MPN Personalised Risk Calculator

MPN Personalised Risk Calculator

Input New Patient Data

Enter data for new patient. Unknown data will be imputed from available variables.

Input New Patient Data From File

Download data template (.csv file) Download Template
Complete template using 0/1 for absence/presence. Age in years, Haemoglobin in g/l, white cell and platelet counts x10^9/l, 1 for female, 2 for male For unknown variables: leave as NA and this will be imputed

Patient Description
Patient Outcomes

Frequency of genomic variables across MPN phenotypes

This web tool allows for the input of clinical and genomic information from individual patients with Myeloproliferative Neoplasms to provide personalised predictions on patient outcome and disease progression. It is based on data and prognostic models from Grinfeld and Nangalia et al. 2018.

The original publication can be found at

This calculator is intended as an adjunct to the paper and for research purposes only.
It has not been prospectively validated. Data regarding the accuracy of the model are provided in the publication. In general, predictions are accurate in approximately 80% of cases.

To generate individual patient prognostic predictions: First select the diagnosis of interest: ET, PV, MF or other (MPNu, MDS/MPN overlap, etc).
Then choose between:

  • Selecting a patient already used in the analysis to view their clinical and genomic parameters, predicted and actual outcomes,
  • Inputting variables for a new patient by manually inputting variables, or
  • Inputting variables for a new patient by downloading, completing and uploading a csv template file.

  • Please click on the 'Calculate Risk' button to generate predictions.

Please note that changes in input parameters will only reflect in the predictions following 'Calculate Risk' being clicked.
If you need to generate a downloadable report, please make sure that you click on 'Calculate Risk' for the selected patient before you generate a report for that particular patient.

Outcome predictions are from diagnosis and assume that all input parameters are present at diagnosis. If the time of genomic sampling is post diagnosis then we suggest adjusting patient age to time of genomic sampling, and to use this as the starting time for predictions.

The Genomics tab allows the user to view the frequency of mutations(s) across MPN subtypes.

Please address clinical queries to Dr Jyoti Nangalia or Dr Jacob Grinfeld.
Please address technical queries related to the web site and the app functionality to Dr Eugene Nadezhdin or Dr Jyoti Nangalia.

Shiny implementation - Jacob Grinfeld, with additional work by Eugene Nadezhdin.

Last update: August 2020.