Читать книгу Machine Learning for Healthcare Applications - Группа авторов - Страница 42

In general, health status can be predicted by consultancy experts. If an individual wants to know about their sleep status (i.e. whether their sleep pattern is good? And whether they are taking the adequate amount of sleep?), they can consult an expert at sleep centers. If an individual wants to know about their calorie status (i.e. How much calories they need to consume to maintain/increase/decrease weight? How much exercise they need to do to maintain the calories in balance?), they can consult physicians.

But what the experts do, they give some suggestions by considering the measures and activities mentioned previously. For this, the experts use some rules and conditions on the measures and activities. For example, ‘A boy of age 21, height 176 cm, weight 63 kg with a less physical activity needs to consume 1,950 calories per day to maintain weight’. But the limitation of this approach is not considered some of the important parameters like (i) Different Health Parameters (Sleep Status, Calorie Status, etc.) have different consultants. (ii) They may not be very accurate in predicting them manually without any calculations. (iii) Consulting experts might be costly for a low-middle and middle-class family.

Thus, it demands the need for designing a model that can predict their health status from daily life activities.