{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T16:54:12Z","timestamp":1785430452630,"version":"3.56.0"},"reference-count":38,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100012725","name":"Tecnol\u00f3gico Nacional de M\u00e9xico","doi-asserted-by":"publisher","award":["21636.25-P"],"award-info":[{"award-number":["21636.25-P"]}],"id":[{"id":"10.13039\/100012725","id-type":"DOI","asserted-by":"publisher"}]},{"award":["21636.25-P"],"award-info":[{"award-number":["21636.25-P"]}],"id":[{"id":"https:\/\/ror.org\/00davry38","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Type 1 diabetes mellitus (T1DM) is a chronic, non-preventable, and incurable disease that requires lifelong insulin administration. The principal challenge is calculating the prandial insulin bolus to avoid hypoglycemia and hyperglycemia. Traditional bolus calculators are based on limited number of variables, but there are many variables that define the complex interactions among glucose levels, like carbohydrate intake, physical activity, mood, and contextual factors. While recent artificial intelligence (AI) approaches have shown promise in glucose prediction, most remain correlational and offer limited interpretability for clinical decision support. This study evaluates a causal inference-based framework for insulin bolus calculation using Directed Acyclic Graphs (DAGs) and the Greedy Relaxation of the Sparsest Permutation (GRaSP). Historical data from individuals with T1DM were analyzed, incorporating domain knowledge constraints to guide structure learning. A bootstrap-based stability analysis was conducted to evaluate the robustness of inferred relationships. Results show that integrating prior medical knowledge reduces graph complexity and improves interpretability. However, bootstrap stability reflects robustness of the learning procedure rather than causal validity. The findings suggest that the proposed framework is useful for generating plausible causal hypotheses, but not for confirming causal relationships. Further validation using conditional independence testing, equivalence class analysis, and temporal causal methods is required. However, the proposed framework focuses on generating plausible causal hypotheses rather than establishing causal validity, which requires further refutation-based validation.<\/jats:p>","DOI":"10.3390\/e28050506","type":"journal-article","created":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T09:33:17Z","timestamp":1777627997000},"page":"506","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DAGs and GRaSP Causal Inference Algorithms Combined and Applied to the Calculation of Insulin Bolus in Patients with Type 1 Diabetes"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7184-3859","authenticated-orcid":false,"given":"Roc\u00edo","family":"Contreras-Jim\u00e9nez","sequence":"first","affiliation":[{"name":"Divisi\u00f3n de Estudios de Posgrado e Investigaci\u00f3n, Tecnol\u00f3gico Nacional de M\u00e9xico\/I. T. de Morelia, Morelia 58120, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5302-1786","authenticated-orcid":false,"given":"Juan Carlos","family":"Olivares-Rojas","sequence":"additional","affiliation":[{"name":"Divisi\u00f3n de Estudios de Posgrado e Investigaci\u00f3n, Tecnol\u00f3gico Nacional de M\u00e9xico\/I. T. de Morelia, Morelia 58120, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0945-2076","authenticated-orcid":false,"given":"Adriana del Carmen","family":"T\u00e9llez-Anguiano","sequence":"additional","affiliation":[{"name":"Divisi\u00f3n de Estudios de Posgrado e Investigaci\u00f3n, Tecnol\u00f3gico Nacional de M\u00e9xico\/I. T. de Morelia, Morelia 58120, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6514-4571","authenticated-orcid":false,"given":"Jes\u00fas Eduardo","family":"Alcar\u00e1z-Ch\u00e1vez","sequence":"additional","affiliation":[{"name":"Divisi\u00f3n de Estudios de Posgrado e Investigaci\u00f3n, Tecnol\u00f3gico Nacional de M\u00e9xico\/I. T. de Morelia, Morelia 58120, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7898-604X","authenticated-orcid":false,"given":"Jos\u00e9 Antonio","family":"Guti\u00e9rrez-Gnecchi","sequence":"additional","affiliation":[{"name":"Divisi\u00f3n de Estudios de Posgrado e Investigaci\u00f3n, Tecnol\u00f3gico Nacional de M\u00e9xico\/I. T. de Morelia, Morelia 58120, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3374-0059","authenticated-orcid":false,"given":"Enrique","family":"Reyes-Archundia","sequence":"additional","affiliation":[{"name":"Divisi\u00f3n de Estudios de Posgrado e Investigaci\u00f3n, Tecnol\u00f3gico Nacional de M\u00e9xico\/I. T. de Morelia, Morelia 58120, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"ref_1","unstructured":"World Health Organization (2025, July 16). Diabetes. Available online: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/diabetes."},{"key":"ref_2","unstructured":"NHS (2025, October 11). Complications of Type 1 Diabetes. NHS. Available online: https:\/\/www.nhs.uk\/conditions\/type-1-diabetes\/complications\/."},{"key":"ref_3","unstructured":"Metlife (2025, July 16). \u00bfCu\u00e1nto Cuesta Vivir con Diabetes en M\u00e9xico?. Available online: https:\/\/www.metlife.com.mx\/blog\/bienestar-financiero\/gastos-de-vivir-con-diabetes-cuanto-necesitas\/."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1177\/1932296814532906","article-title":"Bolus Calculators","volume":"8","author":"Schmidt","year":"2014","journal-title":"J. Diabetes Sci. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1109\/TBME.2020.3004031","article-title":"Machine-Learning Based Model to Improve Insulin Bolus Calculation in Type 1 Diabetes Therapy","volume":"68","author":"Noaro","year":"2021","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhu, T., Li, K., Kuang, L., Herrero, P., and Georgiou, P. (2020). An insulin bolus advisor for type 1 diabetes using deep reinforcement learning. Sensors, 20.","DOI":"10.3390\/s20185058"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kalita, D., and Mirza, K.B. (2023, January 24\u201327). InsNET: Accurate Basal and Bolus Insulin Dose Prediction for Closed Loop Diabetes Management. Proceedings of the 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Sydney, Australia.","DOI":"10.1109\/EMBC40787.2023.10340480"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"192572","DOI":"10.1109\/ACCESS.2024.3518832","article-title":"Intelligent Dual Basal\u2013Bolus Calculator for Multiple Daily Insulin Injections via Offline Reinforcement Learning","volume":"12","author":"Yoo","year":"2024","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1111\/jdi.70198","article-title":"Efficacy of MiniMed\u2122 780G\u00ae on glucose management, sleep quality, and psychological aspects in persons with type 1 diabetes treated with MiniMed\u2122 770G\u00ae A 3-month prospective single-center observational study","volume":"17","author":"Akiyama","year":"2026","journal-title":"J. Diabetes Investig."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Olivetti, E., Zoonekynd, V., Yam, P., de Prado, M.L., Imbens, G.W., and Hern\u00e1n, M.A. (2026). Can AI Learn Causal Structure? Evidence from ADIA Lab\u2019s Causal Discovery Challenge. SSRN.","DOI":"10.2139\/ssrn.6119986"},{"key":"ref_11","unstructured":"Lam, W.Y., Andrews, B., and Ramsey, J. (2022, January 1\u20135). Greedy relaxations of the sparsest permutation algorithm. Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, Eindhoven, The Netherlands."},{"key":"ref_12","unstructured":"Gomstyn, A., and Jonker, A. (2026, April 18). Qu\u00e9 es un DAG?. Available online: https:\/\/www.ibm.com\/mx-es\/think\/topics\/directed-acyclic-graph."},{"key":"ref_13","unstructured":"Molak, A. (2024). Inferencia y Descubrimiento Causal en Python, Anaya Multimedia."},{"key":"ref_14","unstructured":"Pearl, J., and Mackenzie, D. (2019). The Book of Why, Penguins Books."},{"key":"ref_15","unstructured":"Lam, W.Y., Andrews, B., and Ramsey, J. (2026, February 27). GRaSP Project Repository. Available online: https:\/\/github.com\/cmu-phil\/grasp."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1177\/089443939100900106","article-title":"An Algorithm for Fast Recovery of Sparse Causal","volume":"9","author":"Spirtes","year":"1991","journal-title":"Soc. Sci. Comput. Rev."},{"key":"ref_17","first-page":"1","article-title":"Causal-learn: Causal discovery in python","volume":"25","author":"Zheng","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1007\/s41060-016-0032-z","article-title":"A million variables and more: The Fast Greedy Equivalence Search algorithm for learning high-dimensional graphical causal models, with an application to functional magnetic resonance images","volume":"3","author":"Ramsey","year":"2017","journal-title":"Int. J. Data Sci. Anal."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1093\/biomet\/asaa104","article-title":"Consistency Guarantees for Greedy Permutation-Based Causal Inference Algorithms","volume":"108","author":"Solus","year":"2021","journal-title":"Biometrika"},{"key":"ref_20","unstructured":"Ng, I., Ghassami, A., and Zhang, K. (2021). On the Role of Sparsity and DAG Constraints for Learning Linear DAGs. arXiv."},{"key":"ref_21","first-page":"11","article-title":"Scalable Causal Structure Learning: Scoping Review of Traditional and Deep Learning Algorithms and New Opportunities in Biomedicine","volume":"17","author":"Upadhyaya","year":"2023","journal-title":"JMIR Med. Inform."},{"key":"ref_22","unstructured":"Farooq, M., Hardan, S., Zhumbhayeva, A., Zheng, Y., Nakov, P., and Zhang, K. (2023). Understanding breast cancer survival: Using causality and language models on multi-omics data. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"20220133","DOI":"10.1515\/em-2022-0133","article-title":"Development and application of an evidence-based directed acyclic graph to evaluate the associations between metal mixtures and cardiometabolic outcomes","volume":"12","author":"Riseberg","year":"2023","journal-title":"Epidemiol. Methods"},{"key":"ref_24","first-page":"38","article-title":"The directed acyclic graph helped identify confounders in the association between coronary heart disease and pesticide exposure among greenhouse vegetable farmers","volume":"102","author":"Li","year":"2023","journal-title":"Medicine"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1096","DOI":"10.1093\/aje\/kwm179","article-title":"Directed Acyclic Graphs, Sufficient Causes, and the Properties of Conditioning on a Common Effect","volume":"166","author":"VanderWeele","year":"2007","journal-title":"Am. J. Epidemiol."},{"key":"ref_26","unstructured":"Maradei, S.J. (2025, October 11). Ciencias \u00d3micas: \u00bfEso qu\u00e9 es y con qu\u00e9 se come? Biotecgen. Available online: https:\/\/www.biotecgen.com.co\/blog\/ciencias-omicas."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zeng, D., Legaspi, R., Sun, Y., Dong, X., Ikeda, K., Spirtes, P., and Zhang, K. (2025). Causal discovery and counterfactual reasoning to optimize persuasive dialogue policies. Behav. Inf. Technol., 1\u201315.","DOI":"10.1080\/0144929X.2025.2478276"},{"key":"ref_28","unstructured":"Ferdous, M.H., Hasan, U., and Gani, M.O. (2023, January 11\u201312). CDANs: Temporal Causal Discovery from Autocorrelated and Non-Stationary Time Series Data. Proceedings of the 8th Machine Learning for Healthcare Conference, New York, NY, USA."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"110559","DOI":"10.1016\/j.dib.2024.110559","article-title":"HUPA-UCM diabetes dataset","volume":"55","author":"Hidalgo","year":"2024","journal-title":"Data Brief."},{"key":"ref_30","unstructured":"Oxford University (2025, July 18). Oxford Reference. Available online: https:\/\/www.oxfordreference.com\/display\/10.1093\/oi\/authority.20111005143410337."},{"key":"ref_31","unstructured":"Carnegie Mellon University (2026, February 27). Tetrad. Available online: https:\/\/www.cmu.edu\/dietrich\/philosophy\/tetrad\/."},{"key":"ref_32","unstructured":"Gansner, E.R. (2026, April 18). Using Graphviz as a Library (Cgraph Version). Available online: https:\/\/www.aidoczh.com\/graphviz\/pdf\/libguide.pdf."},{"key":"ref_33","unstructured":"(2026, April 07). DoWhy Documentation. Available online: https:\/\/www.pywhy.org\/dowhy\/v0.14\/."},{"key":"ref_34","unstructured":"Andrews, B., and Ramsey, J. (2026, April 07). Greedy Relaxations of the Sparsest Permutation Algorithm. Available online: https:\/\/www.phil.cmu.edu\/tetrad-javadocs\/7.4.0\/edu\/cmu\/tetrad\/search\/Grasp.html."},{"key":"ref_35","first-page":"1","article-title":"Principle of structural equation modeling for exploring functional interactivity within a putative network of interconnected brain areas","volume":"27","author":"Vrignaud","year":"2009","journal-title":"Magn. Reson. Imaging"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v047.i11","article-title":"Causal Inference Using Graphical Models with the R Package pcalg","volume":"47","author":"Kalisch","year":"2012","journal-title":"J. Stat. Softw."},{"key":"ref_37","unstructured":"IBM (2026, April 08). Gu\u00eda Del Machine Learning 2026. Available online: https:\/\/www.ibm.com\/mx-es\/think\/machine-learning#605511093."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"63945","DOI":"10.52202\/075280-2794","article-title":"Fast scalable and accurate discovery of DAGs using the best order score search and grow shrink trees","volume":"36","author":"Andrews","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/5\/506\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T09:35:03Z","timestamp":1777628103000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/5\/506"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,1]]},"references-count":38,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["e28050506"],"URL":"https:\/\/doi.org\/10.3390\/e28050506","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,1]]}}}