OpenLB
Open Library of Bioscience
Advanced Search
Journal of clinical nursing
Aug, 2024;33 (8): 3145-3160.

Machine learning decision support model for discharge planning in stroke patients.

Yanli Cui, Lijun Xiang, Peng Zhao, Jian Chen, Lei Cheng, Lin Liao, Mingyu Yan, Xiaomei Zhang
Author Information
  1. Yanli Cui: Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China. ORCID
  2. Lijun Xiang: Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China. ORCID
  3. Peng Zhao: Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China.
  4. Jian Chen: Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China. ORCID
  5. Lei Cheng: Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China.
  6. Lin Liao: Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China.
  7. Mingyu Yan: Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China.
  8. Xiaomei Zhang: Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China.
PMID: 38358023 DOI: 10.1111/jocn.16999

Abstract

BACKGROUND/AIM: Efficient discharge for stroke patients is crucial but challenging. The study aimed to develop early predictive models to explore which patient characteristics and variables significantly influence the discharge planning of patients, based on the data available within 24���h of admission.
DESIGN: Prospective observational study.
METHODS: A prospective cohort was conducted at a university hospital with 523 patients hospitalised for stroke. We built and trained six different machine learning (ML) models, followed by testing and tuning those models to find the best-suited predictor for discharge disposition, dichotomized into home and non-home. To evaluate the accuracy, reliability and interpretability of the best-performing models, we identified and analysed the features that had the greatest impact on the predictions.
RESULTS: In total, 523 patients met the inclusion criteria, with a mean age of 61���years. Of the patients with stroke, 30.01% had non-home discharge. Our model predicting non-home discharge achieved an area under the receiver operating characteristic curve of 0.95 and a precision of 0.776. After threshold was moved, the model had a recall of 0.809. Top 10 variables by importance were National Institutes of Health Stroke Scale (NIHSS) score, family income, Barthel index (BI) score, FRAIL score, fall risk, pressure injury risk, feeding method, depression, age and dysphagia.
CONCLUSION: The ML model identified higher NIHSS, BI, and FRAIL, family income, higher fall risk, pressure injury risk, older age, tube feeding, depression and dysphagia as the top 10 strongest risk predictors in identifying patients who required non-home discharge to higher levels of care. Modern ML techniques can support timely and appropriate clinical decision-making.
RELEVANCE TO CLINICAL PRACTICE: This study illustrates the characteristics and risk factors of non-home discharge in patients with stroke, potentially contributing to the improvement of the discharge process.
REPORTING METHOD: STROBE guidelines.

Keywords

decision support discharge disposition discharge planning machine learning medical decision���making predictive factors prospective study stroke

References

  1. Bacchi, S., Oakden���Rayner, L., Menon, D. K., Jannes, J., Kleinig, T., & Koblar, S. (2020). Stroke prognostication for discharge planning with machine learning: A derivation study. Journal of Clinical Neuroscience, 79, 100���103. https://doi.org/10.1016/j.jocn.2020.07.046
  2. Bacchi, S., Oakden���Rayner, L., Menon, D. K., Moey, A., Jannes, J., Kleinig, T., & Koblar, S. (2022). Prospective and external validation of stroke discharge planning machine learning models. Journal of Clinical Neuroscience, 96, 80���84. https://doi.org/10.1016/j.jocn.2021.12.031
  3. Baumhauer, J. F., & Bozic, K. J. (2016). Value���based healthcare: Patient���reported outcomes in clinical decision making. Clinical Orthopaedics and Related Research, 474(6), 1375���1378. https://doi.org/10.1007/s11999���016���4813���4
  4. B��jot, Y., Daubail, B., Sensenbrenner, B., Legris, N., Durier, J., & Giroud, M. (2015). iScore for predicting institutional care after ischemic stroke: A population���based study. Journal of Stroke and Cerebrovascular Diseases, 24(3), 694���698. https://doi.org/10.1016/j.jstrokecerebrovasdis.2014.11.010
  5. Boehme, A. K., Esenwa, C., & Elkind, M. S. V. (2017). Stroke risk factors, genetics, and prevention. Circulation Research, 120(3), 472���495. https://doi.org/10.1161/CIRCRESAHA.116.308398
  6. Brofenbrenner, U. (1977). Toward an experimental ecology of human development. American Psychologist, 32(7), 513���531.
  7. Burton, J. K., Ferguson, E. E. C., Barugh, A. J., Walesby, K. E., MacLullich, A. M. J., Shenkin, S. D., & Quinn, T. J. (2018). Predicting discharge to institutional long���term care after stroke: A systematic review and Metaanalysis. Journal of the American Geriatrics Society, 66(1), 161���169. https://doi.org/10.1111/jgs.15101
  8. Chevalley, O., Truijen, S., Saeys, W., & Opsommer, E. (2022). Socio���environmental predictive factors for discharge destination after inpatient rehabilitation in patients with stroke: A systematic review and meta���analysis. Disability and Rehabilitation, 44(18), 4974���4985. https://doi.org/10.1080/09638288.2021.1923838
  9. Cho, J., Place, K., Salstrand, R., Rahmat, M., Mansouri, M., Fell, N., & Sartipi, M. (2021). Developing a predictive tool for hospital discharge disposition of patients Poststroke with 30���day readmission validation. Stroke Research and Treatment, 2021, 1���9. https://doi.org/10.1155/2021/5546766
  10. Collaborators, G. S. (2021). Global, regional, and national burden of stroke and its risk factors, 1990���2019: A systematic analysis for the global burden of disease study 2019. Lancet Neurology, 20(10), 795���820. https://doi.org/10.1016/S1474���4422(21)00252���0
  11. Cui, G. H., Yao, Y. H., Xu, R. F., Tang, H. D., Jiang, G. X., Wang, Y., Wang, G., Chen, S. D., & Cheng, Q. (2011). Cognitive impairment using education���based cutoff points for CMMSE scores in elderly Chinese people of agricultural and rural Shanghai China. Acta Neurologica Scandinavica, 124(6), 361���367. https://doi.org/10.1111/j.1600���0404.2010.01484.x
  12. de Berker, H., de Berker, A., Aung, H., Duarte, P., Mohammed, S., Shetty, H., & Hughes, T. (2021). Pre���stroke disability and stroke severity as predictors of discharge destination from an acute stroke ward. Clinical Medicine, 21(2), e186���e191. https://doi.org/10.7861/clinmed.2020���0834
  13. Dent, E., Kowal, P., & Hoogendijk, E. O. (2016). Frailty measurement in research and clinical practice: A review. European Journal of Internal Medicine, 31, 3���10. https://doi.org/10.1016/j.ejim.2016.03.007
  14. Drozdowska, B. A., Singh, S., & Quinn, T. J. (2019). Thinking about the future: A review of prognostic scales used in acute stroke. Frontiers in Neurology, 10. https://doi.org/10.3389/fneur.2019.00274
  15. Fast, L., Temuulen, U., Villringer, K., Kufner, A., Ali, H. F., Siebert, E., Huo, S., Piper, S. K., Sperber, P. S., Liman, T., Endres, M., & Ritter, K. (2023). Machine learning���based prediction of clinical outcomes after first���ever ischemic stroke. Frontiers in Neurology, 14. https://doi.org/10.3389/fneur.2023.1114360
  16. Gadodia, G., Rizk, N., Camp, D., Bryant, K., Zimmerman, S., Brasher, C., Connelly, K., Dunn, J., Frankel, M., Ido, M. S., Lugtu, J., & Nahab, F. (2016). Presenting symptoms and dysphagia screen predict outcome in mild and rapidly improving acute ischemic stroke patients. Journal of Stroke and Cerebrovascular Diseases, 25(12), 2876���2881. https://doi.org/10.1016/j.jstrokecerebrovasdis.2016.07.049
  17. Gkantzios, A., Kokkotis, C., Tsiptsios, D., Moustakidis, S., Gkartzonika, E., Avramidis, T., Aggelousis, N., & Vadikolias, K. (2023). Evaluation of blood biomarkers and parameters for the prediction of stroke Survivors' functional outcome upon discharge utilizing explainable machine learning. Diagnostics, 13(3), 532. https://doi.org/10.3390/diagnostics13030532
  18. Gonz��lez���Fern��ndez, M., Ottenstein, L., Atanelov, L., & Christian, A. B. (2013). Dysphagia after stroke: An overview. Current Physical Medicine and Rehabilitation Reports, 1(3), 187���196. https://doi.org/10.1007/s40141���013���0017���y
  19. Gorelick, P. B. (2019). The global burden of stroke: Persistent and disabling. Lancet Neurology, 18(5), 417���418. https://doi.org/10.1016/S1474���4422(19)30030���4
  20. Hamilton, A. J., Strauss, A. T., Martinez, D. A., Hinson, J. S., Levin, S., Lin, G., & Klein, E. Y. (2021). Machine learning and artificial intelligence: Applications in healthcare epidemiology. Antimicrobial Stewardship and Healthcare Epidemiology, 1(1). https://doi.org/10.1017/ash.2021.192
  21. Hong, K., & Saver, J. L. (2009). Quantifying the value of stroke disability outcomes. Stroke, 40(12), 3828���3833. https://doi.org/10.1161/STROKEAHA.109.561365
  22. Huybrechts, K. F., & Jaime Caro, J. (2007). The Barthel index and modified Rankin scale as prognostic tools for long���term outcomes after stroke: A qualitative review of the literature. Current Medical Research and Opinion, 23(7), 1627���1636. https://doi.org/10.1185/030079907X210444
  23. Jiang, Y., Wang, H., Qu, C., Wang, Y., Le, X., & Huang, H. (2022). Status and predictors of discharge disposition in patients with stroke. Journal of Nursing Science, 37(10), 106���109. https://doi.org/10.3870/j.issn.1001���4152.2022.10.106
  24. Louie, D. R., Simpson, L. A., Mortenson, W. B., Field, T. S., Yao, J., & Eng, J. J. (2022). Prevalence of walking limitation after acute stroke and its impact on discharge to home. Physical Therapy, 102(1). https://doi.org/10.1093/ptj/pzab246
  25. Luker, J. A., Bernhardt, J., Grimmer, K. A., & Edwards, I. (2014). A qualitative exploration of discharge destination as an outcome or a driver of acute stroke care. BMC Health Services Research, 14, 193. https://doi.org/10.1186/1472���6963���14���193
  26. Mickle, C. F., & Deb, D. (2022). Early prediction of patient discharge disposition in acute neurological care using machine learning. BMC Health Services Research, 22(1). https://doi.org/10.1186/s12913���022���08615���w
  27. Miller, K. K., Lin, S. H., & Neville, M. (2019). From hospital to home to participation: A position paper on transition planning Poststroke. Archives of Physical Medicine and Rehabilitation, 100(6), 1162���1175. https://doi.org/10.1016/j.apmr.2018.10.017
  28. Nguyen, V. Q. C., PrvuBettger, J., Guerrier, T., Hirsch, M. A., Thomas, J. G., Pugh, T. M., & Rhoads, C. F. (2015). Factors associated with discharge to home versus discharge to institutional care after inpatient stroke rehabilitation. Archives of Physical Medicine and Rehabilitation, 96(7), 1297���1303. https://doi.org/10.1016/j.apmr.2015.03.007
  29. Nuyen, J., Spreeuwenberg, P. M., Groenewegen, P. P., van den Bos, G. A. M., & Schellevis, F. G. (2008). Impact of preexisting depression on length of stay and discharge destination among patients hospitalized for acute stroke. Stroke, 39(1), 132���138. https://doi.org/10.1161/STROKEAHA.107.490565
  30. Pashmdarfard, M., & Azad, A. (2020). Assessment tools to evaluate activities of daily living (ADL) and instrumental activities of daily living (IADL) in older adults: A systematic review. Medical Journal of the Islamic Republic of Iran, 34, 33. https://doi.org/10.34171/mjiri.34.33
  31. Pilotto, A., Brass, C., Fassbender, K., Merzou, F., Morotti, A., K��mpfer, N., Siniscalchi, A., Padovani, A., & Lochner, P. (2022). Premorbid frailty predicts short��� and long���term outcomes of reperfusion treatment in acute stroke. Journal of Neurology, 269(6), 3338���3342. https://doi.org/10.1007/s00415���022���10966���7
  32. Prvu Bettger, J. A., & Stineman, M. G. (2007). Effectiveness of multidisciplinary rehabilitation Services in Postacute Care: State���of���the���science. A review. Archives of Physical Medicine and Rehabilitation, 88(11), 1526���1534. https://doi.org/10.1016/j.apmr.2007.06.768
  33. Shogenji, M., Yoshida, M., Sumiya, K., Shimada, T., Ikenaga, Y., Ogawa, Y., Hirako, K., & Sai, Y. (2022). Relationship between bowel/bladder function and discharge in older stroke patients in convalescent rehabilitation wards: A retrospective cohort study. Prog Rehabil Med, 7, 20220028. https://doi.org/10.2490/prm.20220028
  34. Shuiyuan, X. (1994). The theoretical basis and research application of social support rating scale. Journal of Clinical Psychiatry, 02, 98���100. https://kns.cnki.net/kcms/detail/detail.aspx?File���Name=LCJS402.019&DbName=CJFQ1994.
  35. Singh, M., Stewart, R., & White, H. (2014). Importance of frailty in patients with cardiovascular disease. European Heart Journal, 35(26), 1726���1731. https://doi.org/10.1093/eurheartj/ehu197
  36. Slenders, J. P. L., Verberne, D. P. J., Visser���Meily, J. M. A., Van den Berg���Vos, R. M., Kwa, V. I. H., & van Heugten, C. M. (2020). Early cognitive and emotional outcome after stroke is independent of discharge destination. Journal of Neurology, 267(11), 3354���3361. https://doi.org/10.1007/s00415���020���09999���7
  37. Sokas, C. M., Cowan, J., Dalton, M. K., Coogan, K., Bader, A., Bernacki, R., Orkaby, A. R., & Cooper, Z. (2020). Association between patient���reported frailty and non���home discharge among older adults undergoing surgery. Journal of the American Geriatrics Society, 68(12), 2909���2913. https://doi.org/10.1111/jgs.16846
  38. Souza, J. T., Ribeiro, P. W., de Paiva, S. A. R., Tanni, S. E., Minicucci, M. F., Zornoff, L. A. M., Polegato, B. F., Bazan, S. G. Z., Modolo, G. P., Bazan, R., & Azevedo, P. S. (2020). Dysphagia and tube feeding after stroke are associated with poorer functional and mortality outcomes. Clinical Nutrition, 39(9), 2786���2792. https://doi.org/10.1016/j.clnu.2019.11.042
  39. van Kan, G. A., Rolland, Y. M., Morley, J. E., & Vellas, B. (2008). Frailty: Toward a clinical definition. Journal of the American Medical Directors Association, 9(2), 71���72. https://doi.org/10.1016/j.jamda.2007.11.005
  40. Virani, S. S., Alonso, A., Aparicio, H. J., Benjamin, E. J., Bittencourt, M. S., Callaway, C. W., Carson, A. P., Chamberlain, A. M., Cheng, S., Delling, F. N., Elkind, M., Evenson, K. R., Ferguson, J. F., Gupta, D. K., Khan, S. S., Kissela, B. M., Knutson, K. L., Lee, C. D., Lewis, T. T., ��� Tsao, C. W. (2021). Heart disease and stroke Statistics���2021 update: A report from the American Heart Association. Circulation, 143(8), e254���e743. https://doi.org/10.1161/CIR.0000000000000950
  41. Yang, F., Li, N., Yang, L., Chang, J., Yan, A., & Wei, W. (2022). Association of pre���stroke Frailty with Prognosis of elderly patients with acute cerebral infarction: A cohort study. Frontiers in Neurology, 13, 855532. https://doi.org/10.3389/fneur.2022.855532
  42. Young, Y., Boyd, C. M., Guralnik, J. M., & Fried, L. P. (2010). Does self���reported function correspond to objective measures of functional impairment? Journal of the American Medical Directors Association, 11(9), 645���653. https://doi.org/10.1016/j.jamda.2009.12.084
  43. Zhang, J., Wang, M., & Liu, Y. (2016). Psychometric validation of the Chinese version of the Johns Hopkins fall risk assessment tool for older Chinese inpatients. Journal of Clinical Nursing, 25(19���20), 2846���2853. https://doi.org/10.1111/jocn.13331

MeSH Term

Humans
Patient Discharge
Middle Aged
Female
Male
Prospective Studies
Stroke
Machine Learning
Aged
Decision Support Techniques
Cohort Studies
Journal Article Observational Study

Word Cloud

Created with Highcharts 10.0.0dischargepatientsstrokerisknon-homestudymodelsmodelplanninglearningMLage0scorehighersupportpredictivecharacteristicsvariablesprospective523machinedispositionidentified10NIHSSfamilyincomeBIFRAILfallpressureinjuryfeedingdepressiondysphagiafactorsdecisionBACKGROUND/AIM:Efficientcrucialchallengingaimeddevelopearlyexplorepatientsignificantlyinfluencebaseddataavailablewithin24���hadmissionDESIGN:ProspectiveobservationalMETHODS:cohortconducteduniversityhospitalhospitalisedbuilttrainedsixdifferentfollowedtestingtuningfindbest-suitedpredictordichotomizedhomeevaluateaccuracyreliabilityinterpretabilitybest-performinganalysedfeaturesgreatestimpactpredictionsRESULTS:totalmetinclusioncriteriamean61���years3001%predictingachievedareareceiveroperatingcharacteristiccurve95precision776thresholdmovedrecall809TopimportanceNationalInstitutesHealthStrokeScaleBarthelindexmethodCONCLUSION:oldertubetopstrongestpredictorsidentifyingrequiredlevelscareModerntechniquescantimelyappropriateclinicaldecision-makingRELEVANCETOCLINICALPRACTICE:illustratespotentiallycontributingimprovementprocessREPORTINGMETHOD:STROBEguidelinesMachinemedicaldecision���making

Similar Articles

Cited By