Intimate Partner Violence and Injury Prediction From Radiology Reports

Intimate partner violence (IPV) is an urgent, prevalent, and under-detected public health issue. We present machine learning models to assess patients for IPV and injury. We train the predictive algorithms on radiology reports with 1) IPV labels based on entry to a violence prevention program and 2) injury labels provided by emergency radiology fellowship-trained physicians. Our dataset includes 34,642 radiology reports and 1479 patients of IPV victims and control patients. Our best model predicts IPV a median of 3.08 years before violence prevention program entry with a sensitivity of 64% and a specificity of 95%. We conduct error analysis to determine for which patients our model has especially high or low performance and discuss next steps for a deployed clinical risk model.

[1]  David A. Sontag,et al.  Population-Level Prediction of Type 2 Diabetes From Claims Data and Analysis of Risk Factors , 2015, Big Data.

[2]  P. Tjaden,et al.  Prevalence and Consequences of Male-to-female and Female-to-male Intimate Partner Violence as Measured by the National Violence Against Women Survey , 2000 .

[3]  Peter Szolovits,et al.  MIMIC-III, a freely accessible critical care database , 2016, Scientific Data.

[4]  Jacquelyn C Campbell,et al.  Health consequences of intimate partner violence , 2002, The Lancet.

[5]  Thomas Lavergne,et al.  Natural language processing of radiology reports for the detection of thromboembolic diseases and clinically relevant incidental findings , 2014, BMC Bioinformatics.

[6]  Jaewoo Kang,et al.  BioBERT: a pre-trained biomedical language representation model for biomedical text mining , 2019, Bioinform..

[7]  Kathleen C. Basile,et al.  Intimate Partner Violence against Women , 2011 .

[8]  C. Watts,et al.  Intimate partner violence and women's physical and mental health in the WHO multi-country study on women's health and domestic violence: an observational study , 2008, The Lancet.

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

[10]  M. Ghassemi,et al.  Can AI Help Reduce Disparities in General Medical and Mental Health Care? , 2019, AMA journal of ethics.

[11]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[12]  B. Rosner,et al.  Radiologic Findings in Intimate Partner Violence. , 2019, Radiology.

[13]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[14]  D. Koller,et al.  Integration of Early Physiological Responses Predicts Later Illness Severity in Preterm Infants , 2010, Science Translational Medicine.

[15]  L. Flashman,et al.  Predicting the Risk of Suicide by Analyzing the Text of Clinical Notes , 2014, PloS one.

[16]  Peter Szolovits,et al.  What’s in a Note? Unpacking Predictive Value in Clinical Note Representations , 2018, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[17]  A. Chouldechova,et al.  Toward Algorithmic Accountability in Public Services: A Qualitative Study of Affected Community Perspectives on Algorithmic Decision-making in Child Welfare Services , 2019, CHI.

[18]  S. Seltzer,et al.  Making the ‘invisible’ visible: transforming the detection of intimate partner violence , 2019, BMJ Quality & Safety.

[19]  M. Ghassemi,et al.  Predicting early psychiatric readmission with natural language processing of narrative discharge summaries , 2016, Translational psychiatry.

[20]  Alexandra Chouldechova,et al.  A case study of algorithm-assisted decision making in child maltreatment hotline screening decisions , 2018, FAT.

[21]  Bo Zhao,et al.  Deep learning in clinical natural language processing: a methodical review , 2019, J. Am. Medical Informatics Assoc..

[22]  Jacquelyn C. Campbell,et al.  Intimate Partner Violence Against Women , 2001, Annual Review of Nursing Research.

[23]  L. Olson,et al.  Health indicators and intimate partner violence among women who are members of a managed care organization. , 1999, Preventive medicine.

[24]  C. Rennison.  Intimate Partner Violence and Age of Victim , 1993-99 , 2001 .

[25]  Marzyeh Ghassemi,et al.  A Review of Challenges and Opportunities in Machine Learning for Health. , 2020, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[26]  Andrew L. Beam,et al.  Practical guidance on artificial intelligence for health-care data. , 2019, The Lancet. Digital health.

[27]  Jacquelyn C. Campbell,et al.  Prevalence of intimate partner abuse in women treated at community hospital emergency departments. , 1998, JAMA.

[28]  Jacquelyn C Campbell,et al.  The global prevalence of intimate partner homicide: a systematic review , 2013, The Lancet.

[29]  A. Reginelli,et al.  Imaging of Violence Against the Elderly and the Women. , 2019, Seminars in ultrasound, CT, and MR.

[30]  G. Larkin,et al.  The Role of Intimate Partner Violence, Race, and Ethnicity in Help-Seeking Behaviors , 2006, Ethnicity & health.

[31]  Shang Gao,et al.  Hierarchical attention networks for information extraction from cancer pathology reports , 2017, J. Am. Medical Informatics Assoc..

[32]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

[33]  Hongfang Liu,et al.  Natural language processing of clinical notes for identification of critical limb ischemia , 2017, Int. J. Medical Informatics.

[34]  C. García-Moreno,et al.  Prevalence of and factors associated with male perpetration of intimate partner violence: findings from the UN Multi-country Cross-sectional Study on Men and Violence in Asia and the Pacific. , 2013, The Lancet. Global health.

[35]  Wei-Hung Weng,et al.  Publicly Available Clinical BERT Embeddings , 2019, Proceedings of the 2nd Clinical Natural Language Processing Workshop.

[36]  D. Hien,et al.  Interpersonal partner violence and women in the United States: an overview of prevalence rates, psychiatric correlates and consequences and barriers to help seeking. , 2009, International journal of law and psychiatry.

[37]  Rajesh Ranganath,et al.  ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission , 2019, ArXiv.

[38]  David Sontag,et al.  Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health KnowledgeGraph , 2019, PSB.

[39]  K. Hegarty,et al.  Screening women for intimate partner violence in healthcare settings. , 2015, The Cochrane database of systematic reviews.

[40]  M. Howell,et al.  Ensuring Fairness in Machine Learning to Advance Health Equity , 2018, Annals of Internal Medicine.

[41]  Marzyeh Ghassemi,et al.  Treating health disparities with artificial intelligence , 2020, Nature Medicine.

[42]  S. Seltzer,et al.  Exacerbation of Physical Intimate Partner Violence during COVID-19 Lockdown , 2020, Radiology.

[43]  Luke S. Zettlemoyer,et al.  AllenNLP: A Deep Semantic Natural Language Processing Platform , 2018, ArXiv.

[44]  Sharon G. Smith,et al.  National Intimate Partner and Sexual Violence Survey: 2010 Summary Report , 2011 .

[45]  S. Oertelt-Prigione,et al.  COVID-19: Reducing the risk of infection might increase the risk of intimate partner violence , 2020, EClinicalMedicine.

[46]  P. Emmelkamp,et al.  Prediction of intimate partner violence by type of substance use disorder. , 2014, Journal of substance abuse treatment.

[47]  Kenneth L Kehl,et al.  Assessment of Deep Natural Language Processing in Ascertaining Oncologic Outcomes From Radiology Reports. , 2019, JAMA oncology.

[48]  Kevin Gimpel,et al.  ALBERT: A Lite BERT for Self-supervised Learning of Language Representations , 2019, ICLR.

[49]  John Paoli,et al.  Human–computer collaboration for skin cancer recognition , 2020, Nature Medicine.

[50]  S. Bassuk,et al.  The Relationship Between Intimate Partner Violence and the Use of Addictive Substances in Poor and Homeless Single Mothers , 2002 .

[51]  Long Chen,et al.  Clinical trial cohort selection based on multi-level rule-based natural language processing system , 2019, J. Am. Medical Informatics Assoc..