Creative Commons source reading · Explainable decision support
Self-explaining artificial intelligence for the classification of B cell non-Hodgkin lymphoma: A diagnostic decision support study
Thrun MC; Hoffmann J; Krause SW; Krawitz P; Stier Q; Neubauer A; Brendel C; Ultsch A
Originally published in PLoS Med · 2026-07-13
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
Abstract
AbstractBackgroundMultiparameter flow cytometry is a cornerstone of B cell non-Hodgkin lymphoma (B-NHL) diagnostics, but interpretation requires substantial expertise and is complicated by high-dimensional data, variable sample quality, limited data for rare entities, and evolving clinical classification systems. Current artificial intelligence approaches often require large training datasets and provide limited insight into the rationale behind individual diagnostic decisions.Methods and findingsWe developed FlowXAI, a self-explaining artificial intelligence system designed to support B-NHL classification while explicitly reporting case-level diagnostic trustworthiness. FlowXAI combines unsupervised structural analysis with a clinically motivated, multi-level diagnostic framework reflecting routine diagnostic priorities. An…
Discussion
The FlowXAI system was designed as a supportive tool for assisting and teaching the diagnostic process of B-NHL using multiparameter flow cytometry–based immunophenotyping. To ensure that diagnostic performance was assessed against clinically relevant reference standards, both datasets were accompanied by comprehensive clinical evidence, including genetic and histopathological information, as previously published [6,7]. Following the initial descriptions of Hodgkin lymphoma in 1832 and non-Hodgkin lymphoma in 1925, multiple classification systems coexisted until the Revised European and American Lymphoma (R.E.A.L.) classification was introduced in 1994, incorporating immunopathological aspects for the first time. This framework was subsequently replaced by the World Health Organization (WHO) classification, with its 5th edition…
Editorial reading guide
- What data created and tested the model, and was evaluation independent?
- What is the cost of a false positive, false negative or out-of-distribution decision?
