AdvanceCare can scale by serving more customers, while maintaining an exceptional claims experience
Invoices from many categories, including hospital, dental, pharmaceutical, independent workers and optical were processed with a high degree of accuracy
Sprout.ai’s AI technology increases the work capacity and reduce the work volume per team member
AdvanceCare is now using Sprout.ai’s technology to automatically extract relevant data from healthcare invoices. This follows a successful pilot, in which AdvanceCare cut down the claims settlement turnaround time to near real time.
Healthcare insurance group AdvanceCare integrated with the Generali Group, an international group present in more than 50 countries, in 2020. The merger enhanced their ability to grow and serve more customers.
With Sprout.ai’s technology, AdvanceCare will unlock full end-to-end claims automation, allowing the team to index claims with far greater efficiency and speed.
The pilot
During the pilot, Sprout.ai analysed a significant sample of healthcare invoices across a series of categories of invoices, including hospital, dental, pharmaceutical, independent workers and optical. The pilot outcomes showed very high accuracy levels in the collected fields across all categories.
Sprout.ai’s AI technology will increase the work capacity and reduce the work volume per team member. AdvanceCare will be able to scale up its business by serving more customers, while maintaining an exceptional claims experience.
With Sprout.ai, claims handlers no longer need to spend their time on low-value, repetitive tasks, allowing them to dedicate more quality time to tasks that are more valuable and rewarding, optimising the customer experience.
Sprout.ai supports digitalisation and efficiency
“AdvanceCare is continuously looking for innovative ways to improve the insurance claims experience,” said Sergio Melro, chief operating officer at AdvanceCare.
“We selected Sprout.ai as our partner as they have demonstrated that their technology and approach can take us one step forward in our digitalization and efficiency journey.”
In the past year, Sprout.ai has partnered with several new customers in the Health and Property & Casualty (P&C) categories including an international health insurance provider in APAC, and other leading insurers Zurich and Metlife.
Sprout.ai CEO Roi Amir said: “We are delighted to be partnering with AdvanceCare, one of the largest health insurance platforms in Portugal.”
“Using AI in the indexing process will allow the AdvanceCare team to manage claims quicker and more efficiently, improving the customer experience. It’s a win-win for everyone and we are happy to be part of this positive change.”
About Sprout.ai
Sprout.ai is an end-to-end claims automation technology solution for the insurance industry. Sprout.ai works in partnership with major insurers, including Zurich UK, Metlife and AdvanceCare to build groundbreaking AI and data-led products to automate the claims process for customers.
Sprout.ai’s vision is to provide a frictionless claims experience to everyone in the world. The average time it takes for insurers to process claims is around 30 days. At a time when you’re emotionally and financially vulnerable, this is often frustrating and stressful. Sprout.ai enables insurers to make a decision on a customers’ claim, in near real-time. Sprout’s technology delivers fast and accurate decisions and an exceptional claims experience, driving high customer retention with improved efficiency.
To learn more about how Sprout.ai can boost efficiency and enhance customer experience, book a call with one of the team.
Zurich UK provides business, casualty, motor, property and travel insurance, life insurance and pension products for individuals and corporate customers.
Sprout.ai partnered with Zurich UK, integrating cutting edge, data-led technology with their existing systems and processes to enable end-to-end property claims automation.
The partnership followed a successful three-month pilot in which Sprout.ai’s automated policy checking and claim settlement AI was tailored to the major insurer’s needs and claims philosophy.
Key results from the pilot
98% accuracy from over 2000 claims assessed
£75K+ leakage and additional recoveries identified
+100 TNPS from handlers, with increased consistency, confidence and clarity
“A fantastic example of a collaboration which provides one of the solutions to the issues that can stand in the way of creating customer loyalty.
Helen Rogers, Head of Claims Digital Experience, Zurich
Challenges
At a glance
Meeting consumer expectation of rapid interactions, responses, and decisions
Cost and time taken to train new claims handlers
High costs of low-value administrative claim handling work including time spent on repetitive tasks such as manual reserve updating and manual policy reading from disconnected systems
Zurich has made a company-wide commitment to innovation. The insurer aims to deliver a faster service and provide a positive customer claims experience for every customer.
The goal is to serve their customers as quickly as possible at their most vulnerable time.
“Claims are, and have always been, the ‘moment of truth’ in insurance. Our collective responsibility is to support customers in the best possible way when they need us most. At Zurich we always strive to do this better. We knew we could settle claims quicker and do more to help our customers. Combining Zurich’s experience with Sprout.ai’s innovative approach alongside a range of other interventions we’ve managed to shift the dial.
Helen Rogers, Head of Claims Digital Experience, Zurich
Claims: the moment of truth
Claim handlers will always be constrained by the information they have available to them and the volume of data they can process. Insurers have to dedicate high levels resource in processing evidence and entering it into their systems. Understanding the information is critical for making the appropriate decision and delivering better outcomes for customers. Processing an average insurance claim requires claims handlers to compile and analyse anything up to 20 to 30 pages of complicated documents.
For example, evidence arrives in both a structured and unstructured format. It can be a combination of handwritten notes, pdf, word and excel documents, as well as photographs and scanned copies of original documents.
Zurich’s goals
By partnering with Sprout.ai alongside a range of other interventions, Zurich aimed to control costs, achieve operational efficiency, provide a swift, personal customer experience and remain competitive in the market as more insurers use AI to manage claims.
Sprout.ai’s partnership with Zurich
Sprout.ai partners with insurers, integrating data-led technology with their claim management systems and processes for a tailored, individualised approach. Sprout.ai’s open API enables automation and digital transformation through existing systems.
This drives tangible results for insurers and helps ensure Sprout.ai’s Automated Policy Checking AI meets insurers’ distinct needs. As partners, Sprout.ai and insurers speak the same language and prioritise the same results.
“Our main goal is to create a better customer experience in claims whilst remaining competitive in the market.”
Helen Rogers, Head of Claims Digital Experience, Zurich
How Sprout.ai’s Automated Policy Checking AI works
Visual AI pulls the data from documents
Natural language processing (NLP) and Optical Character Recognition (OCR) parses the data, even when it is handwritten in character-based languages, including Japanese.
Sprout.ai’s patented technology has access to millions of data points that enable it to analyse insurance data. This enables it to make decisions quickly, more accurately, and with less risk
Sprout.ai’s open API approach to service architecture connects with the insurer’s existing claims management platform
Sprout.ai checks the claim against the insurer’s policies and claims settlement philosophy
Sprout.ai makes a final recommendation to the claims handler suggesting settlement or flagging other action required by the claims handler,
The process reduces errors, increases fairness and frees handlers from repetitive tasks so they can focus on customer service and complicated claims..
Sprout.ai was developed using more than 20,000 historical claims. Every new claim added to the platform brings new knowledge and experience. As with a human claims handler, this will help the AI to keep getting better at what it does.
“Sprout.ai is a really exciting innovation. By combining our experience with Sprout.ai’s innovative approach, we have been able to co-create a solution that will catalyse change for our handlers and customers. We are enabling our colleagues to make a full, accurate decisions on liability and quantum from the very first time a customer contacts us.
Helen Rogers, Head of Claims Digital Experience, Zurich
About the pilot
Sprout.ai mapped out key value drivers with Zurich to select areas of focus.
Efficiencies that drive better customer experience were prioritised. They were
Improved net promoter scores through reduced time to settle
Reduced time to communicate outcomes
Increased accuracy and consistency
In parallel, drivers that help reduce costs and increase operational efficiencies were considered.
The pilot was part of a company-wide commitment to innovation at Zurich. The insurer aims to deliver a faster, more efficient service with the best possible outcomes for every customer, every time. Everyone involved in the pilot, from the claims handlers to the executive decision makers, felt that it was a success in helping the company achieve those goals
Sprout.ai ’s Claims Automation Analysts worked with Zurich claim handlers to build claim expertise and train the AI to act according to Zurich’s claim handling philosophy. This establishes clear and simple guidelines to claim processing.
The pilot was great fun and I learned some things along the way. The Sprout.ai team was second to none. They were fully invested and listened to our feedback to ensure it’s a success for all. I will certainly be singing their praises.”
Experienced claims handler at Zurich
From simple claims to complex claims
During the pilot, Sprout.ai ’s technology was first applied to simpler, lower-end claims. Over the three-month period, as it learned more about Zurich’s processes, it built up to more complex claims:
Accidental damage to TV, phones, laptops and tablet
Loss, food in Freezer and theft
Gadgets, bikes and jewellery
Accidental damage to buildings and escape of water
Storms
“We look at new perils and items in every sprint to make sure we focus on areas where results will bring value and build the confidence of the organisation and its claims handlers, encouraging them to use the AI. We set a clear roadmap, but we prioritise the elements that we see will bring the biggest value to Zurich, working in an iterative and agile way.”
Roi Amir, CEO Sprout.ai
Results
Zurich UK can settle 45% of customer claims in real time, whether they are made by phone or online, with the help of Sprout and other key initiatives.
For claims that are not settled in real time, Sprout.ai, alongside other key interventions, increased claims settled within five days of initial submission by 10%.
For some claims, policy documents can be reviewed in seconds. Historically, it could take claims handlers up to 30 minutes per claim. Claims handlers are no longer constrained by the many documents associated with each claim, leaving them with more time to spend with customers, at times when human touch and empathy can make a real difference.
Value from claims data and systems is maximised. Sprout.ai delivers data insights that facilitate agility, improve retention rate and control costs.
Accuracy is improved.
Sprout.ai ’s products have been built to ensure that the rationale behind the AI’s decision-making process is clear and simple to understand. The decision-making process is more transparent, and handlers can explain decisions more easily.
What’s next for Zurich and Sprout.ai
We are working on expanding in three areas:
1) Support for additional perils
2) Increased coverage for each peril
3) Shortening the claim cycle further
Operational efficiency and tNPS are important metrics. We have monthly meetings with key stakeholders from Zurich and Sprout.ai to discuss features new and old that will drive them. It’s imperative that the work going on from both sides continues to enhance our operational efficiency so we keep on improving customer experience.
Helen Rogers, Head of Claims Digital Experience, Zurich
If you would like to learn more about how Sprout.ai can help you boost efficiency, accuracy and savings, please get in touch
One of the biggest insurance providers in South America is using Sprout.ai to drastically cut claims processing time
50% to 60% of the insurer’s million annual claims will be automated
The insurer selected Sprout.ai to help it reduce claim resolution time, reduce rejection time, improve customer experience, increase tNPS scores and continue to drive innovation
One of the biggest insurance providers in South America, is now using our claims automation technology to process claims and improve customer satisfaction. Their entire claim process, from data extraction, to decision-making and action, will be enhanced and sped up by our AI and data-led products.
Over 50% of the insurer’s million annual claims will be automated, enabling the claims handling team to spend more time working directly with customers.
It previously took weeks for the insurers’ policyholders to learn about the outcome of their claim. Now, claims can be resolved in real time.
The insurer, one of the world’s largest, tested our technology in a POV. In that time, 30% of claims were fully processed using our technology.
Sprout.ai is helping the insurer to:
Reduce claim resolution time
Reduce rejection time by identifying fraudulent claims and policy mistakes faster
Improve customer experience with quick claims processing and reduced human error
Increase tNPS scores as customers experience a smoother claims process
Continue to drive innovation and transformation internally and across the insurance industry
At the end of the POV, the insurer decided to bring us on as a partner in their claims process.
“This partnership with Sprout.ai will be very beneficial for us and our customers alike. The pilot demonstrated that Sprout.ai’s market-leading innovative technology can deliver true end-to-end claims automation with no need for human involvement. This type of technology is exactly the kind of innovative solution that we are looking to implement to make us more efficient and improve customer experience and satisfaction.
Why our claims automation offering is unique
Our groundbreaking AI and data-led products are automating claims processes for leading insurers around the world. Our technology can read the contents of individual insurance policies to analyse coverage and conditions, and then match and settle the claim. This creates a frictionless claims experience and will drive high customer retention with improved efficiency.
Other providers offer either claims automation or fraud filtering, but our light touch solution delivers both. Engineering this state-of-the-art tool has been made possible by fusing the power of machines and a vast external data network. The result is a non-intrusive solution that enhances data, offers actionable insights on fraud suspicions and automates claim processes.
About Sprout.ai
We are an end-to-end claims automation technology solution for the insurance industry. We work in partnership with major insurers, including Zurich UK and AdvanceCare, part of the Generali Group, to build groundbreaking AI and data-led products to automate the claims process for customers.
Our vision is to provide a frictionless claims experience to everyone in the world. The average time it takes for insurers to process claims is around 30 days. At a time when you’re emotionally and financially vulnerable, this is often frustrating and stressful. We enable insurers to make a decision on a customers’ claim, in near real-time. Our technology delivers fast and accurate decisions and an exceptional claims experience, driving high customer retention with improved efficiency.
We have raised $15 million to date from top tier investors Octopus Ventures, Amadeus Capital Partners and Playfair Capital.
Key features
Data extraction and enrichment
Our technology generates contextual reasoning through using NLP and Knowledge Graphs. NLP is used to understand the contents of the policy document and enables us to build the rules within the policy to automatically check whether the claim is valid in regard to the policy agreement.
Policy Check
Once NLP has interpreted the policy document, we match this to the description of the claim to automatically check whether the claim is covered under the customer’s specific policy.
Interested in learning more about automating your claims processes? Speak to the team
The insurance media is buzzing this month with the news that a trial of the Automated Policy Checking AI solution developed by Sprout.ai means Zurich Insurance can cut property claims settlement times to sub 24 hours. The announcement was made following a three-month pilot of the technology, run between December 2020 and February 2021.
What is Automated Policy Checking?
This AI engine uses what we call explainable AI – tools like Natural Language Processing and Knowledge Graphs add layers of context and aid decision making. To put the software’s capabilities into context, its speed and ability are the equivalent of a claims handler with 100 years’ experience and a reading speed of 10,000 words per microsecond. That equates to 600 million words per minute, compared to the most commonly cited average human reading speed of 300 words per minute.
The software is not, however, designed to replace claims handlers any more than a calculator is designed to replace an accountant. On the contrary, it is a tool that the handler uses and drives in order to aid decision-making and to triage and process claims better and faster. That was the exact outcome of the three-month pilot at Zurich.
Better accuracy, improved transparency
Checks found an accuracy rate of more than 98 percent during the pilot, which exceeds the average accuracy of human claims handlers. By automatically providing links to the insurance ombudsman data used to arrive at each recommendation, it also means there is greater transparency to support every decision.
The AI solution was developed using more than 20,000 historic claims. However, it is important to understand that those were just the beginning – they can be thought of as the training material used so that the software could learn its craft. Every new claim added to the database brings new knowledge and experience, and as with a human claims handler, this will help the AI to keep getting better at what it does.
A success for all
The pilot is part of a company-wide commitment to innovation at Zurich aimed at delivering a faster service with the best possible outcomes for every customer. Everyone involved in the pilot, from the claims handlers to the executive decision makers, felt that it was an unqualified success in helping the company achieve those goals.
One highly experienced claims handler who was directly involved in the pilot took the trouble to email us at Sprout.ai afterwards. Here’s what she said:
“Just want to say thanks for the opportunity to participate in the pilot, it’s been great fun and I’ve certainly learned some things along the way! The Sprout.ai team have been second to none and fully invested/listened in our feedback to ensure it’s a success for all! I will certainly be singing your praises.”
Meanwhile, Amy Brettell, Zurich’s Head of Customer, UK Claims described this project as “a fantastic example of a collaboration which provides a true solution to some of the issues that often stand in the way of creating customer loyalty and helping rebuild trust in our sector.”
Think of contextual AI in the insurance sector, and your mind has a tendency to go straight to the automotive and perhaps home insurance markets. These, after all, are the types of insurance most commonly associated with fraudulent claims. However, insurance fraud goes way beyond these specific silos and Blockclaim’s software solutions similarly go beyond fraud detection and prevention.
This is plainly demonstrated in the latest pilot project, in which Blockclaim is working alongside one of Europe’s giants in risk consultancy and medical insurance to implement contextual AI solutions. For this particular case, the technology will be used to automatically match treatment and medication with patient conditions and illnesses.
More data means better results
Contextual AI seeks to enrich insurance claims data by using relevant contextual data to increase the information that Machine Learning algorithms use in order to learn. It is literally a training process, and the more they study, the better and more accurate they become at what they do.
It creates a virtuous circle, a little like a human in some specialist sphere, who inevitably gets better at what he or she does with practice and experience. The ultimate outcome is more accurate predictive performance compared with the conventional AI solutions currently in place.
To get the training process underway, the client has provided Blockclaim with more than 10,000 historical data entries, each of which has information on medical conditions and the medications prescribed. We have then been able to add further enrichment and detail to this data.
Challenges
It goes without saying that automating any part of a medical diagnosis process needs to be approached extremely cautiously and methodically. As things stand at present, there is a standard requirement for the manual approval of any medical condition to illness correlation and that this step must take place three times for each patient before the process can be automated. Yes, that’s three times for every patient.
Extra use possibilities
During a workshop session, it soon became clear that use of Blockclaim’s technology could easily be expanded to bring additional side benefits. These include recognising different variants of similar medications, automation of new medication entries and analysis of both medical conditions and their treatments to bring yet richer data.
Potential savings
With the present level of AI usage, the client is able to automate around 564,000 claims per year. This corresponds to a financial saving of around €285,000. Just by enhancing these processes to contextual AI, the savings could be increased by around 38% to €388,000. However, that is only the beginning.
Further development of contextual AI into a second stage would see the savings increase to more than €1 million. Even this, however, does not take into consideration the extra use possibilities. When they are factored in, the anticipated savings mount to more than €2.3 million per year.
A world of possibilities
Faster and more accurate diagnoses that at the same time result in such significant cost savings represent a win / win for both the industry and the patients it serves. The findings so far represent only the tip of the iceberg in what can be achieved. There are exciting times ahead, and Blockclaim is proud to be at the heart of this innovative development.
