Hong Kong Med J 2023;29(Suppl 1):S24-6
High-dimensional machine learning to predict hospital readmission among older people with chronic kidney disease: abridged secondary publication
Q Zhang1, E Leung2, JTF Lau2, KKF Tsoi2, HY So3, WWS Ho4, SCY Cheung5
1 School of Data Science, City University of Hong Kong, Hong Kong SAR, China
2 The Jockey Club School of Public Health and Primary Care, The Chinese University of Hong Kong, Hong Kong SAR, China
3 Department of Quality and Safety, Prince of Wales Hospital, Hong Kong SAR, China
4 Department of Medicine and Therapeutics, Prince of Wales Hospital, Hong Kong SAR, China
5 Department of Medicine, Queen Elizabeth Hospital, Hong Kong SAR, China
 
 
  1. A novel factorisation-based machine-learning model, which is Hong Kong–weighted with fuzzy partition, is proposed to predict the risk of hospital readmission among patients with chronic kidney disease.
  2. This is one of the first machine-learning models for readmission prediction based on territory-wide data in Hong Kong.
  3. Application of this model may help reduce the cost of hospital management and improve the quality of life among patients with chronic kidney disease.