FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4301431397> ?p ?o ?g. }

• W4301431397 abstract "Abstract Purpose The purpose of this study is to identify additional clinical features for sepsis detection through the use of a novel mechanism for interpreting black-box machine learning models trained and to provide a suitable evaluation for the mechanism. Methods We use the publicly available dataset from the 2019 PhysioNet Challenge. It has around 40,000 Intensive Care Unit (ICU) patients with 40 physiological variables. Using Long Short-Term Memory (LSTM) as the representative black-box machine learning model, we adapted the Multi-set Classifier to globally interpret the black-box model for concepts it learned about sepsis. To identify relevant features, the result is compared against: i) features used by a computational sepsis expert, ii) clinical features from clinical collaborators, iii) academic features from literature, and iv) significant features from statistical hypothesis testing. Results Random Forest (RF) was found to be the computational sepsis expert because it had high accuracies for solving both the detection and early detection, and a high degree of overlap with clinical and literature features. Using the proposed interpretation mechanism and the dataset, we identified 17 features that the LSTM used for sepsis classification, 11 of which overlaps with the top 20 features from the RF model, 10 with academic features and 5 with clinical features. Clinical opinion suggests, 3 LSTM features have strong correlation with some clinical features that were not identified by the mechanism. We also found that age, chloride ion concentration, pH and oxygen saturation should be investigated further for connection with developing sepsis. Conclusion Interpretation mechanisms can bolster the incorporation of state-of-the-art machine learning models into clinical decision support systems, and might help clinicians to address the issue of early sepsis detection. The promising results from this study warrants further investigation into creation of new and improvement of existing interpretation mechanisms for black-box models, and into clinical features that are currently not used in clinical assessment of sepsis." @default.
• W4301431397 created "2022-10-05" @default.
• W4301431397 creator A5001081885 @default.
• W4301431397 creator A5005096045 @default.
• W4301431397 creator A5043909574 @default.
• W4301431397 creator A5056232741 @default.
• W4301431397 creator A5056842924 @default.
• W4301431397 date "2022-10-04" @default.
• W4301431397 modified "2023-10-18" @default.
• W4301431397 title "What do Black-box Machine Learning Prediction Models See?- An Application Study With Sepsis Detection" @default.
• W4301431397 cites W1943063538 @default.
• W4301431397 cites W1987412927 @default.
• W4301431397 cites W1993376168 @default.
• W4301431397 cites W2000645789 @default.
• W4301431397 cites W2035350889 @default.
• W4301431397 cites W2064675550 @default.
• W4301431397 cites W2103053257 @default.
• W4301431397 cites W2114273947 @default.
• W4301431397 cites W2144212877 @default.
• W4301431397 cites W2148143831 @default.
• W4301431397 cites W2151608510 @default.
• W4301431397 cites W2280404143 @default.
• W4301431397 cites W2282181907 @default.
• W4301431397 cites W2282821441 @default.
• W4301431397 cites W2337688125 @default.
• W4301431397 cites W2406218407 @default.
• W4301431397 cites W2599245417 @default.
• W4301431397 cites W2604972438 @default.
• W4301431397 cites W2776803885 @default.
• W4301431397 cites W2783006608 @default.
• W4301431397 cites W2786635213 @default.
• W4301431397 cites W2795639367 @default.
• W4301431397 cites W2800813736 @default.
• W4301431397 cites W2893893301 @default.
• W4301431397 cites W2906484232 @default.
• W4301431397 cites W2910910290 @default.
• W4301431397 cites W2919240966 @default.
• W4301431397 cites W2937307539 @default.
• W4301431397 cites W2947615475 @default.
• W4301431397 cites W2965450334 @default.
• W4301431397 cites W2983753125 @default.
• W4301431397 cites W2995282027 @default.
• W4301431397 cites W2995584125 @default.
• W4301431397 cites W2999112567 @default.
• W4301431397 cites W2999513477 @default.
• W4301431397 cites W2999759928 @default.
• W4301431397 cites W2999845962 @default.
• W4301431397 cites W3008421095 @default.
• W4301431397 cites W3033551534 @default.
• W4301431397 cites W3048074762 @default.
• W4301431397 cites W3048587623 @default.
• W4301431397 cites W3048688409 @default.
• W4301431397 cites W3080107788 @default.
• W4301431397 cites W3083657953 @default.
• W4301431397 cites W3090266264 @default.
• W4301431397 cites W3097666541 @default.
• W4301431397 cites W3100777112 @default.
• W4301431397 cites W3126579551 @default.
• W4301431397 cites W3158067219 @default.
• W4301431397 cites W3174786846 @default.
• W4301431397 cites W3214348223 @default.
• W4301431397 cites W4232872328 @default.
• W4301431397 doi "https://doi.org/10.21203/rs.3.rs-1991366/v2" @default.
• W4301431397 hasPublicationYear "2022" @default.
• W4301431397 type Work @default.
• W4301431397 citedByCount "0" @default.
• W4301431397 crossrefType "posted-content" @default.
• W4301431397 hasAuthorship W4301431397A5001081885 @default.
• W4301431397 hasAuthorship W4301431397A5005096045 @default.
• W4301431397 hasAuthorship W4301431397A5043909574 @default.
• W4301431397 hasAuthorship W4301431397A5056232741 @default.
• W4301431397 hasAuthorship W4301431397A5056842924 @default.
• W4301431397 hasBestOaLocation W43014313971 @default.
• W4301431397 hasConcept C111472728 @default.
• W4301431397 hasConcept C119857082 @default.
• W4301431397 hasConcept C138885662 @default.
• W4301431397 hasConcept C154945302 @default.
• W4301431397 hasConcept C169258074 @default.
• W4301431397 hasConcept C203014093 @default.
• W4301431397 hasConcept C2778384902 @default.
• W4301431397 hasConcept C41008148 @default.
• W4301431397 hasConcept C71924100 @default.
• W4301431397 hasConcept C89611455 @default.
• W4301431397 hasConcept C94966114 @default.
• W4301431397 hasConcept C95623464 @default.
• W4301431397 hasConceptScore W4301431397C111472728 @default.
• W4301431397 hasConceptScore W4301431397C119857082 @default.
• W4301431397 hasConceptScore W4301431397C138885662 @default.
• W4301431397 hasConceptScore W4301431397C154945302 @default.
• W4301431397 hasConceptScore W4301431397C169258074 @default.
• W4301431397 hasConceptScore W4301431397C203014093 @default.
• W4301431397 hasConceptScore W4301431397C2778384902 @default.
• W4301431397 hasConceptScore W4301431397C41008148 @default.
• W4301431397 hasConceptScore W4301431397C71924100 @default.
• W4301431397 hasConceptScore W4301431397C89611455 @default.
• W4301431397 hasConceptScore W4301431397C94966114 @default.
• W4301431397 hasConceptScore W4301431397C95623464 @default.
• W4301431397 hasLocation W43014313971 @default.
• W4301431397 hasOpenAccess W4301431397 @default.
• W4301431397 hasPrimaryLocation W43014313971 @default.

• next