{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T08:00:47Z","timestamp":1772006447079,"version":"3.50.1"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T00:00:00Z","timestamp":1771977600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100021856","name":"Ministero dell'Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100021856","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Machine Learning (ML) applied to healthcare Real World Data (RWD) may improve patient management. RWD, however, requires extensive preprocessing to make it ML-ready. Our aim was to explore the impact of preprocessing on ML models applied to RWD from 20 years of type 2 diabetes patients visits.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Our cohort consisted of patients with at least two glycated hemoglobin (HbA1c) measurements three years apart. We set up three different experimental settings consisting of different data preprocessing pipelines. Logistic Regression (LR), XGBoost and a Decision Tree Classifier (DTC) were then applied and tuned to optimize precision.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The final dataset comprised 12 variables from 1,651 patients treated between 2003 and 2023. 921 (56%) patients had a HbA1c decrease at three years. This group had a higher baseline HbA1c, higher BMI and shorter first visit gap from the date of diagnosis (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&amp;lt;\u20090.0001). Precision scores for LR, XGBoost did not vary across different experimental conditions while DTC benefitted from missing data imputation. Shapley Additive Explanations confirmed the Exploratory Data Analysis findings, with worse baseline values being predictors of HbA1c decrease at three years.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>ML models' performance and their explanation did not vary substantially across experimental conditions, with worse baseline values being predictors of HbA1c decrease at three years. Insights such as this, extracted by ML application to RWD, enable clinical discussion and may foster improvements in patient management.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fdgth.2026.1685842","type":"journal-article","created":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T07:04:35Z","timestamp":1772003075000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["From raw data to actionable insights: preprocessing real-world data for machine learning in diabetes care"],"prefix":"10.3389","volume":"8","author":[{"given":"Marco","family":"Montagna","sequence":"first","affiliation":[{"name":"Department of Medicine, IRCCS San Raffaele Scientific Institute","place":["Milan, Italy"]},{"name":"School of Medicine, Vita-Salute San Raffaele University","place":["Milan, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aleksandar Svilenov","family":"Rabadzhiev","sequence":"additional","affiliation":[{"name":"School of Medicine, Vita-Salute San Raffaele University","place":["Milan, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alberto","family":"Traverso","sequence":"additional","affiliation":[{"name":"S-RACE (S-Raffaele Ai CEnter), Vita-Salute San Raffaele University","place":["Milan, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuela","family":"Setola","sequence":"additional","affiliation":[{"name":"Diabetology Unit, IRCCS San Raffaele Scientific Institute","place":["Milan, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edoardo","family":"Draetta","sequence":"additional","affiliation":[{"name":"S-RACE (S-Raffaele Ai CEnter), Vita-Salute San Raffaele University","place":["Milan, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessio","family":"Dimonte","sequence":"additional","affiliation":[{"name":"S-RACE (S-Raffaele Ai CEnter), Vita-Salute San Raffaele University","place":["Milan, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simone","family":"Barbieri","sequence":"additional","affiliation":[{"name":"S-RACE (S-Raffaele Ai CEnter), Vita-Salute San Raffaele University","place":["Milan, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bruno","family":"Fabiani","sequence":"additional","affiliation":[{"name":"S-RACE (S-Raffaele Ai CEnter), Vita-Salute San Raffaele University","place":["Milan, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lorenzo","family":"Piemonti","sequence":"additional","affiliation":[{"name":"School of Medicine, Vita-Salute San Raffaele University","place":["Milan, Italy"]},{"name":"Diabetes Research Institute, IRCCS San Raffaele Scientific Institute","place":["Milan, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Esposito","sequence":"additional","affiliation":[{"name":"S-RACE (S-Raffaele Ai CEnter), Vita-Salute San Raffaele University","place":["Milan, Italy"]},{"name":"Experimental Imaging Center, IRCCS San Raffaele Scientific Institute","place":["Milan, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlo","family":"Tacchetti","sequence":"additional","affiliation":[{"name":"S-RACE (S-Raffaele Ai CEnter), Vita-Salute San Raffaele University","place":["Milan, Italy"]},{"name":"Experimental Imaging Center, IRCCS San Raffaele Scientific Institute","place":["Milan, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrizia","family":"Rovere Querini","sequence":"additional","affiliation":[{"name":"Department of Medicine, IRCCS San Raffaele Scientific Institute","place":["Milan, Italy"]},{"name":"School of Medicine, Vita-Salute San Raffaele University","place":["Milan, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,25]]},"reference":[{"key":"B1","volume-title":"IDF Diabetes Atlas","year":"2025"},{"key":"B2","doi-asserted-by":"publisher","first-page":"95","DOI":"10.4137\/BMI.S38440","article-title":"Significance of HbA1c test in diagnosis and prognosis of diabetic patients","volume":"11","author":"Sherwani","year":"2016","journal-title":"Biomark Insights"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.1210\/jcem.84.4.5612","article-title":"Type 2 diabetes mellitus: update on diagnosis, pathophysiology, and treatment","volume":"84","author":"Mahler","year":"1999","journal-title":"J Clin Endocrinol Metab"},{"key":"B4","doi-asserted-by":"publisher","first-page":"e16922","DOI":"10.2196\/16922","article-title":"Artificial intelligence and big data in diabetes care: a position statement of the Italian association of medical diabetologists","volume":"22","author":"Musacchio","year":"2020","journal-title":"J Med Internet Res"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1316","DOI":"10.2337\/dc22-1438","article-title":"Use of real-world data in population science to improve the prevention and care of diabetes-related outcomes","volume":"46","author":"Gregg","year":"2023","journal-title":"Diabetes Care"},{"key":"B6","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1017\/cts.2023.352","article-title":"297 identifying opportunities and challenges for translational informatics approaches to real-world data: a diabetes case study","volume":"7","author":"Barlean","year":"2023","journal-title":"J Clin Transl Sci"},{"key":"B7","doi-asserted-by":"publisher","first-page":"110013","DOI":"10.1016\/j.diabres.2022.110013","article-title":"Prediction of complications of type 2 diabetes: a machine learning approach","volume":"190","author":"Nicolucci","year":"2022","journal-title":"Diabetes Res Clin Pract"},{"key":"B8","doi-asserted-by":"publisher","first-page":"110092","DOI":"10.1016\/j.diabres.2022.110092","article-title":"A prediction model to assess the risk of egfr loss in patients with type 2 diabetes and preserved kidney function: the amd annals initiative","volume":"192","author":"Russo","year":"2022","journal-title":"Diabetes Res Clin Pract"},{"key":"B9","doi-asserted-by":"publisher","first-page":"e001362","DOI":"10.1136\/bmjdrc-2020-001362","article-title":"Determinants of good metabolic control without weight gain in type 2 diabetes management: a machine learning analysis","volume":"8","author":"Giorda","year":"2020","journal-title":"BMJ Open Diabetes Res Care"},{"key":"B10","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.kjms.2012.08.016","article-title":"Comparison of three data mining models for predicting diabetes or prediabetes by risk factors","volume":"29","author":"Meng","year":"2013","journal-title":"Kaohsiung J Med Sci"},{"key":"B11","doi-asserted-by":"publisher","first-page":"e25237","DOI":"10.2196\/25237","article-title":"Improving current glycated hemoglobin prediction in adults: use of machine learning algorithms with electronic health records","volume":"9","author":"Alhassan","year":"2021","journal-title":"JMIR Med Inform"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2704","DOI":"10.1111\/dom.13860","article-title":"Predicting short- and long-term glycated haemoglobin response after insulin initiation in patients with type 2 diabetes mellitus using machine-learning algorithms","volume":"21","author":"Nagaraj","year":"2019","journal-title":"Diabetes Obes Metab"},{"key":"B13","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1001\/jama.2019.21579","article-title":"Artificial intelligence in health care: a report from the national academy of medicine","volume":"323","author":"Matheny","year":"2020","journal-title":"J Am Med Assoc"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-020-00333-z","article-title":"A short guide for medical professionals in the era of artificial intelligence","volume":"3","author":"Mesk\u00f3","year":"2020","journal-title":"npj Digit Med"},{"key":"B15","doi-asserted-by":"publisher","first-page":"e100784","DOI":"10.1136\/bmjhci-2023-100784","article-title":"Road map for clinicians to develop and evaluate AI predictive models to inform clinical decision-making","volume":"30","author":"Hassan","year":"2023","journal-title":"BMJ Health Care Inform"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1056\/NEJMp2404691","article-title":"Compared with what? Measuring AI against the health care we have","volume":"391","author":"Kohane","year":"2024","journal-title":"N Engl J Med"},{"key":"B17","first-page":"1","article-title":"Data quality considerations for big data and machine learning: going beyond data cleaning and transformations","volume":"10","author":"Gudivada","year":"2017","journal-title":"Int J Adv Softw"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1001\/jama.2025.1335","article-title":"Moving toward implementation of responsible artificial intelligence in health care: the European TRAIN initiative","volume":"333","author":"Genderen","year":"2025","journal-title":"JAMA"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.1001\/jama.2025.1331","article-title":"Launching the trustworthy and responsible AI network (TRAIN): a consortium to facilitate safe and effective AI adoption","volume":"333","author":"Emb\u00ed","year":"2025","journal-title":"JAMA"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1041","DOI":"10.1111\/j.1464-5491.2010.03055.x","article-title":"Four-year impact of a continuous quality improvement effort implemented by a network of diabetes outpatient clinics: the AMD-annals initiative","volume":"27","author":"Nicolucci","year":"2010","journal-title":"Diabet Med"},{"key":"B21","doi-asserted-by":"publisher","first-page":"108075","DOI":"10.1016\/j.lungcan.2024.108075","article-title":"Exploring machine learning tools in a retrospective case-study of patients with metastatic non-small cell lung cancer treated with first-line immunotherapy: a feasibility single-centre experience","volume":"199","author":"Ogliari","year":"2025","journal-title":"Lung Cancer"},{"key":"B22","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1093\/clinchem\/18.6.499","article-title":"Estimation of the concentration of low-density lipoprotein cholesterol in plasma, without use of the preparative ultracentrifuge","volume":"18","author":"Friedewald","year":"1972","journal-title":"Clin Chem"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.07874","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017","journal-title":"arXiv [Preprint]. arXiv:1705.07874"},{"key":"B24","author":"Bastani","year":""},{"key":"B25","doi-asserted-by":"publisher","first-page":"34","DOI":"10.69882\/adba.cem.2024075","article-title":"Machine learning interpretability in diabetes risk assessment: a SHAP analysis","volume":"1","author":"Kutlu","year":"2024","journal-title":"Comput Electron Med"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e0327120","DOI":"10.1371\/journal.pone.0327120","article-title":"Enhancing diabetes risk prediction through focal active learning and machine learning models","volume":"20","author":"Zhang","year":"2025","journal-title":"PLoS One"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1186\/s12889-025-22419-7","article-title":"Interpretable machine learning method to predict the risk of pre-diabetes using a national-wide cross-sectional data: evidence from CHNS","volume":"25","author":"Li","year":"2025","journal-title":"BMC Public Health"},{"key":"B28","year":""},{"key":"B29","doi-asserted-by":"publisher","first-page":"104510","DOI":"10.1016\/j.ijmedinf.2021.104510","article-title":"The need to separate the wheat from the chaff in medical informatics: introducing a comprehensive checklist for the (self)-assessment of medical AI studies","volume":"153","author":"Cabitza","year":"2021","journal-title":"Int J Med Inform"},{"key":"B30","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1093\/jamia\/ocaa088","article-title":"MINIMAR (MINimum information for medical AI reporting): developing reporting standards for artificial intelligence in health care","volume":"27","author":"Hernandez-Boussard","year":"2020","journal-title":"J Am Med Inform Assoc"},{"key":"B31","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1186\/s12874-022-01768-6","article-title":"Real-world data: a brief review of the methods, applications, challenges and opportunities","volume":"22","author":"Liu","year":"2022","journal-title":"BMC Med Res Methodol"},{"key":"B32","doi-asserted-by":"publisher","first-page":"e641","DOI":"10.1016\/S2666-7568(22)00214-8","article-title":"Strengthening evidence-based medicine with real-world evidence","volume":"3","author":"Dreyer","year":"2022","journal-title":"Lancet Healthy Longev"},{"key":"B33","doi-asserted-by":"publisher","first-page":"e52290","DOI":"10.2196\/52290","article-title":"A call for a health data\u2013informed workforce among clinicians","volume":"10","author":"Doll","year":"2024","journal-title":"JMIR Med Educ"},{"key":"B34","first-page":"623","article-title":"Accurate intelligible models with pairwise interactions","author":"Lou","year":""},{"key":"B35","first-page":"6679","article-title":"Tabnet: attentive interpretable tabular learning","author":"Ar\u0131k","year":"2021"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1685842\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T07:04:37Z","timestamp":1772003077000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1685842\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,25]]},"references-count":35,"alternative-id":["10.3389\/fdgth.2026.1685842"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2026.1685842","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,25]]},"article-number":"1685842"}}