PMID- 36897699
OWN - NLM
STAT- MEDLINE
DCOM- 20230314
LR  - 20230916
IS  - 1536-5964 (Electronic)
IS  - 0025-7974 (Print)
IS  - 0025-7974 (Linking)
VI  - 102
IP  - 10
DP  - 2023 Mar 10
TI  - Which model is better in predicting the survival of laryngeal squamous cell 
      carcinoma?: Comparison of the random survival forest based on machine learning 
      algorithms to Cox regression: analyses based on SEER database.
PG  - e33144
LID - 10.1097/MD.0000000000033144 [doi]
LID - e33144
AB  - Prediction of postoperative survival for laryngeal carcinoma patients is very 
      important. This study attempts to demonstrate the utilization of the random 
      survival forest (RSF) and Cox regression model to predict overall survival of 
      laryngeal squamous cell carcinoma (LSCC) and compare their performance. A total 
      of 8677 patients diagnosed with LSCC from 2004 to 2015 were obtained from 
      surveillance, epidemiology, and end results database. Multivariate imputation by 
      chained equations was applied to filling the missing data. Lasso regression 
      algorithm was conducted to find potential predictors. RSF and Cox regression were 
      used to develop the survival prediction models. Harrell's concordance index 
      (C-index), area under the curve (AUC), Brier score, and calibration plot were 
      used to evaluate the predictive performance of the 2 models. For 3-year survival 
      prediction, the C-index in training set were 0.74 (0.011) and 0.84 (0.013) for 
      Cox and RSF respectively. For 5-year survival prediction, the C-index in training 
      set were 0.75 (0.022) and 0.80 (0.011) for Cox and RSF respectively. Similar 
      results were found in validation set. The AUC were 0.795 for RSF and 0.715 for 
      Cox in the training set while the AUC were 0.765 for RSF and 0.705 for Cox in the 
      validation set. The prediction error curves for each model based on Brier score 
      showed the RSF model had lower prediction errors both in training group and 
      validation group. What's more, the calibration curve displayed similar results of 
      2 models both in training set and validation set. The performance of RSF model 
      were better than Cox regression model. The RSF algorithms provide a relatively 
      better alternatives to be of clinical use for estimating the survival probability 
      of LSCC patients.
CI  - Copyright (c) 2023 the Author(s). Published by Wolters Kluwer Health, Inc.
FAU - Sun, Haili
AU  - Sun H
AD  - Ping Yang Hospital Affiliated to Wenzhou Medical University, Wenzhou, China.
FAU - Wu, Shuangshuang
AU  - Wu S
AD  - Ping Yang Hospital Affiliated to Wenzhou Medical University, Wenzhou, China.
FAU - Li, Shaoxiao
AU  - Li S
AD  - Ping Yang Hospital Affiliated to Wenzhou Medical University, Wenzhou, China.
FAU - Jiang, Xiaohua
AU  - Jiang X
AUID- ORCID: 0000-0001-6851-8090
AD  - Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, 
      China.
LA  - eng
PT  - Journal Article
PL  - United States
TA  - Medicine (Baltimore)
JT  - Medicine
JID - 2985248R
SB  - IM
MH  - Humans
MH  - Squamous Cell Carcinoma of Head and Neck
MH  - *Algorithms
MH  - Random Forest
MH  - Machine Learning
MH  - *Head and Neck Neoplasms
PMC - PMC9997795
COIS- The authors have no funding and conflicts of interest to disclose.
EDAT- 2023/03/11 06:00
MHDA- 2023/03/15 06:00
PMCR- 2023/03/10
CRDT- 2023/03/10 12:04
PHST- 2023/03/10 12:04 [entrez]
PHST- 2023/03/11 06:00 [pubmed]
PHST- 2023/03/15 06:00 [medline]
PHST- 2023/03/10 00:00 [pmc-release]
AID - 00005792-202303100-00034 [pii]
AID - 10.1097/MD.0000000000033144 [doi]
PST - ppublish
SO  - Medicine (Baltimore). 2023 Mar 10;102(10):e33144. doi: 
      10.1097/MD.0000000000033144.