Machine learning in intensive care medicine: ready for take-off?

Fleuren, Lucas M.; Thoral, Patrick; Shillan, Duncan; Ercole, Ari; Elbers, Paul

doi:10.1007/s00134-020-06045-y

Cited by 51 publications

(39 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We extracted information on the following study characteristics: (1) design (categorized as retrospective-, prospective observational-and clinical [categorized as the following study designs: non-randomized clinical trials and randomized clinical trials/randomized controlled trials (RCT)] designs); (2) aim (categorized as alarm reduction, assessing clinical notes, classifying sub-populations, detecting spurious recorded values, determining physiological thresholds, improving prognostic models/risk scoring system, improving upon previous methods, predicting complications, predicting health improvement, predicting length of stay, predicting medication administration, predicting mortality and predicting readmissions) (in case studies had more than one aim, all aims were recorded); (3) size of the dataset (the total number of patients used for data analysis); (4) level of validation (categorized as internal validation [models are validated on patients who are included in studies' own dataset], external validation [models are validated on data of patients from other geographical locations or times], prospective observational validation, clinical validation and no reported validation); (5) AI level of readiness, which was assessed over time by applying the general concept of technology readiness levels introduced by National Aeronautics and Space Administration (NASA), which previously has been translated to the ICU environment [the consecutive levels increase from development to the clinical implementation of AI: problem identification (level 1), proposal of solution (level 2), model prototyping and development (level 3 and 4), model validation (level 5), real-time testing (level 6), workflow integration (level 7), clinical testing (level 8), and integration in clinical practice (level 9)] [21,22]; (6) clinical study design and effects on patient outcome measures were extracted [categorized as reduced length of ICU stay, reduced overall mortality, reduced time on mechanical ventilation, reduced rate of complications and other (with details)]. Clinical study designs were considered to be either pre-postimplementation trials, non-randomized clinical trials or randomized clinical trials.…”

Section: Data Collection and Review Processmentioning

confidence: 99%

Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit

Sande

Genderen

Huiskens³

et al. 2021

Intensive Care Med

134

View full text Add to dashboard Cite

Purpose: Due to the increasing demand for intensive care unit (ICU) treatment, and to improve quality and efficiency of care, there is a need for adequate and efficient clinical decision-making. The advancement of artificial intelligence (AI) technologies has resulted in the development of prediction models, which might aid clinical decision-making. This systematic review seeks to give a contemporary overview of the current maturity of AI in the ICU, the research methods behind these studies, and the risk of bias in these studies.Methods: A systematic search was conducted in Embase, Medline, Web of Science Core Collection and Cochrane Central Register of Controlled Trials databases to identify eligible studies. Studies using AI to analyze ICU data were considered eligible. Specifically, the study design, study aim, dataset size, level of validation, level of readiness, and the outcomes of clinical trials were extracted. Risk of bias in individual studies was evaluated by the Prediction model Risk Of Bias ASsessment Tool (PROBAST). Results:Out of 6455 studies identified through literature search, 494 were included. The most common study design was retrospective [476 studies (96.4% of all studies)] followed by prospective observational [8 (1.6%)] and clinical [10 (2%)] trials. 378 (80.9%) retrospective studies were classified as high risk of bias. No studies were identified that reported on the outcome evaluation of an AI model integrated in routine clinical practice. Conclusion:The vast majority of developed ICU-AI models remain within the testing and prototyping environment; only a handful were actually evaluated in clinical practice. A uniform and structured approach can support the development, safe delivery, and implementation of AI to determine clinical benefit in the ICU.

show abstract

Section: Data Collection and Review Processmentioning

confidence: 99%

Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit

Sande

Genderen

Huiskens³

et al. 2021

Intensive Care Med

134

View full text Add to dashboard Cite

show abstract

“…To develop the prediction models, we applied five algorithms, including conventional logistic regression, 28 Ridge regression, 29 Elastic net, 30 Kernel‐based Support Vector Machine (SVM), 31 and Random forest, 32 to the derivation dataset. The hyperparameters and model architecture for these algorithms were selected using a 10‐fold cross‐validation (CV) to prevent overfitting and to eliminate data bias in model selection.…”

Section: Methodsmentioning

confidence: 99%

Machine learning prediction models for postpartum depression: A multicenter study in Japan

Matsuo

Ushida

Emoto

et al. 2022

J of Obstet and Gynaecol

View full text Add to dashboard Cite

Aim Postpartum depression (PPD) and perinatal mental health care are of growing importance worldwide. Here we aimed to develop and validate machine learning models for the prediction of PPD, and to evaluate the usefulness of the recently adopted 2‐week postpartum checkup in some parts of Japan for the identification of women at high risk of PPD. Methods A multicenter retrospective study was conducted using the clinical data of 10 013 women who delivered at ≥35 weeks of gestation at 12 maternity care hospitals in Japan. PPD was defined as an Edinburgh Postnatal Depression Scale score of ≥9 points at 4 weeks postpartum. We developed prediction models using conventional logistic regression and four machine learning algorithms based on the information that can be routinely collected in daily clinical practice. The model performance was evaluated using the area under the receiver operating characteristic curve (AUROC). Results In the machine learning models developed using clinical data before discharge, the AUROCs were similar to those in the conventional logistic regression models (AUROC, 0.569–0.630 vs. 0.626). The incorporation of additional 2‐week postpartum checkup data into the model significantly improved the predictive performance for PPD compared to that without in the Ridge regression and Elastic net (AUROC, 0.702 vs. 0.630 [p < 0.01] and 0.701 vs. 0.628 [p < 0.01], respectively). Conclusions Our machine learning models did not achieve better predictive performance for PPD than conventional logistic regression models. However, we demonstrated the usefulness of the 2‐week postpartum checkup for the identification of women at high risk of PPD.

show abstract

“…In a recent review of 172 AI-driven solutions created from routinely collected chart data, the clinical readiness level for AI was low. In that study, the maturity of the AI was classified into nine stages corresponding to real world application [ 33 ]. Strikingly, around 93% of all analyzed articles remained below stage 4, with no external validation process, and only 2% of published studies had performed prospective validation.…”

Section: Pitfalls Of Ai In Critical Carementioning

confidence: 99%

Artificial Intelligence in Critical Care Medicine

2022

View full text Add to dashboard Cite

This article is one of ten reviews selected from the Annual Update in Intensive Care and Emergency Medicine 2022. Other selected articles can be found online at https://www.biomedcentral.com/collections/annualupdate2022 . Further information about the Annual Update in Intensive Care and Emergency Medicine is available from https://link.springer.com/bookseries/8901 .

show abstract

Machine learning in intensive care medicine: ready for take-off?

Cited by 51 publications

References 3 publications

Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit

Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit

Machine learning prediction models for postpartum depression: A multicenter study in Japan

Artificial Intelligence in Critical Care Medicine

Contact Info

Product

Resources

About