Data-Driven Quantitation of Movement Abnormality after Stroke

Parnandi, Avinash; Kaku, Aakash; Venkatesan, Anita; Pandit, Natasha; Fokas, Emily E.; Yu, Boyang; Nilsen, Dawn; Fernandez‐Granda, Carlos; Schambra, Heidi M.

doi:10.3390/bioengineering10060648

Cited by 4 publications

(2 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We previously created a functional motion taxonomy that breaks down upper extremity (UE) activities into five classes of motion elements, called functional primitives: reach, reposition, transport, stabilization, and idle (Schambra et al, 2019). Functional primitives are strung together to complete basic and instrumental ADLs (IADLs) and their identification serves as the basis for measuring movement repetitions (Parnandi et al, 2022) and movement quality (Parnandi et al, 2023). However, the functional motion taxonomy has not been applied to UE motions used in UBD.…”

Section: Introductionmentioning

confidence: 99%

A novel taxonomy to assess dressing activity in chronic stroke

Fokas,

Ahmed,

Parnandi

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Upper-body dressing (UBD) is a key aspect of motor rehabilitation after stroke, but most individuals with stroke require long-term dressing assistance. Having a measurement approach that captures the quantity and quality of dressing movements during training could support more targeted strategies. As the basis of an approach, we modified our previously developed motion taxonomy, which categorizes elemental motions into classes of functional primitives (e.g.reaches, transports, stabilizations). Three expert coders examined videos of two healthy subjects performing dressing tasks, and expanded the taxonomy to account for the unique arm and trunk motions of UBD. An expert and a trained coder then applied the expanded taxonomy to dressing videos of five chronic stroke subjects. We examined the interrater reliability (IRR) for classifying primitives. Using the expanded taxonomy, IRR for identifying primitives in UBD was overall low (k = 0.52) but varied by primitive class: IRR was moderate forreach(k = 0.75),transport(k = 0.63), andidle(k = 0.68), lower forreposition(k = 0.58), and negligible forstabilization(k = -0.02). IRR increased with increasing UE-FMA score (ρ=1, p<0.0001), indicating that the reliability of primitive classification improved with less impaired movement. With additional modification, the expanded taxonomy could support the measurement of training doses and impaired motion during dressing activities.

show abstract

Section: Introductionmentioning

confidence: 99%

A novel taxonomy to assess dressing activity in chronic stroke

Fokas,

Ahmed,

Parnandi

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…If the study used more than one model it will appear more than once. (Full description of the method names in the Appendix)115,121,123,124] ASRF[105] kNN[5,18,20,23,33, 48, 49, 59, 61, 68, 70, 71, 78, 81, 82, 86, 89, 94, 96, 103, 107, 118, 121, 123, 124] BEDT [125] CNN [6, 9, 14, 16, 17, 19, 24, 26, 30, 31, 34, 43, 45, 56, 58, 76, 77, 80, 101, 116] NN-DTW [88] LR [4, 8, 15, 20, 21, 44, 45, 55, 68, 81, 88, 94, 96, 108, 112, 121, 124] RNN [37] DT [5, 23, 25, 44, 45, 46, 48, 49, 59, 61, 74, 78, 79, 82, 103, 121, 123] CT [20] NB [5, 20, 23, 33, 45, 46, 62, 68, 70, 82, 84, 91, 92, 94] GK [20] MLP [22, 25, 45, 54, 57, 73, 81, 107, 111, 123] GRU [14] The median dataset sizes varied significantly across different medical fields. The field of General and Preventive Medicine utilized the smallest median dataset size at 24(IQR not applicable), followed by Pediatric Medicine with 36(IQR 4).…”

mentioning

confidence: 99%

The Use of Artificial Intelligence and Wearable IMUs in Medicine: A Systematic Review (Preprint)

Smits Serena,

Hinterwimmer,

Burgkart

et al. 2024

Preprint

View full text Add to dashboard Cite

BACKGROUND Artificial Intelligence (AI) has already revolutionized the analysis of image, text, and tabular data, bringing significant advances across many medical sectors. Now, by combining with Wearable Inertial Measurement Units (IMUs), AI could transform healthcare again by opening new opportunities in patient care and medical research. OBJECTIVE This systematic review aims to evaluate the integration of Artificial Intelligence (AI) with Wearable Inertial Measurement Units (IMUs) in healthcare, identifying current applications, challenges, and future opportunities. The focus will be on the types of AI models used, the characteristics of the datasets, and the potential for expanding and enhancing the use of this technology to improve patient care and advance medical research. METHODS This systematic review examines this synergy of AI and IMU data by employing a systematic methodology, following PRISMA guidelines, to explore three core questions: Which medical fields are most actively researching AI and IMU data? Which AI models are being utilized in the analysis of IMU data within these medical fields? and what are the characteristics of the datasets used for AI training in this fields? RESULTS The median dataset size is of 50 participants, which poses significant limitations for AI methods given their dependency on large datasets for effective training and generalization. Moreover, our analysis reveals the current dominance of Machine Learning models in 76% on the surveyed studies, suggesting a preference for traditional models like linear regression, support vector machine, and random forest, but also indicating significant growth potential for Deep Learning models in this area. Impressively, 93% of the studies employed Supervised Learning, revealing an underutilization of Unsupervised Learning, and indicating an important area for future exploration on discovering hidden patterns and insights without predefined labels or outcomes. Additionally, there was a preference for conducting studies in clinical settings (77%), rather than in real-life scenarios, a choice that, along with the underutilization of the full potential of wearable IMUs, is recognized as a limitation in terms of practical applicability. Furthermore, the focus of 65% of the studies on neurological issues suggests an opportunity to broaden research scope to other clinical areas such as musculoskeletal applications, where AI could have significant impacts. CONCLUSIONS In conclusion, the review calls for a collaborative effort to address the highlighted challenges, including improvements in data collection, increasing dataset sizes, a move that inherently pushes the field towards the adoption of more complex Deep Learning models, and the expansion of the application of AI on IMU data methodologies across various medical fields. This approach aims to enhance the reliability, generalizability, and clinical applicability of research findings, ultimately improving patient outcomes and advancing medical research.

show abstract

Quantifying impairment and disease severity using AI models trained on healthy subjects

Yu,

Kaku,

Liu

et al. 2024

npj Digit. Med.

View full text Add to dashboard Cite

Automatic assessment of impairment and disease severity is a key challenge in data-driven medicine. We propose a framework to address this challenge, which leverages AI models trained exclusively on healthy individuals. The COnfidence-Based chaRacterization of Anomalies (COBRA) score exploits the decrease in confidence of these models when presented with impaired or diseased patients to quantify their deviation from the healthy population. We applied the COBRA score to address a key limitation of current clinical evaluation of upper-body impairment in stroke patients. The gold-standard Fugl-Meyer Assessment (FMA) requires in-person administration by a trained assessor for 30-45 minutes, which restricts monitoring frequency and precludes physicians from adapting rehabilitation protocols to the progress of each patient. The COBRA score, computed automatically in under one minute, is shown to be strongly correlated with the FMA on an independent test cohort for two different data modalities: wearable sensors (ρ = 0.814, 95% CI [0.700,0.888]) and video (ρ = 0.736, 95% C.I [0.584, 0.838]). To demonstrate the generalizability of the approach to other conditions, the COBRA score was also applied to quantify severity of knee osteoarthritis from magnetic-resonance imaging scans, again achieving significant correlation with an independent clinical assessment (ρ = 0.644, 95% C.I [0.585,0.696]).

show abstract

Data-Driven Quantitation of Movement Abnormality after Stroke

Cited by 4 publications

References 66 publications

A novel taxonomy to assess dressing activity in chronic stroke

A novel taxonomy to assess dressing activity in chronic stroke

The Use of Artificial Intelligence and Wearable IMUs in Medicine: A Systematic Review (Preprint)

Quantifying impairment and disease severity using AI models trained on healthy subjects

Contact Info

Product

Resources

About