Fusion Survival Path
The survival path is a machine learning analytical approach, which automatically converts the timeseries data of cancer patients into a cascading survival map based selected key prognostic features at different times. The aim of the model is to facilitate dynamic prognosis prediction and potential treatment planning. The fusion survival path model added in the function of fusion of neighbor nodes using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. Th fusion SP showed enhanced performance compared to conventional SP model in generalization.
The code and demonstration data is publicly available on github a https://github.com/CMXyiduyun/Fusion-survival-path.
2025-2-11:
The web-based interface of fusion survival path model is formally established, with the main function of building survival path model available by clicking on the “Analysis” button.
The researchers need to prepare their own dataset in order to build new models. All datasets/documents will be erased when the website is closed to ensure the data security of users.
Citation:
Shen L, Jiang Y, Lu L, et al. Dynamic prognostication and treatment planning for hepatocellular carcinoma: A machine learning-enhanced survival study using multi-centric data. The Innovation Medicine. 2025;3:100125. doi: 10.59717/j.xinn-med.2025.100125.
Shen L, Zeng Q, Guo P, Huang J, Li C, Pan T, Chang B, Wu N, Yang L, Chen Q, Huang T, Li W, Wu P. Dynamically prognosticating patients with hepatocellular carcinoma through survival paths mapping based on time-series data. Nat Commun. 2018 Jun 8;9(1):2230. doi: 10.1038/s41467-018-04633-7.
Shen L, Mo J, Yang C, Jiang Y, Ke L, Hou D, Yan J, Zhang T, Fan W. SurvivalPath:A R package for conducting personalized survival path mapping based on time-series survival data. PLoS Comput Biol. 2023 Jan 6;19(1):e1010830. doi: 10.1371/journal.pcbi.1010830.