{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:17:38Z","timestamp":1778527058699,"version":"3.51.4"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T00:00:00Z","timestamp":1745971200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T00:00:00Z","timestamp":1745971200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>This study introduces a system for predicting disease progression events in multiple myeloma patients from the CoMMpass study (<jats:italic>N<\/jats:italic>\u2009=\u20091186). Utilizing a hybrid neural network architecture, our model predicts future blood work from historical lab results with high accuracy, significantly outperforming baseline estimators for key disease parameters. Disease progression events are annotated in the forecasted data, predicting these events with significant reliability. We externally validated our model using the GMMG-MM5 study dataset (<jats:italic>N<\/jats:italic>\u2009=\u2009504), and could reproduce the main results of our study. Our approach enables early detection and personalized monitoring of patients at risk of impeding progression. Designed modularly, our system enhances interpretability, facilitates integration of additional modules, and uses routine blood work measurements to ensure accessibility in clinical settings. With this, we contribute to the development of a scalable, cost-effective virtual human twin system for optimized healthcare resource utilization and improved outcomes in multiple myeloma patient care.<\/jats:p>","DOI":"10.1038\/s41746-025-01636-9","type":"journal-article","created":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T01:03:45Z","timestamp":1746061425000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Predicting progression events in multiple myeloma from routine blood work"],"prefix":"10.1038","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2730-4093","authenticated-orcid":false,"given":"Maximilian","family":"Ferle","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nora","family":"Grieb","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus","family":"Kreuz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonas","family":"Ader","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hartmut","family":"Goldschmidt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elias K.","family":"Mai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Uta","family":"Bertsch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Uwe","family":"Platzbecker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Neumuth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kristin","family":"Reiche","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Oeser","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2805-5973","authenticated-orcid":false,"given":"Maximilian","family":"Merz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,30]]},"reference":[{"key":"1636_CR1","doi-asserted-by":"publisher","DOI":"10.1038\/s41408-018-0155-7","volume":"8","author":"SZ Usmani","year":"2024","unstructured":"Usmani, S. Z. et al. Clinical predictors of long-term survival in newly diagnosed transplant eligible multiple myeloma\u2014an IMWG Research Project. Blood Cancer J. 8, 123 (2024).","journal-title":"Blood Cancer J."},{"key":"1636_CR2","doi-asserted-by":"publisher","first-page":"3412","DOI":"10.1200\/JCO.2005.04.242","volume":"23","author":"PR Greipp","year":"2023","unstructured":"Greipp, P. R. et al. International staging system for multiple myeloma. JCO 23, 3412\u20133420 (2023).","journal-title":"JCO"},{"key":"1636_CR3","doi-asserted-by":"publisher","first-page":"2863","DOI":"10.1200\/JCO.2015.61.2267","volume":"33","author":"A Palumbo","year":"2023","unstructured":"Palumbo, A. et al. Revised international staging system for multiple myeloma: a report from international myeloma working group. JCO 33, 2863\u20132869 (2023).","journal-title":"JCO"},{"key":"1636_CR4","doi-asserted-by":"publisher","first-page":"3406","DOI":"10.1200\/JCO.21.02614","volume":"40","author":"M D\u2019Agostino","year":"2024","unstructured":"D\u2019Agostino, M. et al. Second revision of the international staging system (R2-ISS) for overall survival in multiple myeloma: a European myeloma network (EMN) report within the HARMONY project. JCO 40, 3406\u20133418 (2024).","journal-title":"JCO"},{"key":"1636_CR5","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1200\/JCO.23.01277","volume":"42","author":"F Maura","year":"2024","unstructured":"Maura, F. et al. Genomic Classification and Individualized Prognosis in Multiple Myeloma. JCO 42, 1229\u20131240 (2024).","journal-title":"JCO"},{"key":"1636_CR6","doi-asserted-by":"publisher","first-page":"1660","DOI":"10.1038\/s43018-023-00657-1","volume":"4","author":"F Maura","year":"2024","unstructured":"Maura, F. et al. Genomic and immune signatures predict clinical outcome in newly diagnosed multiple myeloma treated with immunotherapy regimens. Nat. Cancer 4, 1660\u20131674 (2024).","journal-title":"Nat. Cancer"},{"key":"1636_CR7","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1016\/j.annonc.2020.11.014","volume":"32","author":"M Dimopoulos","year":"2024","unstructured":"Dimopoulos, M. et al. Multiple myeloma: EHA-ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up\u2020. Ann. Oncol. 32, 309\u2013322 (2024).","journal-title":"Ann. Oncol."},{"key":"1636_CR8","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"2024","unstructured":"Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735\u20131780 (2024).","journal-title":"Neural Comput."},{"key":"1636_CR9","doi-asserted-by":"crossref","unstructured":"Amin, J. et al. Brain tumor detection: a long short-term memory (LSTM)-based learning model. Neural Comput. Applic. 32, 15965\u201315973 (2024).","DOI":"10.1007\/s00521-019-04650-7"},{"key":"1636_CR10","doi-asserted-by":"publisher","first-page":"2469","DOI":"10.1007\/s00345-020-03080-8","volume":"38","author":"KC Koo","year":"2024","unstructured":"Koo, K. C. et al. Long short-term memory artificial neural network model for prediction of prostate cancer survival outcomes according to initial treatment strategy: development of an online decision-making support system. World J. Urol. 38, 2469\u20132476 (2024).","journal-title":"World J. Urol."},{"key":"1636_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105362","volume":"144","author":"X Wu","year":"2024","unstructured":"Wu, X. et al. Long short-term memory model \u2013 A deep learning approach for medical data with irregularity in cancer predication with tumor markers. Comput. Biol. Med. 144, 105362 (2024).","journal-title":"Comput. Biol. Med."},{"key":"1636_CR12","unstructured":"Prediction of cancer symptom trajectory using longitudinal electronic health record data and long short-term memory neural network. JCO Clin. Cancer Inform. 8, e2300039 (2024)."},{"key":"1636_CR13","doi-asserted-by":"publisher","first-page":"606","DOI":"10.3390\/cancers14030606","volume":"14","author":"A Allegra","year":"2024","unstructured":"Allegra, A. et al. Machine learning and deep learning applications in multiple myeloma diagnosis, prognosis, and treatment selection. Cancers 14, 606 (2024).","journal-title":"Cancers"},{"key":"1636_CR14","doi-asserted-by":"publisher","first-page":"2924","DOI":"10.1038\/s41375-021-01286-2","volume":"35","author":"A Mosquera Orgueira","year":"2024","unstructured":"Mosquera Orgueira, A. et al. Survival prediction and treatment optimization of multiple myeloma patients using machine-learning models based on clinical and gene expression data. Leukemia 35, 2924\u20132935 (2024).","journal-title":"Leukemia"},{"key":"1636_CR15","doi-asserted-by":"publisher","first-page":"652063","DOI":"10.3389\/fonc.2021.652063","volume":"11","author":"N Borisov","year":"2024","unstructured":"Borisov, N. et al. Machine learning applicability for classification of PAD\/VCD chemotherapy response using 53 multiple myeloma RNA sequencing profiles. Front. Oncol. 11, 652063 (2024).","journal-title":"Front. Oncol."},{"key":"1636_CR16","doi-asserted-by":"crossref","unstructured":"Venezian Povoa, L., Ribeiro, C. H. C. & Silva, I. T. D. Machine learning predicts treatment sensitivity in multiple myeloma based on molecular and clinical information coupled with drug response. PLoS ONE 16, e0254596 (2024).","DOI":"10.1371\/journal.pone.0254596"},{"key":"1636_CR17","doi-asserted-by":"publisher","first-page":"e581","DOI":"10.1038\/bcj.2017.56","volume":"7","author":"AK Mitra","year":"2017","unstructured":"Mitra, A. K. et al. A gene expression signature distinguishes innate response and resistance to proteasome inhibitors in multiple myeloma. Blood Cancer J. 7, e581\u2013e581 (2017).","journal-title":"Blood Cancer J."},{"key":"1636_CR18","doi-asserted-by":"publisher","first-page":"5952","DOI":"10.1158\/1078-0432.CCR-20-0742","volume":"26","author":"J Ubels","year":"2020","unstructured":"Ubels, J., Sonneveld, P., Van Vliet, M. H. & De Ridder, J. Gene networks constructed through simulated treatment learning can predict proteasome inhibitor benefit in multiple myeloma. Clin. Cancer Res. 26, 5952\u20135961 (2020).","journal-title":"Clin. Cancer Res."},{"key":"1636_CR19","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1109\/JBHI.2023.3323688","volume":"28","author":"M Viceconti","year":"2024","unstructured":"Viceconti, M., De Vos, M., Mellone, S. & Geris, L. Position paper from the digital twins in healthcare to the virtual human twin: a moon-shot project for digital health research. IEEE J. Biomed. Health Inform. 28, 491\u2013501 (2024).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"1636_CR20","unstructured":"Weirauch, U. et al. Design Specifications for Biomedical Virtual Twins in Engineered Adoptive Cellular Immunotherapies. Under revision at npj Digital Medicine."},{"key":"1636_CR21","doi-asserted-by":"publisher","first-page":"e328","DOI":"10.1016\/S1470-2045(16)30206-6","volume":"17","author":"S Kumar","year":"2016","unstructured":"Kumar, S. et al. International Myeloma working group consensus criteria for response and minimal residual disease assessment in multiple myeloma. Lancet Oncol. 17, e328\u2013e346 (2016).","journal-title":"Lancet Oncol."},{"key":"1636_CR22","unstructured":"Baeza-Yates, R. & Ribeiro-Neto, B. Modern Information Retrieval 2nd edn, Vol 944 (Addison-Wesley Educational Publishers Inc, 1999)."},{"key":"1636_CR23","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1093\/clinchem\/25.6.985","volume":"25","author":"HJ Van Der Helm","year":"1979","unstructured":"Van Der Helm, H. J. & Hische, E. A. Application of Bayes\u2019s theorem to results of quantitative clinical chemical determinations. Clin. Chem. 25, 985\u2013988 (1979).","journal-title":"Clin. Chem."},{"key":"1636_CR24","doi-asserted-by":"crossref","unstructured":"Lu, C. Channels\u2019 confirmation and predictions\u2019 confirmation: from the medical test to the raven paradox. Entropy 22, 384 (2020).","DOI":"10.3390\/e22040384"},{"key":"1636_CR25","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1067\/mem.2003.274","volume":"42","author":"MD Brown","year":"2003","unstructured":"Brown, M. D. & Reeves, M. J. Interval likelihood ratios: Another advantage for the evidence-based diagnostician. Ann. Emerg. Med. 42, 292\u2013297 (2003).","journal-title":"Ann. Emerg. Med."},{"key":"1636_CR26","doi-asserted-by":"publisher","first-page":"1392","DOI":"10.1093\/ije\/dyaa090","volume":"49","author":"MP Fox","year":"2020","unstructured":"Fox, M. P., Lash, T. L. & Bodnar, L. M. Common misconceptions about validation studies. Int. J. Epidemiol. 49, 1392\u20131396 (2020).","journal-title":"Int. J. Epidemiol."},{"key":"1636_CR27","doi-asserted-by":"publisher","first-page":"485","DOI":"10.7326\/M14-2086","volume":"162","author":"PF Pinsky","year":"2015","unstructured":"Pinsky, P. F. et al. Performance of lung-RADS in the national lung screening trial: a retrospective assessment. Ann. Intern. Med. 162, 485\u2013491 (2015).","journal-title":"Ann. Intern. Med."},{"key":"1636_CR28","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1038\/s41416-020-01221-9","volume":"124","author":"SER Bailey","year":"2021","unstructured":"Bailey, S. E. R. et al. Diagnostic performance of a faecal immunochemical test for patients with low-risk symptoms of colorectal cancer in primary care: an evaluation in the South West of England. Br. J. Cancer 124, 1231\u20131236 (2021).","journal-title":"Br. J. Cancer"},{"key":"1636_CR29","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1148\/radiol.2016161174","volume":"283","author":"CD Lehman","year":"2017","unstructured":"Lehman, C. D. et al. National performance benchmarks for modern screening digital mammography: update from the breast cancer surveillance consortium. Radiology 283, 49\u201358 (2017).","journal-title":"Radiology"},{"key":"1636_CR30","doi-asserted-by":"publisher","first-page":"1266","DOI":"10.1016\/j.annonc.2020.04.013","volume":"31","author":"W Taylor","year":"2020","unstructured":"Taylor, W. Comment on \u2018Sensitive and specific multi-cancer detection and localization using methylation signatures in cell-free DNA\u2019 by M. C. Liu et al. Ann. Oncol. 31, 1266\u20131267 (2020).","journal-title":"Ann. Oncol."},{"key":"1636_CR31","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1182\/bloodadvances.2022007082","volume":"7","author":"S Goldman-Mazur","year":"2023","unstructured":"Goldman-Mazur, S. et al. Outcomes after biochemical or clinical progression in patients with multiple myeloma. Blood Adv. 7, 909\u2013917 (2023).","journal-title":"Blood Adv."},{"key":"1636_CR32","doi-asserted-by":"publisher","first-page":"255","DOI":"10.3390\/fi15080255","volume":"15","author":"VI Kontopoulou","year":"2023","unstructured":"Kontopoulou, V. I., Panagopoulos, A. D., Kakkos, I. & Matsopoulos, G. K. A review of ARIMA vs. Machine learning approaches for time series forecasting in data driven networks. Future Int. 15, 255 (2023).","journal-title":"Future Int."},{"key":"1636_CR33","doi-asserted-by":"publisher","first-page":"7585","DOI":"10.1016\/j.aej.2022.01.011","volume":"61","author":"K ArunKumar","year":"2022","unstructured":"ArunKumar, K., Kalaga, D. V., Mohan Sai Kumar, C., Kawaji, M. & Brenza, T. M. Comparative analysis of gated recurrent units (GRU), long short-term memory (LSTM) cells, autoregressive integrated moving average (arima), seasonal autoregressive integrated moving average (SARIMA) for forecasting covid-19 trends. Alex. Eng. J. 61, 7585\u20137603 (2022).","journal-title":"Alex. Eng. J."},{"key":"1636_CR34","doi-asserted-by":"publisher","first-page":"110015","DOI":"10.1016\/j.chaos.2020.110015","volume":"138","author":"\u0130 K\u0131rba\u015f","year":"2020","unstructured":"K\u0131rba\u015f, \u0130, S\u00f6zen, A., Tuncer, A. D. & Kazanc\u0131o\u011flu, F. \u015e Comparative analysis and forecasting of COVID-19 cases in various European countries with ARIMA, NARNN and LSTM approaches. Chaos. Soli-tons Fractals 138, 110015 (2020).","journal-title":"Chaos. Soli-tons Fractals"},{"key":"1636_CR35","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1016\/0002-9343(62)90262-0","volume":"33","author":"MJ Cline","year":"1962","unstructured":"Cline, M. J. & Berlin, N. I. Studies of the anemia of multiple myeloma. Am. J. Med. 33, 510\u2013525 (1962).","journal-title":"Am. J. Med."},{"key":"1636_CR36","doi-asserted-by":"publisher","first-page":"S23","DOI":"10.3816\/CLM.2003.s.005","volume":"4","author":"M Mittelman","year":"2003","unstructured":"Mittelman, M. The implications of anemia in multiple Myeloma. Clin. Lymphoma 4, S23\u2013S29 (2003).","journal-title":"Clin. Lymphoma"},{"key":"1636_CR37","doi-asserted-by":"publisher","first-page":"f3863","DOI":"10.1136\/bmj.f3863","volume":"346","author":"D Smith","year":"2013","unstructured":"Smith, D. & Yong, K. Multiple Myeloma. BMJ 346, f3863\u2013f3863 (2013).","journal-title":"BMJ"},{"key":"1636_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.ctarc.2019.100159","volume":"21","author":"MJ Buege","year":"2019","unstructured":"Buege, M. J. et al. Corrected calcium versus ionized calcium measurements for identifying hypercalcemia in patients with multiple myeloma. Cancer Treat. Res. Commun. 21, 100159 (2019).","journal-title":"Cancer Treat. Res. Commun."},{"key":"1636_CR39","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1111\/j.1600-0609.1994.tb00190.x","volume":"53","author":"LM Knudsen","year":"1994","unstructured":"Knudsen, L. M., Hippe, E., Hjorth, M., Holmberg, E. & Westin, J. Renal function in newly diagnosed multiple myeloma \u2014 a demographic study of 1353 patients. Eur. J. Haematol. 53, 207\u2013212 (1994).","journal-title":"Eur. J. Haematol."},{"key":"1636_CR40","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1038\/ki.1995.421","volume":"48","author":"CG Winearls","year":"1995","unstructured":"Principal Discussant & Winearls, C. G. Acute Myeloma kidney. Kidney Int. 48, 1347\u20131361 (1995).","journal-title":"Kidney Int."},{"key":"1636_CR41","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1056\/NEJMoa1411321","volume":"372","author":"AK Stewart","year":"2015","unstructured":"Stewart, A. K. et al. Carfilzomib, Lenalidomide, and dexamethasone for relapsed multiple Myeloma. N. Engl. J. Med.372, 142\u2013152 (2015).","journal-title":"N. Engl. J. Med."},{"key":"1636_CR42","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/S1470-2045(09)70284-0","volume":"11","author":"SV Rajkumar","year":"2010","unstructured":"Rajkumar, S. V. et al. Lenalidomide plus high-dose dexamethasone versus lenalidomide plus low-dose dexamethasone as initial therapy for newly diagnosed multiple myeloma: an open-label randomised controlled trial. Lancet Oncol. 11, 29\u201337 (2010).","journal-title":"Lancet Oncol."},{"key":"1636_CR43","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1056\/NEJMoa1606038","volume":"375","author":"A Palumbo","year":"2016","unstructured":"Palumbo, A. et al. Daratumumab, Bortezomib, and dexamethasone for multiple Myeloma. N. Engl. J. Med. 375, 754\u2013766 (2016).","journal-title":"N. Engl. J. Med"},{"key":"1636_CR44","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1056\/NEJMoa1607751","volume":"375","author":"MA Dimopoulos","year":"2016","unstructured":"Dimopoulos, M. A. et al. Daratumumab, lenalidomide, and dexamethasone for multiple Myeloma. N. Engl. J. Med. 375, 1319\u20131331 (2016).","journal-title":"N. Engl. J. Med"},{"key":"1636_CR45","doi-asserted-by":"publisher","first-page":"1721","DOI":"10.1038\/leu.2015.80","volume":"29","author":"EK Mai","year":"2015","unstructured":"Mai, E. K. et al. Phase III trial of bortezomib, cyclophosphamide and dexamethasone (VCD) versus bortezomib, doxorubicin and dexamethasone (PAd) in newly diagnosed myeloma. Leukemia 29, 1721\u20131729 (2015).","journal-title":"Leukemia"},{"key":"1636_CR46","doi-asserted-by":"crossref","unstructured":"for the German-speaking Myeloma Multicenter Group (GMMG) et al. Response-adapted lenalidomide maintenance in newly diagnosed myeloma: results from the phase III GMMG-MM5 trial. Leukemia 34, 1853\u20131865 (2020).","DOI":"10.1038\/s41375-020-0724-1"},{"key":"1636_CR47","doi-asserted-by":"publisher","first-page":"3007","DOI":"10.1038\/s41375-021-01298-y","volume":"35","author":"H Salwender","year":"2021","unstructured":"Salwender, H. et al. Long-term follow-up of subcutaneous versus intravenous bortezomib during induction therapy for newly diagnosed multiple myeloma treated within the GMMG-MM5 Phase III Trial. Leukemia 35, 3007\u20133011 (2021).","journal-title":"Leukemia"},{"key":"1636_CR48","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F. et al. Scikit-learn: Machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"1636_CR49","unstructured":"Mnih, V., Larochelle, H. & Hinton, G. E. Conditional restricted boltzmann machines for structured output prediction. arXiv http:\/\/arxiv.org\/abs\/1202.3748 (2024)."},{"key":"1636_CR50","first-page":"147","volume":"9","author":"D Ackley","year":"1985","unstructured":"Ackley, D., Hinton, G. & Sejnowski, T. A learning algorithm for boltzmann machines. Cogn. Sci. 9, 147\u2013169 (1985).","journal-title":"Cogn. Sci."},{"key":"1636_CR51","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-49656-2","volume":"9","author":"CK Fisher","year":"2019","unstructured":"Fisher, C. K. et al. Machine learning for comprehensive forecasting of Alzheimer\u2019s disease progression. Sci. Rep. 9, 13622 (2019).","journal-title":"Sci. Rep."},{"key":"1636_CR52","unstructured":"Walsh, J. R. et al. Generating digital twins with multiple sclerosis using probabilistic neural networks. arXiv http:\/\/arxiv.org\/abs\/2002.02779 (2024)."},{"key":"1636_CR53","unstructured":"Lang, A. H., Loukianov, A. D. & Fisher, C. K. Neural boltzmann machines. arXiv http:\/\/arxiv.org\/abs\/2305.08337 (2024)."},{"key":"1636_CR54","unstructured":"Paszke, A. et al. PyTorch: An imperative style, high-performance deep learning library. arXiv http:\/\/arxiv.org\/abs\/1912.01703 (2024)."},{"key":"1636_CR55","unstructured":"Falcon, W. & Team, T. P. L. PyTorch lightning version 1.9.5. Zenodo https:\/\/zenodo.org\/record\/7822836 (2024)."},{"key":"1636_CR56","unstructured":"Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. arXiv http:\/\/arxiv.org\/abs\/1711.05101 (2024)."},{"key":"1636_CR57","unstructured":"Assessing The Reliability Of Complex Models: Mathematical And Statistical Foundations Of Verification, Validation, And Uncertainty Quantification. (National Academies Press, Washington, D.C., 2012)."},{"key":"1636_CR58","unstructured":"Shrikumar, A., Greenside, P. & Kundaje, A. Learning important features through propagating activation differences. arXiv http:\/\/arxiv.org\/abs\/1704.02685 (2024)."},{"key":"1636_CR59","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1007\/s10115-013-0679-x","volume":"41","author":"E \u0160trumbelj","year":"2014","unstructured":"\u0160trumbelj, E. & Kononenko, I. Explaining prediction models and individual predictions with feature contributions. Knowl. Inf. Syst. 41, 647\u2013665 (2014).","journal-title":"Knowl. Inf. Syst."},{"key":"1636_CR60","unstructured":"Lundberg, S. & Lee, S.-I. A unified approach to interpreting model predictions. arXiv http:\/\/arxiv.org\/abs\/1705.07874 (2024)."},{"key":"1636_CR61","doi-asserted-by":"crossref","unstructured":"Shapley, L. S. In Contributions to the Theory of Games (AM-28), Volume II (eds Kuhn, H. W. & Tucker, A. W.) 307\u2013318 (Princeton University Press, 1953).","DOI":"10.1515\/9781400881970-018"}],"updated-by":[{"DOI":"10.1038\/s41746-025-01719-7","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:00:00Z","timestamp":1748390400000}}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01636-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01636-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01636-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T07:02:40Z","timestamp":1748502160000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01636-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,30]]},"references-count":61,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1636"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01636-9","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,30]]},"assertion":[{"value":"19 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1038\/s41746-025-01719-7","URL":"https:\/\/doi.org\/10.1038\/s41746-025-01719-7","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"H.G. received financial support from Janssen-Cilag GmbH, Celgene GmbH, Novartis Pharma GmbH, Onyx Pharmaceuticals Inc., Takeda Pharma Vertrieb GmbH and Roche Deutschland Holding GmbH. EKM received financial support from and had consultancy or advisory agreements with Amgen GmbH, Oncopeptides AB (publ), Bristol Myers Squibb\/Celgene GmbH, GlaxoSmithKline GmbH, Janssen-Cilag GmbH, Pfizer Pharma GmbH, Sanofi-Aventis Deutschland GmbH, Stemline Therapeutics, Inc., and Takeda Pharma Vertrieb GmbH. UP. received financial support from Syros Pharmaceuticals Inc., Silence Therapeutics GmbH, Celgene GmbH, Takeda Pharma Vertrieb GmbH, Fibrogen Inc., Servier Deutschland GmbH, Roche Deutschland Holding GmbH, Merck KGaA, Amgen Inc., Novartis Pharma GmbH, Curis Inc., Janssen Pharmaceuticals Inc., Jazz Pharmaceuticals Inc., BeiGene Germany GmbH, Geron Inc., and Bristol-Myers Squibb GmbH. A.O. received financial support from Janssen-Cilag GmbH. MM received financial support from SpringWorks Therapeutics Inc., Janssen-Cilag GmbH, and Roche Deutschland Holding GmbH. M.F., N.G., M.K., J.A., U.B., T.N., and K.R. declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"231"}}