An Interpretable Experimental Data Augmentation Method to Improve Knee Health Classification Using Joint Acoustic Emissions.
Data augmentation
Knee health
Knee sounds
Machine learning
Journal
Annals of biomedical engineering
ISSN: 1573-9686
Titre abrégé: Ann Biomed Eng
Pays: United States
ID NLM: 0361512
Informations de publication
Date de publication:
Sep 2021
Sep 2021
Historique:
received:
09
02
2021
accepted:
24
04
2021
pubmed:
15
5
2021
medline:
27
1
2022
entrez:
14
5
2021
Statut:
ppublish
Résumé
The characteristics of joint acoustic emissions (JAEs) measured from the knee have been shown to contain information regarding underlying joint health. Researchers have developed methods to process JAE measurements and combined them with machine learning algorithms for knee injury diagnosis. While these methods are based on JAEs measured in controlled settings, we anticipate that JAE measurements could enable accessible and affordable diagnosis of acute knee injuries also in field-deployable settings. However, in such settings, the noise and interference would be greater than in sterile, laboratory environments, which could decrease the performance of existing knee health classification methods using JAEs. To address the need for an objective noise and interference detection method for JAE measurements as a step towards field-deployable settings, we propose a novel experimental data augmentation method to locate and then, remove the corrupted parts of JAEs measured in clinical settings. In the clinic, we recruited 30 participants, and collected data from both knees, totaling 60 knees (36 healthy and 24 injured knees) to be used subsequently for knee health classification. We also recruited 10 healthy participants to collect artifact and joint sounds (JS) click templates, which are audible, short duration and high amplitude JAEs from the knee. Spectral and temporal features were extracted, and clinical data was augmented in five-dimensional subspace by fusing the existing clinical dataset into experimentally collected templates. Then knee scores were calculated by training and testing a linear soft classifier utilizing leave-one-subject-out cross-validation (LOSO-CV). The area under the curve (AUC) was 0.76 for baseline performance without any window removal with a logistic regression classifier (sensitivity = 0.75, specificity = 0.78). We obtained an AUC of 0.86 with the proposed algorithm (sensitivity = 0.80, specificity = 0.89), and on average, 95% of all clinical data was used to achieve this performance. The proposed algorithm improved knee health classification performance by the added information through identification and collection of common artifact sources in JAE measurements. This method when combined with wearable systems could provide clinically relevant supplementary information for both underserved populations and individuals requiring point-of-injury diagnosis in field-deployable settings.
Identifiants
pubmed: 33987807
doi: 10.1007/s10439-021-02788-x
pii: 10.1007/s10439-021-02788-x
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
2399-2411Subventions
Organisme : NIBIB NIH HHS
ID : 1R01EB023808
Pays : United States
Organisme : NIBIB NIH HHS
ID : 1R01EB023808
Pays : United States
Informations de copyright
© 2021. Biomedical Engineering Society.
Références
Anderson, A. F., and A. B. Lipscomb. Clinical diagnosis of meniscal tearsXX Description of a new manipulative test. Am. J. Sports Med. 14(4):291–293, 1986. https://doi.org/10.1177/036354658601400408 .
doi: 10.1177/036354658601400408
pubmed: 3755297
Blodgett, W. E. Auscultation of the knee joint. Bost. Med. Surg. J. 146(3):63–66, 1902. https://doi.org/10.1056/nejm190201161460304 .
doi: 10.1056/nejm190201161460304
Bolus, N. B., H. K. Jeong, D. C. Whittingslow, and O. T. Inan. A glove-based form factor for collecting joint acoustic emissions: design and validation. Sensors (Switzerland). 19:12, 2019. https://doi.org/10.3390/s19122683 .
doi: 10.3390/s19122683
Caine, D. J., and Y. M. Golightly. Osteoarthritis as an outcome of paediatric sport: An epidemiological perspective. Br. J. Sports Med. 45(4):298–303, 2011. https://doi.org/10.1136/bjsm.2010.081984 .
doi: 10.1136/bjsm.2010.081984
pubmed: 21330645
Coravos, A., S. Khozin, and K. D. Mandl. Developing and adopting safe and effective digital biomarkers to improve patient outcomes. npj Digit Med. 2:1, 2019. https://doi.org/10.1038/s41746-019-0090-4 .
doi: 10.1038/s41746-019-0090-4
Donaldson, W. F., R. F. Warren, and T. Wickiewicz. A comparison of acute anterior cruciate ligament examinations: Initial versus examination under anesthesia. Am. J. Sports Med. 13(1):5–10, 1985. https://doi.org/10.1177/036354658501300102 .
doi: 10.1177/036354658501300102
pubmed: 3976980
Evans, P. J., G. D. Bell, and C. Frank. Prospective evaluation of the McMurray test. Am. J. Sports Med. 21(4):604–608, 1993. https://doi.org/10.1177/036354659302100420 .
doi: 10.1177/036354659302100420
pubmed: 8368424
Falzon, O., A. Ciantar, L. Sammut, et al. Principal component analysis of dynamic thermography data from pregnant and non-pregnant women. Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS. 2018. https://doi.org/10.1109/embc.2018.8513497 .
doi: 10.1109/embc.2018.8513497
Frobell, R. B., H. P. Roos, E. M. Roos, et al. The acutely ACL injured knee assessed by MRI: are large volume traumatic bone marrow lesions a sign of severe compression injury? Osteoarthr Cartil. 16(7):829–836, 2008. https://doi.org/10.1016/j.joca.2007.11.003 .
doi: 10.1016/j.joca.2007.11.003
Gage, B. E., N. M. McIlvain, C. L. Collins, S. K. Fields, and R. D. Comstock. Epidemiology of 6.6 million knee injuries presenting to United States emergency departments from 1999 through 2008. Acad. Emerg. Med. 19(4):378–385, 2012. https://doi.org/10.1111/j.1553-2712.2012.01315.x .
doi: 10.1111/j.1553-2712.2012.01315.x
pubmed: 22506941
Gharehbaghi, S., D.C Whittingslow, L.A Ponder, S. Prahalad OI. Joint acoustic emissions as a biomarker for knee health assessment in loaded and unloaded exercises. In: American Society of Biomechanics Annual Meeting; 2020:106.
Gitajn, I., and E. Rodriguez. Biomech. Musculoskeletal. Injury 20:11, 2011. https://doi.org/10.5772/20672 .
doi: 10.5772/20672
Inan, O. T., P. Tenaerts, S. A. Prindiville, et al. Digitizing clinical trials. npj Digit Med. 3(1):20, 2020. https://doi.org/10.1038/s41746-020-0302-y .
doi: 10.1038/s41746-020-0302-y
Järvinen, T. L. N., R. Sihvonen, and M. Englund. Arthroscopy for degenerative knee—A difficult habit to break? Acta Orthop. 85(3):215–217, 2014. https://doi.org/10.3109/17453674.2014.922736 .
doi: 10.3109/17453674.2014.922736
pubmed: 24847793
pmcid: 4062784
Jiang, C. C., Y. J. Liu, K. M. Yip, S. E. Fu, and J. L. Su. Vibration arthrometry of the knee with torn meniscus: a preliminary report. J. Formos Med. Assoc. 93(7):622–625, 1994.
pubmed: 7866062
Katz, J. W., and R. J. Fingeroth. The diagnostic accuracy of ruptures of the anterior cruciate ligament comparing the Lachman test, the anterior drawer sign, and the pivot shift test in acute and chronic knee injuries. Am. J. Sports Med. 14(1):88–91, 1986. https://doi.org/10.1177/036354658601400115 .
doi: 10.1177/036354658601400115
pubmed: 3752353
Kernohan, W. G., D. E. Beverland, G. F. Mccoy, A. Hamilton, P. Watson, and R. Mollan. Vibration arthrometry. Acta Orthop. 61(1):70–79, 1990. https://doi.org/10.3109/17453679008993071 .
doi: 10.3109/17453679008993071
Kim, S., J. Bosque, J. P. Meehan, A. Jamali, and R. Marder. Increase in outpatient knee arthroscopy in the United States: A comparison of national surveys of ambulatory surgery, 1996 and 2006. J. Bone Jt Surg.-Am. 93(11):994–1000, 2011. https://doi.org/10.2106/JBJS.I.01618 .
doi: 10.2106/JBJS.I.01618
Krishnan, S., R. M. Rangayyan, G. D. Bell, C. B. Frank, and K. O. Ladly. Adaptive filtering, modelling and classification of knee joint vibroarthrographic signals for non-invasive diagnosis of articular cartilage pathology. Med. Biol. Eng. Comput. 35(6):677–684, 1997. https://doi.org/10.1007/BF02510977 .
doi: 10.1007/BF02510977
pubmed: 9538545
Loos, W. C., J. M. Fox, M. E. Blazina, W. Del Pizzo, and M. J. Friedman. Acute posterior cruciate ligament injuries. Am. J. Sports Med. 9(2):86–92, 1981. https://doi.org/10.1177/036354658100900203 .
doi: 10.1177/036354658100900203
pubmed: 7223926
Lysholm, J., J. Gillquist, and S. O. Liljedahl. Arthroscopy in the early diagnosis of injuries to the knee joint. Acta Orthop. 52(1):111–118, 1981. https://doi.org/10.3109/17453678108991770 .
doi: 10.3109/17453678108991770
Mahalanobis, P. C. On the generalized distance in statistics. Natl. Inst. Sci. India 2:49–55, 1936.
Malanga, G. A., S. Andrus, S. F. Nadler, and J. McLean. Physical examination of the knee: A review of the original test description and scientific validity of common orthopedic tests. Arch Phys Med Rehabil. 84(4):592–603, 2003. https://doi.org/10.1053/apmr.2003.50026 .
doi: 10.1053/apmr.2003.50026
pubmed: 12690600
McClure, P. W., J. M. Rothstein, and D. L. Riddle. Intertester reliability of clinical judgments of medial knee ligament integrity. Phys. Ther. 69(4):268–275, 1989. https://doi.org/10.1093/ptj/69.4.268 .
doi: 10.1093/ptj/69.4.268
pubmed: 2928393
McCoy, G.F., J.D. McCrea, D.E. Beverland, W.G. Kernohan, R.A. Mollan, Vibration arthrography as a diagnostic aid in diseases of the knee. A preliminary report. J Bone Joint Surg Br. 1987;69(2):288–293. Accessed March 20, 2020. http://www.ncbi.nlm.nih.gov/pubmed/3818762
Ozmen, G. C., M. Safaei, L. Lan, and O. T. Inan. A novel accelerometer mounting method for sensing performance improvement in acoustic measurements from the knee. J. Vib. Acoust. 143(3):1–27, 2020. https://doi.org/10.1115/1.4048554 .
doi: 10.1115/1.4048554
Ozmen, G. C., M. Safaei, B. Semiz, et al. Detection of meniscal tear effects on tibial vibration using passive knee sound measurements. IEEE Trans. Biomed. Eng. 202:1–1, 2021. https://doi.org/10.1109/tbme.2020.3048930 .
doi: 10.1109/tbme.2020.3048930
Penn-Barwell, J. G., S. A. G. Roberts, M. J. Midwinter, and J. R. B. Bishop. Improved survival in UK combat casualties from Iraq and Afghanistan: 2003-2012. J. Trauma Acute Care Surg. 78(5):1014–1020, 2015. https://doi.org/10.1097/TA.0000000000000580 .
doi: 10.1097/TA.0000000000000580
pubmed: 25909424
Petersson, I. F. Occurrence of osteoarthritis of the peripheral joints in European populations. Ann. Rheum. Dis. 55:659–661, 1996. https://doi.org/10.1136/ard.55.9.659 .
doi: 10.1136/ard.55.9.659
pubmed: 8882143
pmcid: 1010270
Rangayyan, R. M., and Y. F. Wu. Screening of knee-joint vibroarthrographic signals using statistical parameters and radial basis functions. Med. Biol. Eng. Comput. 46(3):223–232, 2008. https://doi.org/10.1007/s11517-007-0278-7 .
doi: 10.1007/s11517-007-0278-7
pubmed: 17960443
Ricci, J. A., W. F. Stewart, E. Chee, C. Leotta, K. Foley, and M. C. Hochberg. Pain exacerbation as a major source of lost productive time in US workers with arthritis. Arthritis Rheum. 53(5):673–681, 2005. https://doi.org/10.1002/art.21453 .
doi: 10.1002/art.21453
pubmed: 16208644
Rubinstein, R. A., K. D. Shelbourne, J. R. McCarroll, C. D. Vanmeter, and A. C. Rettig. The accuracy of the clinical examination in the setting of posterior cruciate ligament injuries. Am. J. Sports Med. 22(4):550–557, 1994. https://doi.org/10.1177/036354659402200419 .
doi: 10.1177/036354659402200419
pubmed: 7943523
Safaei, M., N. B. Bolus, D. C. Whittingslow, H. K. Jeong, A. Erturk, and O. T. Inan. Vibration stimulation as a non-invasive approach to monitor the severity of meniscus tears. IEEE Trans. Neural. Syst. Rehabil. Eng. 20:21, 2021. https://doi.org/10.1109/tnsre.2021.3050439 .
doi: 10.1109/tnsre.2021.3050439
Sallay, P. I., J. Poggi, K. P. Speer, and W. E. Garrett. Acute dislocation of the patella: A correlative pathoanatomic study. Am. J. Sports Med. 24(1):52–60, 1996. https://doi.org/10.1177/036354659602400110 .
doi: 10.1177/036354659602400110
pubmed: 8638754
Schneider, S., B. Seither, S. Tönges, and H. Schmitt. Sports injuries: Population based representative data on incidence, diagnosis, sequelae, and high risk groups. Br. J. Sports Med. 40(4):334–339, 2006. https://doi.org/10.1136/bjsm.2005.022889 .
doi: 10.1136/bjsm.2005.022889
pubmed: 16556789
pmcid: 2586164
Sun, Y., M. S. Kamel, A. K. C. Wong, and Y. Wang. Cost-sensitive boosting for classification of imbalanced data. Pattern Recognit. 40(12):3358–3378, 2007. https://doi.org/10.1016/j.patcog.2007.04.009 .
doi: 10.1016/j.patcog.2007.04.009
Teague, C. N., J. A. Heller, B. N. Nevius, et al. A wearable, multimodal sensing system to monitor knee joint health. IEEE Sens. J. 2020. https://doi.org/10.1109/jsen.2020.2994552 .
doi: 10.1109/jsen.2020.2994552
Thomeé, R., J. Augustsson, and J. Karlsson. Patellofemoral pain syndrome. A review of current issues. Sport Med. 28(4):245–262, 1999. https://doi.org/10.2165/00007256-199928040-00003 .
doi: 10.2165/00007256-199928040-00003
Umapathy, K., and S. Krishnan. Modified local discriminant bases algorithm and its application in analysis of human knee joint vibration signals. IEEE Trans. Biomed. Eng. 53(3):517–523, 2006. https://doi.org/10.1109/TBME.2005.869787 .
doi: 10.1109/TBME.2005.869787
pubmed: 16532778
Vigdorchik, J. M., J. J. Nepple, N. Eftekhary, M. Leunig, and J. C. Clohisy. What is the association of elite sporting activities with the development of hip osteoarthritis? Am. J. Sports Med. 45(4):961–964, 2017. https://doi.org/10.1177/0363546516656359 .
doi: 10.1177/0363546516656359
pubmed: 27474380
Whittingslow, D. C., H. K. Jeong, V. G. Ganti, N. J. Kirkpatrick, G. F. Kogler, and O. T. Inan. Acoustic Emissions as a Non-invasive Biomarker of the Structural Health of the Knee. Ann. Biomed. Eng. 48(1):225–235, 2020. https://doi.org/10.1007/s10439-019-02333-x .
doi: 10.1007/s10439-019-02333-x
pubmed: 31350620
Whittingslow, D., J. Zia, S. Gharehbaghi, et al. Knee acoustic emissions as a digital biomarker of disease status in juvenile idiopathic arthritis. Front. Digit. Heal. 2:36, 2020. https://doi.org/10.3389/FDGTH.2020.571839 .
doi: 10.3389/FDGTH.2020.571839