Literature DB >> 32909908

Deep Learning and Multivariable Models Select EVAR Patients for Short-Stay Discharge.

Devin S Zarkowsky1, Besma Nejim2, Itay Hubara3, Caitlin W Hicks2, Philip P Goodney4, Mahmoud B Malas5.   

Abstract

OBJECTIVES: We sought to develop a prediction score with data from the Vascular Quality Initiative (VQI) EVAR in efforts to assist endovascular specialists in deciding whether or not a patient is appropriate for short-stay discharge.
BACKGROUND: Small series describe short-stay discharge following elective EVAR. Our study aims to quantify characteristics associated with this decision.
METHODS: The VQI EVAR and NSQIP datasets were queried. Patients who underwent elective EVAR recorded in VQI, between 1/2010-5/2017 were split 2:1 into test and analytic cohorts via random number assignment. Cross-reference with the Medicare claims database confirmed all-cause mortality data. Bootstrap sampling was employed in model. Deep learning algorithms independently evaluated each dataset as a sensitivity test.
RESULTS: Univariate outcomes, including 30-day survival, were statistically worse in the DD group when compared to the SD group (all P < 0.05). A prediction score, SD-EVAR, derived from the VQI EVAR dataset including pre- and intra-op variables that discriminate between SD and DD was externally validated in NSQIP (Pearson correlation coefficient = 0.79, P < 0.001); deep learning analysis concurred. This score suggests 66% of EVAR patients may be appropriate for short-stay discharge. A free smart phone app calculating short-stay discharge potential is available through QxMD Calculate https://qxcalc.app.link/vqidis.
CONCLUSIONS: Selecting patients for short-stay discharge after EVAR is possible without increasing harm. The majority of infrarenal AAA patients treated with EVAR in the United States fit a risk profile consistent with short-stay discharge, representing a significant cost-savings potential to the healthcare system.

Entities:  

Keywords:  EVAR; aneurysm; care pathways; health services research

Mesh:

Year:  2020        PMID: 32909908      PMCID: PMC7792630          DOI: 10.1177/1538574420954299

Source DB:  PubMed          Journal:  Vasc Endovascular Surg        ISSN: 1538-5744            Impact factor:   1.089


  22 in total

1.  Hospital volume and surgical mortality in the United States.

Authors:  John D Birkmeyer; Andrea E Siewers; Emily V A Finlayson; Therese A Stukel; F Lee Lucas; Ida Batista; H Gilbert Welch; David E Wennberg
Journal:  N Engl J Med       Date:  2002-04-11       Impact factor: 91.245

2.  Major trends in the U.S. health economy since 1950.

Authors:  Victor R Fuchs
Journal:  N Engl J Med       Date:  2012-03-15       Impact factor: 91.245

Review 3.  Measured GFR as a confirmatory test for estimated GFR.

Authors:  Lesley A Stevens; Andrew S Levey
Journal:  J Am Soc Nephrol       Date:  2009-10-15       Impact factor: 10.121

Review 4.  Learning multiple layers of representation.

Authors:  Geoffrey E Hinton
Journal:  Trends Cogn Sci       Date:  2007-10       Impact factor: 20.229

5.  Endovascular aneurysm repair patients who are lost to follow-up have worse outcomes.

Authors:  Caitlin W Hicks; Devin S Zarkowsky; Ian C Bostock; David H Stone; James H Black; Jens Eldrup-Jorgensen; Philip P Goodney; Mahmoud B Malas
Journal:  J Vasc Surg       Date:  2017-02-16       Impact factor: 4.268

6.  Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes.

Authors:  Daniel Shu Wei Ting; Carol Yim-Lui Cheung; Gilbert Lim; Gavin Siew Wei Tan; Nguyen D Quang; Alfred Gan; Haslina Hamzah; Renata Garcia-Franco; Ian Yew San Yeo; Shu Yen Lee; Edmund Yick Mun Wong; Charumathi Sabanayagam; Mani Baskaran; Farah Ibrahim; Ngiap Chuan Tan; Eric A Finkelstein; Ecosse L Lamoureux; Ian Y Wong; Neil M Bressler; Sobha Sivaprasad; Rohit Varma; Jost B Jonas; Ming Guang He; Ching-Yu Cheng; Gemmy Chui Ming Cheung; Tin Aung; Wynne Hsu; Mong Li Lee; Tien Yin Wong
Journal:  JAMA       Date:  2017-12-12       Impact factor: 56.272

7.  Comparison of endovascular aneurysm repair with open repair in patients with abdominal aortic aneurysm (EVAR trial 1), 30-day operative mortality results: randomised controlled trial.

Authors:  R M Greenhalgh; L C Brown; G P S Kwong; J T Powell; S G Thompson
Journal:  Lancet       Date:  2004 Sep 4-10       Impact factor: 79.321

8.  Endovascular vs. open repair of abdominal aortic aneurysms in the Medicare population.

Authors:  Marc L Schermerhorn; A James O'Malley; Ami Jhaveri; Philip Cotterill; Frank Pomposelli; Bruce E Landon
Journal:  N Engl J Med       Date:  2008-01-31       Impact factor: 91.245

9.  Cerebrovascular risk factors and brain microstructural abnormalities on diffusion tensor images in HIV-infected individuals.

Authors:  Beau K Nakamoto; Neda Jahanshad; Aaron McMurtray; Kalpana J Kallianpur; Dominic C Chow; Victor G Valcour; Robert H Paul; Liron Marotz; Paul M Thompson; Cecilia M Shikuma
Journal:  J Neurovirol       Date:  2012-05-15       Impact factor: 2.643

10.  A machine learning model to predict the risk of 30-day readmissions in patients with heart failure: a retrospective analysis of electronic medical records data.

Authors:  Sara Bersche Golas; Takuma Shibahara; Stephen Agboola; Hiroko Otaki; Jumpei Sato; Tatsuya Nakae; Toru Hisamitsu; Go Kojima; Jennifer Felsted; Sujay Kakarmath; Joseph Kvedar; Kamal Jethwani
Journal:  BMC Med Inform Decis Mak       Date:  2018-06-22       Impact factor: 2.796

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.