{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T12:13:18Z","timestamp":1788437598280,"version":"build-2803163510"},"reference-count":42,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T00:00:00Z","timestamp":1788393600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Traumatic intracranial hemorrhage (tICH) in older adults following low-energy falls (LEF) represents a common yet diagnostically challenging condition in the emergency department (ED), where predicting injury prior to computed tomography (CT) remains difficult. Machine learning (ML) has been proposed to support CT decision-making, but its feasibility using routinely available pre-CT clinical variables in this specific population remains unclear. This study presents a systematic exploratory benchmarking of ML pipeline configurations for pre-CT tICH prediction in a well-defined retrospective cohort of older emergency patients following LEF. Methods: We performed a secondary analysis from a retrospective observational bicentric study from two university hospital EDs, including 2250 patients aged \u226565 years presenting after an LEF and undergoing cranial CT. Clinical data were extracted manually from electronic health records (EHRs). Eighteen pre-CT clinical features retrieved from electronic health records were selected based on routine availability and \u226410% missingness. Overall, 1224 valid ML pipeline configurations, combining nine classification algorithms, six imputation strategies, four class-balancing approaches, and optional hyperparameter tuning, were evaluated using 10-fold stratified cross-validation on a training set. The 20 highest-ranked configurations by cross-validation AUC were then assessed on a previously inspected exploratory hold-out test set (n = 563); training-derived rule-out operating points were evaluable for 17 of these 20, as three tuned SVM configurations lacked stored out-of-fold predictions. Results: tICH prevalence was 7.0% (n = 158). Across the 20 highest-ranked configurations, hold-out AUC ranged from 0.517 to 0.585, with Matthews correlation coefficient near zero and balanced accuracy of approximately 50% throughout, indicating differences in operating point rather than in discriminative ability. Some of these top-ranked pipelines reached higher cross-validation AUC (up to 0.679) but detected no cases at the default 0.5 threshold\u2014an effect of the decision threshold under class imbalance rather than of the models\u2019 rank-order discrimination, which was itself limited (hold-out AUC of 0.517\u20130.585). Conclusions: Despite comprehensive exploratory benchmarking across 1224 ML pipelines, routinely available pre-CT clinical features did not provide sufficient discriminatory signal to develop a clinically useful tICH prediction model in this cohort of CT-imaged older adults following LEF. These findings indicate that none of the evaluated configurations produced clinically adequate performance; this near-chance result persisted across all pipelines and most plausibly reflects a combination of limited feature signal, low outcome prevalence, and a sample size below the level required for reliable model development at this event rate. Future studies should target substantially larger prospective multicenter cohorts and evaluate additional feature domains, including structured clinical examination findings, point-of-care biomarkers, and imaging features.<\/jats:p>","DOI":"10.3390\/diagnostics16172840","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T11:08:53Z","timestamp":1788433733000},"page":"2840","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Limited Predictability of Traumatic Intracranial Hemorrhage from Routine Pre-CT Clinical Variables in Older Adults with Low-Energy Falls: A Systematic Benchmarking Study in a Retrospective Bicentric Cohort"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2788-9316","authenticated-orcid":false,"given":"Robert","family":"Stahl","sequence":"first","affiliation":[{"name":"Institute for Diagnostic and Interventional Neuroradiology, LMU University Hospital, LMU Munich, Marchioninistr. 15, 81377 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5236-4373","authenticated-orcid":false,"given":"Anna Theresa","family":"St\u00fcber","sequence":"additional","affiliation":[{"name":"Department of Radiology, LMU University Hospital, LMU Munich, Marchioninistr. 15, 81377 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Rebecca","family":"Wania","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics and Trauma Surgery, Klinikum Dritter Orden, Menzinger Str. 44, 80638 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0268-9078","authenticated-orcid":false,"given":"Michael","family":"Ingrisch","sequence":"additional","affiliation":[{"name":"Department of Radiology, LMU University Hospital, LMU Munich, Marchioninistr. 15, 81377 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"given":"Maryam","family":"Ostadi Ataabadi","sequence":"additional","affiliation":[{"name":"Department of Radiology, LMU University Hospital, LMU Munich, Marchioninistr. 15, 81377 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2214-3315","authenticated-orcid":false,"given":"Marco","family":"\u00d6chsner","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Neuroradiology, LMU University Hospital, LMU Munich, Marchioninistr. 15, 81377 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1054-1463","authenticated-orcid":false,"given":"Robert","family":"Forbrig","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Neuroradiology, LMU University Hospital, LMU Munich, Marchioninistr. 15, 81377 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1249-3338","authenticated-orcid":false,"given":"Christoph G.","family":"Trumm","sequence":"additional","affiliation":[{"name":"Radiologie Augsburg Friedberg \u00dcBAG, Hermanstra\u00dfe 15, 86150 Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Thomas","family":"Liebig","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Neuroradiology, LMU University Hospital, LMU Munich, Marchioninistr. 15, 81377 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0554-0201","authenticated-orcid":false,"given":"Wolfgang","family":"B\u00f6cker","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics and Trauma Surgery, Musculoskeletal University Center Munich (MUM), LMU University Hospital, LMU Munich, Marchioninistr. 15, 81377 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0542-5684","authenticated-orcid":false,"given":"Vera","family":"Pedersen","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics and Trauma Surgery, Musculoskeletal University Center Munich (MUM), LMU University Hospital, LMU Munich, Marchioninistr. 15, 81377 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"289","DOI":"10.5811\/westjem.2012.3.11559","article-title":"Emergency department visits for traumatic brain injury in older adults in the United States: 2006-08","volume":"13","author":"Pearson","year":"2012","journal-title":"West. J. Emerg. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"E20","DOI":"10.3171\/2020.7.FOCUS20520","article-title":"A population-based study of fall-related traumatic brain injury identified in older adults in hospital emergency departments","volume":"49","author":"Cusimano","year":"2020","journal-title":"Neurosurg. Focus."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"110902","DOI":"10.1016\/j.injury.2023.110902","article-title":"Increasing incidence of ED-visits and admissions due to traumatic brain injury among elderly patients in the Netherlands, 2011\u20132020","volume":"54","author":"Santing","year":"2023","journal-title":"Injury"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1111\/jgs.16400","article-title":"Prevalence and Severity of Traumatic Intracranial Hemorrhage in Older Adults with Low-Energy Falls","volume":"68","author":"Lampart","year":"2020","journal-title":"J. Am. Geriatr. Soc."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1111\/jgs.16338","article-title":"Clinical Predictors of Intracranial Bleeding in Older Adults Who Have Fallen: A Cohort Study","volume":"68","author":"Parpia","year":"2020","journal-title":"J. Am. Geriatr. Soc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1470","DOI":"10.1111\/j.1532-5415.2009.02344.x","article-title":"Prevalence and characteristics of traumatic intracranial hemorrhage in elderly fallers presenting to the emergency department without focal findings","volume":"57","author":"Gangavati","year":"2009","journal-title":"J. Am. Geriatr. Soc."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"953","DOI":"10.1111\/jgs.16399","article-title":"Intracranial Hemorrhage in Older Adults: Implications for Fall Risk Assessment and Prevention","volume":"68","author":"Shih","year":"2020","journal-title":"J. Am. Geriatr. Soc."},{"key":"ref_8","first-page":"483","article-title":"CT Overuse for Mild Traumatic Brain Injury","volume":"38","author":"Melnick","year":"2012","journal-title":"Jt. Comm. J. Qual. Patient Saf."},{"key":"ref_9","first-page":"e103861","article-title":"Rethinking Head Computed Tomography (CT) in the Emergency Department: From Reflex Imaging to Reasoned Care","volume":"18","author":"Sakamoto","year":"2026","journal-title":"Cureus"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1391","DOI":"10.1016\/S0140-6736(00)04561-X","article-title":"The Canadian CT Head Rule for patients with minor head injury","volume":"357","author":"Stiell","year":"2001","journal-title":"Lancet"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1056\/NEJM200007133430204","article-title":"Indications for Computed Tomography in Patients with Minor Head Injury","volume":"343","author":"Haydel","year":"2000","journal-title":"N. Engl. J. Med."},{"key":"ref_12","unstructured":"National Institute for Health and Care Excellence (2026, May 03). Head Injury: Assessment and Early Management. Available online: https:\/\/www.nice.org.uk\/guidance\/ng232."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1097\/TA.0b013e31820d090f","article-title":"Clinical decision rules for adults with minor head injury: A systematic review","volume":"71","author":"Harnan","year":"2011","journal-title":"J. Trauma Acute Care Surg."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"E1614","DOI":"10.1503\/cmaj.230634","article-title":"Derivation of the Falls Decision Rule to exclude intracranial bleeding without head CT in older adults who have fallen","volume":"195","author":"Mercuri","year":"2023","journal-title":"Can. Med. Assoc. J."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1007\/s43678-025-00937-y","article-title":"Validating the falls decision rule: Optimizing head CT use in older adults with ground-level falls","volume":"27","author":"Kudu","year":"2025","journal-title":"Can. J. Emerg. Med."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e2216393","DOI":"10.1001\/jamanetworkopen.2022.16393","article-title":"A Prehospital Triage System to Detect Traumatic Intracranial Hemorrhage Using Machine Learning Algorithms","volume":"5","author":"Abe","year":"2022","journal-title":"JAMA Netw. Open"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Hsu, S.D., Chao, E., Chen, S.J., Hueng, D.Y., Lan, H.Y., and Chiang, H.H. (2021). Machine Learning Algorithms to Predict In-Hospital Mortality in Patients with Traumatic Brain Injury. J. Pers. Med., 11.","DOI":"10.3390\/jpm11111144"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/s00068-023-02324-7","article-title":"Diagnostic value of protein S100b as predictor of traumatic intracranial haemorrhage in elderly adults with low-energy falls: Results from a retrospective observational study","volume":"50","author":"Wania","year":"2023","journal-title":"Eur. J. Trauma Emerg. Surg."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.neunet.2007.12.031","article-title":"Training neural network classifiers for medical decision making: The effects of imbalanced datasets on classification performance","volume":"21","author":"Mazurowski","year":"2008","journal-title":"Neural Netw."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"(2026). Show us the evidence for the value of medical AI. Nat. Med., 32, 1163.","DOI":"10.1038\/s41591-026-04389-4"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"von Elm, E., Altman, D.G., Egger, M., Pocock, S.J., G\u00f8tzsche, P.C., and Vandenbroucke, J.P. (2007). The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) Statement: Guidelines for Reporting Observational Studies. PLoS Med., 4.","DOI":"10.1371\/journal.pmed.0040296"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lampart, A., Arnold, I., Mader, N., Niedermeier, S., Escher, A., Stahl, R., Trumm, C., Kammerlander, C., Bocker, W., and Nickel, C. (2019). Prevalence of Fractures and Diagnostic Accuracy of Emergency X-ray in Older Adults Sustaining a Low-Energy Fall: A Retrospective Study. J. Clin. Med., 9.","DOI":"10.3390\/jcm9010097"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1903","DOI":"10.21105\/joss.01903","article-title":"mlr3: A modern object-oriented machine learning framework in R","volume":"4","author":"Lang","year":"2019","journal-title":"J. Open Source Softw."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_26","unstructured":"Breiman, L., Friedman, J.H., Olshen, R.A., and Stone, C.J. (1984). Classification and Regression Trees, CRC Press."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v033.i01","article-title":"Regularization paths for generalized linear models via coordinate descent","volume":"33","author":"Friedman","year":"2010","journal-title":"J. Stat. Softw."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Uddin, S., Khan, A., Hossain, M.E., and Moni, M.A. (2019). Comparing different supervised machine learning algorithms for disease prediction. BMC Med. Inf. Decis. Mak., 19.","DOI":"10.1186\/s12911-019-1004-8"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v077.i01","article-title":"ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R","volume":"77","author":"Wright","year":"2017","journal-title":"J. Stat. Softw."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and Variable Selection via the Elastic Net","volume":"67","author":"Zou","year":"2005","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"ref_34","first-page":"1","article-title":"Tunability: Importance of Hyperparameters of Machine Learning Algorithms","volume":"20","author":"Probst","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref_35","first-page":"5","article-title":"Head Injury in Older Adults: To Scan or Not to Scan? Ten Tips to Make the Best Decision","volume":"4","author":"Brousseau","year":"2023","journal-title":"J. Geriatr. Emerg. Med."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.annemergmed.2025.05.021","article-title":"Risk Factors for Traumatic Intracranial Hemorrhage in Older Adults Sustaining a Head Injury in Ground-Level Falls: A Systematic Review and Meta-analysis","volume":"87","author":"Dubucs","year":"2026","journal-title":"Ann. Emerg. Med."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"16","DOI":"10.21037\/jhmhp-23-97","article-title":"Web-based calculator using machine learning to predict intracranial hematoma in geriatric traumatic brain injury","volume":"7","author":"Tunthanathip","year":"2023","journal-title":"J. Hosp. Manag. Health Policy"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1276","DOI":"10.1002\/sim.7992","article-title":"Minimum sample size for developing a multivariable prediction model: PART II-binary and time-to-event outcomes","volume":"38","author":"Riley","year":"2019","journal-title":"Stat. Med."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Dhiman, P., Ma, J., Qi, C., Bullock, G., Sergeant, J.C., Riley, R.D., and Collins, G.S. (2023). Sample size requirements are not being considered in studies developing prediction models for binary outcomes: A systematic review. BMC Med. Res. Methodol., 23.","DOI":"10.1186\/s12874-023-02008-1"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1306","DOI":"10.1016\/j.injury.2023.02.023","article-title":"Validation of the cutaneous impact location to predict intracranial lesion among elderly admitted to the Emergency Department after a ground-level fall","volume":"54","author":"Dubucs","year":"2023","journal-title":"Injury"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1038\/s41746-022-00592-y","article-title":"Machine learning for medical imaging: Methodological failures and recommendations for the future","volume":"5","author":"Varoquaux","year":"2022","journal-title":"NPJ Digit. Med."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1038\/s42256-021-00307-0","article-title":"Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans","volume":"3","author":"Roberts","year":"2021","journal-title":"Nat. Mach. Intell."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/17\/2840\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T11:18:26Z","timestamp":1788434306000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/17\/2840"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,3]]},"references-count":42,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["diagnostics16172840"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16172840","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,3]]}}}