathology: a study of pain drawings and CT/discography. , 1999, The Clinical journal of pain.

[17]  H. Palmer.  Pain charts; a description of a technique whereby functional pain may be diagnosed from organic pain. , 1949, The New Zealand medical journal.

[18]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  M. Albeck.  A critical assessment of clinical diagnosis of disc herniation in patients with monoradicular sciatica , 2005, Acta Neurochirurgica.

[20]  Francis R. Bach,et al.  Online Learning for Latent Dirichlet Allocation , 2010, NIPS.

[21]  Qiaozhu Mei,et al.  Understanding the Limiting Factors of Topic Modeling via Posterior Contraction Analysis , 2014, ICML.

[22]  Chong Wang,et al.  An Adaptive Learning Rate for Stochastic Variational Inference , 2013, ICML.

[23]  Lars-Erik Strender,et al.  Pain drawing in the assessment of neurogenic pain and dysfunction in the neck/shoulder region: inter-examiner reliability and concordance with clinical examination. , 2007, Pain medicine.

[24]  Chong Wang,et al.  Simultaneous image classification and annotation , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.