학술논문
An artificial intelligence-assisted clinical framework to facilitate diagnostics and translational discovery in hematologic neoplasia.
Document Type
Academic Journal
Author
Tang M; Department of Human Genetics, Hannover Medical School, Hannover, Germany; L3S Research Centre, Leibniz University Hannover, Germany.; Antić Ž; Department of Human Genetics, Hannover Medical School, Hannover, Germany.; Fardzadeh P; L3S Research Centre, Leibniz University Hannover, Germany.; Pietzsch S; Department of Human Genetics, Hannover Medical School, Hannover, Germany.; Schröder C; Department of Human Genetics, Hannover Medical School, Hannover, Germany.; Eberhardt A; L3S Research Centre, Leibniz University Hannover, Germany.; van Bömmel A; Leibniz Institute on Aging - Fritz Lipmann Institute (FLI), Jena, Germany.; Escherich G; Clinic of Paediatric Haematology and Oncology, University Medical Centre Hamburg-Eppendorf, Hamburg, Germany.; Hofmann W; Department of Human Genetics, Hannover Medical School, Hannover, Germany.; Horstmann MA; Clinic of Paediatric Haematology and Oncology, University Medical Centre Hamburg-Eppendorf, Hamburg, Germany; Research Institute Children's Cancer Centre Hamburg, Hamburg, Germany.; Illig T; Hannover Unified Bio Bank, Hannover Medical School, Hannover, Germany.; McCrary JM; Department of Human Genetics, Hannover Medical School, Hannover, Germany.; Lentes J; Department of Human Genetics, Hannover Medical School, Hannover, Germany.; Metzler M; Department of Paediatrics, University Hospital Erlangen, Erlangen, Germany.; Nejdl W; L3S Research Centre, Leibniz University Hannover, Germany.; Schlegelberger B; Department of Human Genetics, Hannover Medical School, Hannover, Germany.; Schrappe M; Department of Paediatrics, University Medical Centre Schleswig-Holstein, Campus Kiel, Kiel, Germany.; Zimmermann M; Department of Paediatric Haematology and Oncology, Hannover Medical School, Hannover, Germany.; Miarka-Walczyk K; Department of Paediatrics, Oncology and Haematology, Medical University of Lodz, Lodz, Poland.; Pastorczak A; Department of Paediatrics, Oncology and Haematology, Medical University of Lodz, Lodz, Poland.; Cario G; Department of Paediatrics, University Medical Centre Schleswig-Holstein, Campus Kiel, Kiel, Germany.; Renard BY; Hasso Plattner Institute, Digital Engineering Faculty, University of Potsdam, Potsdam, Germany.; Stanulla M; Department of Paediatric Haematology and Oncology, Hannover Medical School, Hannover, Germany.; Bergmann AK; Department of Human Genetics, Hannover Medical School, Hannover, Germany. Electronic address: Bergmann.Anke@mh-hannover.de.
Source
Publisher: Elsevier B.V Country of Publication: Netherlands NLM ID: 101647039 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2352-3964 (Electronic) Linking ISSN: 23523964 NLM ISO Abbreviation: EBioMedicine Subsets: MEDLINE
Subject
Language
English
Abstract
Background: The increasing volume and intricacy of sequencing data, along with other clinical and diagnostic data, like drug responses and measurable residual disease, creates challenges for efficient clinical comprehension and interpretation. Using paediatric B-cell precursor acute lymphoblastic leukaemia (BCP-ALL) as a use case, we present an artificial intelligence (AI)-assisted clinical framework clinALL that integrates genomic and clinical data into a user-friendly interface to support routine diagnostics and reveal translational insights for hematologic neoplasia.
Methods: We performed targeted RNA sequencing in 1365 cases with haematological neoplasms, primarily paediatric B-cell precursor acute lymphoblastic leukaemia (BCP-ALL) from the AIEOP-BFM ALL study. We carried out fluorescence in situ hybridization (FISH), karyotyping and arrayCGH as part of the routine diagnostics. The analysis results of these assays as well as additional clinical information were integrated into an interactive web interface using Bokeh, where the main graph is based on Uniform Manifold Approximation and Projection (UMAP) analysis of the gene expression data. At the backend of the clinALL, we built both shallow machine learning models and a deep neural network using Scikit-learn and PyTorch respectively.
Findings: By applying clinALL, 78% of undetermined patients under the current diagnostic protocol were stratified, and ambiguous cases were investigated. Translational insights were discovered, including IKZF1plus status dependent subpopulations of BCR::ABL1 positive patients, and a subpopulation within ETV6::RUNX1 positive patients that has a high relapse frequency. Our best machine learning models, LDA and PASNET-like neural network models, achieve F1 scores above 97% in predicting patients' subgroups.
Interpretation: An AI-assisted clinical framework that integrates both genomic and clinical data can take full advantage of the available data, improve point-of-care decision-making and reveal clinically relevant insights promptly. Such a lightweight and easily transferable framework works for both whole transcriptome data as well as the cost-effective targeted RNA-seq, enabling efficient and equitable delivery of personalized medicine in small clinics in developing countries.
Funding: German Ministry of Education and Research (BMBF), German Research Foundation (DFG) and Foundation for Polish Science.
Competing Interests: Declaration of interests GC has received research support from German Cancer aid (70112958) and German Research Society (KFO 5010/1). GC has also participated in an Advisory Board, and received consultancy fees from JazzPharma, and honoraria from Amgen.
(Copyright © 2024 The Authors. Published by Elsevier B.V. All rights reserved.)
Methods: We performed targeted RNA sequencing in 1365 cases with haematological neoplasms, primarily paediatric B-cell precursor acute lymphoblastic leukaemia (BCP-ALL) from the AIEOP-BFM ALL study. We carried out fluorescence in situ hybridization (FISH), karyotyping and arrayCGH as part of the routine diagnostics. The analysis results of these assays as well as additional clinical information were integrated into an interactive web interface using Bokeh, where the main graph is based on Uniform Manifold Approximation and Projection (UMAP) analysis of the gene expression data. At the backend of the clinALL, we built both shallow machine learning models and a deep neural network using Scikit-learn and PyTorch respectively.
Findings: By applying clinALL, 78% of undetermined patients under the current diagnostic protocol were stratified, and ambiguous cases were investigated. Translational insights were discovered, including IKZF1
Interpretation: An AI-assisted clinical framework that integrates both genomic and clinical data can take full advantage of the available data, improve point-of-care decision-making and reveal clinically relevant insights promptly. Such a lightweight and easily transferable framework works for both whole transcriptome data as well as the cost-effective targeted RNA-seq, enabling efficient and equitable delivery of personalized medicine in small clinics in developing countries.
Funding: German Ministry of Education and Research (BMBF), German Research Foundation (DFG) and Foundation for Polish Science.
Competing Interests: Declaration of interests GC has received research support from German Cancer aid (70112958) and German Research Society (KFO 5010/1). GC has also participated in an Advisory Board, and received consultancy fees from JazzPharma, and honoraria from Amgen.
(Copyright © 2024 The Authors. Published by Elsevier B.V. All rights reserved.)