I have been playing with the KM Estimator. Oncology is probably the heaviest user of KM Estimation.
At present, the group column is not permitted any null values, and there is no possibility of selection of subgroups for analysis - you just have to hive off multiple groups then do a KM Estimation.
The output of the plot to a PNG file does not seem possible, only a print to PDF and that looks truncated.
I have some suggestions on functionality.
-
include an option to output to PNG file with a definable name and location
-
when a group is chosen for analysis, permit the choice of 1 or more of the values (these values are listed in the Spec- columns view when viewing the filtered spreadsheet [see image below])
-
Permit the selection of groups.
3a. For example, cancers with the ICD10 codes of C00-C14 and C30-C32 are all grouped into “Head & Neck Cancers”
3b. For example, I may wish to compare a group of cancers (i.e., only C01, C08, C09) with a particular biological parameter (i.e., was p16+ or p16-) and a particular treatment (i.e., had chemotherapy or immunotherapy). This is a frequently used analysis type in medicine. -
where there is no selection of groups (see #2), the null/blank entries should be ignored. This could also be added as an option (Ignore blanks/Ignore nulls).
-
Adding in a Cox Log-Rank statistic would be very very useful.
-
Adding in the 95% Confidence Interval would also be useful
Please understand that I am unable to make these changes myself, but I am a heavy user of KM analysis. The dataset on which I undertook my learning curve has 30,774 rows of cancer data, and the analyses that I list above are what I want to do. The ICD10 Diagnosis list has over a hundred categories. I will most certainly want to analyse Breast cancers separately to Lung cancers.
If you undertake the refinements and wish to dialogue, I am more than happy to take the time and do testing on real data.
A
