Dear all,
I have created a risk score (point-based risk score) to predict time to brain metastases from covariates selected with a backward approach. My risk score ranges from 0 to 45. I need to classify my patients into 4 risk groups:low/intermediate low/ intermediate high/high. My question is: can I use a clustering approach like k-means, by including my clinical characteristics and my risk score, to obtain clusters with similar risk scores and clinical characteristics?
Thank you in advance for your help.
•
written
by
julia.gilhodes •
1 answer
A general answer to your question is yes. In practice, it depends on how many features (clinical characteristics) and data points (patients) you have. It also matters what you plan to do with these clusters: are they just for internal bookkeeping or for future diagnostics? If you are planning to classify/diagnose new patients, I think it may be better to do a formal machine learning approach with (cross)validation, and test it on unseen data. That will also depend on the number of data points and informative features.
There is a great risk of overfitting if you simply cluster based on presently available data, especially if the dataset size is small.
Log in to answer this question.
-
Comparison of ssGSEA scores across different datasets
written by james.zhang20 •
-
Using TidyEstimate scores in the Design Matrix of DESeq2
written by Abhishek •
-
Best way for risk scoring a single sample
written by picsels •
-
General approach for unsupervised clustering of bulk RNAseq samples and deriving/applying gene sign…
written by Mat •
-
Comparing several prognosis scores
written by Hashirama •
-
clusters with no enrichment?
written by demoraesdiogo2017 •
-
data values' transformation and P-value of Cox log rank test
written by huynguyen96.dnu •
-
How to use TCGA data for cancer prediction and prognosis ?
written by Ld_60 •
-
Job: Bioinformatics postdoc at Duke University, USA
written by avb •
-
Select patients for cancer classifier
written by juncheng
