1
|
Darevsky DM, Hu DA, Gomez FA, Davies MR, Liu X, Feeley BT. Algorithmic assessment of shoulder function using smartphone video capture and machine learning. Sci Rep 2023; 13:19986. [PMID: 37968288 PMCID: PMC10652003 DOI: 10.1038/s41598-023-46966-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2023] [Accepted: 11/07/2023] [Indexed: 11/17/2023] Open
Abstract
Tears within the stabilizing muscles of the shoulder, known as the rotator cuff (RC), are the most common cause of shoulder pain-often presenting in older patients and requiring expensive advanced imaging for diagnosis. Despite the high prevalence of RC tears within the elderly population, there is no previously published work examining shoulder kinematics using markerless motion capture in the context of shoulder injury. Here we show that a simple string pulling behavior task, where subjects pull a string using hand-over-hand motions, provides a reliable readout of shoulder mobility across animals and humans. We find that both mice and humans with RC tears exhibit decreased movement amplitude, prolonged movement time, and quantitative changes in waveform shape during string pulling task performance. In rodents, we further note the degradation of low dimensional, temporally coordinated movements after injury. Furthermore, a logistic regression model built on our biomarker ensemble succeeds in classifying human patients as having a RC tear with > 90% accuracy. Our results demonstrate how a combined framework bridging animal models, motion capture, convolutional neural networks, and algorithmic assessment of movement quality enables future research into the development of smartphone-based, at-home diagnostic tests for shoulder injury.
Collapse
Affiliation(s)
- David M Darevsky
- Bioengineering Graduate Program, University of California San Francisco, San Francisco, CA, USA
- Bioengineering Graduate Program, University of California Berkeley, Berkeley, CA, USA
- Medical Scientist Training Program, University of California San Francisco, San Francisco, CA, USA
- Department of Orthopaedic Surgery, University of California San Francisco, San Francisco, USA
- Department of Neurology, University of California San Francisco, San Francisco, CA, USA
- San Francisco Veterans Affairs Health Care System, San Francisco, USA
- Neurology and Rehabilitation Service, San Francisco Veterans Affairs Medical Center, San Francisco, CA, USA
| | - Daniel A Hu
- Department of Orthopaedic Surgery, University of California San Francisco, San Francisco, USA
- San Francisco Veterans Affairs Health Care System, San Francisco, USA
| | - Francisco A Gomez
- Department of Orthopaedic Surgery, University of California San Francisco, San Francisco, USA
- San Francisco Veterans Affairs Health Care System, San Francisco, USA
| | - Michael R Davies
- Department of Orthopaedic Surgery, University of California San Francisco, San Francisco, USA
- San Francisco Veterans Affairs Health Care System, San Francisco, USA
| | - Xuhui Liu
- Department of Orthopaedic Surgery, University of California San Francisco, San Francisco, USA
- San Francisco Veterans Affairs Health Care System, San Francisco, USA
| | - Brian T Feeley
- Department of Orthopaedic Surgery, University of California San Francisco, San Francisco, USA.
- San Francisco Veterans Affairs Health Care System, San Francisco, USA.
| |
Collapse
|
2
|
Darevsky DM, Hu DA, Gomez FA, Davies MR, Liu X, Feeley BT. A Tool for Low-Cost, Quantitative Assessment of Shoulder Function Using Machine Learning. medRxiv 2023:2023.04.14.23288613. [PMID: 37131827 PMCID: PMC10153347 DOI: 10.1101/2023.04.14.23288613] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/04/2023]
Abstract
Tears within the stabilizing muscles of the shoulder, known as the rotator cuff (RC), are the most common cause of shoulder pain-often presenting in older patients and requiring expensive, advanced imaging for diagnosis1-4. Despite the high prevalence of RC tears within the elderly population, there are no accessible and low-cost methods to assess shoulder function which can eschew the barrier of an in-person physical exam or imaging study. Here we show that a simple string pulling behavior task, where subjects pull a string using hand-over-hand motions, provides a reliable readout of shoulder health across animals and humans. We find that both mice and humans with RC tears exhibit decreased movement amplitude, prolonged movement time, and quantitative changes in waveform shape during string pulling task performance. In rodents, we further note the degradation of low dimensional, temporally coordinated movements after injury. Furthermore, a predictive model built on our biomarker ensemble succeeds in classifying human patients as having a RC tear with >90% accuracy. Our results demonstrate how a combined framework bridging task kinematics, machine learning, and algorithmic assessment of movement quality enables future development of smartphone-based, at-home diagnostic tests for shoulder injury.
Collapse
Affiliation(s)
- David M. Darevsky
- Bioengineering Graduate Program, University of California San Francisco and University of California Berkeley, San Francisco, CA and Berkeley, CA
- Medical Scientist Training Program, University of California San Francisco, San Francisco, CA
- University of California, San Francisco, Department of Orthopaedic Surgery
- Department of Neurology, University of California San Francisco, San Francisco, CA
- San Francisco Veterans Affairs Health Care System
- Neurology and Rehabilitation Service, San Francisco Veterans Affairs Medical Center, San Francisco, CA, USA
| | - Daniel A. Hu
- University of California, San Francisco, Department of Orthopaedic Surgery
- San Francisco Veterans Affairs Health Care System
| | - Francisco A. Gomez
- University of California, San Francisco, Department of Orthopaedic Surgery
- San Francisco Veterans Affairs Health Care System
| | - Michael R. Davies
- University of California, San Francisco, Department of Orthopaedic Surgery
- San Francisco Veterans Affairs Health Care System
| | - Xuhui Liu
- University of California, San Francisco, Department of Orthopaedic Surgery
- San Francisco Veterans Affairs Health Care System
| | - Brian T. Feeley
- University of California, San Francisco, Department of Orthopaedic Surgery
- San Francisco Veterans Affairs Health Care System
| |
Collapse
|
3
|
Hung NJ, Darevsky DM, Pandya NK. Pediatric and Adolescent Shoulder Instability: Does Insurance Status Predict Delays in Care, Outcomes, and Complication Rate? Orthop J Sports Med 2020; 8:2325967120959330. [PMID: 33178878 PMCID: PMC7592322 DOI: 10.1177/2325967120959330] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/12/2020] [Accepted: 05/08/2020] [Indexed: 12/16/2022] Open
Abstract
Background: Recurrent shoulder instability results from overuse injuries that are often associated with athletic activity. Timely diagnosis and treatment are necessary to prevent further dislocations and secondary joint damage. In pediatric and adolescent patients, insurance status is a potential barrier to accessing timely care that has not yet been explored. Purpose: To examine the effect of insurance status on access to clinical consultation, surgical intervention, and surgical outcome of pediatric and adolescent patients with recurrent shoulder instability. Study Design: Cohort study; Level of evidence, 3. Methods: We conducted a retrospective review of pediatric and adolescent patients who were treated at a single tertiary children’s hospital for recurrent shoulder instability between 2011 and 2017. Patients were sorted into private and public insurance cohorts. Dates of injury, consultation, and surgery were recorded. Number of previous dislocations, magnetic resonance imaging (MRI) results, surgical findings, and postoperative complications were also noted. Delays in care were compared between the cohorts. The presence of isolated anterior versus complex labral pathology as well as bony involvement at the time of surgery was recorded. The incidences of labral pathology and secondary bony injury were then compared between the 2 cohorts. Postoperative notes were reviewed to compare rates of repeat dislocation and repeat surgery. Results: A total of 37 patients had public insurance, while 18 patients had private insurance. Privately insured patients were evaluated nearly 5 times faster than were publicly insured patients (P < .001), and they obtained MRI scans over 4 times faster than did publicly insured patients (P < .001). Publicly insured patients were twice as likely to have secondary bony injuries (P = .016). Postoperatively, a significantly greater number (24.3%) of publicly insured patients experienced redislocation versus the complete absence of redislocation in the privately insured patients (P = .022). Conclusion: Public insurance status affected access to care and was correlated with the development of secondary bony injury and a higher rate of postoperative dislocations. Clinicians should practice with increased awareness of how public insurance status can significantly affect patient outcomes by delaying access to care—particularly if delays lead to increased patient morbidity and health care costs.
Collapse
Affiliation(s)
- Nicole J Hung
- School of Medicine, University of California, San Francisco, San Francisco, California, USA
| | - David M Darevsky
- School of Medicine, University of California, San Francisco, San Francisco, California, USA
| | - Nirav K Pandya
- Department of Orthopaedic Surgery, University of California, San Francisco, San Francisco, California, USA
| |
Collapse
|
4
|
Miller AM, Miocinovic S, Swann NC, Rajagopalan SS, Darevsky DM, Gilron R, de Hemptinne C, Ostrem JL, Starr PA. Effect of levodopa on electroencephalographic biomarkers of the parkinsonian state. J Neurophysiol 2019; 122:290-299. [PMID: 31066605 DOI: 10.1152/jn.00141.2019] [Citation(s) in RCA: 23] [Impact Index Per Article: 4.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022] Open
Abstract
The objective of this study was to evaluate proposed electroencephalographic (EEG) biomarkers of Parkinson's disease (PD) and test their correlation with motor impairment in a new, well-characterized cohort of PD patients and controls. Sixty-four-channel EEG was recorded from 14 patients with rigid-akinetic PD with minimal tremor and from 14 age-matched healthy controls at rest and during voluntary movement. Patients were tested off and on medication during a single session. Recordings were analyzed for phase-amplitude coupling over sensorimotor cortex and for pairwise coherence from all electrode pairs in the recording montage (distributed coherence). Phase-amplitude coupling and distributed coherence were found to be elevated Off compared with On levodopa, and their reduction was correlated with motor improvement. In the Off medication state, phase-amplitude coupling was greater in sensorimotor contacts contralateral to the most affected body part and reduced by voluntary movement. We conclude that phase-amplitude coupling and distributed coherence are cortical biomarkers of the parkinsonian state that are detectable noninvasively and may be useful as objective aids for management of dopaminergic therapy. Several analytic methods may be used for noninvasive measurement of abnormal brain synchronization in PD. Calculation of phase-amplitude coupling requires only a single electrode over motor cortex. NEW & NOTEWORTHY Several EEG biomarkers of the parkinsonian state have been proposed that are related to abnormal cortical synchronization. We report several new findings in this study: correlations of EEG markers of synchronization with specific motor signs of Parkinson's disease (PD), and demonstration that one of the EEG markers, phase-amplitude coupling, is more elevated over the more clinically affected brain hemisphere. These findings underscore the potential utility of scalp EEG for objective, noninvasive monitoring of medication state in PD.
Collapse
Affiliation(s)
- Andrew M Miller
- Department of Neurological Surgery, University of California , San Francisco, California.,School of Medicine, University of Kansas , Kansas City, Kansas
| | | | - Nicole C Swann
- Department of Human Physiology, University of Oregon , Eugene, Oregon
| | - Sheila S Rajagopalan
- Department of Neurological Surgery, University of California , San Francisco, California
| | - David M Darevsky
- Department of Neurological Surgery, University of California , San Francisco, California.,Graduate Program in Neuroscience, University of California , San Francisco, California
| | - Ro'ee Gilron
- Department of Neurological Surgery, University of California , San Francisco, California
| | - Coralie de Hemptinne
- Department of Neurological Surgery, University of California , San Francisco, California
| | - Jill L Ostrem
- Department of Neurology, University of California , San Francisco, California.,Parkinson's Disease Research, Education and Clinical Center at the San Francisco Veteran's Affairs Medical Center , San Francisco, California
| | - Philip A Starr
- Department of Neurological Surgery, University of California , San Francisco, California.,Parkinson's Disease Research, Education and Clinical Center at the San Francisco Veteran's Affairs Medical Center , San Francisco, California.,Graduate Program in Neuroscience, University of California , San Francisco, California
| |
Collapse
|