Evaluating Explainable AI Methods in Deep Learning Models for Early Detection of Cerebral Palsy Article Swipe
Kimji N. Pellano
,
Inga Strümke
,
Daniel Groos
,
Lars Adde
,
Espen A. F. Ihlen
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2409.00001
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2409.00001
Early detection of Cerebral Palsy (CP) is crucial for effective intervention and monitoring. This paper tests the reliability and applicability of Explainable AI (XAI) methods using a deep learning method that predicts CP by analyzing skeletal data extracted from video recordings of infant movements. Specifically, we use XAI evaluation metrics -- namely faithfulness and stability -- to quantitatively assess the reliability of Class Activation Mapping (CAM) and Gradient-weighted Class Activation Mapping (Grad-CAM) in this specific medical application. We utilize a unique dataset of infant movements and apply skeleton data perturbations without distorting the original dynamics of the infant movements. Our CP prediction model utilizes an ensemble approach, so we evaluate the XAI metrics performances for both the overall ensemble and the individual models. Our findings indicate that both XAI methods effectively identify key body points influencing CP predictions and that the explanations are robust against minor data perturbations. Grad-CAM significantly outperforms CAM in the RISv metric, which measures stability in terms of velocity. In contrast, CAM performs better in the RISb metric, which relates to bone stability, and the RRS metric, which assesses internal representation robustness. Individual models within the ensemble show varied results, and neither CAM nor Grad-CAM consistently outperform the other, with the ensemble approach providing a representation of outcomes from its constituent models.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2409.00001
- https://arxiv.org/pdf/2409.00001
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4402952868
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4402952868Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2409.00001Digital Object Identifier
- Title
-
Evaluating Explainable AI Methods in Deep Learning Models for Early Detection of Cerebral PalsyWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-08-14Full publication date if available
- Authors
-
Kimji N. Pellano, Inga Strümke, Daniel Groos, Lars Adde, Espen A. F. IhlenList of authors in order
- Landing page
-
https://arxiv.org/abs/2409.00001Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2409.00001Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2409.00001Direct OA link when available
- Concepts
-
Cerebral palsy, Artificial intelligence, Computer science, Deep learning, Machine learning, Medicine, Physical medicine and rehabilitationTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4402952868 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2409.00001 |
| ids.doi | https://doi.org/10.48550/arxiv.2409.00001 |
| ids.openalex | https://openalex.org/W4402952868 |
| fwci | |
| type | preprint |
| title | Evaluating Explainable AI Methods in Deep Learning Models for Early Detection of Cerebral Palsy |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T14510 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.8794999718666077 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2204 |
| topics[0].subfield.display_name | Biomedical Engineering |
| topics[0].display_name | Medical Imaging and Analysis |
| topics[1].id | https://openalex.org/T10510 |
| topics[1].field.id | https://openalex.org/fields/27 |
| topics[1].field.display_name | Medicine |
| topics[1].score | 0.8730999827384949 |
| topics[1].domain.id | https://openalex.org/domains/4 |
| topics[1].domain.display_name | Health Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2742 |
| topics[1].subfield.display_name | Rehabilitation |
| topics[1].display_name | Stroke Rehabilitation and Recovery |
| topics[2].id | https://openalex.org/T11396 |
| topics[2].field.id | https://openalex.org/fields/36 |
| topics[2].field.display_name | Health Professions |
| topics[2].score | 0.835099995136261 |
| topics[2].domain.id | https://openalex.org/domains/4 |
| topics[2].domain.display_name | Health Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/3605 |
| topics[2].subfield.display_name | Health Information Management |
| topics[2].display_name | Artificial Intelligence in Healthcare |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2779421357 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7293955087661743 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q210427 |
| concepts[0].display_name | Cerebral palsy |
| concepts[1].id | https://openalex.org/C154945302 |
| concepts[1].level | 1 |
| concepts[1].score | 0.5208614468574524 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[1].display_name | Artificial intelligence |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.4895382821559906 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C108583219 |
| concepts[3].level | 2 |
| concepts[3].score | 0.48768746852874756 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[3].display_name | Deep learning |
| concepts[4].id | https://openalex.org/C119857082 |
| concepts[4].level | 1 |
| concepts[4].score | 0.42644453048706055 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[4].display_name | Machine learning |
| concepts[5].id | https://openalex.org/C71924100 |
| concepts[5].level | 0 |
| concepts[5].score | 0.2919456958770752 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11190 |
| concepts[5].display_name | Medicine |
| concepts[6].id | https://openalex.org/C99508421 |
| concepts[6].level | 1 |
| concepts[6].score | 0.18715429306030273 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2678675 |
| concepts[6].display_name | Physical medicine and rehabilitation |
| keywords[0].id | https://openalex.org/keywords/cerebral-palsy |
| keywords[0].score | 0.7293955087661743 |
| keywords[0].display_name | Cerebral palsy |
| keywords[1].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[1].score | 0.5208614468574524 |
| keywords[1].display_name | Artificial intelligence |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.4895382821559906 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/deep-learning |
| keywords[3].score | 0.48768746852874756 |
| keywords[3].display_name | Deep learning |
| keywords[4].id | https://openalex.org/keywords/machine-learning |
| keywords[4].score | 0.42644453048706055 |
| keywords[4].display_name | Machine learning |
| keywords[5].id | https://openalex.org/keywords/medicine |
| keywords[5].score | 0.2919456958770752 |
| keywords[5].display_name | Medicine |
| keywords[6].id | https://openalex.org/keywords/physical-medicine-and-rehabilitation |
| keywords[6].score | 0.18715429306030273 |
| keywords[6].display_name | Physical medicine and rehabilitation |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2409.00001 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2409.00001 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2409.00001 |
| locations[1].id | doi:10.48550/arxiv.2409.00001 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2409.00001 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5093976029 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-5423-9418 |
| authorships[0].author.display_name | Kimji N. Pellano |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Pellano, Kimji N. |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5000311801 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-1820-6544 |
| authorships[1].author.display_name | Inga Strümke |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Strümke, Inga |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5010644299 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-0676-2324 |
| authorships[2].author.display_name | Daniel Groos |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Groos, Daniel |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5033077256 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-5532-0034 |
| authorships[3].author.display_name | Lars Adde |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Adde, Lars |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5077369441 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-2469-1809 |
| authorships[4].author.display_name | Espen A. F. Ihlen |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Ihlen, Espen Alexander F. |
| authorships[4].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2409.00001 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Evaluating Explainable AI Methods in Deep Learning Models for Early Detection of Cerebral Palsy |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T14510 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.8794999718666077 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2204 |
| primary_topic.subfield.display_name | Biomedical Engineering |
| primary_topic.display_name | Medical Imaging and Analysis |
| related_works | https://openalex.org/W2731899572, https://openalex.org/W2961085424, https://openalex.org/W3215138031, https://openalex.org/W4306674287, https://openalex.org/W3009238340, https://openalex.org/W4321369474, https://openalex.org/W4360585206, https://openalex.org/W4285208911, https://openalex.org/W3046775127, https://openalex.org/W3082895349 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2409.00001 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2409.00001 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2409.00001 |
| primary_location.id | pmh:oai:arXiv.org:2409.00001 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2409.00001 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2409.00001 |
| publication_date | 2024-08-14 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 26, 79, 208 |
| abstract_inverted_index.-- | 50, 55 |
| abstract_inverted_index.AI | 22 |
| abstract_inverted_index.CP | 32, 100, 136 |
| abstract_inverted_index.In | 163 |
| abstract_inverted_index.We | 77 |
| abstract_inverted_index.an | 104 |
| abstract_inverted_index.by | 33 |
| abstract_inverted_index.in | 72, 152, 159, 168 |
| abstract_inverted_index.is | 6 |
| abstract_inverted_index.of | 2, 20, 41, 61, 82, 95, 161, 210 |
| abstract_inverted_index.so | 107 |
| abstract_inverted_index.to | 56, 174 |
| abstract_inverted_index.we | 45, 108 |
| abstract_inverted_index.CAM | 151, 165, 196 |
| abstract_inverted_index.Our | 99, 123 |
| abstract_inverted_index.RRS | 179 |
| abstract_inverted_index.XAI | 47, 111, 128 |
| abstract_inverted_index.and | 11, 18, 53, 66, 85, 119, 138, 177, 194 |
| abstract_inverted_index.are | 142 |
| abstract_inverted_index.for | 8, 114 |
| abstract_inverted_index.its | 213 |
| abstract_inverted_index.key | 132 |
| abstract_inverted_index.nor | 197 |
| abstract_inverted_index.the | 16, 59, 92, 96, 110, 116, 120, 140, 153, 169, 178, 189, 201, 204 |
| abstract_inverted_index.use | 46 |
| abstract_inverted_index.(CP) | 5 |
| abstract_inverted_index.RISb | 170 |
| abstract_inverted_index.RISv | 154 |
| abstract_inverted_index.This | 13 |
| abstract_inverted_index.body | 133 |
| abstract_inverted_index.bone | 175 |
| abstract_inverted_index.both | 115, 127 |
| abstract_inverted_index.data | 36, 88, 146 |
| abstract_inverted_index.deep | 27 |
| abstract_inverted_index.from | 38, 212 |
| abstract_inverted_index.show | 191 |
| abstract_inverted_index.that | 30, 126, 139 |
| abstract_inverted_index.this | 73 |
| abstract_inverted_index.with | 203 |
| abstract_inverted_index.(CAM) | 65 |
| abstract_inverted_index.(XAI) | 23 |
| abstract_inverted_index.Class | 62, 68 |
| abstract_inverted_index.Early | 0 |
| abstract_inverted_index.Palsy | 4 |
| abstract_inverted_index.apply | 86 |
| abstract_inverted_index.minor | 145 |
| abstract_inverted_index.model | 102 |
| abstract_inverted_index.paper | 14 |
| abstract_inverted_index.terms | 160 |
| abstract_inverted_index.tests | 15 |
| abstract_inverted_index.using | 25 |
| abstract_inverted_index.video | 39 |
| abstract_inverted_index.which | 156, 172, 181 |
| abstract_inverted_index.assess | 58 |
| abstract_inverted_index.better | 167 |
| abstract_inverted_index.infant | 42, 83, 97 |
| abstract_inverted_index.method | 29 |
| abstract_inverted_index.models | 187 |
| abstract_inverted_index.namely | 51 |
| abstract_inverted_index.other, | 202 |
| abstract_inverted_index.points | 134 |
| abstract_inverted_index.robust | 143 |
| abstract_inverted_index.unique | 80 |
| abstract_inverted_index.varied | 192 |
| abstract_inverted_index.within | 188 |
| abstract_inverted_index.Mapping | 64, 70 |
| abstract_inverted_index.against | 144 |
| abstract_inverted_index.crucial | 7 |
| abstract_inverted_index.dataset | 81 |
| abstract_inverted_index.medical | 75 |
| abstract_inverted_index.methods | 24, 129 |
| abstract_inverted_index.metric, | 155, 171, 180 |
| abstract_inverted_index.metrics | 49, 112 |
| abstract_inverted_index.models. | 122, 215 |
| abstract_inverted_index.neither | 195 |
| abstract_inverted_index.overall | 117 |
| abstract_inverted_index.relates | 173 |
| abstract_inverted_index.utilize | 78 |
| abstract_inverted_index.without | 90 |
| abstract_inverted_index.Cerebral | 3 |
| abstract_inverted_index.Grad-CAM | 148, 198 |
| abstract_inverted_index.approach | 206 |
| abstract_inverted_index.assesses | 182 |
| abstract_inverted_index.dynamics | 94 |
| abstract_inverted_index.ensemble | 105, 118, 190, 205 |
| abstract_inverted_index.evaluate | 109 |
| abstract_inverted_index.findings | 124 |
| abstract_inverted_index.identify | 131 |
| abstract_inverted_index.indicate | 125 |
| abstract_inverted_index.internal | 183 |
| abstract_inverted_index.learning | 28 |
| abstract_inverted_index.measures | 157 |
| abstract_inverted_index.original | 93 |
| abstract_inverted_index.outcomes | 211 |
| abstract_inverted_index.performs | 166 |
| abstract_inverted_index.predicts | 31 |
| abstract_inverted_index.results, | 193 |
| abstract_inverted_index.skeletal | 35 |
| abstract_inverted_index.skeleton | 87 |
| abstract_inverted_index.specific | 74 |
| abstract_inverted_index.utilizes | 103 |
| abstract_inverted_index.analyzing | 34 |
| abstract_inverted_index.approach, | 106 |
| abstract_inverted_index.contrast, | 164 |
| abstract_inverted_index.detection | 1 |
| abstract_inverted_index.effective | 9 |
| abstract_inverted_index.extracted | 37 |
| abstract_inverted_index.movements | 84 |
| abstract_inverted_index.providing | 207 |
| abstract_inverted_index.stability | 54, 158 |
| abstract_inverted_index.velocity. | 162 |
| abstract_inverted_index.(Grad-CAM) | 71 |
| abstract_inverted_index.Activation | 63, 69 |
| abstract_inverted_index.Individual | 186 |
| abstract_inverted_index.distorting | 91 |
| abstract_inverted_index.evaluation | 48 |
| abstract_inverted_index.individual | 121 |
| abstract_inverted_index.movements. | 43, 98 |
| abstract_inverted_index.outperform | 200 |
| abstract_inverted_index.prediction | 101 |
| abstract_inverted_index.recordings | 40 |
| abstract_inverted_index.stability, | 176 |
| abstract_inverted_index.Explainable | 21 |
| abstract_inverted_index.constituent | 214 |
| abstract_inverted_index.effectively | 130 |
| abstract_inverted_index.influencing | 135 |
| abstract_inverted_index.monitoring. | 12 |
| abstract_inverted_index.outperforms | 150 |
| abstract_inverted_index.predictions | 137 |
| abstract_inverted_index.reliability | 17, 60 |
| abstract_inverted_index.robustness. | 185 |
| abstract_inverted_index.application. | 76 |
| abstract_inverted_index.consistently | 199 |
| abstract_inverted_index.explanations | 141 |
| abstract_inverted_index.faithfulness | 52 |
| abstract_inverted_index.intervention | 10 |
| abstract_inverted_index.performances | 113 |
| abstract_inverted_index.Specifically, | 44 |
| abstract_inverted_index.applicability | 19 |
| abstract_inverted_index.perturbations | 89 |
| abstract_inverted_index.significantly | 149 |
| abstract_inverted_index.perturbations. | 147 |
| abstract_inverted_index.quantitatively | 57 |
| abstract_inverted_index.representation | 184, 209 |
| abstract_inverted_index.Gradient-weighted | 67 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile |