Читать книгу Biomedical Data Mining for Information Retrieval - Группа авторов - Страница 21

After data pre-processing, normalization, feature extraction and feature reduction, different models are employed to predict the patient’s mortality in an in-hospital stage and calculate the accuracy. The models predict either patient will survive or die. This is determined by using classification technique as mortality prediction is a binary classification problem. This process is done step by step as shown in Figure 1.1.

Table 1.2 Time series variables with physical units [30].

S. no.	Variables	Physical units
1.	Temperature	Celsius
2.	Heart Rate	bpm
3.	Urine Output	mL
4.	pH	[0–14]
5.	Respiration Rate	bpm
6.	GCS (Glassgow Coma Index)	[3–15]
7.	FiO2 (Fractional Inspired Oxygen)	[0–1]
8.	PaCo2 (Partial Pressure Carbon dioxide)	mmHg
9.	MAP (Invasive Mean arterial blood pressure)	mmHg
10.	SysABP (Invasive Systolic arterial blood pressure)	mmHg
11.	DiasABP (Invasive Diastolic arterial blood pressure)	mmHg
12.	NIMAP (Non-invasive mean arterial blood pressure)	mmHg
13.	NIDiasABP (Non-invasive diastolic arterial blood pressure)	mmHg
14.	Mechanical ventilation respiration	[yes/no]
15.	NISysABP (Non-invasive systolic arterial blood pressure)	mmHg