{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T18:15:50Z","timestamp":1777745750210,"version":"3.51.4"},"reference-count":23,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Deanship of Scientific Research and Libraries","award":["NP-45-008"],"award-info":[{"award-number":["NP-45-008"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Tomography"],"abstract":"<jats:p>Background and aim: Chest CT is a major contributor to population radiation exposure. Conventional, pooled diagnostic reference levels (DRLs) do not account for inter-individual variability in body habitus and are typically used retrospectively. We evaluated dose behavior in adult chest CT, derived BMI-stratified local DRLs, and developed models to enable AI-assisted, prescan dose prediction. Methods: Consecutive adult chest CT examinations from a single center were analyzed. Dose indices (CTDIvol, DLP) and patient factors (BMI, weight, height, age, sex; scan length and planned technical parameters where available) were extracted. DRLs were defined as the 75th percentile overall and within BMI categories (underweight, normal, overweight, and obese). Group differences were assessed using non-parametric tests; associations were examined using correlation analysis. Supervised learning (e.g., Random Forest, Gradient Boosting) was trained to predict CTDIvol and DLP from routinely available variables. Results: BMI-stratified DRLs increased monotonically with habitus: underweight 444.95 mGy\u00b7cm\/9.60 mGy; normal 513.00\/11.55; overweight 756.08\/14.65; obese 931.60\/20.25 (DLP\/CTDIvol). Differences across BMI groups were significant for DLP (H = 31.53, p &lt; 0.001) and CTDIvol (H = 33.61, p &lt; 0.001). DLP correlated moderately with weight and BMI (r \u2248 0.54\u20130.56, p &lt; 0.001), with a weaker association for age; height was not a meaningful predictor. No sex-based differences in CTDIvol or DLP were observed. Predictive models estimated CTDIvol and DLP with high performance (R2 up to ~0.79 and ~0.77, respectively), enabling comparison of predicted dose against BMI-matched DRLs before acquisition. Conclusions: Size-aware, BMI-stratified DRLs provide clinically interpretable investigation levels that avoid pitfalls of pooled benchmarks. Coupled with robust prediction of individualized dose from routine variables, this framework supports a shift from retrospective audit to prospective, point-of-care dose governance and protocol optimization in chest CT.<\/jats:p>","DOI":"10.3390\/tomography12050061","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:34:42Z","timestamp":1777458882000},"page":"61","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AI-Driven Prediction of Chest CT Radiation Doses: Establishing BMI-Based Diagnostic Reference Levels and Patient\u2013Factor Correlations for Machine-Learning Models"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2895-2284","authenticated-orcid":false,"given":"Zuhal Y.","family":"Hamd","sequence":"first","affiliation":[{"name":"Department of Radiological Sciences, College of Health and Rehabilitation Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6320-9878","authenticated-orcid":false,"given":"Mohamed","family":"Abuzaid","sequence":"additional","affiliation":[{"name":"Medical Diagnostic Imaging Department, College of Health Sciences, University of Sharjah, Sharjah P.O. Box 26666, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Alharbi","sequence":"additional","affiliation":[{"name":"Medical Imaging Department, King Abdullah bin Abdul-Aziz University Hospital, Riyadh 11564, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9709-2754","authenticated-orcid":false,"given":"Nissren","family":"Tamam","sequence":"additional","affiliation":[{"name":"Department of Physics, College of Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9434-4335","authenticated-orcid":false,"given":"Amal I.","family":"Alorainy","sequence":"additional","affiliation":[{"name":"Department of Radiological Sciences, College of Health and Rehabilitation Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lena","family":"Alrujaee","sequence":"additional","affiliation":[{"name":"Altakassusi Alliance Medical LLC, King Fahad Medical City, Riyadh 12311, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Najla","family":"Almutairi","sequence":"additional","affiliation":[{"name":"Medical Imaging Department, King Abdullah bin Abdul-Aziz University Hospital, Riyadh 11564, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aljouharah Abdullah","family":"Alyagoub","sequence":"additional","affiliation":[{"name":"Medical Imaging Department, King Abdullah bin Abdul-Aziz University Hospital, Riyadh 11564, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Sabiniewicz-Ziajka, D., Szarmach, A., Grzywi\u0144ska, M., Ga\u0107, P., and Piskunowicz, M. (2024). Redefining Radiation Metrics: Evaluating Actual Doses in Computed Tomography Scans. Biomedicines, 12.","DOI":"10.3390\/biomedicines12030600"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1148\/radiol.2015141520","article-title":"Identifying Institutional Diagnostic Reference Levels for CT with Radiation Dose Index Monitoring Software","volume":"276","author":"MacGregor","year":"2015","journal-title":"Radiology"},{"key":"ref_3","unstructured":"Brat, H., Zanca, F., Rizk, B., Montandon, S., and Racine, D. (2019). Influence of BMI on clinical DRLs for CT examinations: A prospective multicenter study after protocol harmonization and optimization. Proceedings of the European Congress of Radiology-EuroSafe Imaging, European Congress of Radiology (ECR)."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"6794","DOI":"10.1007\/s00330-019-06257-x","article-title":"Local clinical diagnostic reference levels for chest and abdomen CT examinations in adults as a function of body mass index and clinical indication: A prospective multicenter study","volume":"29","author":"Brat","year":"2019","journal-title":"Eur. Radiol."},{"key":"ref_5","first-page":"1","article-title":"Establishment of facility reference level in computed tomography in selective examinations in a single institution in South Australia: A preliminary study","volume":"2","author":"Chau","year":"2019","journal-title":"J. Radiol. Med. Diagn. Imaging"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Dalah, E.Z., and Bradley, D.A. (2024). Clinical and technical challenges associated with CT dose optimization in practice. Radiat. Phys. Chem., 223.","DOI":"10.1016\/j.radphyschem.2024.111903"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1093\/rpd\/ncae113","article-title":"Clinical diagnostic reference levels in neuroradiology based on clinical indication","volume":"200","author":"Aly","year":"2024","journal-title":"Radiat. Prot. Dosim."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1111\/1754-9485.13375","article-title":"National diagnostic reference levels: What they are, why we need them and what\u2019s next","volume":"66","author":"Thomas","year":"2022","journal-title":"J. Med. Imaging Radiat. Oncol."},{"key":"ref_9","first-page":"1","article-title":"ICRP Publication 135: Diagnostic Reference Levels in Medical Imaging","volume":"46","author":"Miller","year":"2017","journal-title":"Ann. ICRP"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.2214\/AJR.16.16361","article-title":"Diagnostic reference levels and monitoring practice can help reduce patient dose from CT examinations","volume":"208","author":"Tonkopi","year":"2017","journal-title":"Am. J. Roentgenol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"623","DOI":"10.2174\/1573405617666210913093839","article-title":"A review of diagnostic reference levels in computed tomography","volume":"18","author":"Dawd","year":"2022","journal-title":"Curr. Med. Imaging Rev."},{"key":"ref_12","unstructured":"Wardlaw, G.M., and Martel, N. (2016). Canadian Computed Tomography Survey, Health Canada."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.ejrad.2017.11.002","article-title":"Using diagnostic reference levels to evaluate the improvement of patient dose optimisation and the influence of recent technologies in radiography and computed tomography","volume":"98","author":"Roch","year":"2018","journal-title":"Eur. J. Radiol."},{"key":"ref_14","first-page":"62","article-title":"Local diagnostic reference levels for some common diagnostic X-ray examinations in Sabzevar county of Iran","volume":"15","author":"Zarghani","year":"2018","journal-title":"Iran. J. Med. Phys."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Demircio\u011flu, A., Quinsten, A.S., Umutlu, L., Forsting, M., Nassenstein, K., and Bos, D. (2025). Determining body height and weight from thoracic and abdominal CT localizers in pediatric and young adult patients using deep learning. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-46080-5"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1051\/radiopro\/2024047","article-title":"National diagnostic reference levels (DRLs) for general and interventional radiography, mammography, and CT scan based on the latest surveys in Iran","volume":"60","author":"Sina","year":"2025","journal-title":"Radioprotection"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1007\/s00330-019-06422-2","article-title":"Long-term experience and analysis of data on diagnostic reference levels: The good, the bad, and the ugly","volume":"30","author":"Roch","year":"2019","journal-title":"Eur. Radiol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"J\u00e4rvinen, H., Vassileva, J., Samei, E., Wallace, A., Vano, E., and Rehani, M. (2017). Patient dose monitoring and the use of diagnostic reference levels for the optimization of protection in medical imaging: Current status and challenges worldwide. J. Med. Imaging, 4.","DOI":"10.1117\/1.JMI.4.3.031214"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Clement David-Olawade, A., Olawade, D.B., Vanderbloemen, L., Rotifa, O.B., Fidelis, S.C., Egbon, E., Akpan, A.O., Adeleke, S., Ghose, A., and Boussios, S. (2025). AI-Driven Advances in Low-Dose Imaging and Enhancement\u2014A Review. Diagnostics, 15.","DOI":"10.3390\/diagnostics15060689"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kocak, B., Ponsiglione, A., Romeo, V., Ugga, L., Huisman, M., and Cuocolo, R. (2025). Radiology AI and sustainability paradox: Environmental, economic, and social dimensions. Insights into Imaging, Springer Science and Business Media Deutschland GmbH.","DOI":"10.1186\/s13244-025-01962-2"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"108","DOI":"10.9734\/ajmah\/2025\/v23i61247","article-title":"Impact of Body Mass Index and Sex on Image Quality and Radiation Dose of Routine CT Scan","volume":"23","author":"Sulayman","year":"2025","journal-title":"Asian J. Med. Health"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.15761\/RDI.1000120","article-title":"CT radiation dose optimization and reduction for routine head, chest and abdominal CT examination","volume":"2","author":"Sakhnini","year":"2018","journal-title":"Radiol. Diagn. Imaging"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1177\/0146645320940827","article-title":"Use of artificial intelligence in computed tomography dose optimisation","volume":"49","author":"McCollough","year":"2020","journal-title":"Ann. ICRP"}],"container-title":["Tomography"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2379-139X\/12\/5\/61\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T11:41:33Z","timestamp":1777462893000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2379-139X\/12\/5\/61"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,28]]},"references-count":23,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["tomography12050061"],"URL":"https:\/\/doi.org\/10.3390\/tomography12050061","relation":{},"ISSN":["2379-139X"],"issn-type":[{"value":"2379-139X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,28]]}}}