Pursuing optimal prediction of discharge time in ICUS with machine learning methods
| Autor: | Cuadrado D, Riaño D, Gómez J, Bodí M, Sirgo G, Esteban F, García R, Rodríguez A |
|---|---|
| Přispěvatelé: | Universitat Rovira i Virgili |
| Rok vydání: | 2019 |
| Předmět: |
Medicina ii
Biotecnología Planejamento urbano e regional / demografia Matemática / probabilidade e estatística Ciências agrárias i Comunicació i informació General o multidisciplinar Educação física Medicina iii Engenharias i Medicina veterinaria Geociências Computer science artificial intelligence Ciências sociais aplicadas i Intensive care units Geografía Computer science theory & methods Engenharias ii Computer science (all) Biodiversidade Astronomia / física Química Engenharias iv Farmacia Arquitetura e urbanismo Arquitetura urbanismo e design Saúde coletiva Comunicação e informação Educação Linguística e literatura Artificial neural-networks Materiais Data-driven models Ciências biológicas i Ciência da computação Direito General computer science Discharge time prediction Odontología Medicina i Administração pública e de empresas ciências contábeis e turismo Theoretical computer science Ciências biológicas iii Ciências ambientais Engenharias iii Computer Science (Miscellaneous) Computer Science Artificial Intelligence Computer Science Theory & Methods Theoretical Computer Science Computer science (miscellaneous) Interdisciplinar Psicología Ensino Ciências biológicas ii Administração ciências contábeis e turismo Intelligent data analysis Length-of-stay Model Artes |
| Zdroj: | Lecture Notes In Computer Science Lecture Notes In Computer Science. 11526 LNAI 150-154 Repositori Institucional de la Universitat Rovira i Virgili Consejo Superior de Investigaciones Científicas (CSIC) Lecture Notes In Computer Science. 11526 LNAI150-154 Universitat Rovira i virgili (URV) |
| DOI: | 10.1007/978-3-030-21642-9_20 |
| Popis: | © Springer Nature Switzerland AG 2019. In hospital intensive care units (ICU), patients are under continuous evaluation. One of the purposes of this evaluation is to determine the expected number of days to discharge. This value is important to manage ICUs. Some studies show that health care professionals are good at predicting short-term discharge times, but not as good at long-term predictions. Machine learning methods can achieve 1.79-day average prediction error. We performed a study on 3,787 patient-days in the ICU of the Hospital Joan XXIII (Spain) to obtain a data-driven model to predict the discharge time of ICU patients, in a daily basis. Our model, which is based on random forest technology, obtained an error of 1.34 days. We studied the progression of the model as more data are available and predicted that the number of instances required to reduce the error below one day is 4,745. When we trained the model with all the available data, we obtained a mean error of less than half a day with a coefficient of determination (R2) above 97% in their predictions on either ICU survivors and not survivors. Similar results were obtained differentiating by patients’ gender and age, confirming our approach as a good means to achieve optimal performance when more data will be available. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|