ICU staffing feature phenotypes and their relationship with patients' outcomes: an unsupervised machine learning analysis.
Fernando Godinho ZampieriJorge I F SalluhLuciano C P AzevedoJeremy M KahnLucas P DamianiLunna P BorgesWilliam N VianaRoberto CostaThiago D CorrêaDieter E S ArayaMarcelo O MaiaMarcus A FerezAlexandre G R CarvalhoMarcos F KnibelUlisses O MeloMarcelo S SantinoThiago LisboaEliana B CaserBruno A M P BesenFernando A BozzaDerek C AngusMarcio Soaresnull nullPublished in: Intensive care medicine (2019)
Patients treated in ICUs combining 24/7 expert intensivist coverage, a dedicated pharmacist and nurses with greater autonomy had the best outcomes. All of these features represent achievable targets that should be considered by policy makers with an interest in promoting equal and optimal ICU care.
Keyphrases
- machine learning
- healthcare
- intensive care unit
- end stage renal disease
- newly diagnosed
- ejection fraction
- mental health
- public health
- chronic kidney disease
- artificial intelligence
- mechanical ventilation
- palliative care
- deep learning
- prognostic factors
- peritoneal dialysis
- metabolic syndrome
- patient reported outcomes
- acute respiratory distress syndrome
- skeletal muscle
- pain management
- glycemic control
- weight loss