Connect with us

AI

Build a medical sentence matching application using BERT and Amazon SageMaker

Avatar

Published

on

Determining the relevance of a sentence when compared to a specific document is essential for many different types of applications across various industries. In this post, we focus on a use case within the healthcare field to help determine the accuracy of information regarding patient health.

Frequently, during each patient visit, a new document is created with the information from the visit. This information often consists of a medical transcription that has been dictated by either the nurse or the physician. Such a document may contain a brief description statement (also known as a restatement) that explains the main details from that specific patient visit. In future visits, doctors may rely on previous visits’ restatements to quickly get an overview of the patient’s overall status. Such restatements may also be used during patient handoffs. However, this introduces the potential for errors to be made during patient handoffs to new medical teams if the restatements are difficult to understand or if they contain inadequate information (Staggers et. al. 2011). Therefore, having an accurate description of the patient’s status is important, because the cost of errors in such restatements can be high and may negatively affect the patient’s overall care (Garcia et. al. 2017).

This post walks you through how to deploy a machine learning (ML) model that aims to determine the top sentences from the document that best match the corresponding document restatement; this can be a first step to ensure the accuracy of the patient’s health records overall by determining the relevance of the restatement. We emphasize that this model determines the top ranking sentences that match the restatement; it does not generate the restatement itself.

When creating this solution, we were faced with a dual-sided challenge. Beyond the technical challenge of actually creating an AI/ML model, several surrounding components complicate actually using such models in the real world. Indeed, the actual ML code may be a very small part of the system as a whole (Sculley et al. 2015). This is especially so in complex architectures frequently deployed in the context of the healthcare and life science space.

We focused on one particular challenge: creating the ability to serve the model so that others (applications, services, or people) can use it. By serving a model, we mean to grant others the ability to pass new data to the model so they can get the predictions they need. This post provides a broad overview of the problem, the solution, and a few points to keep in mind if you plan to use a similar approach in your own use cases. A full technical write up, including a readme and a step-by-step deployment of the architecture, is available in the GitHub code repository. For more information about approaches to serving models, see Build, Train, and Deploy a Machine Learning Model With Amazon SageMaker and AWS Deep Learning Containers on Amazon ECS.

Background and use case

In the medical field (as well as other industries), documents are frequently associated with a shorter restatement text of the original document. We use the term restatement, but in fact this shorter text can be a summary, highlight, description, or other metadata about the document. For example, an after-visit clinical summary given to a patient summarizes the content of the patient visit to a physician.

For illustration purposes, the following is an example that’s unrelated to the medical industry.

Document:

On Monday morning, Joshua ate a large breakfast of bacon and eggs. He then went for a brisk walk. Finally, he returned home and sat at his desk.

Restatement:

Joshua went for a walk.

In this example, the restatement is just a rewording of the highlighted sentence in the full document. This example shows that, although the use case that we focus on in this post is specific to the medical field, you can use and modify this approach for many other text analysis applications.

Let’s now take a closer look at the use case for this post. We used data taken from MTSamples (which we downloaded from Kaggle). This data contains many different samples of transcribed medical texts. It includes documents with raw transcriptions of sample notes, as well as shorter descriptions of those notes (which we treat as restatements).

The following is an example from the MTSamples dataset.

Document:

HISTORY OF PRESENT ILLNESS: , I have seen ABC today. He is a very pleasant gentleman who is 42 years old, 344 pounds. He is 5’9″. He has a BMI of 51. He has been overweight for ten years since the age of 33, at his highest he was 358 pounds, at his lowest 260. He is pursuing surgical attempts of weight loss to feel good, get healthy, and begin to exercise again. He wants to be able to exercise and play volleyball. Physically, he is sluggish. He gets tired quickly. He does not go out often. When he loses weight he always regains it and he gains back more than he lost. His biggest weight loss is 25 pounds and it was three months before he gained it back. He did six months of not drinking alcohol and not taking in many calories. He has been on multiple commercial weight loss programs including Slim Fast for one month one year ago and Atkin’s Diet for one month two years ago.,PAST MEDICAL HISTORY: , He has difficulty climbing stairs, difficulty with airline seats, tying shoes, used to public seating, difficulty walking, high cholesterol, and high blood pressure. He has asthma and difficulty walking two blocks or going eight to ten steps. He has sleep apnea and snoring. He is a diabetic, on medication. He has joint pain, knee pain, back pain, foot and ankle pain, leg and foot swelling. He has hemorrhoids.,PAST SURGICAL HISTORY: , Includes orthopedic or knee surgery.,SOCIAL HISTORY: , He is currently single. He drinks alcohol ten to twelve drinks a week, but does not drink five days a week and then will binge drink. He smokes one and a half pack a day for 15 years, but he has recently stopped smoking for the past two weeks.,FAMILY HISTORY: , Obesity, heart disease, and diabetes. Family history is negative for hypertension and stroke.,CURRENT MEDICATIONS:, Include Diovan, Crestor, and Tricor.,MISCELLANEOUS/EATING HISTORY: ,He says a couple of friends of his have had heart attacks and have had died. He used to drink everyday, but stopped two years ago. He now only drinks on weekends. He is on his second week of Chantix, which is a medication to come off smoking completely. Eating, he eats bad food. He is single. He eats things like bacon, eggs, and cheese, cheeseburgers, fast food, eats four times a day, seven in the morning, at noon, 9 p.m., and 2 a.m. He currently weighs 344 pounds and 5’9″. His ideal body weight is 160 pounds. He is 184 pounds overweight. If he lost 70% of his excess body weight that would be 129 pounds and that would get him down to 215.,REVIEW OF SYSTEMS: , Negative for head, neck, heart, lungs, GI, GU, orthopedic, or skin. He also is positive for gout. He denies chest pain, heart attack, coronary artery disease, congestive heart failure, arrhythmia, atrial fibrillation, pacemaker, pulmonary embolism, or CVA. He denies venous insufficiency or thrombophlebitis. Denies shortness of breath, COPD, or emphysema. Denies thyroid problems, hip pain, osteoarthritis, rheumatoid arthritis, GERD, hiatal hernia, peptic ulcer disease, gallstones, infected gallbladder, pancreatitis, fatty liver, hepatitis, rectal bleeding, polyps, incontinence of stool, urinary stress incontinence, or cancer. He denies cellulitis, pseudotumor cerebri, meningitis, or encephalitis.,PHYSICAL EXAMINATION: ,He is alert and oriented x 3. Cranial nerves II-XII are intact. Neck is soft and supple. Lungs: He has positive wheezing bilaterally. Heart is regular rhythm and rate. His abdomen is soft. Extremities: He has 1+ pitting edema.,IMPRESSION/PLAN:, I have explained to him the risks and potential complications of laparoscopic gastric bypass in detail and these include bleeding, infection, deep venous thrombosis, pulmonary embolism, leakage from the gastrojejuno-anastomosis, jejunojejuno-anastomosis, and possible bowel obstruction among other potential complications. He understands. He wants to proceed with workup and evaluation for laparoscopic Roux-en-Y gastric bypass. He will need to get a letter of approval from Dr. XYZ. He will need to see a nutritionist and mental health worker. He will need an upper endoscopy by either Dr. XYZ. He will need to go to Dr. XYZ as he previously had a sleep study. We will need another sleep study. He will need H. pylori testing, thyroid function tests, LFTs, glycosylated hemoglobin, and fasting blood sugar. After this is performed, we will submit him for insurance approval.

Restatement:

Consult for laparoscopic gastric bypass.

Although the raw transcript document is quite long, only a few of the sentences actually appear to be related to the restatement “Consult for laparoscopic gastric bypass.” We highlighted two sentences within the document that you might intuitively think best match the restatement. The approach we deployed quantifies the similarities and reports the sentences in the document that best match the restatement. We did this by using a pretrained BERT language model trained specifically on clinical texts (published by Alsentzer et. al. 2019). The model itself is hosted by HuggingFace, a platform for sharing open-source natural language processing (NLP) projects. We used this model to calculate sentence-by-sentence similarities using the sentence-transform Python library.

It is important to note that in this example and in this solution, we are performing the sentence ranking without explicitly extracting and detecting the medical entities. However, many applications rely on explicitly extracting and analyzing diagnoses, medications, and other health information. For detecting medical entities such as medical conditions, medications, and other medical information in medical text, consider using Amazon Comprehend Medical, a HIPAA-eligible service built to extract medical information from unstructured medical text.

More information about this approach is available in our technical write-up.

Architecture diagram

In this section, we go over the architecture diagram for this solution at a very high level. For more details and to see the step-by-step framework, see our technical write-up.

In the model development and testing phase, we use Amazon SageMaker Studio. Studio is a powerful integrated development environment (IDE) for building, training, testing, and deploying ML models. Because we use a prebuilt model for this solution, we don’t need to use Studio’s full ability to train algorithms at scale. Instead, we use it for development and deployment purposes.

We created a Jupyter notebook that you can import into Studio. This notebook walks you through the entire development and deployment process. We start by writing the code for our model to a file. The model is then built using an NGINX/Flask framework, so that new data can be passed to it at inference time. Prior to deploying the model, we package it as a Docker container, build it using AWS CodeBuild, and push it to Amazon Elastic Container Registry (Amazon ECR). Then we deploy the model using Amazon Elastic Container Service (Amazon ECS).

The final result is a model that you can query using a simple API call. This is an important point: the ability to query models via an API capability is an essential component of designing scalable, easy-to-use interfaces. For more information, see Implementing Microservices on AWS.

After we deploy our model, we create a graphical user interface (using Streamlit) so that our model can be easily accessed through a webpage. Streamlit is an open-source library used to create front ends for ML applications. After we create our webpage, we deploy it in a similar way to how we deployed our model: we package it as a separate Docker container, build it using CodeBuild, push it to Amazon ECR, and deploy it using Amazon ECS.

By creating and deploying this webpage, we provide users with no programming experience the ability to use our model to test their own documents and restatements. The following screenshot shows what the webpage looks like.

After the user inputs their restatement and corresponding document, the top five results (the five sentences that best match the statement) are returned. If you deploy the entire solution using our original MTSamples example, the final result looks like the following screenshot.

The solution reports the following results:

  • The top five sentences within the document that best match the restatement.
  • The similarity distance between each sentence and the restatement. A lower distance means closer similarities between that sentence and the restatement sentence.

In this example, the best matching sentence is “He wants to proceed with workup and evaluation for laparoscopic Roux-en-Y gastric bypass” with a distance of .0672. Therefore, this approach has correctly identified a sentence within the document that matches the restatement.

Limitations

Like any algorithm, this approach has some limitations. For instance, this approach is not designed to handle cases where the restatement of the document is actually high-level metadata about the document not directly related to the text of the document itself. You can solve such use cases by using Amazon Comprehend custom models. For more information, see Comprehend Custom and Building a custom classifier using Amazon Comprehend.

Another limitation in our approach is that it doesn’t explicitly handle negation (words such as “not,” “no,” and “denies”), which may change the meaning of the text. AWS services such as Amazon Comprehend and Amazon Comprehend Medical use deep learning models to handle negation.

Conclusion

In this post, we walked through the high-level steps to deploy a pre-built NLP model to analyze medical texts. If you’re interested in deploying this yourself, see our step-by-step technical write-up.

References

For more information, see the following references:


About the Authors

Joshua Broyde is an AI/ML Specialist Solutions Architect on the Global Healthcare and Life Sciences team at Amazon Web Services. He works with customers in the healthcare and life sciences industry at all levels of the Machine Learning Lifecycle on a number of AI/ML fronts, including analyzing medical images and video, analyzing machine sensor data and performing natural language processing of medical and healthcare texts.

 

Claire Palmer is a Solutions Architect at Amazon Web Services. She is on the Global Account Development team, supporting healthcare and life sciences customers. Claire has a passion for driving innovation initiatives and developing solutions that are both secure and scalable. She is based out of Seattle, Washington and enjoys exploring the PNW in her free time.

Coinsmart. Beste Bitcoin-Börse in Europa
Source: https://aws.amazon.com/blogs/machine-learning/build-a-medical-sentence-matching-application-using-bert/

AI

7 Ways Artificial Intelligence is Improving Healthcare

Avatar

Published

on

Emerging technologies have the potential to completely reshape the healthcare industry and the way people manage their health. In fact, tech innovation in healthcare and the use of artificial intelligence (AI) could provide more convenient, personalized care for patients.

It could also create substantially more value for the industry as a whole—up to $410 billion per year by 2025.

This graphic by RYAH MedTech explores the ways that technology, and more specifically AI, is transforming healthcare.

How is Technology Disrupting the Patient Experience?

Tech innovation is emerging across a wide range of medical applications.

Because of this, AI has the potential to impact every step of a patient’s journey—from early detection, to rehabilitation, and even follow-up appointments.

Here’s a look at each step in the patient journey, and how AI is expected to transform it:

1. Prevention

Wearables and apps track vast amounts of personal data, so in the future, AI could use that information to make health recommendations for patients. For example, AI could track the glucose levels of patients with diabetes to provide personalized, real-time health advice.

2. Early Detection

Devices like smartwatches, biosensors, and fitness trackers can monitor things like heart rate and respiratory patterns. Because of this, health apps could notify users of any abnormalities before conditions become critical.

Wearables could also have a huge impact on fall prevention among seniors. AI-enabled accelerometer bracelets and smart belts could detect early warning signs, such as low grip strength, hydration levels, and muscle mass.

3. Doctors Visits

A variety of smart devices have the potential to provide support for healthcare workers. For instance, voice technology could help transcribe clinical data, which would mean less administrative work for healthcare workers, giving them more time to focus on patient care.

Virtual assistants are expected to take off in the next decade. In fact, the healthcare virtual assistant market is projected to reach USD $2.8 billion by 2027, at a CAGR of 27%.

4. Test Results

Traditionally, test results are analyzed manually, but AI has the potential to automate this process through pattern recognition. This would have a significant impact on infection testing.

5. Surgery / Hospital Visits

Research indicates that the use of robotics in surgery can save lives. In fact, one study found that robot assisted kidney surgeries saw a 52% increase in success rate.

Robotics can also support healthcare workers with repetitive tasks, such as restocking supplies, disinfecting patient rooms, and transporting medical equipment, which gives healthcare workers more time with their patients.

6. Rehabilitation

Personalized apps have significant care management potential. On the patient level, AI-enabled apps could be specifically tailored to individuals to track progress or adjust treatment plans based on real-time patient feedback.

On an industry level, data generated from users may have the potential to reduce costs on research and development, and improve the accuracy of clinical trials.

7. Follow-ups and Remote Monitoring

Virtual nurse apps can help patients stay accountable by consistently monitoring their own progress. This empowers patients by putting the control in their own hands.

This shift in power is already happening—for instance, a recent survey by Deloitte found that more than a third of respondents are willing to use at-home diagnostics, and more than half are comfortable telling their doctor when they disagree with them.

It’s All About the Experience

Through the use of wearables, smart devices, and personalized apps, patients are becoming increasingly more connected, and therefore less dependent on traditional healthcare.

However, as virtual care becomes more common, healthcare workers need to maintain a high quality of care. To do this, virtual training for physicians is critical, along with user-friendly platforms and intentionally designed apps to provide a seamless user experience.

Coinsmart. Beste Bitcoin-Börse in Europa
Source: https://www.visualcapitalist.com/7-ways-artificial-intelligence-is-improving-healthcare/

Continue Reading

AI

The ‘Cyber Attacks’ Winter is Coming — straight for small firms in India Inc.

Avatar

Published

on

Cyber intrusions and attacks have increased exponentially over the last decade approximately, exposing sensitive information pertaining to people and businesses, thus disrupting critical operations, and imposing huge liabilities on the economy. 

Cybersecurity is a responsibility that employees and leaders across functions must shoulder simply because it is the gospel truth – you cannot protect what you cannot see. As organizations have shifted to the work-from-home model due to the outbreak of the COVID-19 pandemic, it’s increasingly important to keep your company’s data secure. 

While the pandemic has led to near or complete digitalization of operations amongst financial institutions, it’s also increased the potential for cyberattacks that lead to adverse financial, reputational, and/or regulatory implications for organizations. 

According to Accenture, cybercrime is said to cost businesses $5.2 trillion worldwide within five years. “With 43% of online attacks now aimed at small businesses, a favorite target of high-tech villains, yet only 14% prepared to defend themselves, owners increasingly need to start making high-tech security a top priority,” the report continues.

A recent McAfee study shows global cybercrime costs crossed US$1 trillion dollars in 2020, up almost 50% from 2018.

India too saw an exponential rise in cybersecurity incidents amid the coronavirus pandemic. Information tracked by the Indian Computer Emergency Response Team (CERT-In) showed that cybersecurity attacks saw a four-fold jump in 2018, and recorded an 89 percent growth in 2019.

The government has set up a Cyber Crisis Management Plan for countering cyber-attacks effectively, while also operating the Cyber Swachhta Kendra (Botnet Cleaning and Malware Analysis Centre).

Banks and Financial Institutions (FIs) are some of the highest targeted market sectors. An analysis by Can we hyperlink this: https://www.fitchratings.com/videos/exploring-bank-cybersecurity-risk-13-04-2021?mkt_tok=NzMyLUNLSC03NjcAAAF82rxN_2lbDTsEp4tfBu4tUGP7i6wyb1OGpyNY0Z8lQPhdz9C7KQ-NIriTcJqNSDyb9qfQ_essxS-TdNWMgJesb-RA4yN4t7T-XqXmVfWW4dau36SW6ZE 

“>FitchRatings in collaboration with SecurityScorecard reveals that banks with higher credit ratings exhibited better cybersecurity scores than banks with lower credit ratings. 

Bharti Airtel’s chief executive officer for India, Gopal Vittal, in a letter to the telco’s 307.9 million subscribers, detailed out how Airtel is carrying out home delivery of SIM cards and cautioned subscribers from falling prey to cyber frauds. He cautioned them against the rapid rise in cyber frauds, highly likely via digital payments. “There has been a massive increase in cyber frauds. And as usual, fraudsters are always finding new ways to trick you,” he added in the letter. 

Barcelona-based Glovo, valued at over $1 billion, that delivers everything from food to household supplies to some 10 million users across 20 countries, came under attack recently when the “hacker gained access to a system on April 29 via an old administrator platform but was ejected as soon as the intrusion was detected”, according to the company.

The attack came less than a month after Glovo raised 450 million euros ($541 million) in funding. 

According to Kaspersky’s telemetry, close on the heels of coronavirus-led pandemic and subsequent lockdown in March 2020, saw a total number of meticulously planned attacks against remote desktop protocol (RDP) jumped from 93.1 million worldwide in February 2020 to 277.4 million 2020 in March — a whopping 197 percent increase. In India, the numbers went from 1.3 million in February 2020 to 3.3 million in March 2020. In July 2020, India recorded its highest number of cyberattacks at 4.5 million.

The recent data breach at the payment firm Mobikwik, affected 3.5 million users, exposing Know Your Customer (KYC) documents such as addresses, phone numbers, Aadhaar card details, PAN card numbers, and so on. The company, however, still maintains that there was no such data breach. It was only after the Reserve Bank of India’s intervention that Mobikwik got a forensic audit conducted immediately by a CERT-IN empaneled auditor and submitted the report. 

Security experts have observed a 500% rise in the number of cyber attacks and security breaches and a 3 to 4 times rise in the number of phishing attacks from March until June 2020.

These attacks, however, are not just pertaining to the BFSI sector, but also the healthcare sector, and the education sector.

Image Source: BusinessStandard.com

What motivates hackers to target SMBs? 

Hackers essentially target SMBs because it’s a source of easy money. From inadequate cyber defenses to lower budgets and/or resources, smaller businesses often lack strong security policies, cybersecurity education programs, and more, making them soft targets. 

SMBs can also be a ‘gateway’ to larger organizations. As many SMBs are usually connected electronically to the IT systems of larger partner organizations, it becomes an inroad to the bigger organizations and their data. 

How can companies shield themselves from a potential cyberattack: 

As a response to the rising number of attacks in cyberspace, the Home Ministry of India issued an advisory with suggestions on the prevention of cyber thefts, especially for the large number of people working from home. Organizations and key decision-makers in a company can also create an effective cybersecurity strategy that’s flexible for adaptation in a changing climate too. Here are a few use cases: 

  • CERT-In conducted ‘Black Swan – Cyber Security Breach Tabletop Exercise’, in order to deal with cyber crisis and incidents emerging amid the COVID-19 pandemic, resulting from lowered security controls. 
  • To counter fraudulent behavior in the finance sector, the government is also considering setting up a Computer Emergency Response Team for the Financial Sector or CERT-Fin.
  • Several tech companies have come forth to address cybersecurity threats by building secure systems and software to mitigate issues like these in the foreseeable future. For example, IBM Security has collaborated with HCL Technologies to streamline threat management for clients through a modernized security operation center (SOC) platform called HCL’s Cybersecurity Fusion Centres. 

Some of the ways through which companies can mitigate potential risks include: 

  • Informing users of hacker tactics and possible attacks
  • Establish security rules, create policies, and an incident response plan to cover the entire gamut of their operations
  • Basic security measures such as regularly updating applications and systems
  • Following a two-factor authentication method for accounts and more

While these measures are some of the ways to be on top of your game in the cybersecurity space, they will also help in sound threat detection while helping gain better insights into attacks and prioritizing security alerts so that India is better prepared for an oncoming attack and battling any unforeseen circumstance that might result in huge loss of data, resources and more. 

Coinsmart. Beste Bitcoin-Börse in Europa Source: https://www.mantralabsglobal.com/blog/the-cyber-attacks-winter-is-coming-straight-for-small-firms-in-india-inc/

Continue Reading

AI

Paris-based Shift Technology becomes the latest insurtech unicorn in France after raising €183.2 million

Avatar

Published

on

shift_technology

Shift Technology, the French startup that has created a solution that enables its insurance clients to detect fraudulent claims, is now worth $1 billion after raising its fourth round of funding. The startup, which also operates in the UK and the US, will expand its team of data scientists, particularly in France.

The AI-based insuretech startup recently announced that it had raised $220 million or around €183.2 million in a series D from Advent International, Avenir Growth, Accel, Bessemer Venture Partners, General Catalyst, Iris Capital and Bpifrance. This latest funding should enable it to structure its R&D, while its offer has expanded since its foundation in 2013. Shift Technology initially focused on fraud detection, but the startup now intends to offer a tool capable of managing the entire chain. It also aims to continue its deployment in the UK and the US, strengthened by its recent unicorn status, whereby its valuation now exceeds one billion dollars.

Originally, the startup sought to facilitate the customer compensation process offered by insurers in the event of a claim – water damage, car accident, etc. Described as the number one fear of policyholders by Jeremy Jawish, CEO and co-founder of Shift Technology and, as such, a major issue for their clients. Once this brick was laid, during its first years of existence, the startup decided to go beyond declaration fraud by making its solution a decision-making aid for insurers. They now offer automated closure of claims files and detection of underwriting fraud. These complementary products are already in production with its customers, who are, to date, around one hundred in some 25 countries. This production was made possible thanks to the previous funding round of €53 million in March 2019.

Shift Technology says it has already analysed 2 billion claims on behalf of insurers since its inception. According to CEO Jeremy Jewish, they receive the data provided by insurers, as well as a number of public data about the claimant. Their algorithms read, among other things, the claim declaration before determining whether to file an appeal or carry out a check for money laundering. The Banque Postale has adopted its solution to accelerate the management of claims for its customers. So has the Axa group, which is also a user. For the latter, the aim is to “limit the manual actions that its employees have to carry out. And to satisfy its customers, Shift Technology is counting on its team of data scientists, which it claims to be “the largest in the insurance sector” and which will be further strengthened.

With 350 employees, the company says that recruitment will be the main focus of its investment strategy following its Series D. “We’re going to recruit a lot in France and a little in the US,” says Jérémy Jawish, who also wants to “approach the health insurance sub-sector more aggressively. Shift Technology says it wants to set up “the largest French centre dedicated to artificial intelligence in insurance” with 300 experts by 2023. With an underlying aim, the startup wants to show that “champions are being created in France”. CEO Jérémy Jawish adds that the COVID-19 crisis has had “a big impact” on its activities according, but has not slowed down the pace of its market openings. A pace that should remain fairly steady.

Shift Technology aims to become an international player in its market. To do this, the french company is counting on its ‘unique’ model based on a single vertical – insurance again and again. However, competition, especially in the US, is a key driver for them to stay on top of their game. As a reminder, this Series D round brings the total amount of funds raised by the company since 2013 to $320 million (nearly €267 million).

Coinsmart. Beste Bitcoin-Börse in Europa
Source: https://www.eu-startups.com/2021/05/paris-based-shift-technology-becomes-the-latest-insurtech-unicorn-in-france-after-raising-e183-2-million/

Continue Reading

AI

Paris-based Shift Technology becomes the latest insurtech unicorn in France after raising €183.2 million

Avatar

Published

on

shift_technology

Shift Technology, the French startup that has created a solution that enables its insurance clients to detect fraudulent claims, is now worth $1 billion after raising its fourth round of funding. The startup, which also operates in the UK and the US, will expand its team of data scientists, particularly in France.

The AI-based insuretech startup recently announced that it had raised $220 million or around €183.2 million in a series D from Advent International, Avenir Growth, Accel, Bessemer Venture Partners, General Catalyst, Iris Capital and Bpifrance. This latest funding should enable it to structure its R&D, while its offer has expanded since its foundation in 2013. Shift Technology initially focused on fraud detection, but the startup now intends to offer a tool capable of managing the entire chain. It also aims to continue its deployment in the UK and the US, strengthened by its recent unicorn status, whereby its valuation now exceeds one billion dollars.

Originally, the startup sought to facilitate the customer compensation process offered by insurers in the event of a claim – water damage, car accident, etc. Described as the number one fear of policyholders by Jeremy Jawish, CEO and co-founder of Shift Technology and, as such, a major issue for their clients. Once this brick was laid, during its first years of existence, the startup decided to go beyond declaration fraud by making its solution a decision-making aid for insurers. They now offer automated closure of claims files and detection of underwriting fraud. These complementary products are already in production with its customers, who are, to date, around one hundred in some 25 countries. This production was made possible thanks to the previous funding round of €53 million in March 2019.

Shift Technology says it has already analysed 2 billion claims on behalf of insurers since its inception. According to CEO Jeremy Jewish, they receive the data provided by insurers, as well as a number of public data about the claimant. Their algorithms read, among other things, the claim declaration before determining whether to file an appeal or carry out a check for money laundering. The Banque Postale has adopted its solution to accelerate the management of claims for its customers. So has the Axa group, which is also a user. For the latter, the aim is to “limit the manual actions that its employees have to carry out. And to satisfy its customers, Shift Technology is counting on its team of data scientists, which it claims to be “the largest in the insurance sector” and which will be further strengthened.

With 350 employees, the company says that recruitment will be the main focus of its investment strategy following its Series D. “We’re going to recruit a lot in France and a little in the US,” says Jérémy Jawish, who also wants to “approach the health insurance sub-sector more aggressively. Shift Technology says it wants to set up “the largest French centre dedicated to artificial intelligence in insurance” with 300 experts by 2023. With an underlying aim, the startup wants to show that “champions are being created in France”. CEO Jérémy Jawish adds that the COVID-19 crisis has had “a big impact” on its activities according, but has not slowed down the pace of its market openings. A pace that should remain fairly steady.

Shift Technology aims to become an international player in its market. To do this, the french company is counting on its ‘unique’ model based on a single vertical – insurance again and again. However, competition, especially in the US, is a key driver for them to stay on top of their game. As a reminder, this Series D round brings the total amount of funds raised by the company since 2013 to $320 million (nearly €267 million).

Coinsmart. Beste Bitcoin-Börse in Europa
Source: https://www.eu-startups.com/2021/05/paris-based-shift-technology-becomes-the-latest-insurtech-unicorn-in-france-after-raising-e183-2-million/

Continue Reading
Blockchain3 days ago

The Reason for Ethereum’s Recent Rally to ATH According to Changpeng Zhao

Aviation4 days ago

American Airlines Passenger Arrested After Alleged Crew Attack

Blockchain2 days ago

Chiliz Price Prediction 2021-2025: $1.76 By the End of 2025

Blockchain3 days ago

Mining Bitcoin: How to Mine Bitcoin

Blockchain3 days ago

Mining Bitcoin: How to Mine Bitcoin

Fintech4 days ago

Talking Fintech: Customer Experience and the Productivity Revolution

Fintech5 days ago

CGS-CIMB Issued S$150-Million Commercial Paper in Digital Securities on iSTOX

Blockchain5 days ago

Ruffer Investment Sold Bitcoin Holdings After Elon Musk’s Bullish Tweets

Blockchain4 days ago

Bitcoin Gains Bullish Momentum, Signals Another Major Rally

PR Newswire2 days ago

Teamsters Lead Historic Defeat of CEO Pay at Marathon Petroleum

Blockchain5 days ago

Weekly Wrap-up: Ether Breaks Past $3K – New All Time High (May 3, 2021)

Blockchain5 days ago

Ethereum Market Capital Overtakes Bank of America

Aviation5 days ago

Lufthansa To Equip Entire Boeing 777F Fleet With Sharkskin Technology

Cyber Security5 days ago

Where To Pirate Audio Books ? | 10 Best Audiobook Torrenting Sites 2021

Blockchain3 days ago

Mining Bitcoin: How to Mine Bitcoin

Startups5 days ago

Equity Monday: TechCrunch goes Yahoo while welding robots raise $56M

Cyber Security4 days ago

Alaska Court System Temporarily Disconnected the Internet After a Cybersecurity Threat

AR/VR1 day ago

Apple is giving a laser company that builds some of its AR tech $410 million

Start Ups5 days ago

British events startup FIXR raises €7.4 million and prepares to welcome back nightlife

Blockchain5 days ago

Ripple Releases $1.6 Billion XRP from Escrow Account

Trending