Index  Topics 
ALARM monitoring system (synthetic) data set
Description
The ALARM ("A Logical Alarm Reduction Mechanism") is a Bayesian network designed to provide an alarm message system for patient monitoring.
Usage
data(alarm)
Format
The alarm
data set contains the following 37 variables:

CVP
(central venous pressure): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
PCWP
(pulmonary capillary wedge pressure): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
HIST
(history): a twolevel factor with levelsTRUE
andFALSE
. 
TPR
(total peripheral resistance): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
BP
(blood pressure): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
CO
(cardiac output): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
HRBP
(heart rate / blood pressure): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
HREK
(heart rate measured by an EKG monitor): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
HRSA
(heart rate / oxygen saturation): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
PAP
(pulmonary artery pressure): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
SAO2
(arterial oxygen saturation): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
FIO2
(fraction of inspired oxygen): a twolevel factor with levelsLOW
andNORMAL
. 
PRSS
(breathing pressure): a fourlevel factor with levelsZERO
,LOW
,NORMAL
andHIGH
. 
ECO2
(expelled CO2): a fourlevel factor with levelsZERO
,LOW
,NORMAL
andHIGH
. 
MINV
(minimum volume): a fourlevel factor with levelsZERO
,LOW
,NORMAL
andHIGH
. 
MVS
(minimum volume set): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
HYP
(hypovolemia): a twolevel factor with levelsTRUE
andFALSE
. 
LVF
(left ventricular failure): a twolevel factor with levelsTRUE
andFALSE
. 
APL
(anaphylaxis): a twolevel factor with levelsTRUE
andFALSE
. 
ANES
(insufficient anesthesia/analgesia): a twolevel factor with levelsTRUE
andFALSE
. 
PMB
(pulmonary embolus): a twolevel factor with levelsTRUE
andFALSE
. 
INT
(intubation): a threelevel factor with levelsNORMAL
,ESOPHAGEAL
andONESIDED
. 
KINK
(kinked tube): a twolevel factor with levelsTRUE
andFALSE
. 
DISC
(disconnection): a twolevel factor with levelsTRUE
andFALSE
. 
LVV
(left ventricular enddiastolic volume): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
STKV
(stroke volume): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
CCHL
(catecholamine): a twolevel factor with levelsNORMAL
andHIGH
. 
ERLO
(error low output): a twolevel factor with levelsTRUE
andFALSE
. 
HR
(heart rate): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
ERCA
(electrocauter): a twolevel factor with levelsTRUE
andFALSE
. 
SHNT
(shunt): a twolevel factor with levelsNORMAL
andHIGH
. 
PVS
(pulmonary venous oxygen saturation): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
ACO2
(arterial CO2): a threelevel factor with levelsLOW
,NORMAL
andHIGH
. 
VALV
(pulmonary alveoli ventilation): a fourlevel factor with levelsZERO
,LOW
,NORMAL
andHIGH
. 
VLNG
(lung ventilation): a fourlevel factor with levelsZERO
,LOW
,NORMAL
andHIGH
. 
VTUB
(ventilation tube): a fourlevel factor with levelsZERO
,LOW
,NORMAL
andHIGH
. 
VMCH
(ventilation machine): a fourlevel factor with levelsZERO
,LOW
,NORMAL
andHIGH
.
Note
The complete BN can be downloaded from http://www.bnlearn.com/bnrepository.
Source
Beinlich I, Suermondt HJ, Chavez RM, Cooper GF (1989). "The ALARM Monitoring System: A Case Study with Two Probabilistic Inference Techniques for Belief Networks". Proceedings of the 2nd European Conference on Artificial Intelligence in Medicine, 247–256.
Examples
# load the data. data(alarm) # create and plot the network structure. modelstring = paste0("[HISTLVF][CVPLVV][PCWPLVV][HYP][LVVHYP:LVF][LVF]", "[STKVHYP:LVF][ERLO][HRBPERLO:HR][HREKERCA:HR][ERCA][HRSAERCA:HR][ANES]", "[APL][TPRAPL][ECO2ACO2:VLNG][KINK][MINVINT:VLNG][FIO2][PVSFIO2:VALV]", "[SAO2PVS:SHNT][PAPPMB][PMB][SHNTINT:PMB][INT][PRSSINT:KINK:VTUB][DISC]", "[MVS][VMCHMVS][VTUBDISC:VMCH][VLNGINT:KINK:VTUB][VALVINT:VLNG]", "[ACO2VALV][CCHLACO2:ANES:SAO2:TPR][HRCCHL][COHR:STKV][BPCO:TPR]") dag = model2network(modelstring) ## Not run: graphviz.plot(dag)
Index  Topics 