Literature DB >> 33132014

Machine Learning Algorithms to Predict Mortality and Allocate Palliative Care for Older Patients With Hip Fracture.

Michael P Cary1, Farica Zhuang2, Rachel Lea Draelos3, Wei Pan4, Sathya Amarasekara4, Brian J Douthit4, Yunah Kang4, Cathleen S Colón-Emeric5.   

Abstract

OBJECTIVES: To evaluate a machine learning model designed to predict mortality for Medicare beneficiaries aged >65 years treated for hip fracture in Inpatient Rehabilitation Facilities (IRFs).
DESIGN: Retrospective design/cohort analysis of Centers for Medicare & Medicaid Services Inpatient Rehabilitation Facility-Patient Assessment Instrument data. SETTING AND PARTICIPANTS: A total of 17,140 persons admitted to Medicare-certified IRFs in 2015 following hospitalization for hip fracture. MEASURES: Patient characteristics include sociodemographic (age, gender, race, and social support) and clinical factors (functional status at admission, chronic conditions) and IRF length of stay. Outcomes were 30-day and 1-year all-cause mortality. We trained and evaluated 2 classification models, logistic regression and a multilayer perceptron (MLP), to predict the probability of 30-day and 1-year mortality and evaluated the calibration, discrimination, and precision of the models.
RESULTS: For 30-day mortality, MLP performed well [acc = 0.74, area under the receiver operating characteristic curve (AUROC) = 0.76, avg prec = 0.10, slope = 1.14] as did logistic regression (acc = 0.78, AUROC = 0.76, avg prec = 0.09, slope = 1.20). For 1-year mortality, the performances were similar for both MLP (acc = 0.68, AUROC = 0.75, avg prec = 0.32, slope = 0.96) and logistic regression (acc = 0.68, AUROC = 0.75, avg prec = 0.32, slope = 0.95). CONCLUSION AND IMPLICATIONS: A scoring system based on logistic regression may be more feasible to run in current electronic medical records. But MLP models may reduce cognitive burden and increase ability to calibrate to local data, yielding clinical specificity in mortality prediction so that palliative care resources may be allocated more effectively.
Copyright © 2020 AMDA – The Society for Post-Acute and Long-Term Care Medicine. Published by Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Functional status; hip fracture; inpatient rehabilitation facilities; mortality

Mesh:

Year:  2020        PMID: 33132014      PMCID: PMC7867606          DOI: 10.1016/j.jamda.2020.09.025

Source DB:  PubMed          Journal:  J Am Med Dir Assoc        ISSN: 1525-8610            Impact factor:   7.802


  29 in total

1.  A practical tool to identify patients who may benefit from a palliative approach: the CARING criteria.

Authors:  Stacy M Fischer; Wendolyn S Gozansky; Angela Sauaia; Sung-Joon Min; Jean S Kutner; Andrew Kramer
Journal:  J Pain Symptom Manage       Date:  2006-04       Impact factor: 3.612

2.  The Functional Independence Measure: tests of scaling assumptions, structure, and reliability across 20 diverse impairment categories.

Authors:  M G Stineman; J A Shea; A Jette; C J Tassoni; K J Ottenbacher; R Fiedler; C V Granger
Journal:  Arch Phys Med Rehabil       Date:  1996-11       Impact factor: 3.966

3.  Estimation of the Youden Index and its associated cutoff point.

Authors:  Ronen Fluss; David Faraggi; Benjamin Reiser
Journal:  Biom J       Date:  2005-08       Impact factor: 2.207

4.  Trends in the utilization and outcomes of Medicare patients hospitalized for hip fracture, 2000-2008.

Authors:  David J Becker; Tarun Arora; Meredith L Kilgore; Jeffrey R Curtis; Elizabeth Delzell; Kenneth G Saag; Huifeng Yun; Michael A Morrisey
Journal:  J Aging Health       Date:  2014-01-08

5.  Development and validation of a 5-year mortality prediction model using regularized regression and Medicare data.

Authors:  Jennifer L Lund; Tzy-Mey Kuo; M Alan Brookhart; Anne-Marie Meyer; Alexandra F Dalton; Christine E Kistler; Stephanie B Wheeler; Carmen L Lewis
Journal:  Pharmacoepidemiol Drug Saf       Date:  2019-03-19       Impact factor: 2.890

6.  Big Data and Machine Learning in Health Care.

Authors:  Andrew L Beam; Isaac S Kohane
Journal:  JAMA       Date:  2018-04-03       Impact factor: 56.272

Review 7.  Preventable risk factors of mortality after hip fracture surgery: Systematic review and meta-analysis.

Authors:  Wenli Chang; Hongzhi Lv; Chen Feng; Peizhi Yuwen; Ning Wei; Wei Chen; Yingze Zhang
Journal:  Int J Surg       Date:  2018-03-09       Impact factor: 6.071

8.  The International Association for Hospice and Palliative Care: Advancing Hospice and Palliative Care Worldwide.

Authors:  Liliana De Lima; Lukas Radbruch
Journal:  J Pain Symptom Manage       Date:  2017-08-08       Impact factor: 3.612

Review 9.  The benefits of rehabilitation for palliative care patients.

Authors:  Edward Barawid; Natalia Covarrubias; Bianca Tribuzio; Solomon Liao
Journal:  Am J Hosp Palliat Care       Date:  2013-12-02       Impact factor: 2.500

10.  Predicting cancer outcomes from histology and genomics using convolutional networks.

Authors:  Pooya Mobadersany; Safoora Yousefi; Mohamed Amgad; David A Gutman; Jill S Barnholtz-Sloan; José E Velázquez Vega; Daniel J Brat; Lee A D Cooper
Journal:  Proc Natl Acad Sci U S A       Date:  2018-03-12       Impact factor: 11.205

View more
  1 in total

1.  Development and internal validation of a machine-learning-developed model for predicting 1-year mortality after fragility hip fracture.

Authors:  Nitchanant Kitcharanant; Pojchong Chotiyarnwong; Thiraphat Tanphiriyakun; Ekasame Vanitcharoenkul; Chantas Mahaisavariya; Wichian Boonyaprapa; Aasis Unnanuntana
Journal:  BMC Geriatr       Date:  2022-05-24       Impact factor: 4.070

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.