Wearable airbag technology and machine learned models to mitigate falls after stroke
Abstract Background Falls are a common complication experienced after a stroke and can cause serious detriments to physical health and social mobility, necessitating a dire need for intervention. Among recent advancements, wearable airbag technology has been designed to detect and mitigate fall impa...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-06-01
|
| Series: | Journal of NeuroEngineering and Rehabilitation |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12984-022-01040-4 |
| _version_ | 1829115622177374208 |
|---|---|
| author | Olivia K. Botonis Yaar Harari Kyle R. Embry Chaithanya K. Mummidisetty David Riopelle Matt Giffhorn Mark V. Albert Vallery Heike Arun Jayaraman |
| author_facet | Olivia K. Botonis Yaar Harari Kyle R. Embry Chaithanya K. Mummidisetty David Riopelle Matt Giffhorn Mark V. Albert Vallery Heike Arun Jayaraman |
| author_sort | Olivia K. Botonis |
| collection | DOAJ |
| description | Abstract Background Falls are a common complication experienced after a stroke and can cause serious detriments to physical health and social mobility, necessitating a dire need for intervention. Among recent advancements, wearable airbag technology has been designed to detect and mitigate fall impact. However, these devices have not been designed nor validated for the stroke population and thus, may inadequately detect falls in individuals with stroke-related motor impairments. To address this gap, we investigated whether population-specific training data and modeling parameters are required to pre-detect falls in a chronic stroke population. Methods We collected data from a wearable airbag’s inertial measurement units (IMUs) from individuals with (n = 20 stroke) and without (n = 15 control) history of stroke while performing a series of falls (842 falls total) and non-falls (961 non-falls total) in a laboratory setting. A leave-one-subject-out crossvalidation was used to compare the performance of two identical machine learned models (adaptive boosting classifier) trained on cohort-dependent data (control or stroke) to pre-detect falls in the stroke cohort. Results The average performance of the model trained on stroke data (recall = 0.905, precision = 0.900) had statistically significantly better recall (P = 0.0035) than the model trained on control data (recall = 0.800, precision = 0.944), while precision was not statistically significantly different. Stratifying models trained on specific fall types revealed differences in pre-detecting anterior–posterior (AP) falls (stroke-trained model’s F1-score was 35% higher, P = 0.019). Using activities of daily living as non-falls training data (compared to near-falls) significantly increased the AUC (Area under the receiver operating characteristic) for classifying AP falls for both models (P < 0.04). Preliminary analysis suggests that users with more severe stroke impairments benefit further from a stroke-trained model. The optimal lead time (time interval pre-impact to detect falls) differed between control- and stroke-trained models. Conclusions These results demonstrate the importance of population sensitivity, non-falls data, and optimal lead time for machine learned pre-impact fall detection specific to stroke. Existing fall mitigation technologies should be challenged to include data of neurologically impaired individuals in model development to adequately detect falls in other high fall risk populations. Trial registration https://clinicaltrials.gov/ct2/show/NCT05076565 ; Unique Identifier: NCT05076565. Retrospectively registered on 13 October 2021 |
| first_indexed | 2024-12-12T16:20:16Z |
| format | Article |
| id | doaj.art-f663806fdb764370a6fda80583799e18 |
| institution | Directory Open Access Journal |
| issn | 1743-0003 |
| language | English |
| last_indexed | 2024-12-12T16:20:16Z |
| publishDate | 2022-06-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of NeuroEngineering and Rehabilitation |
| spelling | doaj.art-f663806fdb764370a6fda80583799e182022-12-22T00:19:01ZengBMCJournal of NeuroEngineering and Rehabilitation1743-00032022-06-0119111410.1186/s12984-022-01040-4Wearable airbag technology and machine learned models to mitigate falls after strokeOlivia K. Botonis0Yaar Harari1Kyle R. Embry2Chaithanya K. Mummidisetty3David Riopelle4Matt Giffhorn5Mark V. Albert6Vallery Heike7Arun Jayaraman8Max Nader Rehabilitation Technologies and Outcomes Lab, Shirley Ryan AbilityLabMax Nader Rehabilitation Technologies and Outcomes Lab, Shirley Ryan AbilityLabMax Nader Rehabilitation Technologies and Outcomes Lab, Shirley Ryan AbilityLabMax Nader Rehabilitation Technologies and Outcomes Lab, Shirley Ryan AbilityLabDepartment of Physical Medicine and Rehabilitation, Northwestern UniversityMax Nader Rehabilitation Technologies and Outcomes Lab, Shirley Ryan AbilityLabDepartment of Computer Science and Engineering, Department of Biomedical Engineering, University of North TexasDepartment of BioMechanical Engineering, Delft University of TechnologyMax Nader Rehabilitation Technologies and Outcomes Lab, Shirley Ryan AbilityLabAbstract Background Falls are a common complication experienced after a stroke and can cause serious detriments to physical health and social mobility, necessitating a dire need for intervention. Among recent advancements, wearable airbag technology has been designed to detect and mitigate fall impact. However, these devices have not been designed nor validated for the stroke population and thus, may inadequately detect falls in individuals with stroke-related motor impairments. To address this gap, we investigated whether population-specific training data and modeling parameters are required to pre-detect falls in a chronic stroke population. Methods We collected data from a wearable airbag’s inertial measurement units (IMUs) from individuals with (n = 20 stroke) and without (n = 15 control) history of stroke while performing a series of falls (842 falls total) and non-falls (961 non-falls total) in a laboratory setting. A leave-one-subject-out crossvalidation was used to compare the performance of two identical machine learned models (adaptive boosting classifier) trained on cohort-dependent data (control or stroke) to pre-detect falls in the stroke cohort. Results The average performance of the model trained on stroke data (recall = 0.905, precision = 0.900) had statistically significantly better recall (P = 0.0035) than the model trained on control data (recall = 0.800, precision = 0.944), while precision was not statistically significantly different. Stratifying models trained on specific fall types revealed differences in pre-detecting anterior–posterior (AP) falls (stroke-trained model’s F1-score was 35% higher, P = 0.019). Using activities of daily living as non-falls training data (compared to near-falls) significantly increased the AUC (Area under the receiver operating characteristic) for classifying AP falls for both models (P < 0.04). Preliminary analysis suggests that users with more severe stroke impairments benefit further from a stroke-trained model. The optimal lead time (time interval pre-impact to detect falls) differed between control- and stroke-trained models. Conclusions These results demonstrate the importance of population sensitivity, non-falls data, and optimal lead time for machine learned pre-impact fall detection specific to stroke. Existing fall mitigation technologies should be challenged to include data of neurologically impaired individuals in model development to adequately detect falls in other high fall risk populations. Trial registration https://clinicaltrials.gov/ct2/show/NCT05076565 ; Unique Identifier: NCT05076565. Retrospectively registered on 13 October 2021https://doi.org/10.1186/s12984-022-01040-4Pre-impact fall detectionFall mitigationMachine-learningWearable sensorsStrokeInjury prevention |
| spellingShingle | Olivia K. Botonis Yaar Harari Kyle R. Embry Chaithanya K. Mummidisetty David Riopelle Matt Giffhorn Mark V. Albert Vallery Heike Arun Jayaraman Wearable airbag technology and machine learned models to mitigate falls after stroke Journal of NeuroEngineering and Rehabilitation Pre-impact fall detection Fall mitigation Machine-learning Wearable sensors Stroke Injury prevention |
| title | Wearable airbag technology and machine learned models to mitigate falls after stroke |
| title_full | Wearable airbag technology and machine learned models to mitigate falls after stroke |
| title_fullStr | Wearable airbag technology and machine learned models to mitigate falls after stroke |
| title_full_unstemmed | Wearable airbag technology and machine learned models to mitigate falls after stroke |
| title_short | Wearable airbag technology and machine learned models to mitigate falls after stroke |
| title_sort | wearable airbag technology and machine learned models to mitigate falls after stroke |
| topic | Pre-impact fall detection Fall mitigation Machine-learning Wearable sensors Stroke Injury prevention |
| url | https://doi.org/10.1186/s12984-022-01040-4 |
| work_keys_str_mv | AT oliviakbotonis wearableairbagtechnologyandmachinelearnedmodelstomitigatefallsafterstroke AT yaarharari wearableairbagtechnologyandmachinelearnedmodelstomitigatefallsafterstroke AT kylerembry wearableairbagtechnologyandmachinelearnedmodelstomitigatefallsafterstroke AT chaithanyakmummidisetty wearableairbagtechnologyandmachinelearnedmodelstomitigatefallsafterstroke AT davidriopelle wearableairbagtechnologyandmachinelearnedmodelstomitigatefallsafterstroke AT mattgiffhorn wearableairbagtechnologyandmachinelearnedmodelstomitigatefallsafterstroke AT markvalbert wearableairbagtechnologyandmachinelearnedmodelstomitigatefallsafterstroke AT valleryheike wearableairbagtechnologyandmachinelearnedmodelstomitigatefallsafterstroke AT arunjayaraman wearableairbagtechnologyandmachinelearnedmodelstomitigatefallsafterstroke |