A clinically applicable approach to continuous prediction of future acute kidney injury
| Autor: | Hugh Montgomery, Alan Karthikesalingam, Xavier Glorot, Christopher Nielson, Harry Askham, Suman V. Ravuri, Trevor Back, Joseph R. Ledsam, Michal Zielinski, Kelly S. Peterson, Geraint Rees, Alistair Connell, Nenad Tomasev, Julien Cornebise, Ivan Protsyuk, Andre Saraiva, Demis Hassabis, Cian Hughes, Chris Laing, Ruth M. Reeves, Shakir Mohamed, Dominic King, Anne Mottram, Jack W. Rae, Mustafa Suleyman, Clemens Meyer, Clifton R. Baker |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Adult
Male medicine.medical_specialty Adolescent medicine.medical_treatment 030232 urology & nephrology Datasets as Topic Translational research Context (language use) Risk Assessment Article Pulmonary Disease Chronic Obstructive Young Adult 03 medical and health sciences 0302 clinical medicine Humans Medicine Computer Simulation False Positive Reactions 030212 general & internal medicine Young adult Adverse effect Intensive care medicine Dialysis Aged Preventive healthcare Aged 80 and over Multidisciplinary Clinical Laboratory Techniques business.industry Uncertainty Acute kidney injury Acute Kidney Injury Middle Aged medicine.disease ROC Curve Female business Risk assessment |
| Zdroj: | Nature |
| ISSN: | 1476-4687 0028-0836 |
| Popis: | The early prediction of deterioration could have an important role in supporting healthcare professionals, as an estimated 11% of deaths in hospital follow a failure to promptly recognize and treat deteriorating patients1. To achieve this goal requires predictions of patient risk that are continuously updated and accurate, and delivered at an individual level with sufficient context and enough time to act. Here we develop a deep learning approach for the continuous risk prediction of future deterioration in patients, building on recent work that models adverse events from electronic health records2–17 and using acute kidney injury—a common and potentially life-threatening condition18—as an exemplar. Our model was developed on a large, longitudinal dataset of electronic health records that cover diverse clinical environments, comprising 703,782 adult patients across 172 inpatient and 1,062 outpatient sites. Our model predicts 55.8% of all inpatient episodes of acute kidney injury, and 90.2% of all acute kidney injuries that required subsequent administration of dialysis, with a lead time of up to 48 h and a ratio of 2 false alerts for every true alert. In addition to predicting future acute kidney injury, our model provides confidence assessments and a list of the clinical features that are most salient to each prediction, alongside predicted future trajectories for clinically relevant blood tests9. Although the recognition and prompt treatment of acute kidney injury is known to be challenging, our approach may offer opportunities for identifying patients at risk within a time window that enables early treatment. A deep learning approach that predicts the risk of acute kidney injury may help to identify patients at risk of health deterioration within a time window that enables early treatment. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink