Matches in SemOpenAlex for { <https://semopenalex.org/work/W2777459094> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2777459094 abstract "Autism spectrum disorder (ASD) diagnosis can be delayed due in part to the time required for administration of standard exams, such as the Autism Diagnostic Observation Schedule (ADOS). Shorter and potentially mobilized approaches would help to alleviate bottlenecks in the healthcare system. Previous work using machine learning suggested that a subset of the behaviors measured by ADOS can achieve clinically acceptable levels of accuracy. Here we expand on this initial work to build sparse models that have higher potential to generalize to the clinical population.We assembled a collection of score sheets for two ADOS modules, one for children with phrased speech (Module 2; 1319 ASD cases, 70 controls) and the other for children with verbal fluency (Module 3; 2870 ASD cases, 273 controls). We used sparsity/parsimony enforcing regularization techniques in a nested cross validation grid search to select features for 17 unique supervised learning models, encoding missing values as additional indicator features. We augmented our feature sets with gender and age to train minimal and interpretable classifiers capable of robust detection of ASD from non-ASD.By applying 17 unique supervised learning methods across 5 classification families tuned for sparse use of features and to be within 1 standard error of the optimal model, we find reduced sets of 10 and 5 features used in a majority of models. We tested the performance of the most interpretable of these sparse models, including Logistic Regression with L2 regularization or Linear SVM with L1 regularization. We obtained an area under the ROC curve of 0.95 for ADOS Module 3 and 0.93 for ADOS Module 2 with less than or equal to 10 features.The resulting models provide improved stability over previous machine learning efforts to minimize the time complexity of autism detection due to regularization and a small parameter space. These robustness techniques yield classifiers that are sparse, interpretable and that have potential to generalize to alternative modes of autism screening, diagnosis and monitoring, possibly including analysis of short home videos." @default.
- W2777459094 created "2018-01-05" @default.
- W2777459094 creator A5005667479 @default.
- W2777459094 creator A5027872863 @default.
- W2777459094 creator A5033025890 @default.
- W2777459094 creator A5069105490 @default.
- W2777459094 date "2017-12-01" @default.
- W2777459094 modified "2023-10-16" @default.
- W2777459094 title "Sparsifying machine learning models identify stable subsets of predictive features for behavioral detection of autism" @default.
- W2777459094 cites W1480376833 @default.
- W2777459094 cites W1964011803 @default.
- W2777459094 cites W1973402429 @default.
- W2777459094 cites W1987493092 @default.
- W2777459094 cites W2011847916 @default.
- W2777459094 cites W2068040982 @default.
- W2777459094 cites W2069107231 @default.
- W2777459094 cites W2074766612 @default.
- W2777459094 cites W2077830280 @default.
- W2777459094 cites W2103185075 @default.
- W2777459094 cites W2144446993 @default.
- W2777459094 cites W2153969495 @default.
- W2777459094 cites W2164551677 @default.
- W2777459094 cites W2202280262 @default.
- W2777459094 cites W2263602591 @default.
- W2777459094 doi "https://doi.org/10.1186/s13229-017-0180-6" @default.
- W2777459094 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/5735531" @default.
- W2777459094 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29270283" @default.
- W2777459094 hasPublicationYear "2017" @default.
- W2777459094 type Work @default.
- W2777459094 sameAs 2777459094 @default.
- W2777459094 citedByCount "68" @default.
- W2777459094 countsByYear W27774590942018 @default.
- W2777459094 countsByYear W27774590942019 @default.
- W2777459094 countsByYear W27774590942020 @default.
- W2777459094 countsByYear W27774590942021 @default.
- W2777459094 countsByYear W27774590942022 @default.
- W2777459094 countsByYear W27774590942023 @default.
- W2777459094 crossrefType "journal-article" @default.
- W2777459094 hasAuthorship W2777459094A5005667479 @default.
- W2777459094 hasAuthorship W2777459094A5027872863 @default.
- W2777459094 hasAuthorship W2777459094A5033025890 @default.
- W2777459094 hasAuthorship W2777459094A5069105490 @default.
- W2777459094 hasBestOaLocation W27774590941 @default.
- W2777459094 hasConcept C119857082 @default.
- W2777459094 hasConcept C12267149 @default.
- W2777459094 hasConcept C138496976 @default.
- W2777459094 hasConcept C153180895 @default.
- W2777459094 hasConcept C154945302 @default.
- W2777459094 hasConcept C15744967 @default.
- W2777459094 hasConcept C205778803 @default.
- W2777459094 hasConcept C2776135515 @default.
- W2777459094 hasConcept C2778538070 @default.
- W2777459094 hasConcept C2780055620 @default.
- W2777459094 hasConcept C2908647359 @default.
- W2777459094 hasConcept C41008148 @default.
- W2777459094 hasConcept C71924100 @default.
- W2777459094 hasConcept C99454951 @default.
- W2777459094 hasConceptScore W2777459094C119857082 @default.
- W2777459094 hasConceptScore W2777459094C12267149 @default.
- W2777459094 hasConceptScore W2777459094C138496976 @default.
- W2777459094 hasConceptScore W2777459094C153180895 @default.
- W2777459094 hasConceptScore W2777459094C154945302 @default.
- W2777459094 hasConceptScore W2777459094C15744967 @default.
- W2777459094 hasConceptScore W2777459094C205778803 @default.
- W2777459094 hasConceptScore W2777459094C2776135515 @default.
- W2777459094 hasConceptScore W2777459094C2778538070 @default.
- W2777459094 hasConceptScore W2777459094C2780055620 @default.
- W2777459094 hasConceptScore W2777459094C2908647359 @default.
- W2777459094 hasConceptScore W2777459094C41008148 @default.
- W2777459094 hasConceptScore W2777459094C71924100 @default.
- W2777459094 hasConceptScore W2777459094C99454951 @default.
- W2777459094 hasFunder F4320307187 @default.
- W2777459094 hasFunder F4320309331 @default.
- W2777459094 hasIssue "1" @default.
- W2777459094 hasLocation W27774590941 @default.
- W2777459094 hasLocation W27774590942 @default.
- W2777459094 hasLocation W27774590943 @default.
- W2777459094 hasLocation W27774590944 @default.
- W2777459094 hasLocation W27774590945 @default.
- W2777459094 hasOpenAccess W2777459094 @default.
- W2777459094 hasPrimaryLocation W27774590941 @default.
- W2777459094 hasRelatedWork W2290993951 @default.
- W2777459094 hasRelatedWork W2588314410 @default.
- W2777459094 hasRelatedWork W2759268857 @default.
- W2777459094 hasRelatedWork W2782379361 @default.
- W2777459094 hasRelatedWork W2883808992 @default.
- W2777459094 hasRelatedWork W2907813052 @default.
- W2777459094 hasRelatedWork W2983113363 @default.
- W2777459094 hasRelatedWork W3005935337 @default.
- W2777459094 hasRelatedWork W3186235679 @default.
- W2777459094 hasRelatedWork W2345184372 @default.
- W2777459094 hasVolume "8" @default.
- W2777459094 isParatext "false" @default.
- W2777459094 isRetracted "false" @default.
- W2777459094 magId "2777459094" @default.
- W2777459094 workType "article" @default.