Forskning
Udskriv Udskriv
Switch language
Region Hovedstaden - en del af Københavns Universitetshospital
Udgivet

Machine learning classifiers do not improve prediction of hospitalization > 2 days after fast-track hip and knee arthroplasty compared with a classical statistical risk model

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

DOI

  1. Feasibility, safety, and patient-reported outcomes 90 days after same-day total knee arthroplasty: a matched cohort study

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. Optimized medial unicompartmental knee arthroplasty outcome: learning from 20 years of propensity score matched registry data

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  1. Tranexamic Acid in Patients Undergoing Noncardiac Surgery

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. Reasons for staying in hospital after video-assisted thoracoscopic surgery lobectomy

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  3. AHA STEROID trial, dexamethasone in acute high-risk abdominal surgery, the protocol for a randomized controlled trial

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  4. Continuous monitoring of vital sign abnormalities; association to clinical complications in 500 postoperative patients

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  5. Functional recovery after discharge in enhanced recovery video-assisted thoracoscopic lobectomy: a pilot prospective cohort study

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  • Centre for Fast-track Hip and Knee Replacement Collaborative Group
  • Mikkel Rathsach Andersen (Medlem af forfattergruppering)
Vis graf over relationer

Background and purpose - Prediction of postoperative outcomes and length of hospital stay (LOS) of patients is vital for allocation of healthcare resources. We investigated the performance of prediction models based on machinelearning algorithms compared with a previous risk stratification model using traditional multiple logistic regression, for predicting the risk of a LOS of > 2 days after fast-track total hip and knee replacement. Patients and methods - 3 different machine learning classifiers were trained on data from the Lundbeck Centre for Fast-track Hip and Knee Replacement Database (LCDB) collected from 9,512 patients between 2016 and 2017. The chosen classifiers were a random forest classifier (RF), a support vector machine classifier with a polynomial kernel (SVM), and a multinomial Naïve-Bayes classifier (NB). Results - Comparing performance measures of the classifiers with the traditional model revealed that all the models had a similar performance in terms of F1 score, accuracy, sensitivity, specificity, area under the receiver operating curve (AUC), and area under the precision-recall curve (AUPRC). A feature importance analysis of the RF classifier found hospital, age, use of walking aid, living alone, and joint operated on to be the most relevant input features. None of the classifiers reached a clinically relevant performance with the input data from the LCDB. Interpretation - Despite the promising prospects of machine-learning practices for disease and risk prediction, none of the machine learning models tested outperformed the traditional multiple regression model in predicting which patients in this cohort had a LOS > 2 days.

OriginalsprogEngelsk
TidsskriftActa Orthopaedica
Vol/bind93
Sider (fra-til)117-123
Antal sider7
ISSN1745-3674
DOI
StatusUdgivet - 2022

ID: 70353386