FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315497924> ?p ?o ?g. }

• W4315497924 abstract "Introduction Overall performance of machine learning-based prediction models is promising; however, their generalizability and fairness must be vigorously investigated to ensure they perform sufficiently well for all patients. Objective This study aimed to evaluate prediction bias in machine learning models used for predicting acute postoperative pain. Method We conducted a retrospective review of electronic health records for patients undergoing orthopedic surgery from June 1, 2011, to June 30, 2019, at the University of Florida Health system/Shands Hospital. CatBoost machine learning models were trained for predicting the binary outcome of low (≤4) and high pain (&gt;4). Model biases were assessed against seven protected attributes of age, sex, race, area deprivation index (ADI), speaking language, health literacy, and insurance type. Reweighing of protected attributes was investigated for reducing model bias compared with base models. Fairness metrics of equal opportunity, predictive parity, predictive equality, statistical parity, and overall accuracy equality were examined. Results The final dataset included 14,263 patients [age: 60.72 (16.03) years, 53.87% female, 39.13% low acute postoperative pain]. The machine learning model (area under the curve, 0.71) was biased in terms of age, race, ADI, and insurance type, but not in terms of sex, language, and health literacy. Despite promising overall performance in predicting acute postoperative pain, machine learning-based prediction models may be biased with respect to protected attributes. Conclusion These findings show the need to evaluate fairness in machine learning models involved in perioperative pain before they are implemented as clinical decision support tools." @default.
• W4315497924 created "2023-01-11" @default.
• W4315497924 creator A5007040136 @default.
• W4315497924 creator A5010003241 @default.
• W4315497924 creator A5016332168 @default.
• W4315497924 creator A5023146984 @default.
• W4315497924 creator A5058579794 @default.
• W4315497924 creator A5081527755 @default.
• W4315497924 creator A5084386025 @default.
• W4315497924 date "2023-01-11" @default.
• W4315497924 modified "2023-10-14" @default.
• W4315497924 title "Fairness in the prediction of acute postoperative pain using machine learning models" @default.
• W4315497924 cites W1597326282 @default.
• W4315497924 cites W1675900714 @default.
• W4315497924 cites W1929228473 @default.
• W4315497924 cites W1978433738 @default.
• W4315497924 cites W1978519915 @default.
• W4315497924 cites W2001638015 @default.
• W4315497924 cites W2062724105 @default.
• W4315497924 cites W2065506323 @default.
• W4315497924 cites W2071966593 @default.
• W4315497924 cites W2087018232 @default.
• W4315497924 cites W2096588186 @default.
• W4315497924 cites W2099966451 @default.
• W4315497924 cites W2108563766 @default.
• W4315497924 cites W2109467870 @default.
• W4315497924 cites W2109979737 @default.
• W4315497924 cites W2116365496 @default.
• W4315497924 cites W2120666477 @default.
• W4315497924 cites W2121100292 @default.
• W4315497924 cites W2129003580 @default.
• W4315497924 cites W2129568786 @default.
• W4315497924 cites W2130141996 @default.
• W4315497924 cites W2133046038 @default.
• W4315497924 cites W2142262297 @default.
• W4315497924 cites W2144787005 @default.
• W4315497924 cites W2170621602 @default.
• W4315497924 cites W2414055761 @default.
• W4315497924 cites W2562251009 @default.
• W4315497924 cites W2760543293 @default.
• W4315497924 cites W2765979443 @default.
• W4315497924 cites W2804233742 @default.
• W4315497924 cites W2898251267 @default.
• W4315497924 cites W2915034333 @default.
• W4315497924 cites W2937141392 @default.
• W4315497924 cites W2969777862 @default.
• W4315497924 cites W2981869278 @default.
• W4315497924 cites W2990072080 @default.
• W4315497924 cites W2990768863 @default.
• W4315497924 cites W3007798706 @default.
• W4315497924 cites W3019027775 @default.
• W4315497924 cites W3046101748 @default.
• W4315497924 cites W3122698400 @default.
• W4315497924 cites W3137920042 @default.
• W4315497924 cites W3152856173 @default.
• W4315497924 cites W3156313717 @default.
• W4315497924 cites W3159623667 @default.
• W4315497924 cites W3173081443 @default.
• W4315497924 cites W3189658686 @default.
• W4315497924 cites W3189722576 @default.
• W4315497924 doi "https://doi.org/10.3389/fdgth.2022.970281" @default.
• W4315497924 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36714611" @default.
• W4315497924 hasPublicationYear "2023" @default.
• W4315497924 type Work @default.
• W4315497924 citedByCount "1" @default.
• W4315497924 countsByYear W43154979242023 @default.
• W4315497924 crossrefType "journal-article" @default.
• W4315497924 hasAuthorship W4315497924A5007040136 @default.
• W4315497924 hasAuthorship W4315497924A5010003241 @default.
• W4315497924 hasAuthorship W4315497924A5016332168 @default.
• W4315497924 hasAuthorship W4315497924A5023146984 @default.
• W4315497924 hasAuthorship W4315497924A5058579794 @default.
• W4315497924 hasAuthorship W4315497924A5081527755 @default.
• W4315497924 hasAuthorship W4315497924A5084386025 @default.
• W4315497924 hasBestOaLocation W43154979241 @default.
• W4315497924 hasConcept C105795698 @default.
• W4315497924 hasConcept C119857082 @default.
• W4315497924 hasConcept C141071460 @default.
• W4315497924 hasConcept C154945302 @default.
• W4315497924 hasConcept C160735492 @default.
• W4315497924 hasConcept C162324750 @default.
• W4315497924 hasConcept C1862650 @default.
• W4315497924 hasConcept C27158222 @default.
• W4315497924 hasConcept C31174226 @default.
• W4315497924 hasConcept C33923547 @default.
• W4315497924 hasConcept C41008148 @default.
• W4315497924 hasConcept C45804977 @default.
• W4315497924 hasConcept C50522688 @default.
• W4315497924 hasConcept C71924100 @default.
• W4315497924 hasConceptScore W4315497924C105795698 @default.
• W4315497924 hasConceptScore W4315497924C119857082 @default.
• W4315497924 hasConceptScore W4315497924C141071460 @default.
• W4315497924 hasConceptScore W4315497924C154945302 @default.
• W4315497924 hasConceptScore W4315497924C160735492 @default.
• W4315497924 hasConceptScore W4315497924C162324750 @default.
• W4315497924 hasConceptScore W4315497924C1862650 @default.
• W4315497924 hasConceptScore W4315497924C27158222 @default.
• W4315497924 hasConceptScore W4315497924C31174226 @default.
• W4315497924 hasConceptScore W4315497924C33923547 @default.
• W4315497924 hasConceptScore W4315497924C41008148 @default.

• next