Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 213

The DOI matches its Crossref record; 60 of the 60 references it cites were found in a registry or an index.

Information fusion as an integrative cross-cutting enabler to achieve robust, explainable, and trustworthy medical artificial intelligence

Open access
Holzinger, Andreas, Dehmer, Matthias, Emmert-Streib, Frank, Cucchiara, Rita, Augenstein, Isabelle, Ser, Javier Del, Samek, Wojciech, Jurisica, Igor, Díaz-Rodríguez, Natalia · 2022 · Information Fusion

Abstract

Medical artificial intelligence (AI) systems have been remarkably successful, even outperforming human performance at certain tasks. There is no doubt that AI is important to improve human health in many ways and will disrupt various medical workflows in the future. Using AI to solve problems in medicine beyond the lab, in routine environments, we need to do more than to just improve the performance of existing AI methods. Robust AI solutions must be able to cope with imprecision, missing and incorrect information, and explain both the result and the process of how it was obtained to a medical expert. Using conceptual knowledge as a guiding model of reality can help to develop more robust, explainable, and less biased machine learning models that can ideally learn from less data. Achieving these goals will require an orchestrated effort that combines three complementary Frontier Research Areas: (1) Complex Networks and their Inference, (2) Graph causal models and counterfactuals, and (3) Verification and Explainability methods. The goal of this paper is to describe these three areas from a unified view and to motivate how information fusion in a comprehensive and integrative manner can not only help bring these three areas together, but also have a transformative role by bridging the gap between research and practical applications in the context of future trustworthy medical AI. This makes it imperative to include ethical and legal aspects as a cross-cutting discipline, because all future solutions must not only be ethically responsible, but also legally compliant.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.inffus.2021.10.007

Cites

60 of 60 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 141

  1. Thrall, 2018, Artificial intelligence and machine learning in radiology: Opportunities, challenges, pitfalls, and criteria for success, J. Am. Coll. Radiol., 15, 504, 10.1016/j.jacr.2017.12.026 · DOI · Paper page
  2. J.E. Arco, A. Ortiz, J. Ramirez, F.J. Martínez-Murcia, Y.-D. Zhang, J.M. Górriz, Uncertainty-driven ensembles of deep architectures for multiclass classification. Application to covid-19 diagnosis in chest x-ray images, arXiv:2011.14894. · arXiv
  3. Grapov, 2018, Rise of deep learning for genomic, proteomic, and metabolomic data integration in precision medicine, omics:, J. Integr. Biol., 22, 630
  4. Zhang, 2019, Deep learning in omics: A survey and guideline, Brief. Funct. Genom., 18, 41, 10.1093/bfgp/ely030 · DOI · Paper page
  5. S. Jain, B.C. Wallace, Attention is not explanation, arXiv preprint arXiv:1902.10186. · arXiv
  6. Steels, 2018, The barcelona declaration for the proper development and usage of artificial intelligence in europe, AI Commun., 31, 485, 10.3233/AIC-180607 · DOI
  7. Hussain, 2009, Investigating agile user-centered design in practice: A grounded theory perspective, vol. 5889, 279
  8. Holzinger, 2021, Towards multi-modal causability with graph neural networks enabling information fusion for explainable ai, Inf. Fusion, 71, 28, 10.1016/j.inffus.2021.01.008 · DOI · Paper page
  9. Zitnik, 2015, Data fusion by matrix factorization, IEEE Trans. Pattern Anal. Mach. Intell., 37, 41, 10.1109/TPAMI.2014.2343973 · DOI · Paper page
  10. Zitnik, 2019, Machine learning for integrating data in biology and medicine: Principles, practice, and opportunities, Inf. Fusion, 50, 71, 10.1016/j.inffus.2018.09.012 · DOI · Paper page
  11. Cox, 2009, Comparative systems biology of human and mouse as a tool to guide the modeling of human placental pathology, Mol. Syst. Biol., 5, 279, 10.1038/msb.2009.37 · DOI · Paper page
  12. Enright, 1999, Protein interaction maps for complete genomes based on gene fusion events, Nature, 402, 86, 10.1038/47056 · DOI · Paper page
  13. Del-Toro, 2012, Capturing variation impact on molecular interactions in the IMEx consortium mutations data set, Nature Methods, 9, 345
  14. Gene Ontology Consortium, 2001, Creating the gene ontology resource: Design and implementation, Genome Res., 11, 1425, 10.1101/gr.180801 · DOI · Paper page
  15. McKusick, 2007, Mendelian inheritance in man and its online version, OMIM, Am. J. Hum. Genet., 80, 588, 10.1086/514346 · DOI · Paper page
  16. UniProt Consortium, 2009, The universal protein resource (UniProt) 2009, Nucl. Acids Res., 37, D169, 10.1093/nar/gkn664 · DOI · Paper page
  17. Forbes, 2015, Cosmic: Exploring the world’s knowledge of somatic mutations in human cancer, Nucleic Acids Res., 43, D805, 10.1093/nar/gku1075 · DOI · Paper page
  18. The Gene Ontology Consortium, 2015, Gene ontology consortium: Going forward, Nucleic Acids Res., 43, D1049, 10.1093/nar/gku1179 · DOI · Paper page
  19. The UniProt Consortium, 2015, Uniprot: A hub for protein information, Nucleic Acids Res., 43, D204, 10.1093/nar/gku989 · DOI · Paper page
  20. Rahmati, 2020, pathdip 4: An extended pathway annotations and enrichment analysis resource for human, model organisms and domesticated species, Nucleic Acids Res., 48, D479
  21. Kotlyar, 2019, Iid 2018 update: Context-specific physical protein-protein interactions in human, model organisms and domesticated species, Nucleic Acids Res., 47, D581, 10.1093/nar/gky1037 · DOI · Paper page
  22. Tokar, 2018, mirdip v4.0 – integrative microrna targets prediction and tissue-specificity annotation, Nucl. Acids Res., 46, D360, 10.1093/nar/gkx1144 · DOI · Paper page
  23. Braun, 2009, An experimentally derived confidence score for binary protein-protein interactions, Nat. Methods, 6, 91, 10.1038/nmeth.1281 · DOI · Paper page
  24. Kotlyar, 2015, In silico prediction of physical protein interactions and characterization of interactome orphans, Nature Methods, 12, 79, 10.1038/nmeth.3178 · DOI · Paper page
  25. Azarkhalili, 2019, Deepathology: Deep multi-task learning for inferring molecular pathology from cancer transcriptome, Sci. Rep., 9, 1, 10.1038/s41598-019-52937-5 · DOI
  26. Enfield, 2019, Epithelial tumor suppressor elf3 is a lineage-specific amplified oncogene in lung adenocarcinoma, Nature Commun., 10, 5438, 10.1038/s41467-019-13295-y · DOI
  27. Pržulj, 2004, Functional topology in a network of protein interactions, Bioinformatics, 20, 340, 10.1093/bioinformatics/btg415 · DOI · Paper page
  28. Klimovskaia, 2020, Poincaré maps for analyzing complex hierarchies in single-cell data, Nature Commun., 11, 1, 10.1038/s41467-020-16822-4 · DOI
  29. Fortney, 2010, Inferring the functions of longevity genes with modular subnetwork biomarkers of caenorhabditis elegans aging, Genome Biol., 11, R13, 10.1186/gb-2010-11-2-r13 · DOI
  30. Jörnsten, 2011, Network modeling of the transcriptional effects of copy number aberrations in glioblastoma, Mol. Syst. Biol., 7, 486, 10.1038/msb.2011.17 · DOI
  31. Wong, 2018, Modeling tumor progression via the comparison of stage-specific graphs, Methods, 132, 34, 10.1016/j.ymeth.2017.06.033 · DOI
  32. Monette, 2019, Failed immune responses across multiple pathologies share pan-tumor and circulating lymphocytic targets, J. Clin. Invest., 129, 2463, 10.1172/JCI125301 · DOI
  33. Camacho, 2018, Next-generation machine learning for biological networks, Cell, 173, 1581, 10.1016/j.cell.2018.05.015 · DOI · Paper page
  34. Holzinger, 2014, Trends in interactive knowledge discovery for personalized medicine: Cognitive science meets machine learning, IEEE Intell. Inform. Bull., 15, 6
  35. Ben-Naim, 2004, Complex networks, 10.1007/b98716 · DOI
  36. Dehmer, 2017, Quantitative graph theory: A new branch of graph theory and network science, Inform. Sci., 418, 575, 10.1016/j.ins.2017.08.009 · DOI
  37. H. Bunke, Recent developments in graph matching, in: 15-th International Conference on Pattern Recognition, vol. 2, 2000, pp. 117–124. · DOI · Paper page
  38. Emmert-Streib, 2016, Fifty years of graph matching, network alignment and network comparison, Inform. Sci., 346
  39. Dehmer, 2019, On efficient network similarity measures, Appl. Math. Comput., 362
  40. Laponogov, 2021, Network machine learning maps phytochemically rich hyperfoods to fight covid-19, Hum. Genom., 15, 1, 10.1186/s40246-020-00297-x · DOI
  41. N. Díaz-Rodríguez, A. Härmä, R. Helaoui, I. Huitzil, F. Bobillo, U. Straccia, Couch potato or gym addict? Semantic lifestyle profiling with wearables and fuzzy knowledge graphs, in: Automatic Knowledge Base Construction (AKBC) Workshop at NIPS, 2017, pp. 1–10.
  42. Rodríguez, 2014, A fuzzy ontology for semantic modelling and recognition of human behaviour, Knowl.-Based Syst., 66, 46, 10.1016/j.knosys.2014.04.016 · DOI
  43. Biemann, 2013, Text: Now in 2D! a framework for lexical expansion with contextual similarity, J. Lang. Model., 1, 55
  44. Jeong, 2001, Lethality and centrality in protein networks, Nature, 411, 41, 10.1038/35075138 · DOI · Paper page
  45. Hahn, 2005, Comparative genomics of centrality and essentiality in three eukaryotic protein-interaction networks, Mol. Biol. Evol., 22, 803, 10.1093/molbev/msi072 · DOI · Paper page
  46. Gavin, 2002, Functional organization of the yeast proteome by systematic analysis of protein complexes, Nature, 415, 141, 10.1038/415141a · DOI · Paper page
  47. Wuchty, 2006, Topology and weights in a protein domain interaction network–a novel way to predict protein interactions, BMC Genom., 7, 1471, 10.1186/1471-2164-7-122 · doi:10.1186/1471-2164-7-122
  48. Sharan, 2007, Network-based prediction of protein function, Mol. Syst. Biol., 3, 88, 10.1038/msb4100129 · DOI · Paper page
  49. H. Yu, M. Gerstein, Genomic analysis of the hierarchical structure of regulatory networks, Proc. Natl. Acad. Sci. U S A0027-8424 (Print) Journal article.
  50. Han, 2004, Evidence for dynamically organized modularity in the yeast protein-protein interaction network, Nature, 430, 88, 10.1038/nature02555 · DOI · Paper page
  51. Segal, 2003, Module networks: Identifying regulatory modules and their condition-specific regulators from gene expression data, Nat. Genet., 34, 166, 10.1038/ng1165 · DOI · Paper page
  52. Gavin, 2006, Proteome survey reveals modularity of the yeast cell machinery, Nature, 440, 631, 10.1038/nature04532 · DOI · Paper page
  53. Wong, 2015, Comparative network analysis via differential graphlet communities, Proteomics, 15, 608, 10.1002/pmic.201400233 · DOI
  54. Shen-Orr, 2002, Network motifs in the transcriptional regulation network of escherichia coli, Nat. Gen., 31, 64, 10.1038/ng881 · DOI · Paper page
  55. Rice, 2005, Lasting impressions: Motifs in protein-protein maps may provide footprints of evolutionary events, Proc. Natl. Acad. Sci. U S A, 102, 3173, 10.1073/pnas.0500130102 · DOI
  56. Jeremy Kershenbaum, 2005, Gustavo comment united states proceedings of the national academy of sciences of the united states of america, Proc. Natl. Acad. Sci. U S A, 102, 3173
  57. Singh, 2018, Therapeutic targeting of the premetastatic stage in human lung-to-brain metastasis, Cancer Res., 78, 5124, 10.1158/0008-5472.CAN-18-1022 · DOI
  58. Monette, 2019, Immune-enrichment of non-small cell lung cancer baseline biopsies for multiplex profiling define prognostic immune checkpoint combinations for patient stratification, J. Immunother. Cancer, 7, 86, 10.1186/s40425-019-0544-x · DOI
  59. Barrios-Rodiles, 2005, High-throughput mapping of a dynamic signaling network in mammalian cells, Science, 307, 1621, 10.1126/science.1105776 · DOI · Paper page
  60. Hu, 2007, A single nucleotide polymorphism in the mdm2 gene disrupts the oscillation of p53 and mdm2 levels in cells, Cancer Res., 67, 2757, 10.1158/0008-5472.CAN-06-2656 · DOI
  61. Barshir, 2013, The tissuenet database of human tissue protein-protein interactions, Nucl. Acids Res., 41, D841, 10.1093/nar/gks1198 · DOI
  62. Jansen, 2002, Relating whole-genome expression data with protein-protein interactions, Genome Res., 12, 37, 10.1101/gr.205602 · DOI · Paper page
  63. Brown, 2007, Unequal evolutionary conservation of human protein interactions in interologous networks, Genome Biology, 8, R95, 10.1186/gb-2007-8-5-r95 · DOI · Paper page
  64. Rhodes, 2005, Probabilistic model of the human protein-protein interaction network, Nat. Biotechnol., 23, 951, 10.1038/nbt1103 · DOI · Paper page
  65. Kato, 2006, Network-based de-noising improves prediction from microarray data, BMC Bioinformatics
  66. Jonsson, 2006, Global topological features of cancer proteins in the human interactome, Bioinformatics, 22, 2291, 10.1093/bioinformatics/btl390 · DOI · Paper page
  67. Wachi, 2005, Interactome-transcriptome analysis reveals the high centrality of genes differentially expressed in lung cancer tissues, Bioinformatics, 21, 4205, 10.1093/bioinformatics/bti688 · DOI · Paper page
  68. Reis, 2020, A 4-gene signature from histologically normal surgical margins predicts local recurrence in patients with oral carcinoma: Clinical validation, Sci. Rep., 10, 1, 10.1038/s41598-020-58688-y · DOI
  69. Tokar, 2018, Differentially expressed micrornas in lung adenocarcinoma invert effects of copy number aberrations of prognostic genes, Oncotarget, 9, 9137, 10.18632/oncotarget.24070 · DOI
  70. V. Mandilaras, S. Garg, M. Cabanero, Q. Tan, C. Pastrello, J. Burnier, K. Karakasis, L. Wang, N.C. Dhani, M.O. Butler, P.L. Bedard, L.L. Siu, B. Clarke, P.A. Shaw, T. Stockley, I. Jurisica, A.M. Oza, S. Lheureux, Tp53 mutations in high grade serous ovarian cancer and impact on clinical outcomes: A comparison of next generation sequencing and bioinformatics analyses, International journal of gynecological cancer : Official journal of the International Gynecological Cancer Society.
  71. King, 2004, Protein complex prediction via cost-based clustering, Bioinformatics, 20, 3013, 10.1093/bioinformatics/bth351 · DOI · Paper page
  72. N., 2006, Efficient estimation of graphlet frequency distributions in protein-protein interaction networks, Bioinformatics, 22, 974, 10.1093/bioinformatics/btl030 · DOI
  73. S.W.H. Wong, C. Pastrello, M. Kotlyar, C. Faloutsos, I. Jurisica, Sdregion: Fast spotting of changing communities in biological networks, Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
  74. Berrar, 2021, Deep learning in bioinformatics and biomedicine, Brief. Bioinform., 22, 1513, 10.1093/bib/bbab087 · DOI
  75. Nacu, 2007, Gene expression network analysis and applications to immunology, Bioinformatics, 23, 850, 10.1093/bioinformatics/btm019 · DOI
  76. Hwang, 2009, Predicting essential genes based on network and sequence analysis, Mol. Biosyst., 5, 1672, 10.1039/B900611G · DOI
  77. J.I. Geraci J., Liu G., Algorithms for systematic identification of small subgraphs (2012). · DOI
  78. Schramm, 2013, Disturbed protein-protein interaction networks in metastatic melanoma are associated with worse prognosis and increased functional mutation burden, Pigment Cell Melanoma Res., 26, 708, 10.1111/pcmr.12126 · DOI
  79. Ramanan, 2020, Causal learning from predictive modeling for observational data, Front. Big Data, 3, 34, 10.3389/fdata.2020.535976 · DOI
  80. B. Schölkopf, Causality for machine learning, arXiv:1911.10500. · arXiv
  81. Lu, 2008, Bayesian Generic priors for causal learning, Psychol. Rev., 115, 955, 10.1037/a0013256 · DOI · Paper page
  82. O. Goudet, D. Kalainathan, P. Caillou, I. Guyon, D. Lopez-Paz, M. Sebag, Causal generative neural networks, arXiv preprint arXiv:1711.08936. · arXiv
  83. M. Rojas-Carulla, M. Baroni, D. Lopez-Paz, Causal discovery using proxy variables, arXiv:1702.07306. · arXiv
  84. B. Schölkopf, Causality for machine learning, arXiv preprint arXiv:1911.10500. · arXiv
  85. A.-H. Karimi, J. von Kügelgen, B. Schölkopf, I. Valera, Algorithmic recourse under imperfect causal knowledge: A probabilistic approach, arXiv:2006.06831. · arXiv
  86. M. Sharma, S. Mindermann, J. Brauner, G. Leech, A. Stephenson, T. Gavenčiak, J. Kulveit, Y.W. Teh, L. Chindelevitch, Y. Gal, How robust are the estimated effects of nonpharmaceutical interventions against covid-19? Advances in Neural Information Processing Systems 33.
  87. A. Jesson, S. Mindermann, U. Shalit, Y. Gal, Identifying causal-effect inference failure with uncertainty-aware models, Advances in Neural Information Processing Systems 33.
  88. Elzein, 2019, The demand for contrastive explanations, Philos. Stud., 176, 1325, 10.1007/s11098-018-1065-z · DOI
  89. B. Krarup, S. Krivic, F. Lindner, D. Long, Towards contrastive explanations for comparing the ethics of plans, arXiv preprint arXiv:2006.12632. · arXiv
  90. Dhurandhar, 2018, Explanations based on the missing: Towards contrastive explanations with pertinent negatives, Adv. Neural Inf. Process. Syst., 31, 592
  91. W. Liang, J. Zou, Z. Yu, Alice: Active learning with contrastive natural language explanations, arXiv preprint arXiv:2009.10259. · arXiv
  92. Liu, 2019, Deep feature selection and causal analysis of alzheimer’s disease, Front. Neurosci., 13, 1198, 10.3389/fnins.2019.01198 · DOI
  93. T.R. Besold, A. d. Garcez, S. Bader, H. Bowman, P. Domingos, P. Hitzler, K.-U. Kühnberger, L.C. Lamb, D. Lowd, P.M.V. Lima, et al. Neural-symbolic learning and reasoning: A survey and interpretation, arXiv preprint arXiv:1711.03902. · arXiv
  94. King, 2020, Back-to-back regression: Disentangling the influence of correlated factors from multivariate observations, NeuroImage, 220, 10.1016/j.neuroimage.2020.117028 · DOI
  95. Holzinger, 2016, Interactive machine learning for health informatics: When do we need the human-in-the-loop?, Brain Inform., 3, 119, 10.1007/s40708-016-0042-6 · DOI · Paper page
  96. Buccafurri, 1999, Enhancing model checking in verification by ai techniques, Artificial Intelligence, 112, 57, 10.1016/S0004-3702(99)00039-9 · DOI
  97. Holzinger, 2005, Usability engineering methods for software developers, Commun. ACM, 48, 71, 10.1145/1039539.1039541 · DOI · Paper page
  98. Holzinger, 2020, Measuring the quality of explanations: The system causability scale (scs). comparing human and machine explanations, KI - Künstliche intelligenz (german journal of artificial intelligence), 193
  99. Grigorescu, 2020, A survey of deep learning techniques for autonomous driving, J. Field Robotics, 37, 362, 10.1002/rob.21918 · DOI · Paper page
  100. K. Muhammad, A. Ullah, J. Lloret, J. Del Ser, V.H.C. de Albuquerque, Deep learning for safe autonomous driving: Current challenges and future directions, IEEE Transactions on Intelligent Transportation Systems.
  101. Ting, 2018, Ai for medical imaging goes deep, Nat. Med., 24, 539, 10.1038/s41591-018-0029-3 · DOI · Paper page
  102. K. Muhammad, S. Khan, J. Del Ser, V.H.C. de Albuquerque, Deep learning for multigrade brain tumor classification in smart healthcare systems: A prospective survey, IEEE Transactions on Neural Networks and Learning Systems.
  103. Tellakula, 2021, A survey of ai imaging techniques for covid-19 diagnosis and prognosis, Appl. Comput. Sci., 17, 40, 10.35784/acs-2021-12 · DOI
  104. Xin, 2018, Machine learning and deep learning methods for cybersecurity, IEEE Access, 6, 35365, 10.1109/ACCESS.2018.2836950 · DOI · Paper page
  105. Goodfellow, 2020, Generative adversarial networks, Commun. ACM, 63, 139, 10.1145/3422622 · DOI · Paper page
  106. Y. Ganin, V. Lempitsky, Unsupervised Domain Adaptation by Backpropagation, in: International Conference on Machine Learning, 2015, pp. 1180–1189.
  107. Lin, 2020, Does BERT need domain adaptation for clinical negation detection?, J. Am. Med. Inform. Assoc., 27, 584, 10.1093/jamia/ocaa001 · DOI
  108. Lesort, 2020, Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges, Inf. Fusion, 58, 52, 10.1016/j.inffus.2019.12.004 · DOI · Paper page
  109. J. Bjerva, W. Kouw, I. Augenstein, Back to the future – sequential alignment of text representations, in: Proceedings of the 34th AAAI Conference on Artificial Intelligence. · DOI
  110. A. Bennetot, J.-L. Laurent, R. Chatila, N. Díaz-Rodríguez, Towards explainable neural-symbolic visual reasoning, in: NeSy Workshop IJCAI, 2019, pp. 1–10.
  111. Vapnik, 1991, The necessary and sufficient conditions for consistency in the empirical risk minimization method, Pattern Recognit. Image Anal., 1, 283
  112. Poggio, 2004, General conditions for predictivity in learning theory, Nature, 428, 419, 10.1038/nature02341 · DOI · Paper page
  113. Xu, 2012, Robustness and generalization, Mach. Learn., 86, 391, 10.1007/s10994-011-5268-1 · DOI · Paper page
  114. N. Díaz-Rodríguez, R. Binkyte-Sadauskiene, W. Bakkali, S. Bookseller, P. Tubaro, A. Bacevicius, R. Chatila, Questioning causality on sex, gender and COVID-19, and identifying bias in large-scale data-driven analyses: the Bias Priority Recommendations and Bias Catalog for Pandemics, arXiv preprint arXiv:2104.14492. · arXiv
  115. D. Tsipras, S. Santurkar, L. Engstrom, A. Turner, A. Madry, Robustness may be at odds with accuracy, arXiv:1805.12152. · arXiv
  116. A. Margeloiu, N. Simidjievski, M. Jamnik, A. Weller, Improving interpretability in medical imaging diagnosis using adversarial training, arXiv preprint arXiv:2012.01166. · arXiv
  117. Merkulov, 2019, Empirical study of extreme overfitting points of neural networks, J. Commun. Technol. Electron., 64, 1527, 10.1134/S1064226919120118 · DOI
  118. Lapuschkin, 2019, Unmasking clever hans predictors and assessing what machines really learn, Nature Commun., 10, 1096, 10.1038/s41467-019-08987-4 · DOI · Paper page
  119. A. Jain, M. Ravula, J. Ghosh, Biased models have biased explanations, arXiv preprint arXiv:2012.10986. · arXiv
  120. N. Liu, M. Du, X. Hu, Adversarial machine learning: An interpretation perspective, arXiv preprint arXiv:2004.11488. · arXiv
  121. Heuillet, 2021, Explainability in deep reinforcement learning, Knowl.-Based Syst., 214, 10.1016/j.knosys.2020.106685 · DOI · Paper page
  122. T.W. Killian, H. Zhang, J. Subramanian, M. Fatemi, M. Ghassemi, An empirical study of representation learning for reinforcement learning in healthcare, arXiv preprint arXiv:2011.11235. · arXiv
  123. M.T. Ribeiro, S. Singh, C. Guestrin, why should I trust you?: Explaining the predictions of any classifier, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 1135–1144. · DOI · Paper page
  124. Gehrmann, 2019, Visual interaction with deep learning models through collaborative semantic inference, IEEE Trans. Vis. Comput. Graphics, 26, 884
  125. S. Wallkotter, S. Tulli, G. Castellano, A. Paiva, M. Chetouani, Explainable agents through social cues: A review, arXiv preprint arXiv:2003.05251. · arXiv
  126. Valiant, 1999, Projection learning, Mach. Learn., 37, 115, 10.1023/A:1007678005361 · DOI
  127. F. Rundo, G.L. Banna, L. Prezzavento, F. Trenta, S. Conoci, S. Battiato, 3d non-local neural network: A non-invasive biomarker for immunotherapy treatment outcome prediction. case-study: Metastatic urothelial carcinoma, Journal of Imaging.
  128. Ruff, 2021, A unifying review of deep and shallow anomaly detection, Proc. IEEE, 109, 756, 10.1109/JPROC.2021.3052449 · DOI · Paper page
  129. Holzinger, 2019, Why imaging data alone is not enough: Ai-based integration of imaging, omics, and clinical data, Eur. J. Nucl. Med. Mol. Imaging, 46, 2722, 10.1007/s00259-019-04382-9 · DOI
  130. Bhattacharyya, 2020, Personalized network modeling of the pan-cancer patient and cell line interactome, JCO Clin. Cancer Inform., 4, 399, 10.1200/CCI.19.00140 · DOI
  131. M. Abadi, A. Chu, I. Goodfellow, H.B. McMahan, I. Mironov, K. Talwar, L. Zhang, Deep learning with differential privacy, in: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, 2016, pp. 308–318. · DOI · Paper page
  132. J. Wang, W. Bao, L. Sun, X. Zhu, B. Cao, S.Y. Philip, Private model compression via knowledge distillation, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, 2019, pp. 1190–1197. · DOI
  133. Mehra, 2020, Cardiovascular disease, drug therapy, and mortality in covid-19, N. Engl. J. Med., 382, 10.1056/NEJMoa2007621 · DOI · Paper page
  134. Mulvey, 2020, Analysis of complement deposition and viral rna in placentas of covid-19 patients, Ann. Diagn. Pathol., 46, 10.1016/j.anndiagpath.2020.151530 · DOI
  135. Zeng, 2018, Changing cancer survival in china during 2003–15: A pooled analysis of 17 population-based cancer registries, Lancet Glob. Health, 6, e555, 10.1016/S2214-109X(18)30127-X · DOI · Paper page
  136. Orchard, 2019, Protein interaction data curation: the international molecular exchange (IMEx) consortium, Nature Commun., 10, 345
  137. Porras, 2020, Towards a unified open access dataset of molecular interactions, Nat. Commun., 1, 6144, 10.1038/s41467-020-19942-z · DOI
  138. Hund, 2016, Visual analytics for concept exploration in subspaces of patient groups: Making sense of complex datasets with the doctor-in-the-loop, Brain Inform., 3, 233, 10.1007/s40708-016-0043-5 · DOI
  139. Keim, 2008, Visual analytics: Definition, process, and challenges, vol. 4950, 154
  140. Streeb, 2021, Why visualize? Arguments for visual support in decision making, IEEE Comput. Graph. Appl., 41, 17, 10.1109/MCG.2021.3055971 · DOI
  141. A. holzinger, H. Mueller, Toward human-ai interfaces to support explainability and causability in medical ai, IEEE IEEE COMPUTER, 54, (10). http://dx.doi.org/10.1109/MC.2021.3092610. · DOI

Cited by

See all 213

Metadata

Authors
Holzinger, A., Dehmer, M., Emmert-Streib, F., Cucchiara, R., Augenstein, I., Ser, J. D., Samek, W., Jurisica, I., & Díaz-Rodríguez, N.
Venue
Information Fusion
Publisher
Elsevier BV
Published
2022-03
Volume
79
Pages
263-278
ISSN
1566-2535 (ISSN-L)
OpenAlex
W3213384164
Cited by
213
References
60
FWCI
13.94
Type
journal article
Language
en
Open access
hybrid
Licence
Funders
  • Eusko Jaurlaritza (IJC2019-039152-I, T1294-19, KK-2020/00049, 965221)
  • Canadian Institutes of Health Research (93579)
  • Ontario Research Foundation (RDI 34876)
  • Horizon 2020 (826078)
  • Natural Sciences and Engineering Research Council of Canada (203475)
  • Danmarks Frie Forskningsfond
  • Horizon 2020 Framework Programme
  • International Business Machines Corporation
  • Austrian Science Fund (P-32554)
  • Federal Ministry of Education and Research Bonn Office (0310L0207C, 01IS18025 A, 01IS18037I)
  • Fondation canadienne pour l’innovation (33536, CFI 29272, 225404)
  • European Commission
  • Toronto General and Western Hospital Foundation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.