Adapting transformer-based language models for heart disease detection and risk factors extraction

Journal of Big Data

Table 8 XLNET Evaluation Metrics for each risk factor indicator

Risk Factor	Indicator	Precision	Recall	F1-score	Support
CAD	Mention	0.93	0.92	0.92	301
	Event	0.69	0.78	0.73	241
	Test	0.00	0.00	0.00	63
	Symptom	0.94	0.49	0.64	94
Diabetes	Mention	0.93	0.99	0.96	530
	A1c	0.91	0.81	0.86	75
	Glucose	0.00	0.00	0.00	40
Obese	Mention	0.94	1.00	0.97	114
	Obese_BMI	0.00	0.00	0.00	7
Hypertension	Mention	0.99	0.99	0.99	515
	High bp	0.97	0.98	0.97	205
Hyperlipidemia	Mention	0.86	1.00	0.93	221
	High chol.	0.00	0.00	0.00	7
	High LDL	0.00	0.00	0.00	28
Smoker	Smoker_never	0.80	0.72	0.76	114
	Smoker_ever	0.00	0.00	0.00	3
	Smoker_current	0.00	0.00	0.00	37
	Smoker_past	0.85	0.59	0.69	121
	Smoker_unknown	0.93	0.90	0.91	202
Medication		0.87	0.76	0.81	7352
Family history		0.2000	0.0769	0.1111	13
Weighted average		0.9361	0.9397	0.9371	42946
Macro average		0.3988	0.3848	0.3772	42946
Micro average				0.9397	42946
Accuracy				0.9397	42946