// ~->[DNET-1]->~

// File created by an unlicensed user using Netica 1.12
// on Sep 26, 2003 at 11:48:27.

bnet asia1 {
comment = "\n\
	Chest Clinic                                            \
	Copyright 1998 Norsys Software Corp.\n\n\
	This belief network is also known as \"Asia\", and is an \
	example which is popular \n\
	for introducing belief networks.  It is from \
	Lauritzen&Spiegelhalter88 (see below).\n\
	It is for example purposes only, and should not be used for \
	real decision making.\n\n\
	It is a simplified version of a network that could be used to \
	diagnose patients arriving\n\
	at a clinic.  Each node in the network corresponds to some \
	condition of the patient,\n\
	for example, \"Visit to Asia\" indicates whether the patient \
	recently visited Asia.\n\
	To diagnose a patient, values are entered for nodes when they \
	are known.  \n\
	Netica then automatically re-calculates the probabilities for \
	all the other nodes,\n\
	based on the relationships between them.  The links between \
	the nodes indicate how the\n\
	relationships between the nodes are structured.\n\n\
	The two top nodes are for predispositions which influence the \
	likelihood of the diseases. \n\
	Those diseases appear in the row below them.  At the bottom \
	are symptoms of the diseases.\n\
	To a large degree, the links of the network correspond to \
	causation.  \n\
	This is a common structure for diagnostic networks: \
	predisposition nodes at the top, \n\
	with links to nodes representing internal conditions and \
	failure states, which in turn have\n\
	links to nodes for observables.  Often there are many layers \
	of nodes representing\n\
	internal conditions, with links between them representing \
	their complex inter-relationships.\n\n\
	This network is from Lauritzen, Steffen L. and David J. \
	Spiegelhalter (1988) \"Local \n\
	computations with probabilities on graphical structures and \
	their application to expert \n\
	systems\" in Journal Royal Statistics Society B, 50(2), \
	157-194.\n\n\n\
	TUTORIAL:            Basic Probabilistic Inference\n\
	--------\n\n\
	Keep in mind when doing tutorials that there is a great deal \
	of assitance available\n\
	from Netica's onscreen help, often about the exact networks \
	of the tutorials.\n\
	For this example, choose Help->Contents/Index, click on the \
	Index tab, type in\n\
	\"Asia\", and go to the example.\n\n\
	All the information contained in a belief network can be \
	observed by examining 3 things.\n\n\
	First, there is the network structure, consisting of the \
	nodes and their links,\n\
	which you can see in the network diagram currently being \
	displayed.\n\n\
	Second, are the properties of each node, which you can see in \
	their node dialog box,\n\
	obtained by double-clicking on the node.\n\n\
	Third, are the actual relationships between the nodes, which \
	you can see by \n\
	single-clicking on a node to select it, then choosing \
	Relation->View/Edit.  \n\
	The relationship may be probabilistic or functional.  For \
	example, click on \n\
	\"Lung Cancer\", and then choose Relation->View/Edit, to see \
	its probabilistic relation \n\
	with Smoking (the numbers are for example purposes only, and \
	may not reflect reality).\n\
	If you click on \"Tuberculosis or Cancer\", and choose \
	Relation->View/Edit, you can see\n\
	its functional dependence on Tuberculosis and Lung Cancer.\n\n\
	To compile the network for use, click on its window to make \
	it active,\n\
	and choose Network->Compile. \n\n\
	The appropriate data structures for fast inference have been \
	built internally.  \n\
	The bars in each node have darkened, indicating that they and \
	the numbers beside them\n\
	are now valid data.  The indicate the probabilities of each \
	state of the node.\n\n\
	Suppose we want to \"diagnose\" a new patient.  When she \
	first enters the clinic,\n\
	without having any information about her, we believe she has \
	lung cancer with a\n\
	probability of 5.5%, as can be seen on the Lung Cancer node \
	(the number may be higher\n\
	than that for the general population, because something has \
	led her to the chest clinic).\n\n\
	If she has an abnormal x-ray, that information can be entered \
	by clicking on the word\n\
	\"Abnormal\" of the \"XRay Result\" node (in a real-world \
	belief network, you would probably\n\
	be able to enter in exactly what way the x-ray was \
	\"abnormal\").\n\n\
	All the probability numbers and bars will change to take into \
	account the finding.\n\
	Now the probability that she has lung cancer has increased to \
	48.9%.\n\n\
	If you further indicate that she has made a visit to asia \
	recently, by clicking on\n\
	\"Visit\", the probability of lung cancer decreases to 37.1%, \
	because the abnormal XRay is \n\
	partially explained away by a greater chance of Tuberculosis \
	(which she could \n\
	catch in Asia).  Old fashioned medical expert systems had \
	problems with this kind of \n\
	reasoning, since each of the findings \"Abnormal XRay\" and \
	\"Visit to Asia\" by themselves\n\
	increase or leave the same the probability of lung cancer.\n\n\
	You can try entering and changing some more findings.  To \
	remove a finding, simply click\n\
	on its name again.  If you want to remove all the findings (a \
	new patient has just walked\n\
	in), choose Network->Remove Findings.\n\n\n\n\n\
	";
whenchanged = 1064540903;

visual V1 {
	defdispform = BELIEFBARS;
	nodelabeling = TITLE;
	nodefont = font {shape= "Palatino"; size= 14;};
	linkfont = font {shape= "Arial"; size= 9;};
	windowposn = (22, 22, 816, 492);
	CommentShowing = TRUE;
	CommentWindowPosn = (22, 491, 815, 729);
	resolution = 72;
	drawingbounds = (1104, 730);
	showpagebreaks = FALSE;
	usegrid = TRUE;
	gridspace = (6, 6);
	PrinterSetting A {
		margins = (1270, 1270, 1270, 1270);
		landscape = FALSE;
		magnify = 1;
		};
	};

node VisitAsia {
	kind = NATURE;
	discrete = TRUE;
	chance = CHANCE;
	states = (Visit, No_Visit);
	parents = ();
	probs = 
		// Visit        No_Visit     
		  (0.01,        0.99);
	title = "Visit To Asia";
	comment = "Patient has recently visited Asia";
	whenchanged = 904512863;
	belief = (0.01, 0.99);
	visual V1 {
		center = (126, 54);
		height = 7;
		};
	};

node Tuberculosis {
	kind = NATURE;
	discrete = TRUE;
	chance = CHANCE;
	states = (Present, Absent);
	parents = (VisitAsia);
	probs = 
		// Present      Absent         // VisitAsia 
		 ((0.05,        0.95),         // Visit     
		  (0.01,        0.99));        // No_Visit  ;
	title = "Tuberculosis";
	belief = (0.0104, 0.9896);
	visual V1 {
		center = (126, 156);
		height = 1;
		};
	};

node Smoking {
	kind = NATURE;
	discrete = TRUE;
	chance = CHANCE;
	states = (Smoker, NonSmoker);
	parents = ();
	probs = 
		// Smoker       NonSmoker    
		  (0.5,         0.5);
	title = "Smoking";
	belief = (0.5, 0.5);
	visual V1 {
		center = (618, 54);
		height = 9;
		};
	};

node Pollution {
	kind = NATURE;
	discrete = TRUE;
	chance = CHANCE;
	states = (Low, High);
	parents = ();
	probs = 
		// Low          High         
		  (0.9,         0.1);
	numcases = 1;
	whenchanged = 1064540903;
	belief = (0.9, 0.1);
	visual V1 {
		center = (360, 54);
		height = 10;
		};
	};

node Cancer {
	kind = NATURE;
	discrete = TRUE;
	chance = CHANCE;
	states = (Present, Absent);
	parents = (Smoking, Pollution);
	probs = 
		// Present      Absent          // Smoking   Pollution 
		(((0.1,         0.9),           // Smoker    Low       
		  (0.15,        0.85)),         // Smoker    High      
		 ((0.01,        0.99),          // NonSmoker Low       
		  (0.02,        0.98)));        // NonSmoker High      ;
	numcases = 
		                  // Smoking   Pollution 
		 ((1,             // Smoker    Low       
		   1),            // Smoker    High      
		  (1,             // NonSmoker Low       
		   1));           // NonSmoker High      ;
	title = "Lung Cancer";
	whenchanged = 1064540891;
	belief = (0.058, 0.942);
	visual V1 {
		center = (384, 156);
		height = 4;
		link 2 {
			path = ((369, 92), (376, 118));
			};
		};
	};

node TbOrCa {
	kind = NATURE;
	discrete = TRUE;
	chance = DETERMIN;
	states = (True, False);
	parents = (Tuberculosis, Cancer);
	functable = 
		                     // Tuberculosis Cancer  
		 ((True,             // Present      Present 
		   True),            // Present      Absent  
		  (True,             // Absent       Present 
		   False));          // Absent       Absent  ;
	title = "Tuberculosis\nor Cancer";
	whenchanged = 2147483647;
	belief = (0.0677968, 0.932203);
	visual V1 {
		center = (264, 264);
		height = 3;
		link 1 {
			path = ((171, 193), (217, 228));
			};
		};
	};

node XRay {
	kind = NATURE;
	discrete = TRUE;
	chance = CHANCE;
	states = (Abnormal, Normal);
	parents = (TbOrCa);
	probs = 
		// Abnormal     Normal         // TbOrCa 
		 ((0.98,        0.02),         // True   
		  (0.05,        0.95));        // False  ;
	title = "XRay Result";
	whenchanged = 904512850;
	belief = (0.113051, 0.886949);
	visual V1 {
		center = (138, 366);
		height = 2;
		};
	};

node Bronchitis {
	kind = NATURE;
	discrete = TRUE;
	chance = CHANCE;
	states = (Present, Absent);
	parents = (Smoking);
	probs = 
		// Present      Absent         // Smoking   
		 ((0.6,         0.4),          // Smoker    
		  (0.3,         0.7));         // NonSmoker ;
	title = "Bronchitis";
	belief = (0.45, 0.55);
	visual V1 {
		center = (636, 156);
		height = 6;
		};
	};

node Dyspnea {
	kind = NATURE;
	discrete = TRUE;
	chance = CHANCE;
	states = (Present, Absent);
	parents = (TbOrCa, Bronchitis);
	probs = 
		// Present      Absent          // TbOrCa Bronchitis 
		(((0.9,         0.1),           // True   Present    
		  (0.7,         0.3)),          // True   Absent     
		 ((0.8,         0.2),           // False  Present    
		  (0.1,         0.9)));         // False  Absent     ;
	title = "Dyspnea";
	comment = "Shortness of breath.";
	whenchanged = 904512889;
	belief = (0.436935, 0.563065);
	visual V1 {
		center = (426, 366);
		height = 5;
		link 1 {
			path = ((321, 301), (368, 330));
			};
		};
	};

node TITLE1 {
	kind = ASSUME;
	discrete = FALSE;
	chance = DETERMIN;
	parents = ();
	title = "Chest Clinic";
	whenchanged = 904468693;
	visual V1 {
		center = (660, 306);
		font = font {shape= "Times New Roman"; size= 22;};
		height = 8;
		};
	};
ElimOrder = (VisitAsia, XRay, Tuberculosis, Pollution, Smoking, Cancer, TbOrCa, Bronchitis, Dyspnea);
};