Article Text

other Versions

Download PDFPDF
Machine learning approaches in predicting ambulatory same day discharge patients after total hip arthroplasty
  1. Haoyan Zhong1,
  2. Jashvant Poeran2,
  3. Alex Gu3,
  4. Lauren A Wilson1,
  5. Alejandro Gonzalez Della Valle4,
  6. Stavros G Memtsoudis1 and
  7. Jiabin Liu1,5
  1. 1Department of Anesthesiology, Critical Care & Pain Management, Hospital for Special Surgery, New York, New York, USA
  2. 2Orthopaedics/Population Health Science & Policy, Icahn School of Medicine at Mount Sinai, New York, New York, USA
  3. 3Department of Orthopaedic Surgery, George Washington University School of Public Health and Health Services, Washington, DC, USA
  4. 4Department of Orthopedic Surgery, Hospital for Special Surgery, New York, New York, USA
  5. 5Department of Anesthesiology, Critical Care & Pain Management, Weill Cornell Medical College, New York, New York, USA
  1. Correspondence to Dr Jiabin Liu, Department of Anesthesiology, Critical Care & Pain Management, Hospital for Special Surgery, New York, NY 10021-4898, USA; liuji{at}hss.edu

Abstract

Background With continuing financial and regulatory pressures, practice of ambulatory total hip arthroplasty is increasing. However, studies focusing on selection of optimal candidates are burdened by limitations related to traditional statistical approaches. Hereby we aimed to apply machine learning algorithm to identify characteristics associated with optimal candidates.

Methods This retrospective cohort study included elective total hip arthroplasty (n=63 859) recorded in National Surgical Quality Improvement Program dataset from 2017 to 2018. The main outcome was length of stay. A total of 40 candidate variables were considered. We applied machine learning algorithms (multivariable logistic regression, artificial neural networks, and random forest models) to predict length of stay=0 day. Models’ accuracies and area under the curve were calculated.

Results Applying machine learning models to compare length of stay=0 day to length of stay=1–3 days cases, we found area under the curve of 0.715, 0.762, and 0.804, accuracy of 0.65, 0.73, and 0.81 for logistic regression, artificial neural networks, and random forest model, respectively. Regarding the most important predictive features, anesthesia type, body mass index, age, ethnicity, white blood cell count, sodium level, and alkaline phosphatase were highlighted in machine learning models.

Conclusions Machine learning algorithm exhibited acceptable model quality and accuracy. Machine learning algorithms highlighted the as yet unrecognized impact of laboratory testing on future patient ambulatory pathway assignment.

  • ambulatory
  • outcomes
  • technology

Data availability statement

Data may be obtained from a third party and are not publicly available. The data are acquired from American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP): https://www.facs.org/Quality-Programs/ACS-NSQIP.

Statistics from Altmetric.com

Data availability statement

Data may be obtained from a third party and are not publicly available. The data are acquired from American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP): https://www.facs.org/Quality-Programs/ACS-NSQIP.

View Full Text

Footnotes

  • Twitter @jashvant_p, @sgmemtsoudis, @jbLiujb

  • Contributors HZ helped designed the study, conduct the study, and write the manuscript. JP helped designed the study and write the manuscript. AG helped designed the study and write the manuscript. LAW helped designed the study and conduct the study. AGDV helped designed the study and write the manuscript. SGM helped designed the study, conduct the study, and write the manuscript. JL helped designed the study, conduct the study, and write the manuscript.

  • Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

  • Competing interests None declared.

  • Provenance and peer review Not commissioned; externally peer reviewed.

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.