FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4300537824> ?p ?o ?g. }

• W4300537824 abstract "Unlike linear models which are traditionally used to study all-cause mortality, complex machine learning models can capture non-linear interrelations and provide opportunities to identify unexplored risk factors. Explainable artificial intelligence can improve prediction accuracy over linear models and reveal great insights into outcomes like mortality. This paper comprehensively analyzes all-cause mortality by explaining complex machine learning models.We propose the IMPACT framework that uses XAI technique to explain a state-of-the-art tree ensemble mortality prediction model. We apply IMPACT to understand all-cause mortality for 1-, 3-, 5-, and 10-year follow-up times within the NHANES dataset, which contains 47,261 samples and 151 features.We show that IMPACT models achieve higher accuracy than linear models and neural networks. Using IMPACT, we identify several overlooked risk factors and interaction effects. Furthermore, we identify relationships between laboratory features and mortality that may suggest adjusting established reference intervals. Finally, we develop highly accurate, efficient and interpretable mortality risk scores that can be used by medical professionals and individuals without medical expertise. We ensure generalizability by performing temporal validation of the mortality risk scores and external validation of important findings with the UK Biobank dataset.IMPACT's unique strength is the explainable prediction, which provides insights into the complex, non-linear relationships between mortality and features, while maintaining high accuracy. Our explainable risk scores could help individuals improve self-awareness of their health status and help clinicians identify patients with high risk. IMPACT takes a consequential step towards bringing contemporary developments in XAI to epidemiology.This study identifies characteristics that will make a person more likely to die sooner than expected based on life expectancy for the population. We developed a computer program and applied it to information obtained about the characteristics and medical history of people from the USA. We identified previously unidentified characteristics that impact how likely it is someone will die sooner than expected, for example the circumference of the arm. We also identified combinations of characteristics that interact to increase the likelihood of death sooner than expected. By adding a person’s characteristics to the program, the likelihood of death over the next 5 years can be calculated and characteristics identified that a person could modify to improve their health and reduce their chance of death during this period." @default.
• W4300537824 created "2022-10-03" @default.
• W4300537824 creator A5002945174 @default.
• W4300537824 creator A5024995037 @default.
• W4300537824 creator A5028723221 @default.
• W4300537824 creator A5072198355 @default.
• W4300537824 creator A5072624010 @default.
• W4300537824 creator A5082310478 @default.
• W4300537824 date "2022-10-03" @default.
• W4300537824 modified "2023-10-15" @default.
• W4300537824 title "Interpretable machine learning prediction of all-cause mortality" @default.
• W4300537824 cites W1488720446 @default.
• W4300537824 cites W1513458054 @default.
• W4300537824 cites W1540166912 @default.
• W4300537824 cites W1967862917 @default.
• W4300537824 cites W1974047233 @default.
• W4300537824 cites W1980432185 @default.
• W4300537824 cites W1982087811 @default.
• W4300537824 cites W1994862084 @default.
• W4300537824 cites W1996221805 @default.
• W4300537824 cites W2036103276 @default.
• W4300537824 cites W2058038145 @default.
• W4300537824 cites W2060671390 @default.
• W4300537824 cites W2063686321 @default.
• W4300537824 cites W2064885200 @default.
• W4300537824 cites W2065512846 @default.
• W4300537824 cites W2069211921 @default.
• W4300537824 cites W2077503759 @default.
• W4300537824 cites W2077555687 @default.
• W4300537824 cites W2087018232 @default.
• W4300537824 cites W2090119255 @default.
• W4300537824 cites W2097202055 @default.
• W4300537824 cites W2098983190 @default.
• W4300537824 cites W2119750020 @default.
• W4300537824 cites W2120753776 @default.
• W4300537824 cites W2121091193 @default.
• W4300537824 cites W2139362158 @default.
• W4300537824 cites W2142147297 @default.
• W4300537824 cites W2150092242 @default.
• W4300537824 cites W2158489053 @default.
• W4300537824 cites W2160268722 @default.
• W4300537824 cites W2167375264 @default.
• W4300537824 cites W2168885178 @default.
• W4300537824 cites W2168925860 @default.
• W4300537824 cites W2169218899 @default.
• W4300537824 cites W2171034317 @default.
• W4300537824 cites W2236856444 @default.
• W4300537824 cites W2282821441 @default.
• W4300537824 cites W2557738935 @default.
• W4300537824 cites W2580767461 @default.
• W4300537824 cites W2581082771 @default.
• W4300537824 cites W2605253636 @default.
• W4300537824 cites W2606665849 @default.
• W4300537824 cites W2616821336 @default.
• W4300537824 cites W2739312105 @default.
• W4300537824 cites W2760946358 @default.
• W4300537824 cites W2770051606 @default.
• W4300537824 cites W2795411881 @default.
• W4300537824 cites W2796559433 @default.
• W4300537824 cites W2802841668 @default.
• W4300537824 cites W2908077673 @default.
• W4300537824 cites W2912654909 @default.
• W4300537824 cites W2915203021 @default.
• W4300537824 cites W2923291095 @default.
• W4300537824 cites W2949100461 @default.
• W4300537824 cites W2978647781 @default.
• W4300537824 cites W2991407313 @default.
• W4300537824 cites W2999615587 @default.
• W4300537824 cites W3121792421 @default.
• W4300537824 cites W3135248712 @default.
• W4300537824 cites W3139340352 @default.
• W4300537824 cites W3159078121 @default.
• W4300537824 cites W4287655072 @default.
• W4300537824 cites W4299502495 @default.
• W4300537824 cites W4300537824 @default.
• W4300537824 doi "https://doi.org/10.1038/s43856-022-00180-x" @default.
• W4300537824 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36204043" @default.
• W4300537824 hasPublicationYear "2022" @default.
• W4300537824 type Work @default.
• W4300537824 citedByCount "8" @default.
• W4300537824 countsByYear W43005378242022 @default.
• W4300537824 countsByYear W43005378242023 @default.
• W4300537824 crossrefType "journal-article" @default.
• W4300537824 hasAuthorship W4300537824A5002945174 @default.
• W4300537824 hasAuthorship W4300537824A5024995037 @default.
• W4300537824 hasAuthorship W4300537824A5028723221 @default.
• W4300537824 hasAuthorship W4300537824A5072198355 @default.
• W4300537824 hasAuthorship W4300537824A5072624010 @default.
• W4300537824 hasAuthorship W4300537824A5082310478 @default.
• W4300537824 hasBestOaLocation W43005378241 @default.
• W4300537824 hasConcept C105795698 @default.
• W4300537824 hasConcept C119857082 @default.
• W4300537824 hasConcept C154945302 @default.
• W4300537824 hasConcept C163175372 @default.
• W4300537824 hasConcept C27158222 @default.
• W4300537824 hasConcept C33923547 @default.
• W4300537824 hasConcept C41008148 @default.
• W4300537824 hasConcept C45804977 @default.
• W4300537824 hasConcept C50644808 @default.
• W4300537824 hasConcept C84525736 @default.

• next