{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:15:40Z","timestamp":1760145340111,"version":"build-2065373602"},"reference-count":11,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T00:00:00Z","timestamp":1720137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Carleton College"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The paper \u201cUsing Absorption Models for Insulin and Carbohydrates and Deep Leaning to Improve Glucose Level Predictions\u201d (Sensors\u00a02021, 21, 5273) proposes a novel approach to predicting blood glucose levels for people with type 1 diabetes mellitus (T1DM). By building exponential models from raw carbohydrate and insulin data to simulate the absorption in the body, the authors reported a reduction in their model\u2019s root-mean-square error (RMSE) from 15.5 mg\/dL (raw) to 9.2 mg\/dL (exponential) when predicting blood glucose levels one hour into the future. In this comment, we demonstrate that the experimental techniques used in that paper are flawed, which invalidates its results and conclusions. Specifically, after reviewing the authors\u2019 code, we found that the model validation scheme was malformed, namely, the training and test data from the same time intervals were mixed. This means that the reported RMSE numbers in the referenced paper did not accurately measure the predictive capabilities of the approaches that were presented. We repaired the measurement technique by appropriately isolating the training and test data, and we discovered that their models actually performed dramatically worse than was reported in the paper. In fact, the models presented in the that paper do not appear to perform any better than a naive model that predicts future glucose levels to be the same as the current ones.<\/jats:p>","DOI":"10.3390\/s24134361","type":"journal-article","created":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T03:48:56Z","timestamp":1720151336000},"page":"4361","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comment on Mart\u00ednez-Delgado et al. Using Absorption Models for Insulin and Carbohydrates and Deep Leaning to Improve Glucose Level Predictions. Sensors 2021, 21, 5273"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4247-0935","authenticated-orcid":false,"given":"Josiah Z. R.","family":"Misplon","sequence":"first","affiliation":[{"name":"Department of Computer Science, Carleton College, Northfield, MN 55057, USA"},{"name":"Population Health, Epic Systems, Verona, WI 53593, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3821-0313","authenticated-orcid":false,"given":"Varun","family":"Saini","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Carleton College, Northfield, MN 55057, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4546-2247","authenticated-orcid":false,"given":"Brianna P.","family":"Sloves","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Carleton College, Northfield, MN 55057, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2526-1955","authenticated-orcid":false,"given":"Sarah H.","family":"Meerts","sequence":"additional","affiliation":[{"name":"Neuroscience Program and Department of Psychology, Carleton College, Northfield, MN 55057, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6580-382X","authenticated-orcid":false,"given":"David R.","family":"Musicant","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Carleton College, Northfield, MN 55057, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,7,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/S0140-6736(13)60591-7","article-title":"Type 1 diabetes","volume":"383","author":"Atkinson","year":"2014","journal-title":"Lancet"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"678","DOI":"10.1111\/jdi.12360","article-title":"Carbohydrate intake is associated with time spent in the euglycemic range in patients with type 1 diabetes","volume":"6","author":"Ikeda","year":"2015","journal-title":"J. Diabetes Investig."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3169","DOI":"10.2337\/db08-1084","article-title":"The barrier of hypoglycemia in diabetes","volume":"57","author":"Cryer","year":"2008","journal-title":"Diabetes"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1209","DOI":"10.1001\/archneur.58.8.1209","article-title":"The role of hyperglycemia in acute stroke","volume":"58","author":"Kagansky","year":"2001","journal-title":"Arch. Neurol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"109938","DOI":"10.1016\/j.diabres.2022.109938","article-title":"Hyperglycemia and hypoglycemia exposure are differentially associated with micro- and macrovascular complications in adults with Type 1 Diabetes","volume":"189","author":"Mesa","year":"2022","journal-title":"Diabetes Res. Clin. Pract."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1111\/j.1742-1241.2010.02574.x","article-title":"Insulin pumps","volume":"65","author":"Pickup","year":"2011","journal-title":"Int. J. Clin. Pract. Suppl."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1177\/1932296816672689","article-title":"Sensor-Augmented Insulin Pumps and Hypoglycemia Prevention in Type 1 Diabetes","volume":"11","author":"Steineck","year":"2017","journal-title":"J. Diabetes Sci. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1097\/MED.0000000000000142","article-title":"Progress of artificial pancreas devices towards clinical use: The first outpatient studies","volume":"22","author":"Russell","year":"2015","journal-title":"Curr. Opin. Endocrinol. Diabetes Obes."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Mart\u00ednez-Delgado, L., Munoz-Organero, M., and Queipo-Alvarez, P. (2021). Using Absorption Models for Insulin and Carbohydrates and Deep Leaning to Improve Glucose Level Predictions. Sensors, 21.","DOI":"10.3390\/s21165273"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.ins.2011.12.028","article-title":"On the use of cross-validation for time series predictor evaluation","volume":"191","author":"Bergmeir","year":"2012","journal-title":"Inf. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.imu.2018.09.003","article-title":"The open D1NAMO dataset: A multi-modal dataset for research on non-invasive type 1 diabetes management","volume":"13","author":"Dubosson","year":"2018","journal-title":"Inform. Med. Unlocked"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/13\/4361\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:10:30Z","timestamp":1760109030000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/13\/4361"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,5]]},"references-count":11,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["s24134361"],"URL":"https:\/\/doi.org\/10.3390\/s24134361","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2024,7,5]]}}}