Assessing the Efficacy of Clinical Sentiment Analysis and Topic Extraction in Psychiatric Readmission Risk Prediction

Predicting which patients are more likely to be readmitted to a hospital within 30 days after discharge is a valuable piece of information in clinical decision-making. Building a successful readmission risk classifier based on the content of Electronic Health Records (EHRs) has proved, however, to be a challenging task. Previously explored features include mainly structured information, such as sociodemographic data, comorbidity codes and physiological variables. In this paper we assess incorporating additional clinically interpretable NLP-based features such as topic extraction and clinical sentiment analysis to predict early readmission risk in psychiatry patients.

[1]  R Giel,et al.  Natural course of schizophrenic disorders: a 15-year followup of a Dutch incidence cohort. , 1998, Schizophrenia bulletin.

[2]  M. Bogren,et al.  How common are psychotic and bipolar disorders? A 50-year follow-up of the Lundby population , 2009, Nordic journal of psychiatry.

[3]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[4]  Wiley Interscience.  The journal of mental health policy and economics , 1998 .

[5]  James Pustejovsky,et al.  Distinguishing Clinical Sentiment: The Importance of Domain Adaptation in Psychiatric Patient Health Records , 2019, Proceedings of the 2nd Clinical Natural Language Processing Workshop.

[6]  Nathan Herrmann,et al.  READMIT: a clinical risk index to predict 30-day readmission after discharge from acute psychiatric units. , 2015, Journal of psychiatric research.

[7]  Dan J Stein,et al.  Global, regional, and national incidence, prevalence, and years lived with disability for 301 acute and chronic diseases and injuries in 188 countries, 1990–2013: a systematic analysis for the Global Burden of Disease Study 2013 , 2015, The Lancet.

[8]  James Pustejovsky,et al.  Analysis of risk factor domains in psychosis patient health records , 2018, Journal of Biomedical Semantics.

[9]  J. Suvisaari,et al.  Lifetime prevalence of psychotic and bipolar I disorders in a general population. , 2007, Archives of general psychiatry.

[10]  Risk Factors Associated With Psychiatric Readmission , 2015, The Journal of nervous and mental disease.

[11]  A. David,et al.  Exploring the predictors of early readmission to psychiatric hospital , 2015, Epidemiology and Psychiatric Sciences.

[12]  Alan D. Lopez,et al.  The Global Burden of Disease Study , 2003 .

[13]  Manuel Graña,et al.  Predictive models for hospital readmission risk: A systematic review of methods , 2018, Comput. Methods Programs Biomed..

[14]  I. Aas,et al.  Guidelines for rating Global Assessment of Functioning (GAF) , 2011, Annals of general psychiatry.

[15]  M. Knapp,et al.  Cost of schizophrenia in England. , 2007, The journal of mental health policy and economics.

[16]  Amanda H. Salanitro,et al.  Risk prediction models for hospital readmission: a systematic review. , 2011, JAMA.

[17]  Steven H. Brown,et al.  Automated identification of postoperative complications within an electronic medical record using natural language processing. , 2011, JAMA.

[18]  M. Olfson,et al.  Assessing clinical predictions of early rehospitalization in schizophrenia. , 1999, The Journal of nervous and mental disease.

[19]  R. Kessler,et al.  The economic burden of schizophrenia in the United States in 2002. , 2005, The Journal of clinical psychiatry.

[20]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[21]  Goodarz Danaei,et al.  A Novel Model for Predicting Rehospitalization Risk Incorporating Physical Function, Cognitive Status, and Psychosocial Support Using Natural Language Processing , 2017, Medical care.