Illness severity assessment of older adults in critical illness using machine learning (ELDER-ICU): an international multicentre study with subgroup bias evaluation. Liu X, et al, Lancet Digit Health 2023.

  • Proposé le : 07/11/2024 04:07:15
  • Par : Bot
  • Avec la version du site : v2021_01_12
  • Revu par :
    • Mettre votre nom d'utilisateur
    • Mettre votre nom d'utilisateur
Notes sur les tags :
  • Adopter cette revue :
    Si vous souhaitez prendre en charge cette revue d'article, merci de remplacer le tag Non_attribué par Attribué et ajoutez aussi votre nom d'utilisateur à l'emplacement prévu.
  • Réaliser des modifications :
    Pour modifier ce document, il est nécessaire d'être connecté au site. Pour cela, assurez-vous d'avoir des identifiants valides. Si vous n'en avez pas, contactez-nous. Pour vous connecter, cliquez sur l'icône dans la barre de navigation.
  • Demander la finalisation de la revue de l'article :
    Une fois revue et complétée, merci de remplacer l'étiquette Non_finalisé par A_finaliser. Un administrateur se chargera de valider la revue et de la publier avec le tag Finalisé.

Background: Comorbidity, frailty, and decreased cognitive function lead to a higher risk of death in elderly patients (more than 65 years of age) during acute medical events. Early and accurate illness severity assessment can support appropriate decision making for clinicians caring for these patients. We aimed to develop ELDER-ICU, a machine learning model to assess the illness severity of older adults admitted to the intensive care unit (ICU) with cohort-specific calibration and evaluation for potential model bias.

Methods: In this retrospective, international multicentre study, the ELDER-ICU model was developed using data from 14 US hospitals, and validated in 171 hospitals from the USA and Netherlands. Data were extracted from the Medical Information Mart for Intensive Care database, electronic ICU Collaborative Research Database, and Amsterdam University Medical Centers Database. We used six categories of data as predictors, including demographics and comorbidities, physical frailty, laboratory tests, vital signs, treatments, and urine output. Patient data from the first day of ICU stay were used to predict in-hospital mortality. We used the eXtreme Gradient Boosting algorithm (XGBoost) to develop models and the SHapley Additive exPlanations method to explain model prediction. The trained model was calibrated before internal, external, and temporal validation. The final XGBoost model was compared against three other machine learning algorithms and five clinical scores. We performed subgroup analysis based on age, sex, and race. We assessed the discrimination and calibration of models using the area under receiver operating characteristic (AUROC) and standardised mortality ratio (SMR) with 95% CIs.

Findings: Using the development dataset (n=50 366) and predictive model building process, the XGBoost algorithm performed the best in all types of validations compared with other machine learning algorithms and clinical scores (internal validation with 5037 patients from 14 US hospitals, AUROC=0·866 [95% CI 0·851-0·880]; external validation in the US population with 20 541 patients from 169 hospitals, AUROC=0·838 [0·829-0·847]; external validation in European population with 2411 patients from one hospital, AUROC=0·833 [0·812-0·853]; temporal validation with 4311 patients from one hospital, AUROC=0·884 [0·869-0·897]). In the external validation set (US population), the median AUROCs of bias evaluations covering eight subgroups were above 0·81, and the overall SMR was 0·99 (0·96-1·03). The top ten risk predictors were the minimum Glasgow Coma Scale score, total urine output, average respiratory rate, mechanical ventilation use, best state of activity, Charlson Comorbidity Index score, geriatric nutritional risk index, code status, age, and maximum blood urea nitrogen. A simplified model containing only the top 20 features (ELDER-ICU-20) had similar predictive performance to the full model.

Interpretation: The ELDER-ICU model reliably predicts the risk of in-hospital mortality using routinely collected clinical features. The predictions could inform clinicians about patients who are at elevated risk of deterioration. Prospective validation of this model in clinical practice and a process for continuous performance monitoring and model recalibration are needed.

Funding: National Institutes of Health, National Natural Science Foundation of China, National Special Health Science Program, Health Science and Technology Plan of Zhejiang Province, Fundamental Research Funds for the Central Universities, Drug Clinical Evaluate Research of Chinese Pharmaceutical Association, and National Key R&D Program of China.

Références de l'article


Discussion

  • Cette section peut être éditée par les relecteurs, les rédacteurs, les modérateurs et les administrateurs. Elle regroupe l'ensemble des échanges autours de la référence ci-dessus présentée.
  • Référez-vous à cette page pour connaître le rôle des utilisateurs et pour participer à la discussion.
  • Il n'y a, pour l'instant, aucune discussion en cours.

Éditer la discussion



Gardez le contact

Suivez notre utilisateur Twitter : @AgingPapers
Nos rencontres visio