Machine learning can predict outcomes and determine variables contributing to precise prediction, and can thus classify patients with different risk factors of outcomes. This study aimed to investigate the predictive accuracy for mortality and length of stay in intensive care unit (ICU) patients using machine learning, and to identify the variables contributing to the precise prediction or classification of patients. Patients (n = 12,747) admitted to the ICU at Chiba University Hospital were randomly assigned to the training and test cohorts. After learning using the variables on admission in the training cohort, the area under the curve (AUC) was analyzed in the test cohort to evaluate the predictive accuracy of the supervised machine learning classifiers, including random forest (RF) for outcomes (primary outcome, mortality; secondary outcome, length of ICU stay). The rank of the variables that contributed to the machine learning prediction was confirmed, and cluster analysis of the patients with risk factors of mortality was performed to identify the important variables associated with patient outcomes. Machine learning using RF revealed a high predictive value for mortality, with an AUC of 0.945 (95% confidence interval [CI] 0.922–0.977). In addition, RF showed high predictive value for short and long ICU stays, with AUCs of 0.881 (95% CI 0.876–0.908) and 0.889 (95% CI 0.849–0.936), respectively. Lactate dehydrogenase (LDH) was identified as a variable contributing to the precise prediction in machine learning for both mortality and length of ICU stay. LDH was also identified as a contributing variable to classify patients into sub-populations based on different risk factors of mortality. The machine learning algorithm could predict mortality and length of stay in ICU patients with high accuracy. LDH was identified as a contributing variable in mortality and length of ICU stay prediction and could be used to classify patients based on mortality risk.

There are currently no abstract classifiers, which can be used for new diagnostic test accuracy (DTA) systematic reviews to select primary DTA study abstracts from database searches. Our goal was to develop machine‐learning‐based abstract classifiers for new DTA systematic reviews through an open competition. We prepared a dataset of abstracts obtained through database searches from 11 reviews in different clinical areas. As the reference standard, we used the abstract lists that required manual full‐text review. We randomly splitted the datasets into a train set, a public test set, and a private test set. Competition participants used the training set to develop classifiers and validated their classifiers using the public test set. The classifiers were refined based on the performance of the public test set. They could submit as many times as they wanted during the competition. Finally, we used the private test set to rank the submitted classifiers. To reduce false exclusions, we used the Fbeta measure with a beta set to seven for evaluating classifiers. After the competition, we conducted the external validation using a dataset from a cardiology DTA review. We received 13,774 submissions from 1429 teams or persons over 4 months. The top‐honored classifier achieved a Fbeta score of 0.4036 and a recall of 0.2352 in the external validation. In conclusion, we were unable to develop an abstract classifier with sufficient recall for immediate application to new DTA systematic reviews. Further studies are needed to update and validate classifiers with datasets from other clinical areas.

Background: Machine learning can predict outcomes and determine variables contributing to precise prediction, and can thus classify patients with different risk factors of outcomes. This study aimed to investigate the predictive accuracy for mortality and length of stay in intensive care unit (ICU) patients using machine learning, and to identify the variables contributing to the precise prediction or classification of patients.Methods: Patients (n=12,747) admitted to the ICU at Chiba University Hospital were randomly assigned to the training and test cohorts. After learning using the variables on admission in the training cohort, the area under the curve (AUC) was analyzed in the test cohort to evaluate the predictive accuracy of the supervised machine learning classifiers, including random forest (RF) for outcomes (primary outcome, mortality; secondary outcome, and length of ICU stay). The rank of the variables that contributed to the machine learning prediction was confirmed, and cluster analysis of the patients with risk factors of mortality was performed to identify the important variables associated with patient outcomes.Results: Machine learning using RF revealed a high predictive value for mortality, with an AUC of 0.945. In addition, RF showed high predictive value for short and long ICU stays, with AUCs of 0.881 and 0.889, respectively. Lactate dehydrogenase (LDH) was identified as a variable contributing to the precise prediction in machine learning for both mortality and length of ICU stay. LDH was also identified as a contributing variable to classify patients into sub-populations based on different risk factors of mortality.Conclusion: The machine learning algorithm could predict mortality and length of stay in ICU patients with high accuracy. LDH was identified as a contributing variable in mortality and length of ICU stay prediction and could be used to classify patients based on mortality risk.

Background: Oliguria is an important indicator for the early detection of acute kidney injury (AKI) and prediction of poor outcomes in critically ill patients; however, the accuracy of a prediction model using machine learning has rarely been investigated. This study aimed to develop and evaluate a machine learning algorithm for predicting oliguria in patients admitted to the intensive care unit (ICU). Methods: This retrospective cohort study used electronic health record data of consecutive patients admitted to the ICU between 2010 and 2019. Oliguria was defined as urine output of less than 0.5 mL/kg/h. We developed a machine learning model using a light-gradient boosting machine to predict oliguria between 6 to 72 h. The accuracy of the model was evaluated using receiver operating characteristic curves. We calculated the Shapley additive explanations (SHAP) value to identify important variables in the prediction model. Subgroup analyses were conducted to compare the accuracy of the models in predicting oliguria based on sex, age, and furosemide administration. Results: Among 9,241 patients in the study, the proportions of patients with urine output < 0.5 mL/kg/h for 6 h and those with AKI during the ICU stay were 27.4% and 30.2%, respectively. The area under the curve (AUC) of the prediction algorithm for the onset of oliguria at 6 h and 72 h using 50 clinically relevant variables was 0.966 (95% confidence interval [CI] 0.965–0.968) and 0.923 (95% CI 0.921–0.926), respectively. The SHAP analysis for predicting oliguria at 6 h identified urine-related values, severity scores, serum creatinine, interleukin-6, fibrinogen/fibrin degradation products, and vital signs as important variables. Subgroup analyses revealed that males had a higher AUC than did females (0.969 and 0.952, respectively), and the non-furosemide group had a higher AUC than did the furosemide group (0.971 and 0.957, respectively). Conclusions: The present study demonstrated that a machine learning algorithm could accurately predict oliguria onset in ICU patients, suggesting a potential role for oliguria in the early diagnosis and optimal management of AKI.