So reading medical reports using Artificial Intelligence and machine learning is a challenging task. The use case described here utilizes Laera Information Extraction to assist experts at a life insurance to calculate the health risk for persons. In the end the decision needs to be taken by doctors but the system can greatly assist them to sift through the amount of text provided. Because medical reports attached to a life insurance application can easily exceed 100dreds of pages.

Laera Information Extraction uses advanced AI methods to assess the risks contained in these reports and points them out to the experts. In a first step the diagnoses are extracted base on the common ICD-10 code. But a simple word search is not enough because each diagnosis needs to be put into its context. Here the option of Laera to assign multiple roles to an entity becomes very useful. Once a critical diagnosis is found Laera makes an assessment based on several categories:

• Is the polarity negative or positive? In most cases symptoms are excluded in the reports and therefore the diagnosis is negative. These are of no interest (of course the patient is happy about that). Only the positively confirmed ones are relevant for the risk assessment.
• Is the diagnosis for the present or the past? Many reports contain a lot of history of what happened in the past. While the history might be interesting, the main focus is on the current situation.
• Is the diagnosis for the person herself or maybe for the family? Family history (Father had heart attack) might be important but needs to be assessed differently.

Laera intelligent extraction performs all these tasks and analyzes all pages in milliseconds using semantic and structural methods:

• Find all diagnose and symptoms
• Find the polarity (is the diagnosis excluded or asserted
• Determine the context (role e.g. self or family)
• Classify the paragraph by relevance
• Present and auto-summarize results in ICD10 terms
• Highlight relevant areas in the document for quick visual confirmation

Of course, just to make sure this does not get lost, the roles and assignments are not defined by rules but trained using machine learning from a few hundred labeled examples.

The customer using this system could reduce the time spent to assess an application by more than 50% as the experts get a prepared data set that allows them to quickly jump tp the relevant sections and make the decision.

It is also important to note that this is not a hard coded special solution, but an example of the application of the Laera Information Extraction product. Any other industry can use this approach to solve their specific requirements. Example range from contract management to court documents, but of course also standard default extraction tasks can be easily solved with Laera Information Extraction.

If you are interested to learn more about this use case or the application of AI extraction in your specific domain please let us know via e-Mail at info(at)skilja.com and we will be happy to provide more information.

This is what Skilja with its Laera Classification and Extraction software suites provides. We have completely implemented this new paradigm which is available either as SDKs or as integrated modules to our Vinna Document Processing Platform. But of course what looks easy for the user requires significant infrastructure and automated checks and balances to make this a reliable and stable part of your processing tasks.

Machine Online-Learning of document classification and recognition uses supervised and unsupervised continuous training of incoming data streams. Supervised learning will take the corrections the users have made, analyze them and apply them as new patterns as appropriate. Unsupervised learning will use the results of successful and correct classification and extraction to generate additional knowledge (expanding the space) and statistics of usage of existing knowledge. Both combined are then used to continuously improve the system. The infrastructure is set up quickly and consists of services that do the work in the background: collect statistics, collect samples, analyze the validity of the new data and publish them to the production runtime system if the AI has determined them to be valid additions.

As we know that system administrators might be vary of having their setup changed automatically (at least until they have seen it really works) there is several intermediate levels of AI automation that they can chose. The most important are:

• Have all changes and each new document manually reviewed, benchmarked and checked before explicitly publishing it. This is the box on the left
• Have automatically created improvements be reviewed and explicitly published
• View any conflict and resolve them manually (or at least check them)
• Restrict the users that can contribute to the training to a certain group. Only corrections from this group will be taken into account while the input from less experienced users will be discarded.

But in the end learning can run completely unattended. As in school (think exams) we need to check the validity of the new knowledge before we apply it. Therefore Laera algorithms will always analyze for conflicts that are created and try to resolve them. Im addition each new revision of the training pattern will fully automatically be quality checked in background and only be accepted if the recognition results of the new model exceed the existing one. This is an assurance for the production system: Changes in quality will always only go into one direction – better!

Again, this is not a black box but Laera provides precise insight of what is happening and lets you influence or even revert the suggested improvements at any stage. Laera Monitor is the tool for this, a web application that shows the continuously measured quality numbers of your system.

The example shown here shows a typical curve for the F1 score (average quality measurement). Starting with a setup of a few hundred trained documents the quality quickly deteriorates as new and unknown samples arrive in production. Especially when the real volumes start to be processed. It is interesting to see that the precision stays high close to 95% which is very satisfying, but recall (recognition rate) goes down as the system simply does not “know” the new documents. But then online learning kicks in and uses the new samples and corrections made to quickly improve the quality to 95% after a few thousand new training documents have been processed.

Online Learning will make classification and extraction much easier in the future. After an initial setup AI will simply learn in background what needs to be known to arrive at he best possible automation rate within a few weeks. This makes a whole new area of processes (for example with smaller document volumes) available and will greatly improve quality for existing automation processes.

Please let us know if you have additional questions or need more insight or have a direct interest. Contact us under info (at) skilja.com.

In recent times also practical applications have become available that provide basic functionality in understanding documents. Typically these applications are used by enterprises to manage large amounts of incoming documents (especially paper) and to offer some kind of automatic recognition and distribution of documents. As these early and simple solutions have proven successful we will soon see a wealth of new concepts that will allow providing much larger benefits to companies and end users making use of this. Therefore let’s take a look what this actually is.

The first goal of document understanding is to identify the function and the meaning of a document and its parts. Typically a document is written for a specific purpose which defines its function. An invoice is designed and created to notify a buyer on the goods bought and how much money needs to paid for them along with some other information for accounting and tax purposes. All content of the invoice follows this function. Or an application form in a bank is used to collect all information that is needed to open an account. This document is normally very structured. On the other side an e-Mail (which is also a document) conveys information, opens a discussion and calls for action in a very unstructured way.

So the first step in document understanding is to identify the function and separate the documents to be processed accordingly. Typically this step is called “classification”. However this is only the primary classification as more categorization according to a taxonomy can occur which do not have the purpose to define the function. It is therefore very important to distinguish these two types of classification as a lot of misunderstanding results from confusion between these. The function of a document determines the possible content and the information entities that can be found on it.

The second step of understanding is to identify all information entities or predicates of a document related to the function. Typically only a few entities are needed and required (e.g. the amounts on an invoice) but we would prefer to only talk about “understanding” when all entities have been identified. To identify an entity (like a tax amount) it needs to be detected and a meaning must be attached. A number without a meaning is not a predicate. Only if all entities can be labeled with a meaning the computer system really understands the meaning of the document.

In a third step real understanding can take place if the entities are brought into the context of the document function, the purpose of the communication and the other entities. Typically a (business) document triggers an action. Context and correlation between the discovered predicates needs to be analyzed to determine which action. An e-Mail may contain a request to send some information back (which would be an entity “request for information”). But only in context with the rest of the e-Mail, the e-Mail thread or attachments it becomes clear which actions to perform. I will discuss this in more depth in upcoming posts.

As you have seen it is important to know the function of a document or any text to be able to understand its content. And with the knowledge of function (=purpose) and some content we can take action and already have some kind of document understanding. This is what current solutions provide.