Prediction of Clinical Outcomes with Explainable Artificial Intelligence in Patients with Chronic Lymphocytic Leukemia.

Autor: Hoffmann J; Department of Hematology, Oncology and Immunology, Philipps University Marburg, University Hospital Giessen and Marburg, Baldingerstrasse, 35043 Marburg, Germany., Eminovic S; Department of Hematology, Oncology and Immunology, Philipps University Marburg, University Hospital Giessen and Marburg, Baldingerstrasse, 35043 Marburg, Germany., Wilhelm C; Department of Hematology, Oncology and Immunology, Philipps University Marburg, University Hospital Giessen and Marburg, Baldingerstrasse, 35043 Marburg, Germany., Krause SW; Department of Medicine 5, Universitätsklinikum Erlangen, Maximiliansplatz 2, 91054 Erlangen, Germany., Neubauer A; Department of Hematology, Oncology and Immunology, Philipps University Marburg, University Hospital Giessen and Marburg, Baldingerstrasse, 35043 Marburg, Germany., Thrun MC; Databionics, Mathematics and Computer Science, Philipps University Marburg, Hans-Meerwein-Strasse 6, 35032 Marburg, Germany., Ultsch A; Databionics, Mathematics and Computer Science, Philipps University Marburg, Hans-Meerwein-Strasse 6, 35032 Marburg, Germany., Brendel C; Department of Hematology, Oncology and Immunology, Philipps University Marburg, University Hospital Giessen and Marburg, Baldingerstrasse, 35043 Marburg, Germany.
Jazyk: angličtina
Zdroj: Current oncology (Toronto, Ont.) [Curr Oncol] 2023 Feb 04; Vol. 30 (2), pp. 1903-1915. Date of Electronic Publication: 2023 Feb 04.
DOI: 10.3390/curroncol30020148
Abstrakt: Background: The International Prognostic Index (IPI) is applied to predict the outcome of chronic lymphocytic leukemia (CLL) with five prognostic factors, including genetic analysis. We investigated whether multiparameter flow cytometry (MPFC) data of CLL samples could predict the outcome by methods of explainable artificial intelligence (XAI). Further, XAI should explain the results based on distinctive cell populations in MPFC dot plots.
Methods: We analyzed MPFC data from the peripheral blood of 157 patients with CLL. The ALPODS XAI algorithm was used to identify cell populations that were predictive of inferior outcomes (death, failure of first-line treatment). The diagnostic ability of each XAI population was evaluated with receiver operating characteristic (ROC) curves.
Results: ALPODS defined 17 populations with higher ability than the CLL-IPI to classify clinical outcomes (ROC: area under curve (AUC) 0.95 vs. 0.78). The best single classifier was an XAI population consisting of CD4+ T cells (AUC 0.78; 95% CI 0.70-0.86; p < 0.0001). Patients with low CD4+ T cells had an inferior outcome. The addition of the CD4+ T-cell population enhanced the predictive ability of the CLL-IPI (AUC 0.83; 95% CI 0.77-0.90; p < 0.0001).
Conclusions: The ALPODS XAI algorithm detected highly predictive cell populations in CLL that may be able to refine conventional prognostic scores such as IPI.
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje