Cargando…

Explainable AI identifies diagnostic cells of genetic AML subtypes

Explainable AI is deemed essential for clinical applications as it allows rationalizing model predictions, helping to build trust between clinicians and automated decision support tools. We developed an inherently explainable AI model for the classification of acute myeloid leukemia subtypes from bl...

Descripción completa

Detalles Bibliográficos
Autores principales: Hehr, Matthias, Sadafi, Ario, Matek, Christian, Lienemann, Peter, Pohlkamp, Christian, Haferlach, Torsten, Spiekermann, Karsten, Marr, Carsten
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10016704/
https://www.ncbi.nlm.nih.gov/pubmed/36921004
http://dx.doi.org/10.1371/journal.pdig.0000187
_version_ 1784907459895230464
author Hehr, Matthias
Sadafi, Ario
Matek, Christian
Lienemann, Peter
Pohlkamp, Christian
Haferlach, Torsten
Spiekermann, Karsten
Marr, Carsten
author_facet Hehr, Matthias
Sadafi, Ario
Matek, Christian
Lienemann, Peter
Pohlkamp, Christian
Haferlach, Torsten
Spiekermann, Karsten
Marr, Carsten
author_sort Hehr, Matthias
collection PubMed
description Explainable AI is deemed essential for clinical applications as it allows rationalizing model predictions, helping to build trust between clinicians and automated decision support tools. We developed an inherently explainable AI model for the classification of acute myeloid leukemia subtypes from blood smears and found that high-attention cells identified by the model coincide with those labeled as diagnostically relevant by human experts. Based on over 80,000 single white blood cell images from digitized blood smears of 129 patients diagnosed with one of four WHO-defined genetic AML subtypes and 60 healthy controls, we trained SCEMILA, a single-cell based explainable multiple instance learning algorithm. SCEMILA could perfectly discriminate between AML patients and healthy controls and detected the APL subtype with an F1 score of 0.86±0.05 (mean±s.d., 5-fold cross-validation). Analyzing a novel multi-attention module, we confirmed that our algorithm focused with high concordance on the same AML-specific cells as human experts do. Applied to classify single cells, it is able to highlight subtype specific cells and deconvolve the composition of a patient’s blood smear without the need of single-cell annotation of the training data. Our large AML genetic subtype dataset is publicly available, and an interactive online tool facilitates the exploration of data and predictions. SCEMILA enables a comparison of algorithmic and expert decision criteria and can present a detailed analysis of individual patient data, paving the way to deploy AI in the routine diagnostics for identifying hematopoietic neoplasms.
format Online
Article
Text
id pubmed-10016704
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-100167042023-03-16 Explainable AI identifies diagnostic cells of genetic AML subtypes Hehr, Matthias Sadafi, Ario Matek, Christian Lienemann, Peter Pohlkamp, Christian Haferlach, Torsten Spiekermann, Karsten Marr, Carsten PLOS Digit Health Research Article Explainable AI is deemed essential for clinical applications as it allows rationalizing model predictions, helping to build trust between clinicians and automated decision support tools. We developed an inherently explainable AI model for the classification of acute myeloid leukemia subtypes from blood smears and found that high-attention cells identified by the model coincide with those labeled as diagnostically relevant by human experts. Based on over 80,000 single white blood cell images from digitized blood smears of 129 patients diagnosed with one of four WHO-defined genetic AML subtypes and 60 healthy controls, we trained SCEMILA, a single-cell based explainable multiple instance learning algorithm. SCEMILA could perfectly discriminate between AML patients and healthy controls and detected the APL subtype with an F1 score of 0.86±0.05 (mean±s.d., 5-fold cross-validation). Analyzing a novel multi-attention module, we confirmed that our algorithm focused with high concordance on the same AML-specific cells as human experts do. Applied to classify single cells, it is able to highlight subtype specific cells and deconvolve the composition of a patient’s blood smear without the need of single-cell annotation of the training data. Our large AML genetic subtype dataset is publicly available, and an interactive online tool facilitates the exploration of data and predictions. SCEMILA enables a comparison of algorithmic and expert decision criteria and can present a detailed analysis of individual patient data, paving the way to deploy AI in the routine diagnostics for identifying hematopoietic neoplasms. Public Library of Science 2023-03-15 /pmc/articles/PMC10016704/ /pubmed/36921004 http://dx.doi.org/10.1371/journal.pdig.0000187 Text en © 2023 Hehr et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Hehr, Matthias
Sadafi, Ario
Matek, Christian
Lienemann, Peter
Pohlkamp, Christian
Haferlach, Torsten
Spiekermann, Karsten
Marr, Carsten
Explainable AI identifies diagnostic cells of genetic AML subtypes
title Explainable AI identifies diagnostic cells of genetic AML subtypes
title_full Explainable AI identifies diagnostic cells of genetic AML subtypes
title_fullStr Explainable AI identifies diagnostic cells of genetic AML subtypes
title_full_unstemmed Explainable AI identifies diagnostic cells of genetic AML subtypes
title_short Explainable AI identifies diagnostic cells of genetic AML subtypes
title_sort explainable ai identifies diagnostic cells of genetic aml subtypes
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10016704/
https://www.ncbi.nlm.nih.gov/pubmed/36921004
http://dx.doi.org/10.1371/journal.pdig.0000187
work_keys_str_mv AT hehrmatthias explainableaiidentifiesdiagnosticcellsofgeneticamlsubtypes
AT sadafiario explainableaiidentifiesdiagnosticcellsofgeneticamlsubtypes
AT matekchristian explainableaiidentifiesdiagnosticcellsofgeneticamlsubtypes
AT lienemannpeter explainableaiidentifiesdiagnosticcellsofgeneticamlsubtypes
AT pohlkampchristian explainableaiidentifiesdiagnosticcellsofgeneticamlsubtypes
AT haferlachtorsten explainableaiidentifiesdiagnosticcellsofgeneticamlsubtypes
AT spiekermannkarsten explainableaiidentifiesdiagnosticcellsofgeneticamlsubtypes
AT marrcarsten explainableaiidentifiesdiagnosticcellsofgeneticamlsubtypes