<?xml version="1.0" encoding="ISO-8859-1"?>
<smile version="1.0" id="Asia" numsamples="10000" discsamples="10000">
	<nodes>
		<cpt id="VisitToAsia" diagtype="observation" ranked="true">
			<state id="NoVisit" label="F3" />
			<state id="Visit" label="F4" />
			<probabilities>0.99 0.01</probabilities>
		</cpt>
		<cpt id="Tuberculosis" diagtype="target" ranked="true">
			<state id="Absent" label="F5" />
			<state id="Present" label="F6" fault="true" />
			<parents>VisitToAsia</parents>
			<probabilities>0.99 0.01 0.95 0.05</probabilities>
		</cpt>
		<cpt id="Smoking" diagtype="observation" ranked="true">
			<state id="NonSmoker" label="F7" />
			<state id="Smoker" label="F8" />
			<probabilities>0.5 0.5</probabilities>
		</cpt>
		<cpt id="LungCancer" diagtype="target" ranked="true">
			<state id="Absent" label="F9" />
			<state id="Present" label="F10" fault="true" />
			<parents>Smoking</parents>
			<probabilities>0.99 0.01 0.9 0.1</probabilities>
		</cpt>
		<deterministic id="TbOrCa">
			<state id="Nothing" label="F11" />
			<state id="CancerORTuberculosis" label="F12" />
			<parents>Tuberculosis LungCancer</parents>
			<resultingstates>Nothing CancerORTuberculosis CancerORTuberculosis CancerORTuberculosis</resultingstates>
		</deterministic>
		<cpt id="XRay" diagtype="observation" ranked="true">
			<state id="Normal" label="F13" />
			<state id="Abnormal" label="F14" />
			<parents>TbOrCa</parents>
			<probabilities>0.95 0.05 0.02 0.98</probabilities>
		</cpt>
		<cpt id="Bronchitis" diagtype="target" ranked="true">
			<state id="Absent" label="F15" />
			<state id="Present" label="F16" fault="true" />
			<parents>Smoking</parents>
			<probabilities>0.7 0.3 0.4 0.6</probabilities>
		</cpt>
		<cpt id="Dyspnea" diagtype="observation" ranked="true">
			<state id="Absent" label="F17" />
			<state id="Present" label="F18" />
			<parents>TbOrCa Bronchitis</parents>
			<probabilities>0.9 0.1 0.2 0.8 0.3 0.7 0.1 0.9</probabilities>
		</cpt>
	</nodes>
	<extensions>
		<genie version="1.0" app="GeNIe 2.3.3520.1 1d480d954d39d00" name="David Spiegelhalter&apos;s Asia network" faultnameformat="nodestate">
			<comment>This is an example graphical model useful in demonstrating basics concepts of Bayesian networks in diagnosis.  This version of the model makes use of GeNIe diagnostic extensions.\nReference:\nThe Asia network first appeared in: Lauritzen, Steffen L. &amp; Spiegelhalter, David J. (1988). Local computations with probabilities on graphical structures and their application to expert systems, Journal of the Royal Statistical Society B, 50(2):157-224.</comment>
			<node id="VisitToAsia">
				<name>Visit To Asia?</name>
				<interior color="e5f6f7" />
				<outline color="0000bb" />
				<font color="333399" name="Arial" size="12" />
				<position>42 28 146 64</position>
				<comment>The node models whether the individual in question visited Asia recently. This is considered to be a risk factor in tuberculosis.</comment>
				<barchart active="true" width="128" height="64" />
			</node>
			<node id="Tuberculosis">
				<name>Tuberculosis?</name>
				<interior color="e5f6f7" />
				<outline color="0000bb" />
				<font color="333399" name="Arial" size="12" />
				<position>44 120 145 154</position>
				<comment>Presence or absence of tuberculosis.</comment>
				<barchart active="true" width="128" height="64" />
			</node>
			<node id="Smoking">
				<name>Smoking?</name>
				<interior color="e5f6f7" />
				<outline color="0000bb" />
				<font color="333399" name="Arial" size="12" />
				<position>270 28 350 64</position>
				<comment>Does the individual smoke or not? This is a serious risk factor in both lung cancer and in bronchitis.</comment>
				<barchart active="true" width="128" height="64" />
			</node>
			<node id="LungCancer">
				<name>Lung Cancer?</name>
				<interior color="e5f6f7" />
				<outline color="0000bb" />
				<font color="333399" name="Arial" size="12" />
				<position>200 114 282 161</position>
				<comment>Does the individual suffer from lung cancer?</comment>
				<barchart active="true" width="128" height="64" />
			</node>
			<node id="TbOrCa">
				<name>Tuberculosis or Lung Cancer?</name>
				<interior color="e5f6f7" />
				<outline color="0000bb" />
				<font color="333399" name="Arial" size="12" />
				<position>118 197 253 253</position>
				<comment>Does the individual suffer from either tuberculosis or lung cancer? This node models in practice existence of changes in the lungs, such as presence of a condensed mass.</comment>
				<barchart active="true" width="242" height="66" />
			</node>
			<node id="XRay">
				<name>X-Ray Result</name>
				<interior color="e5f6f7" />
				<outline color="0000bb" />
				<font color="333399" name="Arial" size="12" />
				<position>45 292 143 328</position>
				<comment>This node models the X-ray result. Both tuberculosis and lung cancer can be discovered on the X-ray because of presence of condensed mass in the lungs.</comment>
				<barchart active="true" width="128" height="64" />
			</node>
			<node id="Bronchitis">
				<name>Bronchitis?</name>
				<interior color="e5f6f7" />
				<outline color="0000bb" />
				<font color="333399" name="Arial" size="12" />
				<position>350 119 436 155</position>
				<comment>Does the individual suffer from bronchitis?</comment>
				<barchart active="true" width="128" height="64" />
			</node>
			<node id="Dyspnea">
				<name>Dyspnea?</name>
				<interior color="e5f6f7" />
				<outline color="0000bb" />
				<font color="333399" name="Arial" size="12" />
				<position>288 292 364 328</position>
				<comment>Does the individual suffer from dyspnea (shortness of breath)? Each of the diseases modeled can result in shortness of breath.</comment>
				<barchart active="true" width="128" height="66" />
			</node>
			<textbox>
				<caption>This is an example graphical model useful in demonstrating basics concepts of Bayesian networks in diagnosis.\n\nIt first appeared in:\nLauritzen, Steffen L. &amp; Spiegelhalter, David J. (1988). Local computations with probabilities on graphical structures and their application to expert systems, Journal of the Royal Statistical Society B, 50(2):157-224.\n\nThis version of the model makes use of GeNIe diagnostic extensions.</caption>
				<font color="333399" name="Arial" size="12" bold="true" />
				<position>482 20 800 286</position>
			</textbox>
		</genie>
	</extensions>
</smile>
