PMID- 38298506
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240202
IS  - 2296-858X (Print)
IS  - 2296-858X (Electronic)
IS  - 2296-858X (Linking)
VI  - 10
DP  - 2023
TI  - Random forest can accurately predict the technique failure of peritoneal dialysis 
      associated peritonitis patients.
PG  - 1335232
LID - 10.3389/fmed.2023.1335232 [doi]
LID - 1335232
AB  - INSTRUCTIONS: Peritoneal dialysis associated peritonitis (PDAP) is a major cause 
      of technique failure in peritoneal dialysis (PD) patients. The purpose of this 
      study is to construct risk prediction models by multiple machine learning (ML) 
      algorithms and select the best one to predict technique failure in PDAP patients 
      accurately. METHODS: This retrospective cohort study included maintenance PD 
      patients in our center from January 1, 2010 to December 31, 2021. The risk 
      prediction models for technique failure were constructed based on five ML 
      algorithms: random forest (RF), the least absolute shrinkage and selection 
      operator (LASSO), decision tree, k nearest neighbor (KNN), and logistic 
      regression (LR). The internal validation was conducted in the test cohort. 
      RESULTS: Five hundred and eight episodes of peritonitis were included in this 
      study. The technique failure accounted for 26.38%, and the mortality rate was 
      4.53%. There were resignificant statistical differences between technique failure 
      group and technique survival group in multiple baseline characteristics. The RF 
      prediction model is the best able to predict the technique failure in PDAP 
      patients, with the accuracy of 93.70% and area under curve (AUC) of 0.916. The 
      sensitivity and specificity of this model was 96.67 and 86.49%, respectively. 
      CONCLUSION: RF prediction model could accurately predict the technique failure of 
      PDAP patients, which demonstrated excellent predictive performance and may assist 
      in clinical decision making.
CI  - Copyright (c) 2024 Zang, Xu, Zhou, Ma, Pu, Tang and Li.
FAU - Zang, Zhiyun
AU  - Zang Z
AD  - Department of Nephrology, Institute of Nephrology, West China Hospital of Sichuan 
      University, Chengdu, China.
FAU - Xu, Qijiang
AU  - Xu Q
AD  - Department of Nephrology, Institute of Nephrology, West China Hospital of Sichuan 
      University, Chengdu, China.
AD  - Department of Nephrology, Yibin Second People's Hospital, Yibin, China.
FAU - Zhou, Xueli
AU  - Zhou X
AD  - Department of Nephrology, Institute of Nephrology, West China Hospital of Sichuan 
      University, Chengdu, China.
FAU - Ma, Niya
AU  - Ma N
AD  - Department of Nephrology, Institute of Nephrology, West China Hospital of Sichuan 
      University, Chengdu, China.
FAU - Pu, Li
AU  - Pu L
AD  - Department of Nephrology, Institute of Nephrology, West China Hospital of Sichuan 
      University, Chengdu, China.
FAU - Tang, Yi
AU  - Tang Y
AD  - Department of Nephrology, Institute of Nephrology, West China Hospital of Sichuan 
      University, Chengdu, China.
FAU - Li, Zi
AU  - Li Z
AD  - Department of Nephrology, Institute of Nephrology, West China Hospital of Sichuan 
      University, Chengdu, China.
LA  - eng
PT  - Journal Article
DEP - 20240117
PL  - Switzerland
TA  - Front Med (Lausanne)
JT  - Frontiers in medicine
JID - 101648047
PMC - PMC10829598
OTO - NOTNLM
OT  - machine learning algorithms
OT  - peritoneal dialysis
OT  - peritonitis
OT  - prediction model
OT  - technique failure
COIS- The authors declare that the research was conducted in the absence of any 
      commercial or financial relationships that could be construed as a potential 
      conflict of interest.
EDAT- 2024/02/01 06:43
MHDA- 2024/02/01 06:44
PMCR- 2024/01/17
CRDT- 2024/02/01 04:09
PHST- 2023/11/08 00:00 [received]
PHST- 2023/12/27 00:00 [accepted]
PHST- 2024/02/01 06:44 [medline]
PHST- 2024/02/01 06:43 [pubmed]
PHST- 2024/02/01 04:09 [entrez]
PHST- 2024/01/17 00:00 [pmc-release]
AID - 10.3389/fmed.2023.1335232 [doi]
PST - epublish
SO  - Front Med (Lausanne). 2024 Jan 17;10:1335232. doi: 10.3389/fmed.2023.1335232. 
      eCollection 2023.