AIPSS (Artificial Intelligence Prognostic Scoring System) & Molecular Predictors

Welcome to our app designed to assist physicians in predicting patient risk in myelofibrosis. This application offers two distinct calculators to facilitate comprehensive risk assessment based on various criteria:

  1. AIPSS: Utilizes clinical data alone to provide an estimation of Overall survival (OS).
  2. AIPSS-M: Integrates clinical and molecular data to predict OS and Leukemia-free survival (LFS).
Our interface is organized with a navigable menu to easily switch between these calculators. Please note that to access the AIPSS-M Calculator, you must first enter the requisite clinical and genomic information.

Clinical Data

Age

Hemoglobin (g/L)

e.g. 13 g/dl = 130 g/L

Leukocytes (10^9/L)

e.g. 6000 mcL = 6x10^9/L

Platelets (10^9/L)

e.g. 250000 mcL = 250 x 10^9/L

Blood Blasts (%)

Sex

Constitutional Symptoms

Leukoerythroblastosis

  • Only pathogenic or likely pathogenic variants with a variant allele frequency (VAF) of at least 1% should be considered.
  • All values must be introduced as percentages (e.g. "30").
  • Multiple gene mutations must be introduced separated by comma (e.g. "40,35").

Combine Molecular Data and Clinical Data

Risk Bars
The risk bar graphically represents a patient's risk level as a percentile, ranging from 0 to 100. A score of 0 signifies minimum risk, while 100 represents maximum risk . Visually, the bar evolves in color from green to red to indicate the level of risk: green denotes low risk, and red signifies high risk. This percentile and color-coded system provides an immediate, intuitive understanding of how a patient's risk compares to the broader population, assisting in informed medical decision-making.
Molecular data
Multiple mutation values for a gene can be entered, separated by commas. Each value should represent the mutation percentage and must fall within the range of 1-100%. For instance, if you want to enter three different JAK2 mutation percentages, input should look like "40,20,70", with each number separated by a comma.
Interactive plots
The app features interactive plots that offer a range of functionalities for enhanced data analysis. You can zoom in for a closer look, navigate through the plot to obtain precise X-Y values, and files.
Reference
Mosquera-Orgueira A, Pérez-Encinas M, Hernández-Sánchez A, González-Martínez T, Arellano-Rodrigo E, Martínez-Elicegui J, Villaverde-Ramiro Á, Raya JM, Ayala R, Ferrer-Marín F, Fox ML, Velez P, Mora E, Xicoy B, Mata-Vázquez MI, García-Fortes M, Angona A, Cuevas B, Senín MA, Ramírez-Payer A, Ramírez MJ, Pérez-López R, González de Villambrosía S, Martínez-Valverde C, Gómez-Casares MT, García-Hernández C, Gasior M, Bellosillo B, Steegmann JL, Álvarez-Larrán A, Hernández-Rivas JM, Hernández-Boluda JC. Machine Learning Improves Risk Stratification in Myelofibrosis: An Analysis of the Spanish Registry of Myelofibrosis. Hemasphere. 2022 Dec 20;7(1):e818. doi: 10.1097/HS9.0000000000000818. PMID: 36570691; PMCID: PMC9771324.