Predicting where Parkinson’s disease patients will be discharged from the hospital using machine learning. National cohort study

Machine Learning


  • Bloom, B.R., Okun, M.S., Klein, C. Parkinson’s disease. lancet 3972284–2303 (2021).

    Google Scholar

  • Kalia, LV, Lang, AE Parkinson’s disease. lancet 386896–912 (2015).

    Google Scholar

  • Kamo HaO, G. et al., Real-world feasibility of privacy-preserving non-wearable AI for real-time fall detection with disease-specific video classification in Parkinsonism: A proof-of-concept clinical study. Available at SSRN or https://doi.org/10.2139/ssrn.5675036.

  • Klaptocz, J. et al. Hospitalization patterns before care home admission in patients with Parkinson’s disease: Evidence of a critical period for patients and caregivers. J. Aging Health 311616–1630 (2019).

    Google Scholar

  • Weir, S. and others. Short-term and long-term costs and health resource utilization in Parkinson’s disease in the UK. Move. hindrance. 33974–981 (2018).

    Google Scholar

  • Aarsland, D., Larsen, JP, Tandberg, E. & Laake, K. Predictors of nursing home admission in Parkinson’s disease: A prospective population-based study. J. Am. Geriator. society 48938–942 (2000).

    Google Scholar

  • Marciniak, CM, Choo, CM, Toledo, SD, Semik, PE & Aegesen, AL Do comorbidities and cognition influence functional changes and need for discharge in Parkinson’s disease? morning. J. Phys. medicine. rehabilitation. 90272–280 (2011).

    Google Scholar

  • Gonzalez, MC, Dalen, I., Maple-Grødem, J., Tysnes, OB & Alves, G. Clinical milestones and mortality in Parkinson’s disease. NPJ Parkinson’s disease 858 (2022).

    Google Scholar

  • Zhou, C. et al. Glymphatic system dysfunction and risk of clinical milestones in patients with Parkinson’s disease. EUR. J. Neurol. 31e16521 (2024).

    Google Scholar

  • Schrag, A., Hovris, A., Morley, D., Quinn, N. & Jahanshahi, M. Caregiver burden in Parkinson’s disease is closely associated with psychiatric symptoms, falls, and disability. park. connection. hindrance. 1235–41 (2006).

    Google Scholar

  • Mickle, CF & Deb, D. Early prediction of patient discharge trends in acute neurological care using machine learning. BMC Health Services Resolution twenty two1281 (2022).

    Google Scholar

  • Abad, ZSH, Maslove, DM & Lee, J. Predicting hospital discharge destination for critically ill patients using machine learning. IEEE J. Biomed.Health Information twenty five827–837 (2021).

    Google Scholar

  • Bacchi, S. et al. Prospective and external validation of a stroke discharge planning machine learning model. J. Clin. Neuroscience. 9680–84 (2022).

    Google Scholar

  • Booth, GJ et al. Machine learning predicts discharge destination after total knee and total hip arthroplasty. J. Surg. Orthopedic surgery. advanced winter 32252–258 (2023).

    Google Scholar

  • Lu, Y., Khazi, ZM, Agarwalla, A., Forsythe, B. & Taunton, MJ Development of a machine learning algorithm to predict non-routine discharge after unicompartmental knee arthroplasty. J. Arthroplasty body. 361568–1576 (2021).

    Google Scholar

  • Chen, T.L. et al. Internal and external validation of the generalizability of machine learning algorithms in predicting out-of-home discharge trends after primary total knee arthroplasty. J. Arthroplasty body. 381973-1981 (2023).

    Google Scholar

  • Lam, L., Lam, A., Bacchi, S., Abou-Hamden, A. Neurosurgical inpatient outcome prediction for discharge planning using deep learning and transfer learning. Br. J. Neurosurg. 39110–114 (2025).

    Google Scholar

  • Gebran, A. et al. Developing a machine learning-based prescriptive tool to address racial disparities in access to care following severe trauma. JAMA Surg. 1581088–1095 (2023).

    Google Scholar

  • Shah, AA et al. To predict discharge destination and length of hospital stay after open reduction and internal fixation of distal femur fractures. Daejeon International Airport June 8e364 (2025).

    Google Scholar

  • Kato, C., Uemura, O., Sato, Y., Tsuji, T. Decision tree analysis accurately predicts discharge destination after spinal cord injury rehabilitation. arch. Physics. medicine. rehabilitation. 10588–94 (2024).

    Google Scholar

  • Oson, B. et al. Using artificial intelligence modeling to develop clinical decision support for patients aged 65 years and older with fall-related traumatic brain injury. PLoS ONE 20e0316462 (2025).

    Google Scholar

  • Gowd, AK et al. Machine learning algorithm outperforms comorbidity index in predicting short-term complications after hip fracture surgery. J. Am. Akado. Orthopedic surgery. Surgery. 33e633–e647 (2025).

    Google Scholar

  • Fan, G. et al. Early prognosis of critically ill patients with spinal cord injury: A machine learning study of 1,485 patients. spine 49754–762 (2024).

    Google Scholar

  • McMillan, JM, Michalchuk, Q. & Goodarzi, Z. Frailty in Parkinson’s disease: a systematic review and meta-analysis. Clin. Parklilat. hindrance. 4100095 (2021).

    Google Scholar

  • Chekani, F., Vali, V. & Aparasu, RR Functional status of elderly care facility residents with Parkinson’s disease. J. Parkinson’s disease 6617–624 (2016).

    Google Scholar

  • Garon, M. et al. Systematic practice review: Providing palliative care to people with Parkinson’s disease and their caregivers. Pariat. medicine. 3857–68 (2024).

    Google Scholar

  • Gansler, SA et al. The impact of inpatient mobility on outcomes in Parkinson’s disease. park. connection. hindrance. 135107834 (2025).

    Google Scholar

  • Bartolomeu Pires, S., Kunkel, D., Kipps, C., Goodwin, N. & Portillo, MC Person-centered, integrated care for people living with Parkinson’s disease, Huntington’s disease, and multiple sclerosis: A systematic review. Hope for health. 27e13948 (2024).

    Google Scholar

  • Rutten, JJS et al. Dementia and Parkinson’s disease: risk factors for 30-day mortality in nursing home residents due to COVID-19. J.Alzheimer’s disease 841173–1181 (2021).

    Google Scholar

  • Romero-Brufau, S. et al. Implementing artificial intelligence-based clinical decision support to reduce readmissions in a community hospital. Applied Clin. information 11570–577 (2020).

    Google Scholar

  • Kakarmath, S. et al. Validation of a machine learning algorithm for predicting 30-day readmission of heart failure patients: Prospective cohort study protocol. JMIR Research Institute Protok. 7e176 (2018).

    Google Scholar

  • Hao, S. et al. Development, validation, and implementation of a real-time 30-day readmission risk assessment tool in the Maine Health Information Exchange. PLoS ONE 10e0140271 (2015).

    Google Scholar

  • Zhao, P., Yoo, I. & Naqvi, SH Early prediction of unplanned 30-day readmissions: model development and retrospective data analysis. JMIR Medicine. information 9e16306 (2021).

    Google Scholar

  • Hatano, T. & Kamo, H. Fall risk and management in Parkinson’s disease. cranial nerve 7821–26 (2026).

    Google Scholar

  • Jones, CD et al. Characteristics associated with home health referral at discharge: Results from the 2012 National Inpatient Sample. health department resolution 52879–894 (2017).

    Google Scholar

  • Middleton, A., Graham, JE, Prvu Bettger, J., Haas, A. & Ottenbacher, KJ Facility and geographic variation in community discharge success rates after inpatient rehabilitation among Medicare fee beneficiaries. JAMA Network. open 1e184332 (2018).

    Google Scholar

  • McLagan LC et al. Trends in healthcare service utilization by region among patients with Parkinson’s disease: A repeated population-based cross-sectional study. PLoS ONE 18e0285585 (2023).

    Google Scholar

  • Mantri, S., Fullard, ME, Beck, J. & Willis, AW State-level prevalence, health service utilization, and expenditures vary widely among Medicare beneficiaries with Parkinson’s disease. NPJ Parkinson’s disease. 5https://doi.org/10.1038/s41531-019-0074-8 (2019).

  • Fullard, Main et al. Utilization of rehabilitation therapy services in Parkinson’s disease in the United States. Neurology 891162–1169 (2017).

    Google Scholar

  • Bloom, B.R., Eimers, M., Van Gaalen, M.S., Muneke, M., Darweesh, SKL From clinical trials to clinical practice: Temporal trends in specialty-related health service coverage in Parkinson’s disease. EUR. J. Neurol. 28775–782 (2021).

    Google Scholar

  • Hiroshi Kamo et al. Parkinson’s disease patients hospitalized with urinary tract infections: risk factors and outcomes. Move. hindrance. Clin. Please practice. https://doi.org/10.1002/mdc3.70556 (2026).

  • Hiroshi Kamo et al. 5-year risk of cardiovascular events and Parkinson’s disease associated with orthostatic hypotension: a national cohort study. park. connection. hindrance. 144108217 (2026).



  • Source link