Literature DB >> 31157707

Training and Interpreting Machine Learning Algorithms to Evaluate Fall Risk After Emergency Department Visits.

Brian W Patterson1,2, Collin J Engstrom3, Varun Sah3, Maureen A Smith2,4,5, Eneida A Mendonça6,7, Michael S Pulia1, Michael D Repplinger1, Azita G Hamedani1, David Page3,6, Manish N Shah1,4,8.   

Abstract

BACKGROUND: Machine learning is increasingly used for risk stratification in health care. Achieving accurate predictive models do not improve outcomes if they cannot be translated into efficacious intervention. Here we examine the potential utility of automated risk stratification and referral intervention to screen older adults for fall risk after emergency department (ED) visits.
OBJECTIVE: This study evaluated several machine learning methodologies for the creation of a risk stratification algorithm using electronic health record data and estimated the effects of a resultant intervention based on algorithm performance in test data.
METHODS: Data available at the time of ED discharge were retrospectively collected and separated into training and test datasets. Algorithms were developed to predict the outcome of a return visit for fall within 6 months of an ED index visit. Models included random forests, AdaBoost, and regression-based methods. We evaluated models both by the area under the receiver operating characteristic (ROC) curve, also referred to as area under the curve (AUC), and by projected clinical impact, estimating number needed to treat (NNT) and referrals per week for a fall risk intervention.
RESULTS: The random forest model achieved an AUC of 0.78, with slightly lower performance in regression-based models. Algorithms with similar performance, when evaluated by AUC, differed when placed into a clinical context with the defined task of estimated NNT in a real-world scenario.
CONCLUSION: The ability to translate the results of our analysis to the potential tradeoff between referral numbers and NNT offers decisionmakers the ability to envision the effects of a proposed intervention before implementation.

Entities:  

Mesh:

Year:  2019        PMID: 31157707      PMCID: PMC6590914          DOI: 10.1097/MLR.0000000000001140

Source DB:  PubMed          Journal:  Med Care        ISSN: 0025-7079            Impact factor:   2.983


  37 in total

1.  Geriatric falls: injury severity is high and disproportionate to mechanism.

Authors:  D A Sterling; J A O'Connor; J Bonadies
Journal:  J Trauma       Date:  2001-01

2.  Risk of falls and fractures in older adults using atypical antipsychotic agents: a propensity score-adjusted, retrospective cohort study.

Authors:  Satabdi Chatterjee; Hua Chen; Michael L Johnson; Rajender R Aparasu
Journal:  Am J Geriatr Pharmacother       Date:  2012-02-10

Review 3.  Access in health services research: the battle of the frameworks.

Authors:  Thomas C Ricketts; Laurie J Goldsmith
Journal:  Nurs Outlook       Date:  2005 Nov-Dec       Impact factor: 3.250

Review 4.  A Critical Review for Developing Accurate and Dynamic Predictive Models Using Machine Learning Methods in Medicine and Health Care.

Authors:  Hamdan O Alanazi; Abdul Hanan Abdullah; Kashif Naseer Qureshi
Journal:  J Med Syst       Date:  2017-03-11       Impact factor: 4.460

5.  Can we individualize the 'number needed to treat'? An empirical study of summary effect measures in meta-analyses.

Authors:  Toshiaki A Furukawa; Gordon H Guyatt; Lauren E Griffith
Journal:  Int J Epidemiol       Date:  2002-02       Impact factor: 7.196

6.  A framework for the study of access to medical care.

Authors:  L A Aday; R Andersen
Journal:  Health Serv Res       Date:  1974       Impact factor: 3.402

7.  Revisiting the behavioral model and access to medical care: does it matter?

Authors:  R M Andersen
Journal:  J Health Soc Behav       Date:  1995-03

8.  The number needed to treat: a clinically useful measure of treatment effect.

Authors:  R J Cook; D L Sackett
Journal:  BMJ       Date:  1995-02-18

Review 9.  Assessment and management of fall risk in primary care settings.

Authors:  Elizabeth A Phelan; Jane E Mahoney; Jan C Voit; Judy A Stevens
Journal:  Med Clin North Am       Date:  2015-03       Impact factor: 5.456

10.  Hidden in plain sight: bias towards sick patients when sampling patients with sufficient electronic health record data for research.

Authors:  Alexander Rusanov; Nicole G Weiskopf; Shuang Wang; Chunhua Weng
Journal:  BMC Med Inform Decis Mak       Date:  2014-06-11       Impact factor: 2.796

View more
  10 in total

1.  Collaborative design and implementation of a clinical decision support system for automated fall-risk identification and referrals in emergency departments.

Authors:  Gwen Costa Jacobsohn; Margaret Leaf; Frank Liao; Apoorva P Maru; Collin J Engstrom; Megan E Salwei; Gerald T Pankratz; Alexis Eastman; Pascale Carayon; Douglas A Wiegmann; Joel S Galang; Maureen A Smith; Manish N Shah; Brian W Patterson
Journal:  Healthc (Amst)       Date:  2021-12-16

Review 2.  Data Science Methods for Nursing-Relevant Patient Outcomes and Clinical Processes: The 2019 Literature Year in Review.

Authors:  Mary Anne Schultz; Rachel Lane Walden; Kenrick Cato; Cynthia Peltier Coviak; Christopher Cruz; Fabio D'Agostino; Brian J Douthit; Thompson Forbes; Grace Gao; Mikyoung Angela Lee; Deborah Lekan; Ann Wieben; Alvin D Jeffery
Journal:  Comput Inform Nurs       Date:  2021-05-06       Impact factor: 1.985

3.  Predicting hospital admission from emergency department triage data for patients presenting with fall-related fractures.

Authors:  Dinesh R Pai; Balaraman Rajan; Puneet Jairath; Stephen M Rosito
Journal:  Intern Emerg Med       Date:  2022-09-22       Impact factor: 5.472

4.  Fallacy of Median Door-to-ECG Time: Hidden Opportunities for STEMI Screening Improvement.

Authors:  Maame Yaa A B Yiadom; Wu Gong; Brian W Patterson; Christopher W Baugh; Angela M Mills; Nicholas Gavin; Seth R Podolsky; Gilberto Salazar; Bryn E Mumma; Mary Tanski; Kelsea Hadley; Caitlin Azzo; Stephen C Dorner; Alexander Ulintz; Dandan Liu
Journal:  J Am Heart Assoc       Date:  2022-05-02       Impact factor: 6.106

5.  Fall predictors beyond fall risk assessment tool items for acute hospitalized older adults: a matched case-control study.

Authors:  Hye-Mi Noh; Hong Ji Song; Yong Soon Park; Junhee Han; Yong Kyun Roh
Journal:  Sci Rep       Date:  2021-01-15       Impact factor: 4.379

Review 6.  Application Scenarios for Artificial Intelligence in Nursing Care: Rapid Review.

Authors:  Kathrin Seibert; Dominik Domhoff; Dominik Bruch; Matthias Schulte-Althoff; Daniel Fürstenau; Felix Biessmann; Karin Wolf-Ostermann
Journal:  J Med Internet Res       Date:  2021-11-29       Impact factor: 5.428

7.  Predicting Falls in Long-term Care Facilities: Machine Learning Study.

Authors:  Rahul Thapa; Anurag Garikipati; Sepideh Shokouhi; Myrna Hurtado; Gina Barnes; Jana Hoffman; Jacob Calvert; Lynne Katzmann; Qingqing Mao; Ritankar Das
Journal:  JMIR Aging       Date:  2022-04-01

8.  Effectiveness of a targeted telephone-based case management service on activity in an Emergency Department in the UK: a pragmatic difference-in-differences evaluation.

Authors:  Julian Elston; Felix P Gradinger; Adam J Streeter; Stephen Macey; Susan Martin
Journal:  BMC Health Serv Res       Date:  2022-08-15       Impact factor: 2.908

9.  Development and validation of a fall risk Questionnaire in Greek community-dwelling individuals over 60 years old.

Authors:  Chrysoula Argyrou; Yannis Dionyssiotis; Antonios Galanos; Ingka Kantaidou; John Vlamis; Ioannis K Triantafyllopoulos; George P Lyritis; Ismene A Dontas; Efstathios Chronopoulos
Journal:  J Frailty Sarcopenia Falls       Date:  2022-09-01

10.  Governance of Clinical AI applications to facilitate safe and equitable deployment in a large health system: Key elements and early successes.

Authors:  Frank Liao; Sabrina Adelaine; Majid Afshar; Brian W Patterson
Journal:  Front Digit Health       Date:  2022-08-24
  10 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.