AbstractA significant number of intensive care unit (ICU) survivors experience new-onset functional impairments that impede their activities of daily living (ADL). Currently, no effective assessment tools are available to identify these high-risk patients. This study aims to develop an interpretable machine learning (ML) model for predicting the onset of functional impairment in critically ill patients.

摘要大量重症监护病房（ICU）幸存者经历了新发的功能障碍，阻碍了他们的日常生活活动（ADL）。目前，没有有效的评估工具来识别这些高危患者。这项研究旨在开发一种可解释的机器学习（ML）模型，用于预测危重患者功能障碍的发作。

Data for this study were sourced from a comprehensive hospital in China, focusing on adult patients admitted to the ICU from August 2022 to August 2023 without prior functional impairments. A least absolute shrinkage and selection operator (LASSO) model was utilized to select predictors for inclusion in the model.

这项研究的数据来自中国的一家综合医院，重点是2022年8月至2023年8月入住ICU的成年患者，之前没有功能障碍。使用最小绝对收缩和选择算子（LASSO）模型来选择要包含在模型中的预测变量。

Four models, logistic regression, support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost), were constructed and validated. Model performance was assessed using the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV).

构建并验证了四个模型，逻辑回归，支持向量机（SVM），随机森林（RF）和极端梯度提升（XGBoost）。使用曲线下面积（AUC），准确性，敏感性，特异性，阳性预测值（PPV）和阴性预测值（NPV）评估模型性能。

Additionally, the DALEX package was employed to enhance the interpretability of the final models. The study ultimately included 1,380 patients, with 684 (49.6%) exhibiting new-onset functional impairment on the seventh day after leaving the ICU. Among the four models evaluated, the SVM model demonstrated the best performance, with an AUC of 0.909, accuracy of 0.838, sensitivity of 0.902, specificity of 0.772, PPV of 0.802, and NPV of 0.886.

此外，DALEX软件包被用来提高最终模型的可解释性。该研究最终包括1380名患者，其中684名（49.6%）在离开ICU后第七天表现出新发功能障碍。在评估的四个模型中，SVM模型表现出最佳的性能，AUC为0.909，准确度为0.838，灵敏度为0.902，特异性为0.772，PPV为0.802，NPV为0.886。

ML models are reliable tools for predicting new-onset functional impairments in critically ill patients. Notably, the SVM model emerged as the most effective, enabling early identification of patients at high risk and facilitating the implementation of timely interventions to improve ADL..

ML模型是预测重症患者新发功能障碍的可靠工具。值得注意的是，SVM模型成为最有效的模型，能够早期识别高风险患者，并有助于及时实施干预措施以改善ADL。。

IntroductionWith advances in critical care medicine, the mortality rate among critically ill patients continues to decline, allowing more individuals to be successfully discharged from the intensive care unit (ICU)1. However, a subset of patients experiences new-onset functional impairment post-discharge, which impacts their daily living activities2,3,4.

引言随着重症监护医学的进步，危重病人的死亡率继续下降，使更多的人成功地从重症监护病房（ICU）出院1。然而，一部分患者在出院后出现新发功能障碍，这影响了他们的日常生活活动2,3,4。

Prior research indicates that functional impairment affects 32–59.3% of critically ill patients within 6 months of discharge5,6,7,8, with 22–40% continuing to experience impairment beyond 6 months7,8,9,10. Despite potential improvements in functional status over time, the prevalence of functional impairment among critically ill patients warrants attention.

先前的研究表明，功能障碍会在出院后6个月内影响32-59.3%的危重患者5,6,7,8，其中22-40%的患者在6个月后继续受到损害7,8,9,10。尽管随着时间的推移功能状态可能会有所改善，但危重患者功能障碍的患病率值得关注。

Patients who survive the ICU with functional impairments necessitate ongoing medical and nursing care, diminishing their quality of life and increasing the burden on caregivers and society11,12,13. Numerous studies have linked the onset of functional impairment in critically ill patients to various risk factors, including disease severity, age, mechanical ventilation (MV) use, delirium, fractures, and strokes14,15,16.

患有功能障碍的ICU患者需要持续的医疗和护理，降低他们的生活质量，增加护理人员和社会的负担11,12,13。许多研究已经将危重患者功能障碍的发生与各种危险因素联系起来，包括疾病严重程度，年龄，机械通气（MV）使用，deli妄，骨折和中风14,15,16。

Utilizing these risk factors, four prognostic studies have been undertaken to predict patients at elevated risk for developing functional impairments post-discharge6,7,17,18, and thus implementing active early interventions such as neuromuscular electrical stimulation therapies, hormonal therapies, and early mobilization during the ICU stay14,19.Machine learning (ML) offers sophisticated computational and data mining capabilities for identifying associations among variables within complex, high-dimensional datasets.

利用这些风险因素，已经进行了四项预后研究，以预测出院后发生功能障碍风险升高的患者6,7,17,18，从而实施积极的早期干预措施，如神经肌肉电刺激疗法，激素疗法和早期动员在ICU住院期间14,19。机器学习（ML）提供了复杂的计算和数据挖掘能力，用于识别复杂高维数据集中变量之间的关联。

In recent years, ML models have been widely used in medical research and have shown excellent performance20,21,22. Yet, many existing ML mod.

近年来，ML模型已广泛用于医学研究，并显示出优异的性能20,21,22。然而，许多现有的ML mod。

Data availability

数据可用性

The Supplementary file 1 provides the missing data proportions and hyperparameter tuning methods (including codes) for the predictors. Supplementary file 2 and Supplementary file 3 provide the development dataset and the temporal validation dataset. All Supplementary file have been uploaded in the Supplementary Material..

补充文件1为预测器提供了缺失的数据比例和超参数调整方法（包括代码）。补充文件2和补充文件3提供了开发数据集和时间验证数据集。所有补充文件均已上传到补充材料中。。

ReferencesNeedham, D. M. et al. Improving long-term outcomes after discharge from intensive care unit: Report from a stakeholders’ conference. Crit. Care Med. 40, 502–509 (2012).Article

参考文献Needham，D.M。等人。改善重症监护病房出院后的长期结果：利益相关者会议的报告。暴击。《护理医学》40502-509（2012）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Bakhru, R. N. et al. Physical function impairment in survivors of critical illness in an ICU Recovery Clinic. J. Crit. Care 45, 163–169 (2018).Article

Bakhru，R.N.等人。ICU康复诊所危重病幸存者的身体机能受损。J、 临界护理45163-169（2018）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Ingraham, N. E. et al. National trends and variation of functional status deterioration in the medically critically ill. Crit. Care Med. 48, 1556–1564 (2020).Article

Ingraham，N.E.等人，《医学重症患者功能状态恶化的国家趋势和变化》，《临床护理医学》481556-1564（2020）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Ohbe, H., Matsui, H., Fushimi, K. & Yasunaga, H. Epidemiology of chronic critical illness in Japan: A nationwide inpatient database study. Crit. Care Med. 49, 70–78 (2021).Article

Ohbe，H.，Matsui，H.，Fushimi，K。＆Yasunaga，H。日本慢性危重病流行病学：全国住院患者数据库研究。暴击。护理医学49,70-78（2021）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Iwashyna, T. J., Ely, E. W., Smith, D. M. & Langa, K. M. Long-term cognitive impairment and functional disability among survivors of severe sepsis. JAMA 304, 1787–1794 (2010).Article

Iwashyna，T.J.，Ely，E.W.，Smith，D.M。＆Langa，K.M。严重脓毒症幸存者的长期认知障碍和功能障碍。JAMA 3041787–1794（2010）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Ohbe, H., Goto, T., Nakamura, K., Matsui, H. & Yasunaga, H. Development and validation of early prediction models for new-onset functional impairment at hospital discharge of ICU admission. Intensive Care Med. 48, 679–689 (2022).Article

Ohbe，H.，Goto，T.，Nakamura，K.，Matsui，H。＆Yasunaga，H。ICU入院出院时新发功能障碍早期预测模型的开发和验证。重症监护医学48679-689（2022）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Schandl, A., Bottai, M., Holdar, U., Hellgren, E. & Sackey, P. Early prediction of new-onset physical disability after intensive care unit stay: A preliminary instrument. Crit. Care 18, 455 (2014).Article

Schandl，A.，Bottai，M.，Holdar，U.，Hellgren，E。＆Sackey，P。重症监护病房住院后新发身体残疾的早期预测：初步工具。暴击。Care 18455（2014）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Shima, N. et al. Activities of daily living status and psychiatric symptoms after discharge from an intensive care unit: A single-center 12-month longitudinal prospective study. Acute Med. Surg. 7, e557 (2020).Article

Shima，N.等人，《重症监护病房出院后日常生活状况和精神症状的活动：单中心12个月纵向前瞻性研究》。急性医学外科杂志7，e557（2020）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Hodgson, C. L. et al. The impact of disability in survivors of critical illness. Intensive Care Med. 43, 992–1001 (2017).Article

霍奇森，C.L。等人，《残疾对危重病幸存者的影响》。重症监护医学43992-1001（2017）。文章

PubMed

PubMed

Google Scholar

谷歌学者

García Lizana, F., Peres Bota, D., De Cubber, M. & Vincent, J.-L. Long-term outcome in ICU patients: What about quality of life?. Intensive Care Med. 29, 1286–1293 (2003).Article

García Lizana，F.，Peres Bota，D.，De Cubber，M.＆Vincent，J.-L。ICU患者的长期预后：生活质量如何？。重症监护医学291286-1293（2003）。文章

PubMed

PubMed

Google Scholar

谷歌学者

da Silveira, L. T. Y., da Silva, J. M., Tanaka, C. & Fu, C. Decline in functional status after intensive care unit discharge is associated with ICU readmission: A prospective cohort study. Physiotherapy 105, 321–327 (2019).Article

da Silveira，L.T.Y.，da Silva，J.M.，Tanaka，C。＆Fu，C。重症监护病房出院后功能状态的下降与ICU再入院有关：一项前瞻性队列研究。物理治疗105321-327（2019）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Mankowski, R. T. et al. Older sepsis survivors suffer persistent disability burden and poor long-term survival. J. Am. Geriatr. Soc. 68, 1962–1969 (2020).Article

Mankowski，R.T。等人。老年脓毒症幸存者遭受持续的残疾负担和较差的长期生存。J、 我是老年人。Soc.681962-1969（2020）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Zeng, Y., Feng, Q., Hesketh, T., Christensen, K. & Vaupel, J. W. Survival, disabilities in activities of daily living, and physical and cognitive functioning among the oldest-old in China: A cohort study. Lancet Lond. Engl. 389, 1619–1629 (2017).Article

Zeng，Y.，Feng，Q.，Hesketh，T.，Christensen，K.＆Vaupel，J.W。中国老年人的生存，日常生活活动障碍以及身体和认知功能：一项队列研究。柳叶刀Lond。英语。3891619-1629（2017）。文章

Google Scholar

谷歌学者

Boelens, Y. F. N., Melchers, M. & van Zanten, A. R. H. Poor physical recovery after critical illness: Incidence, features, risk factors, pathophysiology, and evidence-based therapies. Curr. Opin. Crit. Care 28, 409–416 (2022).Article

Boelens，Y.F.N.，Melchers，M。＆van Zanten，A.R.H。危重病后身体恢复不佳：发病率，特征，危险因素，病理生理学和循证治疗。货币。奥平。暴击。护理28409-416（2022）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Lee, M., Kang, J. & Jeong, Y. J. Risk factors for post-intensive care syndrome: A systematic review and meta-analysis. Aust. Crit. Care Off. J. Confed. Aust. Crit. Care Nurses 33, 287–294 (2020).

Lee，M.，Kang，J。＆Jeong，Y.J。重症监护后综合征的危险因素：系统评价和荟萃分析。奥斯特。暴击。保重。J。坦言。奥斯特。暴击。护理护士33287-294（2020）。

Google Scholar

谷歌学者

Ramnarain, D. et al. Post Intensive Care Syndrome (PICS): An overview of the definition, etiology, risk factors, and possible counseling and treatment strategies. Expert Rev. Neurother. 21, 1159–1177 (2021).Article

Ramnarain，D。等。重症监护后综合征（PICS）：定义，病因，危险因素以及可能的咨询和治疗策略的概述。专家Rev.Neurother。211159-1177（2021）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Detsky, M. E. et al. Six-month morbidity and mortality among intensive care unit patients receiving life-sustaining therapy. A prospective cohort study. Ann. Am. Thorac. Soc. 14, 1562–1570 (2017).Article

Detsky，M.E.等人。接受维持生命治疗的重症监护病房患者的六个月发病率和死亡率。一项前瞻性队列研究。安。上午。胸部。Soc.141562-1570（2017）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Ferrante, L. E. et al. Development and validation of a prediction model for persistent functional impairment among older ICU survivors. https://doi.org/10.1111/jgs.18075.Apostolakis, E., Papakonstantinou, N. A., Baikoussis, N. G. & Papadopoulos, G. Intensive care unit-related generalized neuromuscular weakness due to critical illness polyneuropathy/myopathy in critically ill patients.

Ferrante，L.E.等人。老年ICU幸存者持续性功能障碍预测模型的开发和验证。https://doi.org/10.1111/jgs.18075.Apostolakis，E.，Papakonstantinou，N.A.，Baikoussis，N.G。和Papadopoulos，G。重症监护病房相关的全身性神经肌肉无力，由于危重病患者的危重病多发性神经病/肌病。

J. Anesth. 29, 112–121 (2015).Article .

J、 麻醉。29112-121（2015）。文章。

PubMed

PubMed

Google Scholar

谷歌学者

Handelman, G. S. et al. eDoctor: Machine learning and the future of medicine. J. Intern. Med. 284, 603–619 (2018).Article

Handelman，G.S.等人，《Edotor：机器学习与医学的未来》。J、 实习生。医学284603-619（2018）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Zhang, Z., Ho, K. M. & Hong, Y. Machine learning for the prediction of volume responsiveness in patients with oliguric acute kidney injury in critical care. Crit. Care Lond. Engl. 23, 112 (2019).Article

Zhang，Z.，Ho，K.M。＆Hong，Y。机器学习用于预测重症监护中少尿性急性肾损伤患者的容量反应性。暴击。关心Lond。英语。23112（2019）。文章

ADS

广告

Google Scholar

谷歌学者

Dong, J. et al. Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care. Crit. Care Lond. Engl. 25, 288 (2021).Article

Dong，J。等人。用于早期预测儿科重症监护中急性肾损伤（AKI）的机器学习模型。暴击。关心Lond。英语。25288（2021）。文章

Google Scholar

谷歌学者

Watson, D. S. et al. Clinical applications of machine learning algorithms: Beyond the black box. BMJ 364, l886 (2019).Article

Watson，D.S.等人，《机器学习算法的临床应用：超越黑匣子》。BMJ 364，l886（2019）。文章

PubMed

PubMed

Google Scholar

谷歌学者

The Lancet Respiratory Medicine, null. Opening the black box of machine learning. Lancet Respir. Med. 6, 801 (2018).Biecek, P. DALEX: Explainers for complex predictive models in R. J. Mach. Learn. Res. 19, 1–5 (2018).

柳叶刀呼吸医学，无效。打开机器学习的黑匣子。柳叶刀呼吸。医学杂志6801（2018）。Biecek，P.DALEX：R.J.Mach中复杂预测模型的解释者。学习。第19、1-5号决议（2018年）。

Google Scholar

谷歌学者

Guan, C., Ma, F., Chang, S. & Zhang, J. Interpretable machine learning models for predicting venous thromboembolism in the intensive care unit: An analysis based on data from 207 centers. Crit. Care 27, 406 (2023).Article

Guan，C.，Ma，F.，Chang，S。＆Zhang，J。用于预测重症监护病房静脉血栓栓塞的可解释机器学习模型：基于207个中心数据的分析。暴击。护理27406（2023）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Collins, G. S., Reitsma, J. B., Altman, D. G. & Moons, K. G. M. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD statement. BMJ 350, g7594 (2015).Article

Collins，G.S.，Reitsma，J.B.，Altman，D.G。＆Moons，K.G.M。透明报告个体预后或诊断的多变量预测模型（TRIPOD）：TRIPOD声明。BMJ 350，g7594（2015）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Inoue, S. et al. Post-intensive care syndrome: Its pathophysiology, prevention, and future directions. Acute Med. Surg. 6, 233–246 (2019).Article

Inoue，S.等人，《重症监护后综合征：病理生理学、预防和未来方向》。急性医学外科6233-246（2019）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Matsumoto, T. et al. Predictors of activities of daily living in intensive care unit survivors: A propensity score matching analysis. Prog. Rehabil. Med. 8, 20230010 (2023).Article

Matsumoto，T.等人。重症监护病房幸存者日常生活活动的预测因素：倾向评分匹配分析。程序。康复医学820230010（2023）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Knaus, W. A., Draper, E. A., Wagner, D. P. & Zimmerman, J. E. APACHE II: A severity of disease classification system. Crit. Care Med. 13, 818–829 (1985).Article

Knaus，W.A.，Draper，E.A.，Wagner，D.P。＆Zimmerman，J.E.APACHE II：疾病分类系统的严重程度。暴击。《护理医学》13818-829（1985）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Rahmatinejad, Z. et al. Internal validation of the predictive performance of models based on three ED and ICU scoring systems to predict inhospital mortality for intensive care patients referred from the Emergency Department. BioMed Res. Int. 2022, e3964063 (2022).Article

Rahmatinejad，Z.等人。基于三种ED和ICU评分系统的模型预测性能的内部验证，用于预测急诊科重症监护患者的住院死亡率。BioMed Res.Int.2022，e3964063（2022）。文章

Google Scholar

谷歌学者

Rahmatinejad, Z. et al. Prognostic utilization of models based on the APACHE II, APACHE IV, and SAPS II scores for predicting in-hospital mortality in emergency department. Am. J. Emerg. Med. 38, 1841–1846 (2020).Article

Rahmatinejad，Z.等人。基于APACHE II，APACHE IV和SAPS II评分的模型的预后利用，用于预测急诊科住院死亡率。《美国急诊医学杂志》381841-1846（2020）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Mahoney, F. I. & Barthel, D. W. Functional evaluation: The Barthel Index. Md. State Med. J. 14, 61–65 (1965).CAS

Mahoney，F.I。和Barthel，D.W。功能评估：Barthel指数。《州立医学杂志》14，61-65（1965）。中科院

PubMed

PubMed

Google Scholar

谷歌学者

Guyatt, G. H., Deyo, R. A., Charlson, M., Levine, M. N. & Mitchell, A. Responsiveness and validity in health status measurement: A clarification. J. Clin. Epidemiol. 42, 403–408 (1989).Article

Guyatt，G.H.，Deyo，R.A.，Charlson，M.，Levine，M.N。和Mitchell，A。健康状况测量的反应性和有效性：澄清。J、 临床。流行病。42403-408（1989）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Uyttenboogaart, M., Stewart, R. E., Vroomen, P. C. A. J., De Keyser, J. & Luijckx, G.-J. Optimizing cutoff scores for the Barthel Index and the modified rankin scale for defining outcome in acute stroke trials. Stroke 36, 1984–1987 (2005).Article

Uyttenboogaart，M.，Stewart，R.E.，Vroomen，P.C.A.J.，De Keyser，J.＆Luijckx，G.-J.优化Barthel指数和改良rankin量表的临界分数，以确定急性卒中试验的结果。中风361984-1987（2005）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Austin, P. C. et al. Geographic and temporal validity of prediction models: Different approaches were useful to examine model performance. J. Clin. Epidemiol. 79, 76–85 (2016).Article

Austin，P.C.等人，《预测模型的地理和时间有效性：不同的方法可用于检验模型性能。J、 临床。流行病。79,76-85（2016）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Segers, J. et al. Early neuromuscular electrical stimulation reduces the loss of muscle mass in critically ill patient—A within subject randomized controlled trial. J. Crit. Care 62, 65–71 (2021).Article

Segers，J.等人。早期神经肌肉电刺激减少危重患者肌肉质量的损失-受试者内随机对照试验。J、 临界护理62,65-71（2021）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Tipping, C. J. et al. The effects of active mobilisation and rehabilitation in ICU on mortality and function: A systematic review. Intensive Care Med. 43, 171–183 (2017).Article

Tipping，C.J.等人，《ICU积极动员和康复对死亡率和功能的影响：系统评价》。重症监护医学43171-183（2017）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Gandotra, S., Files, D. C., Shields, K. L., Berry, M. & Bakhru, R. N. Activity levels in survivors of the intensive care unit. Phys. Ther. 101, pzab135 (2021).Article

Gandotra，S.，Files，D.C.，Shields，K.L.，Berry，M。和Bakhru，R.N。重症监护病房幸存者的活动水平。物理。他们。101，pzab135（2021）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Tibshirani, R. Regression shrinkage and selection via the Lasso. J. R. Stat. Soc. Ser. B Methodol. 58, 267–288 (1996).Article

Tibshirani，R。通过套索回归收缩和选择。J、 R.统计社会服务。B方法。58267-288（1996）。文章

MathSciNet

MathSciNet

Google Scholar

谷歌学者

Li, S. Stroke recovery is a journey: Prediction and potentials of motor recovery after a stroke from a practical perspective. Life Basel Switz. 13, 2061 (2023).

Li，S。中风恢复是一段旅程：从实践的角度来看，中风后运动恢复的预测和潜力。生活巴塞尔瑞士。132061（2023）。

Google Scholar

谷歌学者

Vesz, P. S., Cremonese, R. V., Rosa, R. G., Maccari, J. G. & Teixeira, C. Impact of mechanical ventilation on quality of life and functional status after ICU discharge: A cross-sectional study. Rev. Assoc. Medica Bras. 1992(64), 47–53 (2018).Article

Vesz，P.S.，Cremonese，R.V.，Rosa，R.G.，Maccari，J.G。＆Teixeira，C。机械通气对ICU出院后生活质量和功能状态的影响：横断面研究。医学协会牧师。1992（64），47-53（2018）。文章

Google Scholar

谷歌学者

Han, J. H. et al. Delirium in the Emergency Department and its extension into hospitalization (DELINEATE) study: Effect on 6-month function and cognition. J. Am. Geriatr. Soc. 65, 1333–1338 (2017).Article

Han，J.H.等人，《急诊科deli妄及其住院延伸（描绘）研究：对6个月功能和认知的影响》。J、 我是老年人。Soc.651333-1338（2017）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Batt, J., Herridge, M. & Dos Santos, C. Mechanism of ICU-acquired weakness: Skeletal muscle loss in critical illness. Intensive Care Med. 43, 1844–1846 (2017).Article

Batt，J.，Herridge，M。＆Dos Santos，C。ICU获得性无力的机制：危重疾病中的骨骼肌损失。重症监护医学431844-1846（2017）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Batt, J., Herridge, M. S. & Dos Santos, C. C. From skeletal muscle weakness to functional outcomes following critical illness: A translational biology perspective. Thorax 74, 1091–1098 (2019).Article

Batt，J.，Herridge，M.S。＆Dos Santos，C.C。从骨骼肌无力到危重疾病后的功能结果：转化生物学的观点。胸部741091-1098（2019）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Kok, L., Slooter, A. J., Hillegers, M. H., van Dijk, D. & Veldhuijzen, D. S. Benzodiazepine use and neuropsychiatric outcomes in the ICU: A systematic review. Crit. Care Med. 46, 1673–1680 (2018).Article

Kok，L.，Slooter，A.J.，Hillegers，M.H.，van Dijk，D。＆Veldhuijzen，D.S。ICU中苯二氮卓类药物的使用和神经精神病学结果：系统评价。暴击。护理医学461673-1680（2018）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Celis-Rodríguez, E. et al. Evidence-based clinical practice guidelines for the management of sedoanalgesia and delirium in critically ill adult patients. Med. Intensiva 44, 171–184 (2020).Article

Celis Rodríguez，E.等人。危重成年患者睡眠分析和谵妄管理的循证临床实践指南。医学强化44171-184（2020）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Brummel, N. E. et al. Understanding and reducing disability in older adults following critical illness. Crit. Care Med. 43, 1265–1275 (2015).Article

Brummel，N.E.等人，《了解和减少危重病后老年人的残疾》。暴击。护理医学431265-1275（2015）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Kowalski, R. G. et al. Recovery of consciousness and functional outcome in moderate and severe traumatic brain injury. JAMA Neurol. 78, 548–557 (2021).Article

Kowalski，R.G.等人。中重度创伤性脑损伤的意识恢复和功能结果。JAMA Neurol。78548-557（2021）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Dietrich, C. et al. Functional ability in younger and older elderlies after discharge from the intensive care unit. A prospective cohort. Rev. Bras. Ter. Intensiva 29, 293–302 (2017).Article

Dietrich，C.等人。从重症监护病房出院后，年轻人和老年人的功能能力。一个前瞻性队列。修订版Bras。三。Intensiva 29293-302（2017）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Moons, K. G. M. et al. Risk prediction models: II. External validation, model updating, and impact assessment. Heart Br. Card. Soc. 98, 691–698 (2012).

Moons，K.G.M.等人。风险预测模型：II。外部验证、模型更新和影响评估。心形名片。Soc.98691-698（2012）。

Google Scholar

谷歌学者

Wolff, R. F. et al. PROBAST: A tool to assess the risk of bias and applicability of prediction model studies. Ann. Intern. Med. 170, 51–58 (2019).Article

Wolff，R.F.等人，《先证者：评估偏倚风险和预测模型研究适用性的工具》。安，实习生。医学170,51-58（2019）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Smit, J. M., Krijthe, J. H. & van Bommel, J. The future of artificial intelligence in intensive care: Moving from predictive to actionable AI. Intensive Care Med. 49, 1114–1116 (2023).Article

Smit，J.M.，Krijthe，J.H。＆van Bommel，J。重症监护中人工智能的未来：从预测到可行的人工智能。重症监护医学491114-1116（2023）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Download referencesFundingThis research was supported by a grant from the Guangdong Province Nurses Association of China (Guangdong Province Nurses Association Research Project 2023, Project No. gdshsxh2023ms06). The content of this manuscript is solely the responsibility of the authors and does not necessarily represent the official views of the funding agency.Author informationAuthors and AffiliationsShantou University Medical College, Shantou, 515000, People’s Republic of ChinaZewei Xiao, Limei Zeng & Suiping ChenDepartment of Nursing, First Affiliated Hospital of Shantou University Medical College, Shantou, 515000, People’s Republic of ChinaJinhua Wu & Haixing HuangAuthorsZewei XiaoView author publicationsYou can also search for this author in.

下载参考文献资助这项研究得到了中国广东省护士协会（广东省护士协会研究项目2023，项目编号gdshsxh2023ms06）的资助。本手稿的内容仅由作者负责，不一定代表资助机构的官方观点。作者信息作者和附属机构汕头大学医学院，汕头，515000，中华人民共和国肖泽伟，曾丽梅和陈遂平汕头大学医学院第一附属医院护理部，汕头，515000，中华人民共和国吴金华和黄海兴作者肖泽伟观点作者出版物您也可以在中搜索这位作者。

PubMed Google ScholarLimei ZengView author publicationsYou can also search for this author in

PubMed Google ScholarLimei ZengView作者出版物您也可以在

PubMed Google ScholarSuiping ChenView author publicationsYou can also search for this author in

PubMed Google ScholarSuiping ChenView作者出版物您也可以在

PubMed Google ScholarJinhua WuView author publicationsYou can also search for this author in

PubMed Google ScholarJinhua WuView作者出版物您也可以在

PubMed Google ScholarHaixing HuangView author publicationsYou can also search for this author in

PubMed谷歌学者黄海星查看作者出版物您也可以在

PubMed Google ScholarContributionsA Zewei Xiao B Limei Zeng C Suiping Chen D Baiwen Huang E Jinhua Wu F Haixing Huang A, C, D and E collected the data, A and F wrote and reviewed the main manuscript text, A and B prepared all the tables and figures, All authors reviewed the manuscript.

PubMed谷歌学术贡献A Zewei Xiao B Limei Zeng C Suiping Chen D Baiwen Huang E Jinhua Wu F Haixing Huang A，C，D和E收集数据，A和F撰写并审阅了主要稿件文本，A和B准备了所有表格和数字，所有作者都审阅了稿件。

All authors approved the final version of the manuscript submitted for publication.Corresponding authorCorrespondence to.

所有作者都批准了提交出版的稿件的最终版本。对应作者对应。

Haixing Huang.Ethics declarations

黄海兴。道德宣言

Competing interests

相互竞争的利益

The authors declare no competing interests.

作者声明没有利益冲突。

Additional informationPublisher's noteSpringer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Supplementary InformationSupplementary Information 1.Supplementary Information 2.Supplementary Information 3.Rights and permissions

Additional informationPublisher的noteSpringer Nature在已发布地图和机构隶属关系中的管辖权主张方面保持中立。补充信息补充信息1。补充信息2。补充信息3。权利和权限

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

开放获取本文是根据知识共享署名4.0国际许可证授权的，该许可证允许以任何媒体或格式使用，共享，改编，分发和复制，只要您对原始作者和来源给予适当的信任，提供知识共享许可证的链接，并指出是否进行了更改。

The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

本文中的图像或其他第三方材料包含在文章的知识共享许可中，除非在材料的信用额度中另有说明。如果材料未包含在文章的知识共享许可中，并且您的预期用途不受法律法规的许可或超出许可用途，则您需要直接获得版权所有者的许可。

To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/..

要查看此许可证的副本，请访问http://creativecommons.org/licenses/by/4.0/..

Reprints and permissionsAbout this articleCite this articleXiao, Z., Zeng, L., Chen, S. et al. Development and validation of early prediction models for new-onset functional impairment in patients after being transferred from the ICU.

转载和许可本文引用本文Xiao，Z.，Zeng，L.，Chen，S。等人。从ICU转移后患者新发功能障碍早期预测模型的开发和验证。

Sci Rep 14, 11902 (2024). https://doi.org/10.1038/s41598-024-62447-8Download citationReceived: 22 December 2023Accepted: 16 May 2024Published: 24 May 2024DOI: https://doi.org/10.1038/s41598-024-62447-8Share this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy to clipboard.

科学报告1411902（2024）。https://doi.org/10.1038/s41598-024-62447-8Download收到引文日期：2023年12月22日接受日期：2024年5月16日发布日期：2024年5月24日OI：https://doi.org/10.1038/s41598-024-62447-8Share本文与您共享以下链接的任何人都可以阅读此内容：获取可共享链接对不起，本文目前没有可共享的链接。复制到剪贴板。

Provided by the Springer Nature SharedIt content-sharing initiative

由Springer Nature SharedIt内容共享计划提供

KeywordsIntensive care unitFunctional impairmentActivities of daily livingPrediction modelMachine learning

关键词重症监护病房功能障碍日常生活活动预测模型机器学习

CommentsBy submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

评论通过提交评论，您同意遵守我们的条款和社区指南。如果您发现有虐待行为或不符合我们的条款或准则，请将其标记为不合适。