Automating the referral pathways for Multiple Myeloma through a Web Application and XMDD

Authors

  • Adam Doherty University of Limerick

DOI:

https://doi.org/10.14279/tuj.eceasst.81.1200

Abstract

Multiple Myeloma (MM), a type of bone marrow cancer, is diagnosed by measuring monoclonal proteins, paraproteins (PP), and serum-free light chains (SFLC) in the blood. These proteins can be detected in healthy individuals at a lower level. This condition is called Monoclonal Gammopathy of Uncertain Significance (MGUS). MGUS is associated with a risk of progression to MM at a rate of 1-2% per year. Early diagnosis of MM correlates with improved overall survival for patients, so early referral of suspect cases is important. Two risk factors determine the risk of progression: a high-level PP (>15g/l) and an abnormal SFLC ratio. This risk stratification process enables General Practitioners (essentially, the family doctors) to manage the patients with low-risk MGUS and provides clear referral pathways for intermediate and high-risk MGUS patients. There are a reference algorithm and a scoring system for patient referrals with possible Multiple Myeloma, that in the current practice are processed manually by trained healthcare staff. In collaboration with the Haematology experts at the University Hospital Limerick and the SCCE group in Computer Science, we designed and implemented a software application that improves and streamlines the current process. This (online) application is developed with modern XMDD technology, using the DIME low-code application development tool. The application faithfully maps the reference algorithm in an automated way and applies it to a consultation data-set. The novelty consists in the adopted technologies, that improve the early validation and correctness of the software, and ease the human understanding and the modification turnaround of the application.

Downloads

Published

2022-11-22

How to Cite

[1]
A. Doherty, “Automating the referral pathways for Multiple Myeloma through a Web Application and XMDD”, eceasst, vol. 81, Nov. 2022.