Comparison of the prevalence of 21 GLIM phenotypic and etiologic criteria combinations and association with 30-day outcomes in people with cancer: A retrospective observational study

Kiss, Nicole; Steer, Belinda; Schueren, Marian A.E. de van der; Loeliger, Jenelle; Alizadehsani, Roohallah; Edbrooke, Lara; Deftereos, Irene; Laing, Erin; Khosravi, Abbas

doi:10.1016/j.clnu.2022.03.024

Cited by 18 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is important to note that we were unable to determine if the most important GLIM combinations to predict 30‐day mortality and unplanned admission were associated with a higher or lower probability of these adverse outcomes. This was the case also in our previous paper, 14 and is due to high entropy in the nodes of the decision tree which classify participants into the predicted class (unplanned admission, no admission). Entropy is a value of one to zero and represents the degree of impurity in the decision tree node.…”

Section: Discussionsupporting

confidence: 73%

“…This indicates that if muscle mass is excluded from the GLIM assessment there is minimal impact on the ability to predict 30‐day mortality. In a prior publication we similarly found that machine learning models using GLIM combinations with and without inflammation performed almost identically in predicting 30‐day mortality 14 . However, it must not be overlooked that excluding the assessment of muscle mass resulted in a substantial number of participants not being diagnosed with malnutrition.…”

Section: Discussionmentioning

confidence: 60%

“…This can be interpreted as follows: 84 out of 100 samples were correctly classified (accuracy), 40% of participants who died were correctly detected (sensitivity) and 85% of participants who did not die were correctly detected. Our previous publication reported the most important GLIM combinations and metrics of the machine learning model for all 21 GLIM combinations 14 . Table 3 provides a comparison between the subset of nine GLIM combinations excluding muscle mass and all 21 GLIM combinations, demonstrating the performance of the model is largely unchanged using the subset excluding muscle mass.…”

Section: Resultsmentioning

confidence: 99%

“…An objective measure of inflammation was not available in this dataset and instead disease severity was rated according to the presence or absence of metastatic disease. Our group recently demonstrated that metastatic disease can be used as a proxy for inflammation in the absence of an objective measure 14 . The data used to apply the GLIM phenotypic or aetiologic criteria and if malnutrition was moderate or severe are presented in Figure 1.…”

Section: Methodsmentioning

confidence: 99%

See 3 more Smart Citations

Machine learning models to predict outcomes at 30‐days using Global Leadership Initiative on Malnutrition combinations with and without muscle mass in people with cancer

Kiss

Steer

Schueren

et al. 2023

J cachexia sarcopenia muscle

Self Cite

View full text Add to dashboard Cite

Background Equipment to assess muscle mass is not available in all health services. Yet we have limited understanding of whether applying the Global Leadership Initiative on Malnutrition (GLIM) criteria without an assessment of muscle mass affects the ability to predict adverse outcomes. This study used machine learning to determine which combinations of GLIM phenotypic and etiologic criteria are most important for the prediction of 30‐day mortality and unplanned admission using combinations including and excluding low muscle mass. Methods In a cohort of 2801 participants from two cancer malnutrition point prevalence studies, we applied the GLIM criteria with and without muscle mass. Phenotypic criteria were assessed using ≥5% unintentional weight loss, body mass index, subjective assessment of muscle stores from the PG‐SGA. Aetiologic criteria included self‐reported reduced food intake and inflammation (metastatic disease). Machine learning approaches were applied to predict 30‐day mortality and unplanned admission using models with and without muscle mass. Results Participants with missing data were excluded, leaving 2494 for analysis [49.6% male, mean (SD) age: 62.3 (14.2) years]. Malnutrition prevalence was 19.5% and 17.5% when muscle mass was included and excluded, respectively. However, 48 (10%) of malnourished participants were missed if muscle mass was excluded. For the nine GLIM combinations that excluded low muscle mass the most important combinations to predict mortality were (1) weight loss and inflammation and (2) weight loss and reduced food intake. Machine learning metrics were similar in models excluding or including muscle mass to predict mortality (average accuracy: 84% vs. 88%; average sensitivity: 41% vs. 38%; average specificity: 85% vs. 89%). Weight loss and reduced food intake was the most important combination to predict unplanned hospital admission. Machine learning metrics were almost identical in models excluding or including muscle mass to predict unplanned hospital admission, with small differences observed only if reported to one decimal place (average accuracy: 77% vs. 77%; average sensitivity: 29% vs. 29%; average specificity: 84% vs. 84%). Conclusions Our results indicate predictive ability is maintained, although the ability to identify all malnourished patients is compromised, when muscle mass is excluded from the GLIM diagnosis. This has important implications for assessment in health services where equipment to assess muscle mass is not available. Our findings support the robustness of the GLIM approach and an ability to apply some flexibility in excluding certain phenotypic or aetiologic components if necessary, although some cases will be missed.

show abstract

Section: Discussionsupporting

confidence: 73%

Section: Discussionmentioning

confidence: 60%

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Machine learning models to predict outcomes at 30‐days using Global Leadership Initiative on Malnutrition combinations with and without muscle mass in people with cancer

Kiss

Steer

Schueren

et al. 2023

J cachexia sarcopenia muscle

Self Cite

View full text Add to dashboard Cite

show abstract

“…The results of evaluating the prepared decision tree on our dataset are available in Table 2 . The evaluation was done based on accuracy [ 41 ], sensitivity [ 42 ], specificity [ 43 ], precision [ 44 ] and F1-score [ 45 ]. In Fig.…”

Section: Resultsmentioning

confidence: 99%

Identification of Clinical Features Associated with Mortality in COVID-19 Patients

et al. 2023

Self Cite

View full text Add to dashboard Cite

Understanding clinical features and risk factors associated with COVID-19 mortality is needed to early identify critically ill patients, initiate treatments and prevent mortality. A retrospective study on COVID-19 patients referred to a tertiary hospital in Iran between March and November 2020 was conducted. COVID-19-related mortality and its association with clinical features including headache, chest pain, symptoms on computerized tomography (CT), hospitalization, time to infection, history of neurological disorders, having a single or multiple risk factors, fever, myalgia, dizziness, seizure, abdominal pain, nausea, vomiting, diarrhoea and anorexia were investigated. Based on the investigation outcome, decision tree and dimension reduction algorithms were used to identify the aforementioned risk factors. Of the 3008 patients (mean age 59.3 ± 18.7 years, 44% women) with COVID-19, 373 died. There was a significant association between COVID-19 mortality and old age, headache, chest pain, low respiratory rate, oxygen saturation < 93%, need for a mechanical ventilator, having symptoms on CT, hospitalization, time to infection, neurological disorders, cardiovascular diseases and having a risk factor or multiple risk factors. In contrast, there was no significant association between mortality and gender, fever, myalgia, dizziness, seizure, abdominal pain, nausea, vomiting, diarrhoea and anorexia. Our results might help identify early symptoms related to COVID-19 and better manage patients according to the extracted decision tree. The proposed ML models identified a number of clinical features and risk factors associated with mortality in COVID-19 patients. These models if implemented in a clinical setting might help to early identify patients needing medical attention and care. However, more studies are needed to confirm these findings.

show abstract

GLIM criteria validation and reliability in critically ill patients with cancer: A prospective study

Gersely,

Klein,

da Rocha

et al. 2024

J Parenter Enteral Nutr

View full text Add to dashboard Cite

BackgroundThe present study aims to assess the interrater reliability of the Global Leadership Initiative on Malnutrition (GLIM) criteria, a framework to provide a consensus diagnosis of malnutrition. We also aimed to investigate its concurrent and predictive validity in the context of patients with cancer admitted to the intensive care unit (ICU).MethodsIndividuals aged ≥19 years with cancer who were admitted to the ICU within 48 h of their initial hospital admission were included. Nutrition status was assessed with the Nutritional Risk Screening 2002, the Subjective Global Assessment (SGA), and the GLIM criteria. Interrater reliability was assessed by the kappa test (>0.80). The SGA served as the established benchmark for assessing concurrent validity. To evaluate predictive validity, the occurrence of mortality within 30 days was the outcome, and Cox regression models were applied.ResultsA total of 212 patients were included: 66.9% were at nutrition risk, and 45.8% were malnourished according to the SGA. According to the GLIM criteria, 68.4% and 66% were identified as malnourished by evaluators 1 and 2, respectively (κ = 0.947; P < 0.001). The GLIM combination incorporating weight loss and the presence of inflammation exhibited sensitivity (82.4%) and specificity (92%). In the multivariate Cox regression models, most GLIM combinations emerged as independent predictors of complications.ConclusionThe GLIM criteria demonstrated satisfactory interrater reliability, and the combination involving weight loss and the presence of inflammation exhibited noteworthy sensitivity and specificity. Most GLIM combinations emerged as independent predictors of 30‐day mortality.

show abstract

Comparison of the prevalence of 21 GLIM phenotypic and etiologic criteria combinations and association with 30-day outcomes in people with cancer: A retrospective observational study

Cited by 18 publications

References 18 publications

Machine learning models to predict outcomes at 30‐days using Global Leadership Initiative on Malnutrition combinations with and without muscle mass in people with cancer

Machine learning models to predict outcomes at 30‐days using Global Leadership Initiative on Malnutrition combinations with and without muscle mass in people with cancer

Identification of Clinical Features Associated with Mortality in COVID-19 Patients

GLIM criteria validation and reliability in critically ill patients with cancer: A prospective study

Contact Info

Product

Resources

About