We have already introduce the differences between MACHINE LEARNING (ML) and DEEP LEARNING (DL) in our previous post. The first require programming to encode the information the second is unsupervised.
ML- MACHINE LEARNING can identify normal conditions, abnormal conditions, and exactly match patterns that indicate degradation and impending process excursions or asset failure well before they happen.
It can predict an accurate time-to-failure indicating precisely
WHEN a known failure will occur,
HOW the failure will occur, and
WHAT to do about it; derived from Prescriptive advice such as the exact failure code directly linked from the EAM system. Knowing the precise, multiple days’ or weeks’ lead time to a failure allows the end user to determine the exact action necessary (often through discussions between Operations, Maintenance, Technical and Planning/Scheduling Departments). Such Prescriptive action enables the best remediation and timing decisions to avoid damage altogether, prevent a breakdown, and solve the problem in the most efficient manner.
In a CAR this is clear. The machine inform you 30 days in advance that something could happen in your engine and that you have to bring the car to a mechanic to get fixed.
The HUMAN BODY is not so different. There are many parameters, indexes, predictors more or less upgraded that can tell you when something wrong might happens and that you need to be fixed before this occurs. This is implemented in Machine learning. It can take the advantage to get the information very early and therefore to prevent the problem if you are using wearables devices that measure permanently relevant data and evaluate existing EBM (evidence based medicine) PROGNOSTIC INDEXES. In other words, based on what happens with the average people that have been exposed to those conditions. In spite of the promissing results the published data up to now have not been very possitive. See 1, 2, 3, 4 & basis for non-intrusive wearables.
DL- DEEP LEARNING, on the contrary is a step forward in the Health 4.0 environment (anytime-anymeans-anywhere-anyhow). It takes all kind of data relevant or not, from your body or from the environment or from the weather or from the news or from the medication or from the pollution or from the type of food you eat or what you drink etc… in order to be able to DISCOVER, in case something wrong is measured in your body, HOW the faillure occured to be prevented with time. DL is carrying for you an HOLISTIC MEDICINE, is putting into practice the 10 requirements for the REAL LIFE EVIDENCE (RLE) of the social determinantes as the WHO stated. Data will be then Predictive- Personalize- Participative.
Before we determine how to handle an holistic medicine with AI (artificial intelligence) techniques, both have to be in place when implementing IoT (internet of the things) for healthcare surveillance.
See also http://catai.net/blog/2015/12/data-analytics-in-healthcare/
