PMID- 37763160
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20231003
IS  - 2075-4426 (Print)
IS  - 2075-4426 (Electronic)
IS  - 2075-4426 (Linking)
VI  - 13
IP  - 9
DP  - 2023 Sep 18
TI  - Comparing Machine Learning Classifiers for Predicting Hospital Readmission of 
      Heart Failure Patients in Rwanda.
LID - 10.3390/jpm13091393 [doi]
LID - 1393
AB  - High rates of hospital readmission and the cost of treating heart failure (HF) 
      are significant public health issues globally and in Rwanda. Using machine 
      learning (ML) to predict which patients are at high risk for HF hospital 
      readmission 20 days after their discharge has the potential to improve HF 
      management by enabling early interventions and individualized treatment 
      approaches. In this paper, we compared six different ML models for this task, 
      including multi-layer perceptron (MLP), K-nearest neighbors (KNN), logistic 
      regression (LR), decision trees (DT), random forests (RF), and support vector 
      machines (SVM) with both linear and radial basis kernels. The outputs of the 
      classifiers are compared using performance metrics including the area under the 
      receiver operating characteristic curve (AUC), sensitivity, and specificity. We 
      found that RF outperforms all the remaining models with an AUC of 94% while SVM, 
      MLP, and KNN all yield 88% AUC. In contrast, DT performs poorly, with an AUC 
      value of 57%. Hence, hospitals in Rwanda can benefit from using the RF classifier 
      to determine which HF patients are at high risk of hospital readmission.
FAU - Rizinde, Theogene
AU  - Rizinde T
AD  - College of Business and Economics, University of Rwanda, Kigali 4285, Rwanda.
FAU - Ngaruye, Innocent
AU  - Ngaruye I
AUID- ORCID: 0000-0002-6750-3572
AD  - College of Science and Technology, University of Rwanda, Kigali 4285, Rwanda.
FAU - Cahill, Nathan D
AU  - Cahill ND
AUID- ORCID: 0000-0002-6164-3291
AD  - School of Mathematics and Statistics, Rochester Institute of Technology, 
      Rochester, NY 14623, USA.
LA  - eng
GR  - NCST-NRIF/ERG-BATCH1/P04/2019/Rwanda National Council for Science and Technology/
PT  - Journal Article
DEP - 20230918
PL  - Switzerland
TA  - J Pers Med
JT  - Journal of personalized medicine
JID - 101602269
PMC - PMC10532623
OTO - NOTNLM
OT  - HF
OT  - ML algorithm
OT  - Rwanda
OT  - hospital readmission
COIS- The authors declare no conflict of interest.
EDAT- 2023/09/28 06:42
MHDA- 2023/09/28 06:43
PMCR- 2023/09/18
CRDT- 2023/09/28 01:24
PHST- 2023/08/02 00:00 [received]
PHST- 2023/08/22 00:00 [revised]
PHST- 2023/08/28 00:00 [accepted]
PHST- 2023/09/28 06:43 [medline]
PHST- 2023/09/28 06:42 [pubmed]
PHST- 2023/09/28 01:24 [entrez]
PHST- 2023/09/18 00:00 [pmc-release]
AID - jpm13091393 [pii]
AID - jpm-13-01393 [pii]
AID - 10.3390/jpm13091393 [doi]
PST - epublish
SO  - J Pers Med. 2023 Sep 18;13(9):1393. doi: 10.3390/jpm13091393.