{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T07:42:16Z","timestamp":1777448536022,"version":"3.51.4"},"reference-count":18,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T00:00:00Z","timestamp":1751500800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"Ruth L. Kirschstein Institutional National Research Service Award of the National Institutes of Health","award":["T32GM144274"],"award-info":[{"award-number":["T32GM144274"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The American Surgeon\u2122"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Traumatic rib fractures can lead to respiratory complications necessitating unplanned intubation, but predictors have been inadequately delineated. We used interpretable machine learning to predict unplanned intubations in rib fracture patients while identifying predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>TQIP 2017-2022 was queried for adult patients admitted to the hospital following a rib fracture injury. An XGBoost model was developed to predict unplanned intubation using variables that can be known on admission. A 70\/10\/20 train\/validation\/test split was used. SHapley Additive exPlanations (SHAP) were used for interpretation. SHAP allows individualized interpretation of predictors for each patient.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The cohort had 905\u00a0615 patients; 2.3% had unplanned intubations. Model metrics at the F1 maximizing threshold (0.78) included AUROC = 0.83, F1 score = 0.17, accuracy = 0.94, precision = 0.12, recall = 0.29, specificity = 0.95, and Brier score = 0.17. The most influential variables, as determined by mean absolute SHAP values, were admission location (0.62), Injury Severity Score (0.40), age (0.37), absence of comorbidities (0.18), pulse rate (0.14), pneumothorax (0.13), oxygen saturation (0.15), chronic obstructive pulmonary disease (0.11), respiratory rate (0.10), and sex (0.10). ICU admission was the location most influential in predicting an unplanned intubation. SHAP dependency plots determined the directional relationship between variables\u2019 values and SHAP values.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Patients above the F1 maximizing threshold had a 7.4-fold increase in unplanned intubations compared to those below. Nearly 30% of all unplanned intubations were captured at this threshold. Our model\u2019s identification of these high-risk patients and influential factors not previously considered in the literature could guide closer monitoring and early interventions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/00031348251358446","type":"journal-article","created":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T14:02:33Z","timestamp":1751551353000},"page":"186-192","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting Unplanned Intubations in Rib Fracture Patients: An Interpretable Machine Learning Approach"],"prefix":"10.1177","volume":"92","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5881-8251","authenticated-orcid":false,"given":"Shamir C.","family":"Harry","sequence":"first","affiliation":[{"name":"University of South Florida"},{"name":"Morsani College of Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9671-1484","authenticated-orcid":false,"given":"Melissa A.","family":"Kendall","sequence":"additional","affiliation":[{"name":"University of South Florida"},{"name":"Morsani College of Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4467-3405","authenticated-orcid":false,"given":"Emily A.","family":"Grimsley","sequence":"additional","affiliation":[{"name":"University of South Florida"},{"name":"Morsani College of Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rachel L.","family":"Wolansky","sequence":"additional","affiliation":[{"name":"University of South Florida"},{"name":"Morsani College of Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johnathan V.","family":"Torikashvili","sequence":"additional","affiliation":[{"name":"University of South Florida"},{"name":"Morsani College of Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Boughanem","sequence":"additional","affiliation":[{"name":"University of South Florida"},{"name":"Morsani College of Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Liang","sequence":"additional","affiliation":[{"name":"University of South Florida"},{"name":"Morsani College of Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajavi","family":"Parikh","sequence":"additional","affiliation":[{"name":"University of South Florida"},{"name":"Morsani College of Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph","family":"Sujka","sequence":"additional","affiliation":[{"name":"University of South Florida"},{"name":"Morsani College of Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2610-4233","authenticated-orcid":false,"given":"Paul C.","family":"Kuo","sequence":"additional","affiliation":[{"name":"University of South Florida"},{"name":"Morsani College of Medicine"},{"name":"Bay Pines Veterans Affairs Health Care System"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tyler","family":"Zander","sequence":"additional","affiliation":[{"name":"University of South Florida"},{"name":"Morsani College of Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,7,3]]},"reference":[{"key":"e_1_3_5_2_2","doi-asserted-by":"publisher","DOI":"10.1097\/01.TA.0000037095.83469.4C"},{"key":"e_1_3_5_3_2","first-page":"73","article-title":"Fatality risk and the presence of rib fractures","volume":"52","author":"Kent R","year":"2008","unstructured":"Kent R, Woods W, Bostrom O. Fatality risk and the presence of rib fractures. Ann Adv Automot Med. 2008;52:73-82.","journal-title":"Ann Adv Automot Med"},{"key":"e_1_3_5_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjsurg.2006.08.048"},{"key":"e_1_3_5_5_2","doi-asserted-by":"publisher","DOI":"10.1097\/00000542-199502000-00007"},{"key":"e_1_3_5_6_2","doi-asserted-by":"publisher","DOI":"10.1213\/ANE.0b013e318257012b"},{"key":"e_1_3_5_7_2","doi-asserted-by":"publisher","DOI":"10.1177\/21925682211053593"},{"key":"e_1_3_5_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinane.2023.111194"},{"key":"e_1_3_5_9_2","doi-asserted-by":"publisher","DOI":"10.1097\/SHK.0000000000002490"},{"key":"e_1_3_5_10_2","doi-asserted-by":"crossref","unstructured":"Chen T Guestrin C. XGBoost: a scalable tree boosting system. In: Presented At: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco CA August 13-17 2016. Accessed November 19 2024.","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_5_11_2","first-page":"507","article-title":"Why do tree-based models still outperform deep learning on typical tabular data?","volume":"35","author":"Grinsztajn L","year":"2022","unstructured":"Grinsztajn L, Oyallon E, Varoquaux G. Why do tree-based models still outperform deep learning on typical tabular data? Adv Neural Inf Process Syst. 2022;35:507-520.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_5_12_2","unstructured":"Watson DS O\u2019Hara J Tax N Mudd R Guy I. Explaining predictive uncertainty with information-theoretic shapley values. arXiv. 2023. https:\/\/arxiv.org\/abs\/2306.05724. Accessed January 25 2025."},{"key":"e_1_3_5_13_2","unstructured":"Harry S. RibFx_UI_XGBoost. https:\/\/github.com\/sharry2356\/RibFx_UI_XGBoost. Accessed January 25 2025."},{"key":"e_1_3_5_14_2","doi-asserted-by":"publisher","DOI":"10.1177\/000313480907500916"},{"key":"e_1_3_5_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.surg.2013.05.006"},{"key":"e_1_3_5_16_2","doi-asserted-by":"publisher","DOI":"10.1097\/ALN.0b013e31821cf6de"},{"key":"e_1_3_5_17_2","doi-asserted-by":"publisher","DOI":"10.1097\/TA.0000000000000086"},{"key":"e_1_3_5_18_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-021-01302-4"},{"key":"e_1_3_5_19_2","doi-asserted-by":"publisher","DOI":"10.1097\/TA.0000000000000788"}],"container-title":["The American Surgeon\u2122"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/00031348251358446","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/00031348251358446","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/00031348251358446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T12:38:11Z","timestamp":1777379891000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/00031348251358446"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,3]]},"references-count":18,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1177\/00031348251358446"],"URL":"https:\/\/doi.org\/10.1177\/00031348251358446","relation":{},"ISSN":["0003-1348","1555-9823"],"issn-type":[{"value":"0003-1348","type":"print"},{"value":"1555-9823","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,3]]}}}