Download PDF
MSK – Muskuloskelettale Physiotherapie 2024; 28(05): 312-321
DOI: 10.1055/a-2402-9982
Fachwissen

KI-gestützte Untersuchung in der nicht-operativen Versorgung symptomgebender Erkrankungen des Kniegelenks – ein multiprofessionelles Konzept (KINEESIO)

AI-Supported Examination in the Non-Surgical Treatment of Symptomatic Diseases of the Knee Joint – A Multiprofessional Concept (KINEESIO)
Elke Schulze
1   Angewandte Sozial- und Gesundheitswissenschaften, Fachbereich Physiotherapie, Ostbayerische Technische Hochschule Regensburg, Regensburg Center of Health Sciences and Technology (RCHST)
,
Christoph Palm
2   Fakultät Informatik und Mathematik, Ostbayerische Technische Hochschule Regensburg, Regensburg Center of Health Sciences and Technology (RCHST)
,
Maximilian Kerschbaum
3   Klinik und Poliklinik für Unfallchirurgie, Universitätsklinikum Regensburg (UKR)
,
Roman Seidel
4   Professur Digital- und Schaltungstechnik, Fakultät für Elektrotechnik und Informationstechnik, Technische Universität Chemnitz
,
Lars Lehmann
4   Professur Digital- und Schaltungstechnik, Fakultät für Elektrotechnik und Informationstechnik, Technische Universität Chemnitz
,
Michael Koller
5   Zentrum für Klinische Studien, Universitätsklinikum Regensburg (UKR)
,
Andrea Pfingsten
6   Professur für Physiotherapie, Ostbayerische Technische Hochschule Regensburg, Regensburg Center of Health Sciences and Technology (RCHST)
› Author Affiliations
› Further Information
    Permissions and Reprints

Zusammenfassung

Beschwerdebilder am Kniegelenk aufgrund muskuloskelettaler degenerativer oder verletzungsbedingter Erkrankungen sind häufig, nehmen im Alter zu und sind mit der steigenden Inanspruchnahme ärztlicher und therapeutischer Behandlungsmaßnahmen verbunden. Einer erfolgreichen Therapie gehen oft notwendige zeit- und ressourcenaufwendige Untersuchungen zur Erkennung und Differenzierung der patient*innenspezifischen Problematik voraus.

Im Zusammenhang mit der nicht-operativen Versorgung des Kniegelenks hat ein sektorübergreifendes multiprofessionelles Forschungsteam ein Konzept entwickelt, um künstliche neuronale Netze so zu trainieren, dass sie bei der ärztlichen und physiotherapeutischen Untersuchung unterstützend Einsatz finden können. Denn gerade in der Erfassung und Auswertung umfassender Datenmengen liegen große Potenziale in der Künstlichen Intelligenz (KI) im Gesundheitswesen.

Das Projekt KINEESIO trainiert und testet KI-gestützte Screening-Tools zur Untersuchung von Patient*innen mit Kniegelenkerkrankungen. Diese unterstützen die Abläufe zwischen Leistungserbringern und Patient*innen, tragen zu einer verbesserten Differenzierung individueller Beschwerdebilder bei und dienen Entscheidungsprozessen für eine adäquate Versorgung. Dadurch sollen Ressourcen im Gesundheitswesen geschont und eine qualitativ hochwertige Therapie ausreichend ermöglicht werden.

Abstract

Complaints regarding knee joints resulting from musculoskeletal degenerative or injury-related conditions are common, increase with age, and are associated with rising demand for treatments by physicians and therapists. The success of a therapeutic intervention is frequently contingent upon necessary time- and resource-intensive examinations to identify and differentiate the patient’s specific issues.

In connection with non-surgical knee joint treatment, a cross-sectoral, multidisciplinary research team has developed a concept for training artificial neural networks to assist in medical and physiotherapeutic examinations. After all, there is great potential for artificial intelligence (AI) in healthcare, particularly in collecting and analyzing large amounts of data.

The KINEESIO project is training and testing screening tools supported by artificial intelligence for the assessment of patients with knee joint disorders. These tools support the workflows between healthcare providers and patients, improve the differentiation of individual symptoms and serve the decision-making process towards appropriate care. This should conserve healthcare resources and enable sufficient high-quality treatment.

Schlüsselwörter

Kniegelenk - Diagnose - Physiotherapie - Künstliche Intelligenz

Keywords

knee joint - diagnosis - physiotherapy - artificial intelligence


Publication History

Article published online:
10 December 2024

© 2024. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 

  • Literatur

  • 1 Peete R, Majowski K, Lauer L, Jay A. Artificial Intelligence in Healthcare. In: Groom FM, Jones SS, edts. Artificial Intelligence and Machine Learning for Business for Non-Engineers. 1st ed. CRC Press; 2019
    CrossrefSearch in Google Scholar
  • 2 Vos T, Abajobir AA, Abate KH. et al. Global, regional, and national incidence, prevalence, and years lived with disability for 328 diseases and injuries for 195 countries, 1990–2016: a systematic analysis for the Global Burden of Disease Study 2016. Lancet 2017; 390: 1211-1259
    CrossrefPubMedSearch in Google Scholar
  • 3 Thiem U, Lamsfuß R, Günther S. et al. Prevalence of Self-Reported Pain, Joint Complaints and Knee or Hip Complaints in Adults Aged ≥ 40 Years: A Cross-Sectional Survey in Herne, Germany. PLoS One 2013; 8: e60753
    CrossrefPubMedSearch in Google Scholar
  • 4 Fuchs J, Prütz F. Prävalenz von Gelenkschmerzen in Deutschland. Robert Koch-Institut. Berlin. Journal of Health Monitoring 2017; 2: 66-71
    CrossrefSearch in Google Scholar
  • 5 DSTATIS. Statistisches Bundesamt. Die 20 häufigsten Operationen insgesamt (OPS 5). Vollstationär behandelte Patientinnen und Patienten in Krankenhäusern 2023. Im Internet: https://bit.ly/47NThAG Stand: 30.09.2024
  • 6 Brophy RH, Fillingham YA. AAOS Clinical Practice Guideline Summary: Management of Osteoarthritis of the Knee (Nonarthroplasty), Third Edition. J Am Acad Orthop Surg 2022; 30: e721-e729
    CrossrefPubMedSearch in Google Scholar
  • 7 Tisch T, Deckenbach B, Nolting HD. Versorgungsreport Knieschmerzen/Gonarthrose. Wie eine bessere Versorgung Gelenkersatz vermeiden kann. DAK Gesundheit. Hamburg: medhochzwei; 2022. Im Internet: https://bit.ly/4dohKxD Stand: 30.09.2024
    Search in Google Scholar
  • 8 Luong MLN, Cleveland RJ, Nyrop KA. et al. Social determinants and osteoarthritis outcomes. Aging Health 2012; 8: 413-437
    CrossrefPubMedSearch in Google Scholar
  • 9 Spahn G, Schiele R, Hofmann G. et al. Die Prävalenz der radiologischen Gonarthrose in Bezug zu Lebensalter, Geschlecht, Jahrgangskohorte und ethnischer Zugehörigkeit. Eine Metaanalyse. Z Orthop Unfall 2011; 149: 145-152
    Thieme ConnectPubMedSearch in Google Scholar
  • 10 Nielsen AB, Yde J. Epidemiology of Acute Knee Injuries: A Prospective Hospital Investigation. J Trauma 1991; 31: 1644-1648
    CrossrefPubMedSearch in Google Scholar
  • 11 Andriacchi TP, Briant PL, Bevill SL. et al. Rotational Changes at the Knee after ACL Injury Cause Cartilage Thinning. Clin Orthop Relat Res 2006; 442: 39-44
    CrossrefPubMedSearch in Google Scholar
  • 12 Berthiaume MJ, Raynauld J-P, Martel-Pelletier J. et al. Meniscal tear and extrusion are strongly associated with progression of symptomatic knee osteoarthritis as assessed by quantitative magnetic resonance imaging. Ann Rheum Dis 2005; 64: 556-563
    CrossrefPubMedSearch in Google Scholar
  • 13 Mahmoudian A, Lohmander LS, Mobasheri A. et al. Early-stage symptomatic osteoarthritis of the knee — time for action. Nat Rev Rheumatol 2021; 17: 621-632
    CrossrefPubMedSearch in Google Scholar
  • 14 Altman R, Asch E, Bloch D. et al. Development of criteria for the classification and reporting of osteoarthritis: Classification of osteoarthritis of the knee. Diagnostic and Therapeutic Criteria Committee of the American Rheumatism Association. Arthritis Rheum 1986; 29: 1039-1049
    CrossrefPubMedSearch in Google Scholar
  • 15 Ariani A, Manara M, Fioravanti A. et al. The Italian Society for Rheumatology clinical practice guidelines for the diagnosis and management of knee, hip and hand osteoarthritis. Reumatismo 2019; 71: 5-21
    CrossrefPubMedSearch in Google Scholar
  • 16 Orlando Júnior N, De Souza Leão MG, De Oliveira NHC. Diagnosis of knee injuries: comparison of the physical examination and magnetic resonance imaging with the findings from arthroscopy. Rev Bras Ortop 2015; 50: 712-719
    CrossrefPubMedSearch in Google Scholar
  • 17 Rayan F, Bhonsle S, Shukla DD. Clinical, MRI, and arthroscopic correlation in meniscal and anterior cruciate ligament injuries. Int Orthop 2009; 33: 129-132
    CrossrefPubMedSearch in Google Scholar
  • 18 Siebert C, Becker R, Buchner M. et al. S2k-Leitlinie Meniskuserkrankung: konservative und operative Therapie. Z Orthop Unfall 2018; 156: 324-329
    Thieme ConnectPubMedSearch in Google Scholar
  • 19 Sokal PA, Norris R, Maddox TW. et al. The diagnostic accuracy of clinical tests for anterior cruciate ligament tears are comparable but the Lachman test has been previously overestimated: a systematic review and meta-analysis. Knee Surg Sports Traumatol Arthrosc 2022; 30: 3287-3303
    CrossrefPubMedSearch in Google Scholar
  • 20 Blyth M, Anthony I, Francq B. et al. Diagnostic accuracy of the Thessaly test, standardised clinical history and other clinical examination tests (Apley’s, McMurray’s and joint line tenderness) for meniscal tears in comparison with magnetic resonance imaging diagnosis. Health Technol Assess 2015; 19: 1-62
    CrossrefPubMedSearch in Google Scholar
  • 21 Ryzewicz M, Peterson B, Siparsky PN. et al. The Diagnosis of Meniscus Tears: The Role of MRI and Clinical Examination. Clin Orthop Relat Res 2007; 455: 123-133
    CrossrefPubMedSearch in Google Scholar
  • 22 Hegedus EJ, Cook C, Hasselblad V. et al. Physical Examination Tests for Assessing a Torn Meniscus in the Knee: A Systematic Review With Meta-analysis. J Orthop Sports Phys Ther 2007; 37: 541-550
    CrossrefPubMedSearch in Google Scholar
  • 23 Smith BE, Thacker D, Crewesmith A. et al. Special tests for assessing meniscal tears within the knee: a systematic review and meta-analysis. Evid Based Med 2015; 20: 88-97
    CrossrefPubMedSearch in Google Scholar
  • 24 Ercin E, Kaya I, Sungur I. et al. History, clinical findings, magnetic resonance imaging, and arthroscopic correlation in meniscal lesions. Knee Surg Sports Traumatol Arthrosc 2012; 20: 851-856
    CrossrefPubMedSearch in Google Scholar
  • 25 Sanders TG, Miller MD. A Systematic Approach to Magnetic Resonance Imaging Interpretation of Sports Medicine Injuries of the Knee. Am J Sports Med 2005; 33: 131-148
    CrossrefPubMedSearch in Google Scholar
  • 26 Kise NJ, Risberg MA, Stensrud S. et al. Exercise therapy versus arthroscopic partial meniscectomy for degenerative meniscal tear in middle aged patients: randomised controlled trial with two year follow-up. BMJ 2016; 20 354 i3740
    CrossrefPubMedSearch in Google Scholar
  • 27 Diemer F, Sutor V, Diemer F. Praxis der medizinischen Trainingstherapie I: Lendenwirbelsäule, Sakroiliakalgelenk und untere Extremität. 3. Aufl. Thieme; 2018
    Thieme ConnectSearch in Google Scholar
  • 28 Ärztezeitung (kaha). Radiologen warnen vor langen Wartezeiten. ÄrzteZeitung (28. März 2023). Im Internet: https://bit.ly/3TRXopH Stand: 30.09.2024
  • 29 Koenig S, Morcos G, Gopinath R. et al. Is MRI Overutilized for Evaluation of Knee Pain in Veterans?. J Knee Surg 2023; 36: 305-309
    Thieme ConnectPubMedSearch in Google Scholar
  • 30 Newman S, Ahmed H, Rehmatullah N. Radiographic vs. MRI vs. arthroscopic assessment and grading of knee osteoarthritis – are we using appropriate imaging?. J Exp Orthop 2022; 9: 2
    CrossrefPubMedSearch in Google Scholar
  • 31 van Doormaal MCM, Meerhoff GA, Vliet Vlieland TPM. et al. A clinical practice guideline for physical therapy in patients with hip or knee osteoarthritis. Musculoskeletal Care 2020; 18: 575-595
    CrossrefPubMedSearch in Google Scholar
  • 32 GKV. Anlage 1 Leistungsbeschreibung zum Vertrag nach § 125 Absatz 1 SGB V über die Versorgung mit Leistungen der Physiotherapie und deren Vergütung (21.07.2021). Im Internet: https://bit.ly/3XSZExZ Stand: 03.10.2024
  • 33 Aaronson N, Elliott T, Greenhalgh J. et al. User’s guide to implementing patient-reported outcomes assessment in clinical practice (02.01.2015). Im Internet: https://bit.ly/3XNtpAx Stand: 03.10.2024
  • 34 Collins NJ, Prinsen CAC, Christensen R. et al. Knee Injury and Osteoarthritis Outcome Score (KOOS): systematic review and meta-analysis of measurement properties. Osteoarthritis Cartilage 2016; 24: 1317-1329
    CrossrefPubMedSearch in Google Scholar
  • 35 Briggs KK, Lysholm J, Tegner Y. et al. The Reliability, Validity, and Responsiveness of the Lysholm Score and Tegner Activity Scale for Anterior Cruciate Ligament Injuries of the Knee: 25 Years Later. Am J Sports Med 2009; 37: 890-897
    CrossrefPubMedSearch in Google Scholar
  • 36 Tegner Y, Lysholm J. Rating systems in the evaluation of knee ligament injuries. Clin Orthop 1985; Sep 198: 43-49
    CrossrefSearch in Google Scholar
  • 37 Baumann F, Weber J, Mahr D. et al. Joint awareness in posttraumatic osteoarthritis of the knee: validation of the forgotten joint score in long term condition after tibial plateau fracture. Health Qual Life Outcomes 2017; 15: 233
    CrossrefPubMedSearch in Google Scholar
  • 38 Fukuda W, Kawamura K, Yokoyama S. et al. A cross-sectional study to assess variability in knee frontal plane movement during single leg squat in patients with anterior cruciate ligament injury. J Bodyw Mov Ther 2021; 28: 144-149
    CrossrefPubMedSearch in Google Scholar
  • 39 Oberländer KD, Brüggemann GP, Höher J. et al. Reduced knee joint moment in ACL deficient patients at a cost of dynamic stability during landing. J Biomech 2012; 45: 1387-1392
    CrossrefPubMedSearch in Google Scholar
  • 40 Waiteman MC, Chia L, Ducatti MHM. et al. Trunk Biomechanics in Individuals with Knee Disorders: A Systematic Review with Evidence Gap Map and Meta-analysis. Sports Med Open 2022; 8: 145
    CrossrefPubMedSearch in Google Scholar
  • 41 Hill J, Bedford J, Houston D. et al. Exploring physiotherapists’ use of clinical practice guidelines, screening, and stratification tools for people with low back pain in New Zealand. N Z J Physiother 2020. Im Internet: https://bit.ly/4eOHrIK Stand: 03.10.2024
  • 42 Jacobson KE, Chi FS. Evaluation and Treatment of Medial Collateral Ligament and Medial-sided Injuries of the Knee. Sports Med Arthrosc Rev 2006; 14: 58-66
    CrossrefPubMedSearch in Google Scholar
  • 43 Kocabey Y, Tetik O, Isbell W. et al. The value of clinical examination versus magnetic resonance imaging in the diagnosis of meniscal tears and anterior cruciate ligament rupture. Arthrosc J Arthrosc Relat Surg 2004; 20: 696-700
    CrossrefPubMedSearch in Google Scholar
  • 44 Laprade RF, Bernhardson AS, Griffith CJ. et al. Correlation of Valgus Stress Radiographs with Medial Knee Ligament Injuries: An in Vitro Biomechanical Study. Am J Sports Med 2010; 38: 330-338
    CrossrefPubMedSearch in Google Scholar
  • 45 Orlando Júnior N, De Souza Leão MG, De Oliveira NHC. Diagnosis of knee injuries: comparison of the physical examination and magnetic resonance imaging with the findings from arthroscopy. Rev Bras Ortop Engl Ed 2015; 50: 712-719
    CrossrefPubMedSearch in Google Scholar
  • 46 Rose NE, Gold SM. A comparison of accuracy between clinical examination and magnetic resonance imaging in the diagnosis of meniscal and anterior cruciate ligament tears. Arthroscopy 1996; 12: 398-405
    CrossrefPubMedSearch in Google Scholar
  • 47 Blyth M, Anthony I, Francq B. et al. Diagnostic accuracy of the Thessaly test, standardised clinical history and other clinical examination tests (Apley’s, McMurray’s and joint line tenderness) for meniscal tears in comparison with magnetic resonance imaging diagnosis. Health Technol Assess 2015; 19: 1-62
    CrossrefPubMedSearch in Google Scholar
  • 48 Hashemi SA, Ranjbar MR, Tahami M. et al Comparison of Accuracy in Expert Clinical Examination versus Magnetic Resonance Imaging and Arthroscopic Exam in Diagnosis of Meniscal Tear. Adv Orthop 2020; 8 2020 1895852
    CrossrefPubMedSearch in Google Scholar
  • 49 Rayan F, Bhonsle S, Shukla DD. Clinical, MRI, and arthroscopic correlation in meniscal and anterior cruciate ligament injuries. Int Orthop 2009; 33: 129-132
    CrossrefPubMedSearch in Google Scholar
  • 50 Yan R, Wang H, Yang Z. et al. Predicted probability of meniscus tears: comparing history and physical examination with MRI. Swiss Med Wkly 2011; 14: w13314
    CrossrefPubMedSearch in Google Scholar
  • 51 Hammer S, Weber Nunes D, Hammer M. et al. Deep learning-based differentiation of peripheral high-flow and low-flow vascular malformations in T2-weighted short tau inversion recovery MRI. Clin Hemorheol Microcirc 2024; 87: 221-235
    CrossrefPubMedSearch in Google Scholar
  • 52 Lehmann L, Seidel R, Hirtz G. 3D Reference-Based Skeletal Movement Evaluation. In: Proceedings of the 3rd International Conference on Image Processing and Vision Engineering (IMPROVE 2023). Prague, Czech Republic: SCITEPRESS – Science and Technology Publications; 2023. Im Internet: https://bit.ly/3Ycif8L Stand: 03.10.2024
    CrossrefSearch in Google Scholar
  • 53 Stahlschmidt SR, Ulfenborg B, Synnergren J. Multimodal deep learning for biomedical data fusion: a review. Brief Bioinform 2022; 23: bbab569
    CrossrefPubMedSearch in Google Scholar
  • 54 Borgetto B, Tomlin GS, Max S, Brinkmann M, Spitzer L, Pfingsten A. Evidenz in der Gesundheitsversorgung: Theorie, Methoden und praktische Umsetzung. In: Haring R, Hrsg. Gesundheitswissenschaften. Berlin, Heidelberg: Springer Berlin Heidelberg; 2022
    Search in Google Scholar