Decoding pan-cancer treatment outcomes using multimodal real-world data and explainable artificial intelligence

Keyl, Julius; Keyl, Philipp; Montavon, Gregoire; Hosch, Rene; Brehmer, Alexander; Mochmann, Liliana; Jurmeister, Philipp; Dernbach, Gabriel; Kim, Moon; Koitka, Sven; Bauer, Sebastian; Bechrakis, Nikolaos; Forsting, Michael; Fuehrer-Sakel, Dagmar; Glas, Martin; Gruenwald, Viktor; Hadaschik, Boris; Haubold, Johannes; Herrmann, Ken; Kasper, Stefan; Kimmig, Rainer; Lang, Stephan; Rassaf, Tienush; Roesch, Alexander; Schadendorf, Dirk; Siveke, Jens T.; Stuschke, Martin; Sure, Ulrich; Totzeck, Matthias; Welt, Anja; Wiesweg, Marcel; Baba, Hideo A.; Nensa, Felix; Egger, Jan; Mueller, Klaus-Robert; Schuler, Martin; Klauschen, Frederick; Kleesiek, Jens

doi:10.1038/s43018-024-00891-1

상세 보기

Decoding pan-cancer treatment outcomes using multimodal real-world data and explainable artificial intelligence

Keyl, Julius;
Keyl, Philipp;
Montavon, Gregoire;
Hosch, Rene;
Brehmer, Alexander;
... Mueller, Klaus-Robert;
외 32명

Citations

WEB OF SCIENCE

54

Citations

SCOPUS

60

초록

Despite advances in precision oncology, clinical decision-making still relies on limited variables and expert knowledge. To address this limitation, we combined multimodal real-world data and explainable artificial intelligence (xAI) to introduce AI-derived (AID) markers for clinical decision support. We used xAI to decode the outcome of 15,726 patients across 38 solid cancer entities based on 350 markers, including clinical records, image-derived body compositions, and mutational tumor profiles. xAI determined the prognostic contribution of each clinical marker at the patient level and identified 114 key markers that accounted for 90% of the neural network's decision process. Moreover, xAI enabled us to uncover 1,373 prognostic interactions between markers. Our approach was validated in an independent cohort of 3,288 patients with lung cancer from a US nationwide electronic health record-derived database. These results show the potential of xAI to transform the assessment of clinical variables and enable personalized, data-driven cancer care.

키워드

Alanine Aminotransferase; Aspartate Aminotransferase; C Reactive Protein; Liothyronine; Pembrolizumab; Biomarkers, Tumor; Alanine Aminotransferase; Aspartate Aminotransferase; C Reactive Protein; Ca 19-9 Antigen; Immune Checkpoint Inhibitor; Liothyronine; Pembrolizumab; Tumor Marker; Aphagia; Article; Body Composition; Body Mass; Body Temperature; Breast Cancer; Cancer Grading; Cancer Prognosis; Cancer Staging; Cancer Therapy; Checkpoint Inhibitor Therapy; Clinical Decision Making; Clinical Decision Support System; Clinical Practice; Cohort Analysis; Comorbidity; Deep Learning; Diastolic Blood Pressure; Distant Metastasis; Ecog Performance Status; Electronic Health Record; Explainable Artificial Intelligence; Female; Heart Rate; Human; Imaging; Immunohistochemistry; Intra-abdominal Fat; Liver Cancer; Liver Metastasis; Lung Cancer; Lymphocytopenia; Machine Learning; Male; Malignant Neoplasm; Nerve Cell Network; Non Small Cell Lung Cancer; Nutritional Status; Omics; Overall Survival; Oxygen Saturation; Personalized Cancer Therapy; Platelet Count; Pleura Effusion; Prothrombin Time; Retrospective Study; Sarcoma; Scoring System; Solid Malignant Neoplasm; Subcutaneous Fat; Systolic Blood Pressure; Thyroid Cancer; Treatment Outcome; Urea Nitrogen Blood Level; Uvea Melanoma; Artificial Intelligence; Artificial Neural Network; Lung Tumor; Neoplasm; Personalized Medicine; Procedures; Prognosis; Therapy; Artificial Intelligence; Biomarkers, Tumor; Clinical Decision-making; Electronic Health Records; Female; Humans; Lung Neoplasms; Male; Neoplasms; Neural Networks, Computer; Precision Medicine; Prognosis; Treatment Outcome; PANCREATIC-CANCER; PROGNOSTIC-FACTOR; NEURAL-NETWORKS; SURVIVAL

제목: Decoding pan-cancer treatment outcomes using multimodal real-world data and explainable artificial intelligence

저자: Keyl, Julius; Keyl, Philipp; Montavon, Gregoire; Hosch, Rene; Brehmer, Alexander; Mochmann, Liliana; Jurmeister, Philipp; Dernbach, Gabriel; Kim, Moon; Koitka, Sven; Bauer, Sebastian; Bechrakis, Nikolaos; Forsting, Michael; Fuehrer-Sakel, Dagmar; Glas, Martin; Gruenwald, Viktor; Hadaschik, Boris; Haubold, Johannes; Herrmann, Ken; Kasper, Stefan; Kimmig, Rainer; Lang, Stephan; Rassaf, Tienush; Roesch, Alexander; Schadendorf, Dirk; Siveke, Jens T.; Stuschke, Martin; Sure, Ulrich; Totzeck, Matthias; Welt, Anja; Wiesweg, Marcel; Baba, Hideo A.; Nensa, Felix; Egger, Jan; Mueller, Klaus-Robert; Schuler, Martin; Klauschen, Frederick; Kleesiek, Jens

DOI: 10.1038/s43018-024-00891-1

발행일: 2025-02

유형: Article

저널명: Nature Cancer

권: 6

호: 2

페이지: 307 ~ 322