FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3192232155> ?p ?o ?g. }

• W3192232155 endingPage "4970" @default.
• W3192232155 startingPage "4958" @default.
• W3192232155 abstract "Background and aims Most nutritional assessment tools are based on pre-defined questionnaires or consensus guidelines. However, it has been postulated that population data can be used directly to develop a solution for assessing malnutrition. This study established a machine learning (ML)-based, individualized decision system to identify and grade malnutrition using large-scale data from cancer patients. Methods This was an observational, nationwide, multicenter cohort study that included 14134 cancer patients from five institutions in four different geographic regions of China. Multi-stage K-means clustering was performed to isolate and grade malnutrition based on 17 core nutritional features. The effectiveness of the identified clusters for reflecting clinical characteristics, nutritional status and patient outcomes was comprehensively evaluated. The study population was randomly split for model derivation and validation. Multiple ML algorithms were developed, validated and compared to screen for optimal models to implement the cluster prediction. Results A well-nourished cluster (n = 8193, 58.0%) and a malnourished cluster with three phenotype-specific severity levels (mild = 2195, 15.5%; moderate = 2491, 17.6%; severe = 1255, 8.9%) were identified. The clusters showed moderate agreement with the Patient-Generated Subjective Global Assessment and the Global Leadership Initiative on Malnutrition criteria. The severity of malnutrition was negatively associated with the nutritional status, physical status, quality of life, and short-term outcomes, and was monotonically correlated with reduced overall survival. A multinomial logistic regression was found to be the optimal ML algorithm, and models built based on this algorithm showed almost perfect performance to predict the clusters in the validation data. Conclusions This study developed a fusion decision system that can be used to facilitate the identification and severity grading of malnutrition in patients with cancer. Moreover, the study workflow is flexible, and might provide a generalizable solution for the artificial intelligence-based assessment of malnutrition in a wider variety of scenarios. Most nutritional assessment tools are based on pre-defined questionnaires or consensus guidelines. However, it has been postulated that population data can be used directly to develop a solution for assessing malnutrition. This study established a machine learning (ML)-based, individualized decision system to identify and grade malnutrition using large-scale data from cancer patients. This was an observational, nationwide, multicenter cohort study that included 14134 cancer patients from five institutions in four different geographic regions of China. Multi-stage K-means clustering was performed to isolate and grade malnutrition based on 17 core nutritional features. The effectiveness of the identified clusters for reflecting clinical characteristics, nutritional status and patient outcomes was comprehensively evaluated. The study population was randomly split for model derivation and validation. Multiple ML algorithms were developed, validated and compared to screen for optimal models to implement the cluster prediction. A well-nourished cluster (n = 8193, 58.0%) and a malnourished cluster with three phenotype-specific severity levels (mild = 2195, 15.5%; moderate = 2491, 17.6%; severe = 1255, 8.9%) were identified. The clusters showed moderate agreement with the Patient-Generated Subjective Global Assessment and the Global Leadership Initiative on Malnutrition criteria. The severity of malnutrition was negatively associated with the nutritional status, physical status, quality of life, and short-term outcomes, and was monotonically correlated with reduced overall survival. A multinomial logistic regression was found to be the optimal ML algorithm, and models built based on this algorithm showed almost perfect performance to predict the clusters in the validation data. This study developed a fusion decision system that can be used to facilitate the identification and severity grading of malnutrition in patients with cancer. Moreover, the study workflow is flexible, and might provide a generalizable solution for the artificial intelligence-based assessment of malnutrition in a wider variety of scenarios." @default.
• W3192232155 created "2021-08-16" @default.
• W3192232155 creator A5000432967 @default.
• W3192232155 creator A5001681060 @default.
• W3192232155 creator A5004283358 @default.
• W3192232155 creator A5007006789 @default.
• W3192232155 creator A5017617692 @default.
• W3192232155 creator A5021379796 @default.
• W3192232155 creator A5024257143 @default.
• W3192232155 creator A5031315906 @default.
• W3192232155 creator A5032404324 @default.
• W3192232155 creator A5036233749 @default.
• W3192232155 creator A5038522283 @default.
• W3192232155 creator A5039412958 @default.
• W3192232155 creator A5042397552 @default.
• W3192232155 creator A5042738110 @default.
• W3192232155 creator A5043644294 @default.
• W3192232155 creator A5049520209 @default.
• W3192232155 creator A5053030535 @default.
• W3192232155 creator A5053561579 @default.
• W3192232155 creator A5054251031 @default.
• W3192232155 creator A5057776374 @default.
• W3192232155 creator A5063647526 @default.
• W3192232155 creator A5064545976 @default.
• W3192232155 creator A5064771173 @default.
• W3192232155 creator A5065516345 @default.
• W3192232155 creator A5066971360 @default.
• W3192232155 creator A5070373016 @default.
• W3192232155 creator A5075166317 @default.
• W3192232155 creator A5083432061 @default.
• W3192232155 creator A5085352453 @default.
• W3192232155 creator A5085375813 @default.
• W3192232155 date "2021-08-01" @default.
• W3192232155 modified "2023-10-16" @default.
• W3192232155 title "A fusion decision system to identify and grade malnutrition in cancer patients: Machine learning reveals feasible workflow from representative real-world data" @default.
• W3192232155 cites W2001246541 @default.
• W3192232155 cites W2028802149 @default.
• W3192232155 cites W2039105774 @default.
• W3192232155 cites W2048929261 @default.
• W3192232155 cites W2056028385 @default.
• W3192232155 cites W2068462992 @default.
• W3192232155 cites W2088209109 @default.
• W3192232155 cites W2104967741 @default.
• W3192232155 cites W2119089141 @default.
• W3192232155 cites W2129618555 @default.
• W3192232155 cites W2132273917 @default.
• W3192232155 cites W2138709573 @default.
• W3192232155 cites W2160889462 @default.
• W3192232155 cites W2164777277 @default.
• W3192232155 cites W2280468452 @default.
• W3192232155 cites W2325857736 @default.
• W3192232155 cites W2399752080 @default.
• W3192232155 cites W2564114373 @default.
• W3192232155 cites W2605053334 @default.
• W3192232155 cites W2680280649 @default.
• W3192232155 cites W2767006273 @default.
• W3192232155 cites W2792396057 @default.
• W3192232155 cites W2809055287 @default.
• W3192232155 cites W2889765177 @default.
• W3192232155 cites W2908231224 @default.
• W3192232155 cites W2914275071 @default.
• W3192232155 cites W2943885339 @default.
• W3192232155 cites W2963938145 @default.
• W3192232155 cites W2971456559 @default.
• W3192232155 cites W2973473903 @default.
• W3192232155 cites W2992467249 @default.
• W3192232155 cites W3021132955 @default.
• W3192232155 cites W3048200244 @default.
• W3192232155 cites W3078897940 @default.
• W3192232155 cites W3118556209 @default.
• W3192232155 cites W3119073133 @default.
• W3192232155 cites W3158716137 @default.
• W3192232155 cites W3178593849 @default.
• W3192232155 cites W3180884803 @default.
• W3192232155 cites W4254929655 @default.
• W3192232155 doi "https://doi.org/10.1016/j.clnu.2021.06.028" @default.
• W3192232155 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34358843" @default.
• W3192232155 hasPublicationYear "2021" @default.
• W3192232155 type Work @default.
• W3192232155 sameAs 3192232155 @default.
• W3192232155 citedByCount "20" @default.
• W3192232155 countsByYear W31922321552021 @default.
• W3192232155 countsByYear W31922321552022 @default.
• W3192232155 countsByYear W31922321552023 @default.
• W3192232155 crossrefType "journal-article" @default.
• W3192232155 hasAuthorship W3192232155A5000432967 @default.
• W3192232155 hasAuthorship W3192232155A5001681060 @default.
• W3192232155 hasAuthorship W3192232155A5004283358 @default.
• W3192232155 hasAuthorship W3192232155A5007006789 @default.
• W3192232155 hasAuthorship W3192232155A5017617692 @default.
• W3192232155 hasAuthorship W3192232155A5021379796 @default.
• W3192232155 hasAuthorship W3192232155A5024257143 @default.
• W3192232155 hasAuthorship W3192232155A5031315906 @default.
• W3192232155 hasAuthorship W3192232155A5032404324 @default.
• W3192232155 hasAuthorship W3192232155A5036233749 @default.
• W3192232155 hasAuthorship W3192232155A5038522283 @default.
• W3192232155 hasAuthorship W3192232155A5039412958 @default.
• W3192232155 hasAuthorship W3192232155A5042397552 @default.

• next