{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T15:12:42Z","timestamp":1780413162916,"version":"3.54.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T00:00:00Z","timestamp":1780358400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T00:00:00Z","timestamp":1780358400000},"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 Biomed. Innov."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The HeMonitor study evaluated the feasibility and accuracy of non-invasive hemoglobin (Hb) assessment using image-based techniques and machine learning in patients with hematologic malignancies. A total of 367 patients with hematologic malignancies and 184 heal\u015b\u015bthy donors were enrolled, with fingernail and eyelid photographs collected and analyzed using Light Gradient-Boosting Machine (LightGBM) regression models. The best-performing model achieved a residual standard deviation of \u00b11.02\u2009mmol\/L for Hb prediction. Our framework further explored a two-stage concept combining (i) a non-invasive image-based Hb predictor and (ii) a post hoc, rule-bas\u015bed corridor aggregation layer integrating EORTC Global Health and Fatigue categories. This exploratory layer was designed to contextualize Hb estimates with patient-reported symptom burden and well-being. Visual analyses suggested that lower Hb levels were generally associated with impaired quality-of-life measures, consistent with the known clinical burden of anemia. Within the QoL subset, the integrated framework showed encouraging concordance with clinician assessments, particularly in borderline Hb ranges. These findings support the feasibility of combining digital biomarkers with patient-reported outcomes for future patient-centered home monitoring strategies, while prospective validation remains necessary.<\/jats:p>","DOI":"10.1038\/s44385-026-00087-5","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T14:33:06Z","timestamp":1780410786000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and early feasibility testing of machine-learning algorithms to non-invasively assess hemoglobin levels"],"prefix":"10.1038","volume":"3","author":[{"given":"Simon","family":"Hefner","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philipp","family":"Stoffers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benedikt","family":"Langenberger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alix","family":"Holstein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miha","family":"Garafolj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christina","family":"Kl\u00f6tzer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carmen","family":"Herling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vladan","family":"Vucinic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reinhard","family":"Henschler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ariel Dora","family":"Stern","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Uwe","family":"Platzbecker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne Sophie","family":"Platzbecker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,2]]},"reference":[{"key":"87_CR1","doi-asserted-by":"crossref","unstructured":"Wang E. J. et al. HemaApp: noninvasive blood screening of hemoglobin using smartphone cameras. In UbiComp 2016: Proc. 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (2016).","DOI":"10.1145\/2971648.2971653"},{"key":"87_CR2","unstructured":"Masimo Corporation. Pronto - product information. Available at: https:\/\/professional.masimo.com\/products\/monitors\/spot-check\/pronto\/ (2023)."},{"key":"87_CR3","unstructured":"Hasan M. K. et al. SmartHeLP: smartphone-based hemoglobin level prediction using an artificial neural network. AMIA Annu. Symp. Proc. 2018, 535\u2013544 (2018)."},{"key":"87_CR4","doi-asserted-by":"publisher","first-page":"3109","DOI":"10.1007\/s11831-021-09691-7","volume":"29","author":"UMR Paturi","year":"2022","unstructured":"Paturi, U. M. R., Cheruku, S. & Reddy, N. S. The role of artificial neural networks in prediction of mechanical and tribological properties of composites\u2014a comprehensive review. Arch. Comput. Methods Eng. 29, 3109\u20133149 (2022).","journal-title":"Arch. Comput. Methods Eng."},{"key":"87_CR5","doi-asserted-by":"crossref","unstructured":"Chen Y., Hu X., Zhu Y., Liu X., Yi B. Real-time non-invasive hemoglobin prediction using deep learning-enabled smartphone imaging. BMC Med. Inf. Decision Making. 24 (2024).","DOI":"10.1186\/s12911-024-02585-1"},{"key":"87_CR6","unstructured":"Ke G. et al. LightGBM: a highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 30, 3146\u20133154 (2017)."},{"key":"87_CR7","doi-asserted-by":"crossref","unstructured":"Lin J. Y., Fisher D. E. Melanocyte biology and skin pigmentation. Nature. 445, 843-850 (2007).","DOI":"10.1038\/nature05660"},{"key":"87_CR8","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1093\/jnci\/85.5.365","volume":"85","author":"NKAS Aaronson","year":"1993","unstructured":"Aaronson, N. K. A. S. et al. QLQ-C30: A quality-of-life instrument for use in international clinical trials in oncology. J. Natl. Cancer Inst. 85, 365\u2013376 (1993).","journal-title":"J. Natl. Cancer Inst."},{"key":"87_CR9","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1016\/j.bja.2023.05.006","volume":"131","author":"P Meybohm","year":"2023","unstructured":"Meybohm, P. et al. German Patient Blood Management Network: effectiveness and safety analysis in 1.2 million patients. Br. J. Anaesth. 131, 472\u2013481 (2023).","journal-title":"Br. J. Anaesth."},{"key":"87_CR10","doi-asserted-by":"crossref","unstructured":"Emmert-Streib F. & Dehmer M. High-dimensional LASSO-based computational regression models: regularization, shrinkage, and selection. Mach. Learn. Knowl. Extr. 1, 359\u2013383 (2019).","DOI":"10.3390\/make1010021"},{"key":"87_CR11","doi-asserted-by":"crossref","unstructured":"Hoerl A. E. & Kennard R. W. Ridge regression: biased estimation for nonorthogonal problems. Technometrics 12, 55\u201367 (1970).","DOI":"10.1080\/00401706.1970.10488634"},{"key":"87_CR12","doi-asserted-by":"crossref","unstructured":"Schreiber-Gregory D. Ridge Regression and Multicollinearity: An In-Depth Review. In Proc. SAS Global Forum 2018 (2018).","DOI":"10.3233\/MAS-180446"},{"key":"87_CR13","doi-asserted-by":"publisher","first-page":"352","DOI":"10.3758\/BF03200862","volume":"22","author":"RM Nosofsky","year":"1994","unstructured":"Nosofsky, R. M., Gluck, M. A., Palmeri, T. J., McKinley, S. C. & Glauthier, P. Comparing models of rule-based classification learning: a replication and extension of Shepard, Hovland, and Jenkins (1961). Mem. Cognition 22, 352\u2013369 (1994).","journal-title":"Mem. Cognition"},{"key":"87_CR14","doi-asserted-by":"crossref","unstructured":"Lin E.-T. et al. Deep learning-based model for non-invasive hemoglobin estimation via body parts images: a retrospective analysis and a prospective emergency department study. J. Imaging Inform. Med. 38, 775\u2013792 (2025).","DOI":"10.1007\/s10278-024-01209-4"},{"key":"87_CR15","doi-asserted-by":"crossref","unstructured":"Str\u00f6fer C. M., Wu J.-L., Xiao H. & Paterson E. Data-driven, physics-based feature extraction from fluid flow fields using convolutional neural networks. Commun. Comput. Phys. 25, 625\u2013650 (2019).","DOI":"10.4208\/cicp.OA-2018-0035"},{"key":"87_CR16","doi-asserted-by":"crossref","unstructured":"Sarvamangala D. R., Kulkarni R. V. Convolutional neural networks in medical image understanding: a survey. 15, 1-22 (2021).","DOI":"10.1007\/s12065-020-00540-3"},{"key":"87_CR17","doi-asserted-by":"crossref","unstructured":"Bhandari A., Koppen J. & Agzarian M. Convolutional neural networks for brain tumour segmentation. Insights Imaging 11, 77 (2020).","DOI":"10.1186\/s13244-020-00869-4"},{"key":"87_CR18","doi-asserted-by":"crossref","unstructured":"Azer S. A. Challenges facing the detection of colonic polyps: What can deep learning do? 55, 473 (2019).","DOI":"10.3390\/medicina55080473"},{"key":"87_CR19","unstructured":"Scikit-learn developers. User guide. scikit-learn 1.5 documentation. Available at: https:\/\/scikit-learn.org\/1.5\/user_guide.html (2023)."},{"key":"87_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.engstruct.2020.110927","volume":"219","author":"N Time","year":"2020","unstructured":"Time, N., Hwang, S. H. & Jeon, J. S. Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach. Eng. Struct. 219, 110927 (2020).","journal-title":"Eng. Struct."},{"key":"87_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115736","volume":"186","author":"L Antwarg","year":"2021","unstructured":"Antwarg, L., Miller, R. M., Shapira, B. & Rokach, L. Explaining anomalies detected by autoencoders using Shapley Additive Explanations. Expert Syst. Appl. 186, 115736 (2021).","journal-title":"Expert Syst. Appl."},{"key":"87_CR22","doi-asserted-by":"publisher","first-page":"3192","DOI":"10.1182\/blood.V128.22.3192.3192","volume":"128","author":"R Buckstein","year":"2016","unstructured":"Buckstein, R. et al. Quality of life scores improve with increasing hemoglobin but optimal thresholds vary according to transfusion dependence and clinical risk scores: a Canadian cross sectional study of 689 patients with 2969 measurements. Blood 128, 3192 (2016).","journal-title":"Blood"},{"key":"87_CR23","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1182\/blood-2020-139919","volume":"136","author":"GA Abel","year":"2020","unstructured":"Abel, G. A. et al. Feasibility of peri-transfusion quality of life assessment for patients with myelodysplastic syndromes. Blood 136, 25\u201326 (2020).","journal-title":"Blood"},{"key":"87_CR24","doi-asserted-by":"crossref","unstructured":"Haring Y. et al. MDS-related anemia is associated with impaired quality of life but improvement is not always achieved by increased hemoglobin level. J. Clin. Med. 12, 5865 (2023).","DOI":"10.3390\/jcm12185865"},{"key":"87_CR25","doi-asserted-by":"publisher","first-page":"265","DOI":"10.21320\/2500-2139-2018-11-3-265-272","volume":"11","author":"NA Romanenko","year":"2018","unstructured":"Romanenko, N. A., Chechetkin, A. V., Zhiguleva, L. & Grishina, G. V. Bondarchuk sV, Bessmel\u2019tsev SS. correction of anemia and evaluation of efficacy of red blood cell transfusion in patients with oncohematological diseases. Clin. Oncohematol. 11, 265\u2013272 (2018).","journal-title":"Clin. Oncohematol."},{"key":"87_CR26","doi-asserted-by":"crossref","unstructured":"Ruan J., Xie M., Gao J., Liu T., Fu Y. EGE-UNet: an efficient group enhanced UNet for skin lesion segmentation (2023).","DOI":"10.1007\/978-3-031-43901-8_46"},{"key":"87_CR27","doi-asserted-by":"crossref","unstructured":"Zhang C., Liu S., Xu X. & Zhu C. C3AE: exploring the limits of compact model for age estimation. In Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (2019).","DOI":"10.1109\/CVPR.2019.01287"},{"key":"87_CR28","first-page":"1","volume":"8","author":"J Harikrishna","year":"2022","unstructured":"Harikrishna, J., Yashovardhan, A. & Boddapati, A. Evaluation of three hemoglobin estimation methods for screening blood donors: an experience in a South Indian Hospital. J. Res. Appl. Basic Med. Sci. 8, 1\u20137 (2022).","journal-title":"J. Res. Appl. Basic Med. Sci."},{"key":"87_CR29","unstructured":"PyTorch Contributors. ResNet18. TorchVision Documentation (2023)."},{"key":"87_CR30","unstructured":"UMAP Contributors. Release notes - umap 0.5 documentation (2023)."},{"key":"87_CR31","unstructured":"MacQueen J. Some methods for classification and analysis of multivariate observations. In Proc. Fifth Berkeley Symposium on Mathematical Statistics and Probability (1967)."},{"key":"87_CR32","unstructured":"Google. MediaPipe face landmark model. Available at: https:\/\/ai.google.dev\/edge\/mediapipe\/solutions\/vision\/face_landmarker (2023)."},{"key":"87_CR33","unstructured":"Ren T. et al. Grounded SAM: assembling open-world models for diverse visual tasks. arXiv 2401.14159 (2024)."},{"key":"87_CR34","doi-asserted-by":"crossref","unstructured":"Wang Y., Chen J., Su G. Efficient Hand Segmentation and Fingertip Detection Using Color Features of Skin and Fingernail. E96.D, 1894-1897 (2013).","DOI":"10.1587\/transinf.E96.D.1894"},{"key":"87_CR35","doi-asserted-by":"crossref","unstructured":"Ballard D. H. Generalizing the Hough transform to detect arbitrary shapes. 13, 111-122 (1981).","DOI":"10.1016\/0031-3203(81)90009-1"},{"key":"87_CR36","doi-asserted-by":"crossref","unstructured":"Basak J. K., Madhavi B. G. K., Paudel B., Kim N. E., Kim H. T. Prediction of total soluble solids and pH of Strawberry Fruits Using RGB, HSV and HSL colour spaces and machine learning models. 11, 2086 (2022).","DOI":"10.3390\/foods11142086"},{"key":"87_CR37","doi-asserted-by":"crossref","unstructured":"Zhong Z., Wang T., Zeng K., Zhou X., Li Z. White Blood Cell Segmentation via Sparsity and Geometry Constraints. 7, 167593-167604 (2019).","DOI":"10.1109\/ACCESS.2019.2954457"},{"key":"87_CR38","doi-asserted-by":"crossref","unstructured":"Tipping M. E., Bishop C. M. Mixtures of probabilistic principal component analyzers. 11, 443-482 (1999).","DOI":"10.1162\/089976699300016728"}],"container-title":["npj Biomedical Innovations"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s44385-026-00087-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44385-026-00087-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44385-026-00087-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T14:33:35Z","timestamp":1780410815000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s44385-026-00087-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,2]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["87"],"URL":"https:\/\/doi.org\/10.1038\/s44385-026-00087-5","relation":{},"ISSN":["3005-1444"],"issn-type":[{"value":"3005-1444","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,2]]},"assertion":[{"value":"12 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no direct financial or non-financial competing interests related to the content of this study. However, Merantix Momentum GmbH, represented by authors A.H. and M.G., was contracted and financially compensated by the academic investigators for the development and analysis of the machine learning models used in this study. Merantix Momentum GmbH is a private company specializing in artificial intelligence solutions. The involvement of its representatives was limited to methodological and technical contributions within the scope of this collaboration and did not influence the study design, data interpretation, or reporting for commercial purposes. A.S.P. serves on the Board of the German Society for Digital Medicine (DGDM). A.D.S. serves on the Scientific Advisory Board of the German Society for Digital Medicine (DGDM) and the Advisory Board of the Peterson Health Technology Institute and is a Research Fellow of the International Collaborative Bioscience Innovation & Law Programme (Inter-CeBIL program), which is supported by Novo Nordisk Foundation Grant NNF23SA0087056. All other authors report no affiliations, financial agreements, or other relationships that could present a potential conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"34"}}