Computational Neurorehabilitation

Jeder Patient in der Neurorehabilitation ist einzigartig, und jede Behandlung muss auf den Patienten zugeschnitten sein. Dieser Akt der Personalisierung wird empirisch jeden Tag zigfach durchgeführt, jedoch gibt es hierfür keine explizite Datengrundlage. Eine Möglichkeit, um der Vielfalt der Patientenbilder gerecht zu werden, besteht darin, sich in Zukunft von populationsbasierten statistischen Modellen zu verabschieden. Eine Alternative sind sogenannte N-of-1 Trials, in denen Daten von einzelnen Patienten und ihren Therapieverläufen gesammelt und Metaanalysen über den Behandlungserfolg durchgeführt werden. Durch maschinelles Lernen werden in großen Datensätzen Repräsentationsräume und Trajektorien identifiziert, die als digitale klinische Entscheidungshilfe fungieren können. Hierfür müssen jedoch intelligente Datenerfassungssysteme im klinischen Alltag Einzug finden, um eine ausreichende Datendichte zu erzielen. Der Artikel stellt ein solches Datenerfassungssystem vor und beschreibt die Erfahrungen einer Implementierung in einer Schlaganfall-Rehaklinik.

Publication History

Article published online:
05 June 2025

• Literatur

• 1 Lawrence ES, Coshall C, Dundas R. et al. Estimates of the prevalence of acute stroke impairments and disability in a multiethnic population. Stroke 2001; 32: 1279-1284
• 2 Carey LM, Abbott DF, Egan GF. et al. Motor impairment and recovery in the upper limb after stroke. Stroke 2005; 36: 625-629
• 3 Grefkes C, Fink GR. Recovery from stroke: Current concepts and future perspectives. Neurol Res Pract 2020; 2: 17
• 4 Holliday RC, Cano S, Freeman JA. et al. Should patients participate in clinical decision making? An optimised balance block design controlled study of goal setting in a rehabilitation unit. J Neurol Neurosurg Psychiatry 2007; 78: 576-580
• 5 Scrivener K, Dorsch S, McCluskey A. et al. Bobath therapy is inferior to task-specific training and not superior to other interventions in improving lower limb activities after stroke: A systematic review. J Physiother 2020; 66: 225-235
• 6 Lillie EO, Patay B, Diamant J. et al. The n-of-1 clinical trial: The ultimate strategy for individualizing medicine?. Pers Med 2011; 8: 161-173
• 7 Panch T, Szolovits P, Atun R. Artificial intelligence, machine learning and health systems. J Glob Health 2018; 8: 020303
• 8 French MA, Roemmich RT, Daley K. et al. Precision rehabilitation: Optimizing function, adding value to health care. Arch Phys Med Rehabil 2022; 103: 1233-1239
• 9 Lin DJ, Backus D, Chakraborty S. et al. Transforming modeling in neurorehabilitation: Clinical insights for personalized rehabilitation. J NeuroEngineering Rehabil 2024; 21: 18
• 10 Ye D, Luo H, Winstein C, Schweighofer N. Towards AI-based precision rehabilitation via contextual model-based reinforcement learning. medRxiv 2025; 01.13.24319196
• 11 Abdellatif AA, Mhaisen N, Mohamed A. et al. Reinforcement learning for intelligent healthcare systems: A review of challenges, applications, and open research issues. IEEE Internet Things J 2023; 10: 21982-22007
• 12 Cotton RJ, Seamon BA, Segal RL. et al. A causal framework for precision rehabilitation. 2024
• 13 Adans-Dester C, Hankov N, O’Brien A. et al. Enabling precision rehabilitation interventions using wearable sensors and machine learning to track motor recovery. NPJ Digit Med 2020; 3: 121
• 14 Pohl J, Verheyden G, Held JPO. et al. Construct validity and responsiveness of clinical upper limb measures and sensor-based arm use within the first year after stroke: A longitudinal cohort study. J NeuroEngineering Rehabil 2025; 22: 14
• 15 Lohse KR, Miller AE, Bland MD. et al. Validation of real-world actigraphy to capture post-stroke motor recovery. medRxiv 2024; 2024.11.03.24316674
• 16 Wang R, Lang CE, Stoykov ME. et al. Wearable-based digital biomarker provides a valid alternative to traditional clinical measures for post-stroke upper-limb motor recovery. medRxiv 2025; 2025.01.13.25320461
• 17 Mayrhuber L, Andrés SD, Legrand ML. et al. Encouraging arm use in stroke survivors: The impact of smart reminders during a home-based intervention. J NeuroEngineering Rehabil 2024; 21: 220
• 18 Pohl J, Ryser A, Veerbeek JM. et al. Accuracy of gait and posture classification using movement sensors in individuals with mobility impairment after stroke. Front Physiol 2022; 13
• 19 Pohl J, Ryser A, Veerbeek JM. et al. Classification of functional and non-functional arm use by inertial measurement units in individuals with upper limb impairment after stroke. Front Physiol 2022; 13: 952757
• 20 Song Y, Yun I, Giovanoli S. et al. A wearable system for monitoring neurological disorder events with multi-class classification model in daily life. 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2024; 1-4
• 21 Olawade DB, Aderinto N, Clement David-Olawade A. et al. Integrating AI-driven wearable devices and biometric data into stroke risk assessment: A review of opportunities and challenges. Clin Neurol Neurosurg 2025; 249: 108689
• 22 Brasier N, Wang J, Gao W. et al. Applied body-fluid analysis by wearable devices. Nature 2024; 636: 57-68
• 23 Wada S, Yoshimura S, Inoue M. et al. Outcome prediction in acute stroke patients by continuous glucose monitoring. J Am Heart Assoc 2018; 7: e008744
• 24 Werner C, Schönhammer JG, Steitz MK. et al. Using wearable inertial sensors to estimate clinical scores of upper limb movement quality in stroke. Front Physiol 2022; 13: 877563
• 25 Maceira-Elvira P, Popa T, Schmid A-C. et al. Wearable technology in stroke rehabilitation: Towards improved diagnosis and treatment of upper-limb motor impairment. J Neuroengineering Rehabil 2019; 16: 142
• 26 Uhlrich SD, Falisse A, Kidziński L. et al. OpenCap: Human movement dynamics from smartphone videos. PLOS Comput Biol 2023; 19: e1011462
• 27 Unger T, de Sousa Ribeiro R, Mokni M. et al. Upper limb movement quality measures: Comparing IMUs and optical motion capture in stroke patients performing a drinking task. Front Digit Health 2024; 6: 1359776
• 28 Wen KY, Gustafson DH, Hawkins RP. et al. Developing and validating a model to predict the success of an IHCS implementation: The readiness for implementation model. J Am Med Inform Assoc JAMIA 2010; 17: 707-713
• 29 SCAI-Lab/ros4hc. 2025. Im Internet https://github.com/SCAI-Lab/ros4hc Stand: 26.03.2025
• 30 Heumos L, Ehmele P, Treis T. et al. An open-source framework for end-to-end analysis of electronic health record data. Nat Med 2024; 30: 3369-3380
• 31 Grafana Labs. Grafana: The open and composable observability platform. Im Internet https://grafana.com/ Stand: 26.03.2025