{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T15:03:22Z","timestamp":1785423802306,"version":"3.56.0"},"reference-count":45,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Science and Higher Education of the Republic of Kazakhstan","award":["AP26103523"],"award-info":[{"award-number":["AP26103523"]}]},{"award":["AP26103523"],"award-info":[{"award-number":["AP26103523"]}],"id":[{"id":"https:\/\/ror.org\/05tyne317","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background. Sleep fragmentation and frailty are interrelated yet underexplored determinants of adverse outcomes in critically ill patients, and no published model has combined objective nocturnal fragmentation metrics with administrative frailty indices to predict adverse outcomes at ICU admission. Methods. Using 31,139 first ICU admissions from the MIMIC-IV (v3.1) database, we developed and compared five supervised machine learning models to predict a composite outcome of 30-day mortality, prolonged mechanical ventilation (&gt;7 days), or discharge to a skilled nursing or rehabilitation facility (outcome prevalence 56.1%). Predictors were drawn exclusively from routinely available admission-time data, including nocturnal chartevent frequency, nighttime RASS scores, the Hospital Frailty Risk Score (HFRS), comorbidity and severity indices, and standard demographic variables. Results. The three gradient boosting models achieved statistically equivalent discrimination (ROC AUC \u2248 0.82\u20130.83) with strong calibration. SHAP analysis of the best-performing model (CatBoost) identified age, HFRS, nocturnal chartevent count, and nighttime RASS as the most influential predictors, confirming that frailty and sleep fragmentation contribute independently to risk. Conclusions. These findings show that EHR-derived frailty signals and nocturnal monitoring intensity, available without additional assessment burden, provide clinically actionable risk stratification at ICU admission and a viable foundation for embedded decision-support tools.<\/jats:p>","DOI":"10.3390\/jcm15145538","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:29:39Z","timestamp":1784100579000},"page":"5538","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting Adverse ICU Outcomes from Admission-Time Frailty and Nocturnal Sleep Fragmentation Using Explainable AI"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4089-6337","authenticated-orcid":false,"given":"Bibars","family":"Amangeldy","sequence":"first","affiliation":[{"name":"AlfaCenter (Al-Farabi AI Center), Farabi University, Almaty 050040, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7279-9910","authenticated-orcid":false,"given":"Assiya","family":"Boltaboyeva","sequence":"additional","affiliation":[{"name":"AlfaCenter (Al-Farabi AI Center), Farabi University, Almaty 050040, Kazakhstan"},{"name":"LLP \u201cKazakhstan R&D Solutions\u201d, Almaty 050056, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1919-3570","authenticated-orcid":false,"given":"Zhanel","family":"Baigarayeva","sequence":"additional","affiliation":[{"name":"AlfaCenter (Al-Farabi AI Center), Farabi University, Almaty 050040, Kazakhstan"},{"name":"LLP \u201cKazakhstan R&D Solutions\u201d, Almaty 050056, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baglan","family":"Imanbek","sequence":"additional","affiliation":[{"name":"AlfaCenter (Al-Farabi AI Center), Farabi University, Almaty 050040, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3039-6715","authenticated-orcid":false,"given":"Nurdaulet","family":"Tasmurzayev","sequence":"additional","affiliation":[{"name":"AlfaCenter (Al-Farabi AI Center), Farabi University, Almaty 050040, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shugyla","family":"Kurmanbek","sequence":"additional","affiliation":[{"name":"AlfaCenter (Al-Farabi AI Center), Farabi University, Almaty 050040, Kazakhstan"},{"name":"LLP \u201cKazakhstan R&D Solutions\u201d, Almaty 050056, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sultan","family":"Tuleukhanov","sequence":"additional","affiliation":[{"name":"Faculty of Biology and Biotechnology, Farabi University, Almaty 050040, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4792-5380","authenticated-orcid":false,"given":"Vyacheslav","family":"Lokshin","sequence":"additional","affiliation":[{"name":"LLP \u201cPERSONA International Clinical Center for Reproductology\u201d, Almaty 050060, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"ref_1","first-page":"103342","article-title":"Dynamic prevalence of sleep disturbance among critically ill patients in intensive care units and after hospitalisation: A systematic review and meta-analysis","volume":"76","author":"Shih","year":"2023","journal-title":"Intensive Crit. Care Nurs."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"151","DOI":"10.3390\/clockssleep1010014","article-title":"Sleep in hospitalized patients","volume":"1","author":"Morse","year":"2019","journal-title":"Clocks Sleep"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e70282","DOI":"10.1002\/brb3.70282","article-title":"Optimizing sleep disorder management in hospitalized patients: Practical approach for healthcare providers","volume":"15","author":"Roostaei","year":"2025","journal-title":"Brain Behav."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1016\/j.chest.2019.12.003","article-title":"Sleep and delirium in adults who are critically ill: A contemporary review","volume":"157","author":"Knauert","year":"2020","journal-title":"Chest"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1001\/jamainternmed.2018.2669","article-title":"Quality and quantity of sleep and factors associated with sleep disturbance in hospitalized patients","volume":"178","author":"Wesselius","year":"2018","journal-title":"JAMA Intern. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"8518396","DOI":"10.1155\/2020\/8518396","article-title":"Sleep quality of hospitalized patients, contributing factors, and prevalence of associated disorders","volume":"2020","author":"Kulpatcharapong","year":"2020","journal-title":"Sleep Disord."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"M146","DOI":"10.1093\/gerona\/56.3.M146","article-title":"Frailty in older adults: Evidence for a phenotype","volume":"56","author":"Fried","year":"2001","journal-title":"J. Gerontol. Ser. A"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1056\/NEJMra2301292","article-title":"Frailty in older adults","volume":"391","author":"Kim","year":"2024","journal-title":"N. Engl. J. Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1007\/s11325-020-02061-w","article-title":"Sleep and frailty risk: A systematic review and meta-analysis","volume":"24","author":"Pourmotabbed","year":"2020","journal-title":"Sleep Breath."},{"key":"ref_10","first-page":"219","article-title":"Sleep-disordered breathing in heart failure: Facts and numbers","volume":"4","author":"Borrelli","year":"2017","journal-title":"ESC Heart Fail."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1016\/S2215-0366(20)30136-X","article-title":"Sleep disturbance and psychiatric disorders","volume":"7","author":"Freeman","year":"2020","journal-title":"Lancet Psychiatry"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Asanau, A.-G., Zabara, M.-L., For\u021bu, C., Mitu, F., and Mihnea, B. (2025). Heart rate variability (HRV) in patients with sleep apnea and COPD: A comprehensive analysis. J. Clin. Med., 14.","DOI":"10.3390\/jcm14134630"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/s11892-023-01510-6","article-title":"Sleep apnea, obesity, and diabetes\u2014An intertwined trio","volume":"23","author":"Khan","year":"2023","journal-title":"Curr. Diabetes Rep."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e26","DOI":"10.1017\/S2045796021000810","article-title":"Sleep disturbance and psychiatric disorders: A bidirectional Mendelian randomisation study","volume":"31","author":"Sun","year":"2022","journal-title":"Epidemiol. Psychiatr. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.smrv.2018.10.006","article-title":"Insomnia as a predictor of mental disorders: A systematic review and meta-analysis","volume":"43","author":"Hertenstein","year":"2022","journal-title":"Sleep Med. Rev."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.1016\/S0140-6736(18)30668-8","article-title":"Development and validation of a Hospital Frailty Risk Score focusing on older people in acute care settings using electronic hospital records: An observational study","volume":"391","author":"Gilbert","year":"2018","journal-title":"Lancet"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e154","DOI":"10.1016\/S2666-7568(21)00004-0","article-title":"The use of linked routine data to optimise calculation of the Hospital Frailty Risk Score on the basis of previous hospital admissions: A retrospective observational cohort study","volume":"2","author":"Street","year":"2021","journal-title":"Lancet Healthy Longev."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1130","DOI":"10.1097\/01.mlr.0000182534.19832.83","article-title":"Coding algorithms for defining comorbidities in ICD-9-CM and ICD-10 administrative data","volume":"43","author":"Quan","year":"2005","journal-title":"Med. Care"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1097\/MLR.0000000000000735","article-title":"Identifying increased risk of readmission and in-hospital mortality using hospital administrative data: The AHRQ Elixhauser Comorbidity Index","volume":"55","author":"Moore","year":"2017","journal-title":"Med. Care"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"dos Santos, R.R., Marumo, M.B., Eckeli, A.L., Salgado, H.C., Silva, L.E.V., Tin\u00f3s, R., and Fazan, R. (2025). The use of heart rate variability, oxygen saturation, and anthropometric data with machine learning to predict the presence and severity of obstructive sleep apnea. Front. Cardiovasc. Med., 12.","DOI":"10.3389\/fcvm.2025.1389402"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Liu, K., Geng, S., Shen, P., Zhao, L., Zhou, P., and Liu, W. (2024). Development and application of a machine learning-based predictive model for obstructive sleep apnea screening. Front. Big Data, 7.","DOI":"10.3389\/fdata.2024.1353469"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"202264","DOI":"10.1098\/rsos.202264","article-title":"A machine learning model for multi-night actigraphic detection of chronic insomnia: Development and validation of a pre-screening tool","volume":"8","author":"Kusmakar","year":"2021","journal-title":"R. Soc. Open Sci."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Shi, Y., Zhang, Y., Cao, Z., Ma, L., Yaun, Y., Niu, X., Su, Y., Xie, Y., Chen, X., and Xing, L. (2023). Application and interpretation of machine learning models in predicting the risk of severe obstructive sleep apnea in adults. BMC Med. Inform. Decis. Mak., 23.","DOI":"10.1186\/s12911-023-02331-z"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1007\/s44196-023-00362-y","article-title":"Predictive power of XGBoost-BiLSTM model: A machine-learning approach for accurate sleep apnea detection using electronic health data","volume":"16","author":"Ahmadi","year":"2023","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e46520","DOI":"10.2196\/46520","article-title":"Predicting the risk of sleep disorders using a machine learning-based simple questionnaire: Development and validation study","volume":"25","author":"Han","year":"2023","journal-title":"J. Med. Internet Res."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Holler, E., Chekani, F., Ai, J., Meng, W., Khandker, R.K., Ben Miled, Z., Owora, A., Dexter, P., Campbell, N., and Solid, C. (2023). Development and Temporal Validation of an Electronic Medical Record-Based Insomnia Prediction Model Using Data from a Statewide Health Information Exchange. J. Clin. Med., 12.","DOI":"10.3390\/jcm12093286"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e14354","DOI":"10.1111\/jdi.14354","article-title":"Association between obstructive sleep apnea syndrome and type 1\/type 2 diabetes mellitus: A systematic review and meta-analysis","volume":"16","author":"Huang","year":"2025","journal-title":"J. Diabetes Investig."},{"key":"ref_28","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 (KDD \u201916), San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Jobanputra, A.M., Scharf, M.T., Androulakis, I.P., and Sunderram, J. (2020). Circadian Disruption in Critical Illness. Front. Neurol., 11.","DOI":"10.3389\/fneur.2020.00820"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"102","DOI":"10.4037\/ajcc2004.13.2.102","article-title":"Nocturnal Care Interactions with Patients in Critical Care Units","volume":"13","author":"Tamburri","year":"2004","journal-title":"Am. J. Crit. Care"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e13223","DOI":"10.1111\/jsr.13223","article-title":"Sleep-Disrupting Effects of Nocturnal Nursing Interventions in Intensive Care Unit Patients: A Systematic Review","volume":"30","author":"Axmann","year":"2021","journal-title":"J. Sleep Res."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1016\/j.jss.2012.05.038","article-title":"Sleep Disruptions and Nocturnal Nursing Interactions in the Intensive Care Unit","volume":"177","author":"Le","year":"2012","journal-title":"J. Surg. Res."},{"key":"ref_33","first-page":"e90465","article-title":"The prognostic performance of artificial intelligence and machine learning models for mortality prediction in intensive care units: A systematic review","volume":"17","author":"Dhami","year":"2025","journal-title":"Cureus"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1038\/s43856-025-01192-z","article-title":"An interpretable machine learning algorithm enables dynamic 48-hour mortality prediction during an ICU stay","volume":"5","author":"Britsch","year":"2025","journal-title":"Commun. Med."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"E607","DOI":"10.9778\/cmajo.20220094","article-title":"Using the Hospital Frailty Risk Score to assess mortality risk in older medical patients admitted to the intensive care unit","volume":"11","author":"Detsky","year":"2023","journal-title":"CMAJ Open"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"14621","DOI":"10.1038\/s41598-022-18970-7","article-title":"External validation of the Hospital Frailty Risk Score among older adults receiving mechanical ventilation","volume":"12","author":"Sy","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Li, X., Cheng, H., Tang, Y., Tan, S., Bai, Z., Li, T., Luo, M., Wang, Y., and Jun, L. (2024). The Hospital Frailty Risk Score effectively predicts adverse outcomes in patients with atrial fibrillation in the intensive care unit. Res. Sq.","DOI":"10.21203\/rs.3.rs-4368526\/v1"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"e70241","DOI":"10.1111\/nicc.70241","article-title":"Sleep quality, circadian rhythm stability and changes in delirium state in predicting mortality risk in intensive care unit patients: A prospective observational study","volume":"30","author":"Lai","year":"2025","journal-title":"Nurs. Crit. Care"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"752","DOI":"10.1186\/s40001-025-03017-0","article-title":"Survey of perceived sleep quality and nursing implications in 172 adult ICU patients","volume":"30","author":"Gao","year":"2025","journal-title":"Eur. J. Med. Res."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1186\/s13054-019-2394-9","article-title":"Sedation practices and clinical outcomes in mechanically ventilated patients in a prospective multicenter cohort","volume":"23","author":"Mongilardi","year":"2019","journal-title":"Crit. Care"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Liao, S.-F., Huang, C.-J., Lee, R.-P., Chen, T.-Y., and Wang, H.-C. (2026). Sedation level variability as an indicator for mortality in mechanically ventilated critically ill patients: A propensity score-weighted cohort study. Front. Med., 13.","DOI":"10.3389\/fmed.2026.1755288"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"k1479","DOI":"10.1136\/bmj.k1479","article-title":"Biases in electronic health record data due to processes within the healthcare system: Retrospective observational study","volume":"361","author":"Agniel","year":"2018","journal-title":"BMJ"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/s41512-020-00077-0","article-title":"Informative missingness in electronic health record systems: The curse of knowing","volume":"4","author":"Groenwold","year":"2020","journal-title":"Diagn. Progn. Res."},{"key":"ref_44","unstructured":"Azam, M.B., and Singh, S.I. (2025). When validation fails: Cross-institutional blood pressure prediction and the limits of electronic health record-based models. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"e73840","DOI":"10.2196\/73840","article-title":"Prediction of moderate-to-severe sepsis-associated acute kidney injury using a dual-timepoint machine learning model: Development, multiregional validation, and clinical deployment study","volume":"27","author":"Ge","year":"2025","journal-title":"J. Med. Internet Res."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/14\/5538\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:41:10Z","timestamp":1784101270000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/14\/5538"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":45,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["jcm15145538"],"URL":"https:\/\/doi.org\/10.3390\/jcm15145538","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]}}}