Literature DB >> 34725687

Temporally informed random forests for suicide risk prediction.

Ilkin Bayramli1,2, Victor Castro3,4, Yuval Barak-Corren1, Emily M Madsen5,6, Matthew K Nock4,7,8, Jordan W Smoller5,6,9, Ben Y Reis1,9.   

Abstract

OBJECTIVE: Suicide is one of the leading causes of death worldwide, yet clinicians find it difficult to reliably identify individuals at high risk for suicide. Algorithmic approaches for suicide risk detection have been developed in recent years, mostly based on data from electronic health records (EHRs). Significant room for improvement remains in the way these models take advantage of temporal information to improve predictions.
MATERIALS AND METHODS: We propose a temporally enhanced variant of the random forest (RF) model-Omni-Temporal Balanced Random Forests (OT-BRFs)-that incorporates temporal information in every tree within the forest. We develop and validate this model using longitudinal EHRs and clinician notes from the Mass General Brigham Health System recorded between 1998 and 2018, and compare its performance to a baseline Naive Bayes Classifier and 2 standard versions of balanced RFs.
RESULTS: Temporal variables were found to be associated with suicide risk: Elevated suicide risk was observed in individuals with a higher total number of visits as well as those with a low rate of visits over time, while lower suicide risk was observed in individuals with a longer period of EHR coverage. RF models were more accurate than Naive Bayesian classifiers at predicting suicide risk in advance (area under the receiver operating curve = 0.824 vs. 0.754, respectively). The proposed OT-BRF model performed best among all RF approaches, yielding a sensitivity of 0.339 at 95% specificity, compared to 0.290 and 0.286 for the other 2 RF models. Temporal variables were assigned high importance by the models that incorporated them. DISCUSSION: We demonstrate that temporal variables have an important role to play in suicide risk detection and that requiring their inclusion in all RF trees leads to increased predictive performance. Integrating temporal information into risk prediction models helps the models interpret patient data in temporal context, improving predictive performance.
© The Author(s) 2021. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  clinical risk; modeling; random forest; suicide; temporal

Mesh:

Year:  2021        PMID: 34725687      PMCID: PMC8714280          DOI: 10.1093/jamia/ocab225

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   4.497


  17 in total

1.  The Unified Medical Language System (UMLS): integrating biomedical terminology.

Authors:  Olivier Bodenreider
Journal:  Nucleic Acids Res       Date:  2004-01-01       Impact factor: 16.971

2.  Predicting suicide attempts in adolescents with longitudinal clinical data and machine learning.

Authors:  Colin G Walsh; Jessica D Ribeiro; Joseph C Franklin
Journal:  J Child Psychol Psychiatry       Date:  2018-04-30       Impact factor: 8.982

3.  Predicting Suicidal Behavior From Longitudinal Electronic Health Records.

Authors:  Yuval Barak-Corren; Victor M Castro; Solomon Javitt; Alison G Hoffnagle; Yael Dai; Roy H Perlis; Matthew K Nock; Jordan W Smoller; Ben Y Reis
Journal:  Am J Psychiatry       Date:  2016-09-09       Impact factor: 18.112

4.  High Throughput Phenotyping for Dimensional Psychopathology in Electronic Health Records.

Authors:  Thomas H McCoy; Sheng Yu; Kamber L Hart; Victor M Castro; Hannah E Brown; James N Rosenquist; Alysa E Doyle; Pieter J Vuijk; Tianxi Cai; Roy H Perlis
Journal:  Biol Psychiatry       Date:  2018-02-26       Impact factor: 13.382

5.  Measuring the suicidal mind: implicit cognition predicts suicidal behavior.

Authors:  Matthew K Nock; Jennifer M Park; Christine T Finn; Tara L Deliberto; Halina J Dour; Mahzarin R Banaji
Journal:  Psychol Sci       Date:  2010-03-09

6.  Calculating the benefits of a Research Patient Data Repository.

Authors:  Ruth Nalichowski; Diane Keogh; Henry C Chueh; Shawn N Murphy
Journal:  AMIA Annu Symp Proc       Date:  2006

7.  Validation of an Electronic Health Record-Based Suicide Risk Prediction Modeling Approach Across Multiple Health Care Systems.

Authors:  Yuval Barak-Corren; Victor M Castro; Matthew K Nock; Kenneth D Mandl; Emily M Madsen; Ashley Seiger; William G Adams; R Joseph Applegate; Elmer V Bernstam; Jeffrey G Klann; Ellen P McCarthy; Shawn N Murphy; Marc Natter; Brian Ostasiewski; Nandan Patibandla; Gary E Rosenthal; George S Silva; Kun Wei; Griffin M Weber; Sarah R Weiler; Ben Y Reis; Jordan W Smoller
Journal:  JAMA Netw Open       Date:  2020-03-02

8.  Bias in random forest variable importance measures: illustrations, sources and a solution.

Authors:  Carolin Strobl; Anne-Laure Boulesteix; Achim Zeileis; Torsten Hothorn
Journal:  BMC Bioinformatics       Date:  2007-01-25       Impact factor: 3.169

9.  Global, regional, and national burden of suicide mortality 1990 to 2016: systematic analysis for the Global Burden of Disease Study 2016.

Authors:  Mohsen Naghavi
Journal:  BMJ       Date:  2019-02-06

10.  Longitudinal histories as predictors of future diagnoses of domestic abuse: modelling study.

Authors:  Ben Y Reis; Isaac S Kohane; Kenneth D Mandl
Journal:  BMJ       Date:  2009-09-29
View more
  1 in total

1.  Predictive structured-unstructured interactions in EHR models: A case study of suicide prediction.

Authors:  Jordan W Smoller; Ben Y Reis; Ilkin Bayramli; Victor Castro; Yuval Barak-Corren; Emily M Madsen; Matthew K Nock
Journal:  NPJ Digit Med       Date:  2022-01-27
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.