July 2023 Newsletter

HAPPY BIRTHDAY TO US!

It’s CampTek’s anniversary month and we have lots to celebrate! As birthdays tend to do, this time always elicits an opportunity to reflect on all the ups and downs one has experienced leading up to this annual commemoration. By all measures, we continue to grow as expected: we are incrementally adding new team members and thereby expanding our expertise, insights, and perspectives. We are also expanding in physical office presence by inviting some local team members to join us in the office in a hybrid-model office space. And this team growth is propelled by the addition of new customers and the expansion of current customers’ RPA program (with our help, of course!).

We are organically growing and expanding, and it is so much fun to witness! But, while much has changed, there is plenty that has also stayed the same. While tech is changing and expanding and becoming more robust with Generative AI, what has remained constant is the need for Managed Services. Growth in technology requires partners, like CampTek, to help guide customers through the ins and outs and expansion of RPA solutions and other technology that are capable of integration to supplement RPA. The advancement of these solutions underscores the need for Managed Services partners. In many ways, this advancement validates the foundation on which CampTek was built.

Let us do the heavy lifting. We’ll even work on our birthday!

Welcome to CAMP a weekly podcast by CampTek Software where we'll cover all things automation and robotic process automation (RPA). You'll hear from various members of the CampTek team on topics such as Citizen Development, How to Prepare for a Scope Call, What RPA Can Mean for You, and so much more! Check out our first two episodes on YouTube, Linkedin, or Transistor!

Hear from our Senior Intelligent Automation Project Manager, Joyce Zhang, and Peter Camp, our CTO & Founder as they discuss the basics of RPA.

What is Generative AI’s impact for Intelligent Automation?

Generative AI, namely ChatGPT, are on the front of everyone’s mind. Thought leaders in the automation space are eagerly trying to apply the technology to use cases and companies like PWC and Deloitte have established a business line and invested over $1 Billion to start. Like others, I think it’s too early to predict the impact it will ultimately have on automation solutions and society, in general. Just like other technologies before it, factors such as security, viable and scalable use cases and the breadth of data that can be fed to the model will impact its success and adoption. That being said, I do think there are some pretty clear areas where Generative AI will gain traction and adoption.

Low Code Application Development

This will be a game changer for many of the Low Code vendors out there. As they have built “activity based” code generation that makes it easier to assemble a workflow. However, it has an inherent ceiling by which users are beholden to the constraints of the activity that was compiled. While there is the ability to provide unique parameters, that is the extent of how much one can customize or control the outcome. Many Low Code apps are built to be “easy to use” but intrinsically don’t have the same level of functionality as a fully-fledged development environment. Generative AI takes care of this issue immediately. The use of Python and other open-source coding languages can make coding or getting the code needed to create a robust workflow an easier task. The feedback model of ChatGPT will only improve the code as issues are identified. I anticipate, over time, that there will be a new breed of Low Code Applications built on Python or other languages in which code will be created by instruction voice or text and the feedback loop provided by ChatGPT will improve the code with minimal developer intervention. The current heavy UI Activity type application will have a hard time building this type of capability into their current architecture in a timely fashion. Another factor to keep in mind is that much of the technical talent entering the workforce has some background in Python, so this will be a natural fit with the use of Generative AI.

Instant Feedback for Real-Time Decisioning

I have long held the belief that the power of AI is to reduce human decisioning to 5%. Meaning AI, in whatever form, can provide a correct, non-emotional answer 95% of the time and require a human to make the more nuanced decision-making for the remaining portion of the decision. With generative AI this possibility seems to be getting closer. The challenge is with data and most notably security. How do you govern what is asked and how much information is fed to generative AI?

This becomes an issue with PHI, PII and any other personally identifiable information. In healthcare, a generative AI agent could provide a clinical diagnosis, but how accurate can it be without a vast amount of historical data? Those problems will be solved over time and businesses will become more sophisticated in their utilization of and in their strategy-building for the use Generative AI. There is still quite a bit of “plumbing” that needs to go into this. For example, a proper feedback model needs to be installed before an operational model for businesses can use this technology in a scalable and reliable way.

RPA will not go away, it will flourish.

I always laugh when I hear other people who claim to be experts indicating that RPA is dead or not a technology that can stand on its own. I think part of that comes from not understanding what RPA really is. UiPath is an automation platform that uses RPA, as do other vendors in this space. With the platform you can literally do anything (document understanding, utilization of stand-alone API’s, use of sophisticated AI models to help with decision-making, and even the utilization of .net custom code). To me, it only makes sense that the orchestration model that UiPath and others provide will only increase the use of these AI platforms. Generative AI is part of a solution but isn’t the whole solution. It needs to be orchestrated with other complimentary software platforms to do its job. RPA interacts with applications from the desktop. Generative AI will increase the speed of the time to market for typical RPA development and provide a feedback loop for Intelligent Document Processing, as an example. We are already seeing vendors implement this in their current tech stack.

These are a few of the areas "I think" tech can and will evolve but as it becomes more robust and widely used it will become clearer which use cases are more effective and useful.

Written by: Peter Camp. CTO & Founder

Overview:

The bot automation is vetting for medical necessities matching the minimum requirements from payers’ medical coverage guidance (MCG) vs. medical documentation and examination documents uploaded by doctors in eCW.

Once vetted for medical necessities, the robot submits the referral into eCW. It also indicates the specific traits or needs, Procedures, and Total Number of procedures requested based on the data extraction.

Where does the need to use AI come from?

When-the robot gathers all the medical documentation and submits the referral once for all the procedures., Each procedure appears in the robot’s input in succession as scheduled by doctors;

-and the referrals are also created by the business office, not only by the bot;

As a result of these two situations, there is an appearance of a risk of duplicate referrals. The AI comes into play here with its ability to identify this situation. We identify the possibility of checking with AI if the procedures the robot will submit exist in the referral’s reason already submitted.

We are using a standard question and append the procedures -to be requested.

Example:

Case 1: -GPT identifies the duplicate (the robot throws the BRE -procedures already requested)

Procedures to be requested = Venaseal LEFT SSV + LEFT AAGSV + RIGHT SSV + RIGHT AAGSV

Reasons of existing referrals = APPROVED MNM VSEAL 36482X4 BIL SSV, BIL AAGSV / VARITHENA 36465X2 BIL GSV

=APPROVED MNM VENASEAL 36482 BIL GSV

CampTek Question: YES or NO, confidence % and how the confidence is calculated, the procedures from this string ‘Venaseal LEFT SSV + LEFT AAGSV + RIGHT SSV + RIGHT AAGSV with CPT code 36482’ appear in this string ‘APPROVED MNM VSEAL 36482X4 BIL SSV, BIL AAGSV / VARITHENA 36465X2 BIL GSV’. Please consider CPT code 36478 means EVLA; 36475 means RFA; 36482 means Venaseal; 37765 means Phlebectomy; 36465 means Varithena; 36471 means Sclero

GPT response: YES, confidence 90%.

The confidence is calculated based on the matching of the procedures and CPT codes between the two strings. The presence of “Venaseal LEFT SSV + LEFT AAGSV + RIGHT SSV + RIGHT AAGSV with CPT code 36482” in the first string matches with “VSEAL 36482X4 BIL SSV, BIL AAGSV” in the second string. Similarly, the presence of “VARITHENA 36465X2 BIL GSV” in the second string matches with “LEFT SSV + RIGHT SSV with CPT code 36465” in the first string. The presence of both Venaseal and Varithena procedures with the same bilateral SSV and AAGSV in both strings further supports the confident match.

CONTENT

Additional Resources

What is Generative AI’s impact for Intelligent Automation?

ChatGPT: Request Submission for Payers/Insurances

Real RPA Case Studies, Real Verifiable Solutions

Industry: Healthcare

Applications: eCW

About Us

Services

Case Studies