Why I'm not Answering: Understanding Determinants of Classification of\n an Abstaining Classifier for Cancer Pathology Reports Article Swipe
Sayera Dhaubhadel
,
Jamaludin Mohd-Yusof
,
Kumkum Ganguly
,
Gopinath Chennupati
,
Sunil Thulasidasan
,
Nicolas Hengartner
,
Brent Mumphrey
,
Eric B. Durbin
,
Jennifer A. Doherty
,
Mireille Lemieux
,
Noah Schaefferkoetter
,
Georgia D. Tourassi
,
Linda Coyle
,
Lynne Penberthy
,
Benjamin H. McMahon
,
Tanmoy Bhattacharya
·
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2009.05094
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2009.05094
Safe deployment of deep learning systems in critical real world applications\nrequires models to make very few mistakes, and only under predictable\ncircumstances. In this work, we address this problem using an abstaining\nclassifier that is tuned to have $>$95% accuracy, and then identify the\ndeterminants of abstention using LIME. Essentially, we are training our model\nto learn the attributes of pathology reports that are likely to lead to\nincorrect classifications, albeit at the cost of reduced sensitivity. We\ndemonstrate an abstaining classifier in a multitask setting for classifying\ncancer pathology reports from the NCI SEER cancer registries on six tasks of\ninterest. For these tasks, we reduce the classification error rate by factors\nof 2--5 by abstaining on 25--45% of the reports. For the specific task of\nclassifying cancer site, we are able to identify metastasis, reports involving\nlymph nodes, and discussion of multiple cancer sites as responsible for many of\nthe classification mistakes, and observe that the extent and types of mistakes\nvary systematically with cancer site (e.g., breast, lung, and prostate). When\ncombining across three of the tasks, our model classifies 50% of the reports\nwith an accuracy greater than 95% for three of the six tasks\\edit, and greater\nthan 85% for all six tasks on the retained samples. Furthermore, we show that\nLIME provides a better determinant of classification than measures of word\noccurrence alone. By combining a deep abstaining classifier with feature\nidentification using LIME, we are able to identify concepts responsible for\nboth correctness and abstention when classifying cancer sites from pathology\nreports. The improvement of LIME over keyword searches is statistically\nsignificant, presumably because words are assessed in context and have been\nidentified as a local determinant of classification.\n
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2009.05094
- https://arxiv.org/pdf/2009.05094
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4287669619
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4287669619Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2009.05094Digital Object Identifier
- Title
-
Why I'm not Answering: Understanding Determinants of Classification of\n an Abstaining Classifier for Cancer Pathology ReportsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2020Year of publication
- Publication date
-
2020-09-10Full publication date if available
- Authors
-
Sayera Dhaubhadel, Jamaludin Mohd-Yusof, Kumkum Ganguly, Gopinath Chennupati, Sunil Thulasidasan, Nicolas Hengartner, Brent Mumphrey, Eric B. Durbin, Jennifer A. Doherty, Mireille Lemieux, Noah Schaefferkoetter, Georgia D. Tourassi, Linda Coyle, Lynne Penberthy, Benjamin H. McMahon, Tanmoy BhattacharyaList of authors in order
- Landing page
-
https://arxiv.org/abs/2009.05094Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2009.05094Direct 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/2009.05094Direct OA link when available
- Concepts
-
Classifier (UML), Computer science, Artificial intelligence, Machine learning, Correctness, Programming languageTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2023: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4287669619 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2009.05094 |
| ids.openalex | https://openalex.org/W4287669619 |
| fwci | 0.14685955 |
| type | preprint |
| title | Why I'm not Answering: Understanding Determinants of Classification of\n an Abstaining Classifier for Cancer Pathology Reports |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10028 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.995199978351593 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Topic Modeling |
| topics[1].id | https://openalex.org/T11710 |
| topics[1].field.id | https://openalex.org/fields/13 |
| topics[1].field.display_name | Biochemistry, Genetics and Molecular Biology |
| topics[1].score | 0.9786999821662903 |
| topics[1].domain.id | https://openalex.org/domains/1 |
| topics[1].domain.display_name | Life Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1312 |
| topics[1].subfield.display_name | Molecular Biology |
| topics[1].display_name | Biomedical Text Mining and Ontologies |
| topics[2].id | https://openalex.org/T13702 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.97079998254776 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Machine Learning in Healthcare |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C95623464 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6931928992271423 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1096149 |
| concepts[0].display_name | Classifier (UML) |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6211475729942322 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.5635166168212891 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C119857082 |
| concepts[3].level | 1 |
| concepts[3].score | 0.46058955788612366 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[3].display_name | Machine learning |
| concepts[4].id | https://openalex.org/C55439883 |
| concepts[4].level | 2 |
| concepts[4].score | 0.45983073115348816 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q360812 |
| concepts[4].display_name | Correctness |
| concepts[5].id | https://openalex.org/C199360897 |
| concepts[5].level | 1 |
| concepts[5].score | 0.0 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[5].display_name | Programming language |
| keywords[0].id | https://openalex.org/keywords/classifier |
| keywords[0].score | 0.6931928992271423 |
| keywords[0].display_name | Classifier (UML) |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6211475729942322 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.5635166168212891 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/machine-learning |
| keywords[3].score | 0.46058955788612366 |
| keywords[3].display_name | Machine learning |
| keywords[4].id | https://openalex.org/keywords/correctness |
| keywords[4].score | 0.45983073115348816 |
| keywords[4].display_name | Correctness |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2009.05094 |
| 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/2009.05094 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| 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/2009.05094 |
| indexed_in | arxiv |
| authorships[0].author.id | https://openalex.org/A5003944649 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Sayera Dhaubhadel |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Dhaubhadel, Sayera |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5088379175 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-9844-689X |
| authorships[1].author.display_name | Jamaludin Mohd-Yusof |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Mohd-Yusof, Jamaludin |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5008394285 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-2255-8940 |
| authorships[2].author.display_name | Kumkum Ganguly |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Ganguly, Kumkum |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5063725454 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-6223-8570 |
| authorships[3].author.display_name | Gopinath Chennupati |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Chennupati, Gopinath |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5028031083 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-0782-1031 |
| authorships[4].author.display_name | Sunil Thulasidasan |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Thulasidasan, Sunil |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5041470785 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-4157-134X |
| authorships[5].author.display_name | Nicolas Hengartner |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Hengartner, Nicolas W. |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5065077927 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Brent Mumphrey |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Mumphrey, Brent J. |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5044901389 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-5600-7645 |
| authorships[7].author.display_name | Eric B. Durbin |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Durbin, Eric B. |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5075544315 |
| authorships[8].author.orcid | https://orcid.org/0000-0002-1454-8187 |
| authorships[8].author.display_name | Jennifer A. Doherty |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Doherty, Jennifer A. |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5033939571 |
| authorships[9].author.orcid | |
| authorships[9].author.display_name | Mireille Lemieux |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Lemieux, Mireille |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5075593089 |
| authorships[10].author.orcid | |
| authorships[10].author.display_name | Noah Schaefferkoetter |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Schaefferkoetter, Noah |
| authorships[10].is_corresponding | False |
| authorships[11].author.id | https://openalex.org/A5014968146 |
| authorships[11].author.orcid | https://orcid.org/0000-0002-9418-9638 |
| authorships[11].author.display_name | Georgia D. Tourassi |
| authorships[11].author_position | middle |
| authorships[11].raw_author_name | Tourassi, Georgia |
| authorships[11].is_corresponding | False |
| authorships[12].author.id | https://openalex.org/A5066875900 |
| authorships[12].author.orcid | |
| authorships[12].author.display_name | Linda Coyle |
| authorships[12].author_position | middle |
| authorships[12].raw_author_name | Coyle, Linda |
| authorships[12].is_corresponding | False |
| authorships[13].author.id | https://openalex.org/A5102866470 |
| authorships[13].author.orcid | https://orcid.org/0000-0002-9961-8139 |
| authorships[13].author.display_name | Lynne Penberthy |
| authorships[13].author_position | middle |
| authorships[13].raw_author_name | Penberthy, Lynne |
| authorships[13].is_corresponding | False |
| authorships[14].author.id | https://openalex.org/A5047461991 |
| authorships[14].author.orcid | https://orcid.org/0000-0002-8226-1276 |
| authorships[14].author.display_name | Benjamin H. McMahon |
| authorships[14].author_position | middle |
| authorships[14].raw_author_name | McMahon, Benjamin H. |
| authorships[14].is_corresponding | False |
| authorships[15].author.id | https://openalex.org/A5045651282 |
| authorships[15].author.orcid | https://orcid.org/0000-0002-1060-652X |
| authorships[15].author.display_name | Tanmoy Bhattacharya |
| authorships[15].author_position | last |
| authorships[15].raw_author_name | Bhattacharya, Tanmoy |
| authorships[15].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/2009.05094 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-07-25T00:00:00 |
| display_name | Why I'm not Answering: Understanding Determinants of Classification of\n an Abstaining Classifier for Cancer Pathology Reports |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10028 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.995199978351593 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Topic Modeling |
| related_works | https://openalex.org/W2961085424, https://openalex.org/W4306674287, https://openalex.org/W3046775127, https://openalex.org/W3107602296, https://openalex.org/W3170094116, https://openalex.org/W4386462264, https://openalex.org/W4364306694, https://openalex.org/W4312192474, https://openalex.org/W4283697347, https://openalex.org/W4210805261 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2023 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 1 |
| best_oa_location.id | pmh:oai:arXiv.org:2009.05094 |
| 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/2009.05094 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| 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/2009.05094 |
| primary_location.id | pmh:oai:arXiv.org:2009.05094 |
| 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/2009.05094 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| 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/2009.05094 |
| publication_date | 2020-09-10 |
| publication_year | 2020 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 77, 200, 212, 257 |
| abstract_inverted_index.By | 210 |
| abstract_inverted_index.In | 21 |
| abstract_inverted_index.an | 29, 73, 173 |
| abstract_inverted_index.as | 135, 256 |
| abstract_inverted_index.at | 66 |
| abstract_inverted_index.by | 103, 106 |
| abstract_inverted_index.in | 6, 76, 251 |
| abstract_inverted_index.is | 32, 244 |
| abstract_inverted_index.of | 2, 42, 55, 69, 110, 131, 149, 163, 170, 180, 203, 207, 239, 260 |
| abstract_inverted_index.on | 90, 108, 191 |
| abstract_inverted_index.to | 12, 34, 61, 123, 223 |
| abstract_inverted_index.we | 24, 47, 97, 120, 196, 220 |
| abstract_inverted_index.50% | 169 |
| abstract_inverted_index.85% | 186 |
| abstract_inverted_index.95% | 177 |
| abstract_inverted_index.For | 94, 113 |
| abstract_inverted_index.NCI | 86 |
| abstract_inverted_index.The | 237 |
| abstract_inverted_index.all | 188 |
| abstract_inverted_index.and | 17, 38, 129, 142, 147, 158, 184, 229, 253 |
| abstract_inverted_index.are | 48, 59, 121, 221, 249 |
| abstract_inverted_index.few | 15 |
| abstract_inverted_index.for | 80, 137, 178, 187 |
| abstract_inverted_index.our | 50, 166 |
| abstract_inverted_index.six | 91, 182, 189 |
| abstract_inverted_index.the | 53, 67, 85, 99, 111, 114, 145, 164, 171, 181, 192 |
| abstract_inverted_index.2--5 | 105 |
| abstract_inverted_index.LIME | 240 |
| abstract_inverted_index.SEER | 87 |
| abstract_inverted_index.Safe | 0 |
| abstract_inverted_index.able | 122, 222 |
| abstract_inverted_index.cost | 68 |
| abstract_inverted_index.deep | 3, 213 |
| abstract_inverted_index.from | 84, 235 |
| abstract_inverted_index.have | 35, 254 |
| abstract_inverted_index.lead | 62 |
| abstract_inverted_index.make | 13 |
| abstract_inverted_index.many | 138 |
| abstract_inverted_index.only | 18 |
| abstract_inverted_index.over | 241 |
| abstract_inverted_index.rate | 102 |
| abstract_inverted_index.real | 8 |
| abstract_inverted_index.show | 197 |
| abstract_inverted_index.site | 154 |
| abstract_inverted_index.task | 116 |
| abstract_inverted_index.than | 176, 205 |
| abstract_inverted_index.that | 31, 58, 144 |
| abstract_inverted_index.then | 39 |
| abstract_inverted_index.this | 22, 26 |
| abstract_inverted_index.very | 14 |
| abstract_inverted_index.when | 231 |
| abstract_inverted_index.with | 152, 216 |
| abstract_inverted_index.LIME, | 219 |
| abstract_inverted_index.LIME. | 45 |
| abstract_inverted_index.error | 101 |
| abstract_inverted_index.learn | 52 |
| abstract_inverted_index.local | 258 |
| abstract_inverted_index.lung, | 157 |
| abstract_inverted_index.model | 167 |
| abstract_inverted_index.site, | 119 |
| abstract_inverted_index.sites | 134, 234 |
| abstract_inverted_index.tasks | 92, 190 |
| abstract_inverted_index.these | 95 |
| abstract_inverted_index.three | 162, 179 |
| abstract_inverted_index.tuned | 33 |
| abstract_inverted_index.types | 148 |
| abstract_inverted_index.under | 19 |
| abstract_inverted_index.using | 28, 44, 218 |
| abstract_inverted_index.words | 248 |
| abstract_inverted_index.work, | 23 |
| abstract_inverted_index.world | 9 |
| abstract_inverted_index.(e.g., | 155 |
| abstract_inverted_index.across | 161 |
| abstract_inverted_index.albeit | 65 |
| abstract_inverted_index.alone. | 209 |
| abstract_inverted_index.better | 201 |
| abstract_inverted_index.cancer | 88, 118, 133, 153, 233 |
| abstract_inverted_index.extent | 146 |
| abstract_inverted_index.likely | 60 |
| abstract_inverted_index.models | 11 |
| abstract_inverted_index.nodes, | 128 |
| abstract_inverted_index.reduce | 98 |
| abstract_inverted_index.tasks, | 96, 165 |
| abstract_inverted_index.25--45% | 109 |
| abstract_inverted_index.address | 25 |
| abstract_inverted_index.because | 247 |
| abstract_inverted_index.breast, | 156 |
| abstract_inverted_index.context | 252 |
| abstract_inverted_index.greater | 175 |
| abstract_inverted_index.keyword | 242 |
| abstract_inverted_index.observe | 143 |
| abstract_inverted_index.of\nthe | 139 |
| abstract_inverted_index.problem | 27 |
| abstract_inverted_index.reduced | 70 |
| abstract_inverted_index.reports | 57, 83, 126 |
| abstract_inverted_index.setting | 79 |
| abstract_inverted_index.systems | 5 |
| abstract_inverted_index.accuracy | 174 |
| abstract_inverted_index.assessed | 250 |
| abstract_inverted_index.concepts | 225 |
| abstract_inverted_index.critical | 7 |
| abstract_inverted_index.identify | 40, 124, 224 |
| abstract_inverted_index.learning | 4 |
| abstract_inverted_index.measures | 206 |
| abstract_inverted_index.multiple | 132 |
| abstract_inverted_index.provides | 199 |
| abstract_inverted_index.reports. | 112 |
| abstract_inverted_index.retained | 193 |
| abstract_inverted_index.samples. | 194 |
| abstract_inverted_index.searches | 243 |
| abstract_inverted_index.specific | 115 |
| abstract_inverted_index.training | 49 |
| abstract_inverted_index.$>$95% | 36 |
| abstract_inverted_index.accuracy, | 37 |
| abstract_inverted_index.combining | 211 |
| abstract_inverted_index.for\nboth | 227 |
| abstract_inverted_index.mistakes, | 16, 141 |
| abstract_inverted_index.model\nto | 51 |
| abstract_inverted_index.multitask | 78 |
| abstract_inverted_index.pathology | 56, 82 |
| abstract_inverted_index.abstaining | 74, 107, 214 |
| abstract_inverted_index.abstention | 43, 230 |
| abstract_inverted_index.attributes | 54 |
| abstract_inverted_index.classifier | 75, 215 |
| abstract_inverted_index.classifies | 168 |
| abstract_inverted_index.deployment | 1 |
| abstract_inverted_index.discussion | 130 |
| abstract_inverted_index.presumably | 246 |
| abstract_inverted_index.prostate). | 159 |
| abstract_inverted_index.registries | 89 |
| abstract_inverted_index.that\nLIME | 198 |
| abstract_inverted_index.classifying | 232 |
| abstract_inverted_index.correctness | 228 |
| abstract_inverted_index.determinant | 202, 259 |
| abstract_inverted_index.factors\nof | 104 |
| abstract_inverted_index.improvement | 238 |
| abstract_inverted_index.metastasis, | 125 |
| abstract_inverted_index.responsible | 136, 226 |
| abstract_inverted_index.Essentially, | 46 |
| abstract_inverted_index.Furthermore, | 195 |
| abstract_inverted_index.sensitivity. | 71 |
| abstract_inverted_index.tasks\\edit, | 183 |
| abstract_inverted_index.greater\nthan | 185 |
| abstract_inverted_index.of\ninterest. | 93 |
| abstract_inverted_index.reports\nwith | 172 |
| abstract_inverted_index.to\nincorrect | 63 |
| abstract_inverted_index.classification | 100, 140, 204 |
| abstract_inverted_index.mistakes\nvary | 150 |
| abstract_inverted_index.systematically | 151 |
| abstract_inverted_index.We\ndemonstrate | 72 |
| abstract_inverted_index.When\ncombining | 160 |
| abstract_inverted_index.of\nclassifying | 117 |
| abstract_inverted_index.been\nidentified | 255 |
| abstract_inverted_index.classifications, | 64 |
| abstract_inverted_index.involving\nlymph | 127 |
| abstract_inverted_index.word\noccurrence | 208 |
| abstract_inverted_index.classification.\n | 261 |
| abstract_inverted_index.the\ndeterminants | 41 |
| abstract_inverted_index.classifying\ncancer | 81 |
| abstract_inverted_index.pathology\nreports. | 236 |
| abstract_inverted_index.abstaining\nclassifier | 30 |
| abstract_inverted_index.applications\nrequires | 10 |
| abstract_inverted_index.feature\nidentification | 217 |
| abstract_inverted_index.predictable\ncircumstances. | 20 |
| abstract_inverted_index.statistically\nsignificant, | 245 |
| cited_by_percentile_year.max | 94 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 16 |
| citation_normalized_percentile.value | 0.60511846 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |