Information Technology Reference
In-Depth Information
same performance. They revealed more difficulty when predicting the class ">= 30
cm
O
". Despite of these results all the models are using real data and are executed in
real-time meaning that the models may present different performances with new data.
Support Vector Machine obtained the best results. Decision Trees were important
to identify the variables that most influence the models.
The models presented demonstrate their viability predicting the Plateau Pressure
class and consequently constitute an important help to prevent the barotrauma
occurrence.
6
Future Work
For future research will take into consideration the following aspects:
•
To consider more variables such as gender, age, respiratory disease, if the
patient is a smoker and others. These variables must be added to the
prediction models in order to improve accuracy;
•
To explore the regression approach to predict continuous values;
•
To make predictions by hour for each one of the ventilated patients;
•
To embed these models into the INTCare Decision Support module and
identify whether the predictions made are valid.
Acknowledgements.
This work has been supported by FCT - Fundação para a
Ciência e Tecnologia within the Project Scope UID/CEC/00319/2013.
The authors would like to thank FCT (Foundation of Science and Technology,
Portugal) for the financial support through the contract PTDC/EEI-SII/1302/2012
(INTCare II).
References
[1]
Santos, M., Azevedo, C.: Data Mining Descoberta do conhecimento em base de dados.
FCA - Editora de Informática, Lda (2005)
[2]
Santos, M., Boa, M., Portela, F., Silva, Á., Rua, F.: Real-time prediction of organ failure
and outcome in intensive medicine. In: 2010 5th Iberian Conference on Information
Systems and Technologies (CISTI), pp. 1-6 (2010)
[3]
Koh, H., Tan, G.: Data mining applications in healthcare. J. Healthc. Inf. Manag. 19(2),
64-72 (2005)
[4]
Anzueto, A., Frutos-Vivar, F., Esteban, A., Alía, I., Brochard, L., Stewart, T., Benito, S.,
Tobin, M.J., Elizalde, J., Palizas, F., David, C.M., Pimentel, J., González, M., Soto, L.,
D'Empaire, G., Pelosi, P.: Incidence, risk factors and outcome of barotrauma in
mechanically ventilated patients. Intensive Care Med. 30(4), 612-619 (2004)
[5]
Al-Rawas, N., Banner, M.J., Euliano, N.R., Tams, C.G., Brown, J., Martin, A.D.,
Gabrielli, A.: Expiratory time constant for determinations of plateau pressure,
respiratory system compliance, and total resistance. Crit. Care 17(1), R23 (2013)
[6]
Boussarsar, M., Thierry, G., Jaber, S., Roudot-Thoraval, F., Lemaire, F., Brochard, L.:
Relationship between ventilatory settings and barotrauma in the acute respiratory
distress syndrome. Intensive Care Med. 28(4), 406-413 (2002)
Search WWH ::
Custom Search