Prof Dr. Maureen Baker CBE

Matteo Berlucchi, CEO & Co-Founder, Healthily

Healthily Smart Symptom Checker API

Martin Cansdale, Principal Data Scientist, Healthily

Martin Cansdale, Principal Data Scientist, Healthily - green background

Using logic to plan business logic for AI at Healthily 

Doctor using a healthcare AI chatbot in partnership

Jonathon Carr-Brown

Doctor holding phone using AI healthcare technology provided by Healthily

Thyroid condition checker from Healthily

Pharmaceutical marketing challenges and Healthily solutions

How Healthily understands your symptoms – our technology explained

Chief Operating Officer

Medical professionals are empowering patients and healthcare systems with the help of technology.

How doctors and artificial intelligence can work together

There are challenges and regulations in pharmaceutical marketing. Healthily provides an award-winning digital solution. 

How digital can help the pharmaceutical industry reach their customers

We recently spoke to Matteo Berlucchi, CEO & Co-Founder at Healthily, to share why we're on a mission to help a billion people find their health. 

Why we’re on a mission to help a billion people find their health

The Healthily Chief Medical Officer, Maureen Baker CBE shares her thoughts on some of your most common menopause questions.

Head data for con-10-menopause-questions-answered-by-healthilys-chief-medical-officer article

10 menopause questions answered by the Healthily Chief Medical Officer

YMD-blog

Healthily has launched an API that makes it easy for developers to integrate its medically-verified Smart Symptom Checker (SSC) into their workflow, app or website.

Smart Symptom Checker now available as an API 

More than 3 million people worldwide have used the Thyroid Condition Checker (available in 6 languages) that we developed for Merck. As a result, Merck has brought an under-diagnosed condition to the forefront of consumers' minds and helped them seek out the right treatment. 

How Healthily helped Merck make users ‘Thyroid Aware’

- __Healthily has launched an API that makes it easy for developers to integrate its medically-verified Smart Symptom Checker (SSC) into their workflow, app or website__

- __The AI-powered SSC lets users check their health symptoms, and  get tailored health information – with medically-verified best next steps, from self-care to urgent medical attention__

- __Benefits to healthcare, business and  customers – it can help to triage unnecessary telehealth consultations or put your customer or employee’s health needs first without wasting time__

The self-service website will [allow developers to integrate artificial intelligence (AI) from Healthily](https://www.livehealthily.com/product/developer) into their existing workflows or create innovative new services leveraging the technology.

The SSC from Healthily is a Class 1 Medical Device offering a solution for any company or organisation that prioritises the health of their customers, patients or staff.

“The self-service portal provides a quick way for our customers to evaluate our technology and work out how to apply it to their environment,” says Matt West, Chief Commercial Officer at Healthily. 

[![Healthily API for developers CTA](//images.ctfassets.net/iqo3fk8od6t9/17dnWs8LuwoPVcNdzVMghV/35f76722ab22a1fb0840f178f2863704/B2B_CTA_Desktop_CTA_1400x488.jpg)](https://www.livehealthily.com/product/developer)

## Who’s already using the Healthily AI Technology?
Join powerful brands like [Walmart](https://www.livehealthily.com/press/releases/healthily-cold-flu-and-covid-checker-pilot-launches-on-walmart) and [Merck](https://www.livehealthily.com/blog/how-healthily-helped-merck-make-users-thyroid-aware), already using Healthily technology for their tailored needs. 

And Healthily is already planning to build on the service by extending the offering to its AI condition checkers and its extensive database of medically-verified content. In April 2022, leading pharmacist Superdrug partnered with Healthily using our trusted content and research to promote their products and brand message. 

“Companies that are innovating in digital healthcare, from wellness app developers to health insurance providers have come to realise that AI triage is a critical component in any offering but one that requires significant investment and time to build,” says West. 

The waiting list of interested parties includes Telemedicine providers in the UK and the US looking to create efficiencies in user triage and health app publishers who are looking to add a deeper layer of functionality for their users via the SSC.

“By offering access to our technology in this way, customers can quickly build a service prototype without any commercial commitment,” adds Matt West.

__[Use our flexible API to integrate our Smart Symptom Checker into your organisation's workflow, app or website.](https://www.livehealthily.com/product/developer)__

## Self-care in your customer's hands

At Healthily, we’re bringing medical knowledge out of the clinic and putting it into the hands of users – your customers.

The SSC underpinned by our Chat API, allows users to start a conversation with any health problem or question they need information on. 

They check-in on symptoms and receive tailored health information – with recommended and medically-verified best next steps, whether that’s urgent medical attention or just a spot of self-care.

And as well as allowing them to assess symptoms your customers will be able to find relevant products and services and search for information on healthcare topics.

![hands-of-consumer](//images.ctfassets.net/iqo3fk8od6t9/5dbgFfl8RPQvymlw2sKq4f/df4d78746ff1012e28aa16aa766151ee/hands-of-consumer.png)

## The symptom checker API helps your customers find solutions 

There are unique benefits of the [SSC API](https://www.livehealthily.com/product/developer). Using Natural Language Processing (NLP) helps people assess their symptoms in a human way by distilling mismatched phrases and using intelligent tech to understand what users are trying to say.  

Our virtual triage helps people take the best next steps for their health. We don’t diagnose; we offer practical and proactive recommendations to promote self-care.

And most importantly, the database of expert-led content created by specialist health writers and approved by the medical team at Healthily provides advice and information to help users decide on the best solutions.

## Why choose the Healthily Smart Symptom Checker API?

- __It is powered by 6 years of unique AI development and medical knowledge.__ “Healthily takes health seriously. Just like a doctor at med school, we’ve taken time to build our knowledge base, content, and guidance. This isn’t something that’s easy to replicate,” explains Matt West, Chief Commercial Officer at Healthily.

- __It is simple and cost-effective to test.__ “We’ve done the hard work for you,” says West. “Using our API allows you to test the environment and discover if our SSC is useful for you without overspending or using up precious developer time.”

- __It is tried and tested by millions of users already.__ Millions are taking control of their health every day with the SSC. Since December 2017, five and a half million users have checked up on their symptoms – and feedback is positive, with comments such as ‘very helpful and easy to use,’ ‘help me decide what to do,’ and ‘easy to use and understand’.

- __Healthily is working to improve and update it so you won't have to.__ “We don’t stand still and we’re continually improving our [technology](https://lp.livehealthily.com/ai-whitepaper) and [safety measures](https://www.livehealthily.com/safety),” adds Matt West.

- __We work to stringent safety and quality standards__. "We put quality and user safety at the heart of all we do," says Chief Medical Officer, Prof Maureen Baker CBE (former chair of the Royal College of General Practitioners (RCGP) and a national leader in primary care and digital technology) leads our clinical team who are guided by an independent [Clinical Advisory Board (CAB)](https://www.livehealthily.com/team/advisory-board).

![Healthily Smart Symptom Checker API](//images.ctfassets.net/iqo3fk8od6t9/1aWfq1Zu87dh2ddnbNHZW3/ffbb6241275d330c521c3805b04da01f/dot-with-code.png)

## Helping to support an over-stretched healthcare system

Already suffering under the weight of the pandemic and general cost-cutting – medical professionals and systems are given breathing room by our intelligent tech. Using the SSC API from Healthily provides solutions for you, your company, and your customers – and helps cut unnecessary visits to a doctor or A&E. 

The US Agency for Healthcare Research and Quality says an estimated 13 to [27% of Emergency Department visits](https://www.ahrq.gov/research/findings/nhqrdr/chartbooks/carecoordination/measure2.html) could be managed by a GP, clinic, or urgent care center. And these are all items that a symptom checker would tell you NOT to go to the emergency room for.

## Book a demonstration

__If you would like a demonstration or want to talk to an expert about integrating the Healthily Smart Symptom Checker into your organisation, we’re here to help.__

[![Book a demo CTA](//images.ctfassets.net/iqo3fk8od6t9/7lOzXheroO039n9Gn4eTL1/6840e150a1a7baa953a3dcdd68f9621f/B2B_CTA_Desktop_CTA_1400x488__1_.jpg)](https://lp.livehealthily.com/book-demo)

Healthily has launched an API that makes it easy for developers to integrate its medically-verified Smart Symptom Checker (SSC) into their workflow, app or website

# How Healthily helped Merck make users ‘Thyroid Aware’

__What you don’t know can’t hurt you – right? That’s the mantra that a lot of us adopt when it comes to our health, but one that can cause unnecessary suffering.__

Designed with doctors, Healthily AI technology helps users answer health questions quickly, highlight (and rule out) possible conditions, and find medically-verified information and content. The technology is also flexible and integratable. 

In 2018, Healthily teamed up with German pharmaceutical company [Merck](https://www.merckgroup.com/) to raise awareness around their global campaign, Thyroid Aware. Using the Healthily AI model, our data scientists and medical team were able to create a specific thyroid condition checker, helping to inform users about the probability of having a thyroid disorder, and providing a way for Merck to engage with customers on a meaningful level.

## How the thyroid condition checker can work for your business

Thyroid disease is a condition that regularly goes undiagnosed. Up to 60% of those suffering from thyroid disease are unaware they have the condition, with women being 5 to 8 times more likely than men to have thyroid issues. Left undiagnosed, it can contribute to the development of serious conditions like cardiovascular disease, osteoporosis and infertility, while pregnant women with undiagnosed hypothyroidism have an increased risk of miscarriage, pre-term delivery and severe developmental problems in children.

Professor Maureen Baker, Chief Medical Officer at Healthily, explains how and why the campaign worked. *“This campaign has shown that people often suspect what might be wrong with them, and just need a nudge to investigate it further. The advantage of creating condition checkers is that we can be much more focused. Ruling a condition out is easier than spotting a condition from an array of random symptoms,”* she says.

### Thyroid Condition Checker Campaign Results

- In 4 years __4.5 million__ people in __175 different countries__ used the Healthily thyroid condition checker to screen themselves for hyper- or hypothyroidism
- The tool has been __translated__ into Spanish, German, Chinese and Vietnamese
- In 2020 alone, __1.8 million__ people checked their susceptibility during a concerted marketing initiative in Latin American countries including Peru, Mexico, Chile, Columbia, and Ecuador
- A third of people who have gone through the SSC has been advised to seek __further testing__ for thyroid conditions

The tool was also able to warn people of possible related conditions like:
-   polycystic ovaries (PCOS)
-   premenstrual tension syndrome (PMT)
-   anxiety
-   type 2 diabetes
-   constipation
-   iron deficiency

## Insights gathered from the Healthily AI approach

The type of data gathered can be used by researchers to discover early indicators and differences across age, genders, and regions of a particular condition.

In the Merck campaign, 72% of respondents were made up of the target audience of 20-40 year-olds, and over 90% of users were women.   

More than half of the participants (53%) noted that they were gaining weight unintentionally, while others talked about hair loss, feeling tired, dry skin, and feeling their heart beating – all common symptoms of thyroid disease.

Healthily data and insights are now being used as a foundation for scientific research. For example, Imperial College London has published a [peer-reviewed paper in the Lancet](https://www.imperial.ac.uk/news/234674/covid-19-mapper-reveals-symptom-variation-between/) based on Healthily COVID data which shows distinct differences in Covid symptoms across regions.

## How a digital-first approach creates value for health conditions

The digital-first approach used with Merck has demonstrated how to raise campaign awareness, position a company at the start of a consumer’s journey and stay on the right side of pharmaceutical regulations.

The condition checker concept has also provided a valuable way for Merck to engage with potential customers without breaking regulatory guidelines on advertising prescription drugs. These restrict pharmaceutical companies in every country except the United States and New Zealand.

Condition checkers allow pharmaceutical companies to get involved in the consumer value chain, rather than relying on traditional product marketing to healthcare professionals.

## Could the symptom checker model work for your company?

Healthily is now actively working with other pharmaceutical companies and recently delivered a symptom checker for US retail giant Walmart to help customers understand whether they’re more likely to have cold, flu or COVID-19.

__Could your company benefit from an AI-powered condition checker? We can help. Visit our [business page](https://www.livehealthily.com/discover/business) to find out more, or [get in touch](https://lp.livehealthily.com/get-in-touch) to speak to an expert.__

[![CTA - AI Health Solutions for Business, Get in touch](//images.ctfassets.net/iqo3fk8od6t9/5i1Q3aMKhVdc3ePrE2PoHP/e930bcfdfeb9745d5c1e8c9a8ee1ce25/B2B_CTA_Desktop_CTA_1400x488__1_.jpg)](https://www.livehealthily.com/discover/business)

Here’s a little known fact: there are only 2 countries in the world that allow the advertising of prescription drugs.

We’re probably all familiar with the wacky world of US TV drug advertisements, which end with a list of side-effects longer than the advert itself. But did you know the other country was the ever-sensible New Zealand?

The near-global prohibition on advertising prescription drugs is undoubtedly sensible, but it does present significant challenges for any pharmaceutical company that wants to expand its market in that area. 

# The pharmaceutical marketing challenge

There is a way for pharmaceutical companies to reach consumers. The rules allow them to talk to consumers about adherence once they’ve been prescribed a drug. And they are allowed to promote and use direct sales teams to tell healthcare professionals about prescription drugs.

However, COVID-19 put a blocker in the way,  so now, the pharmaceutical industry is choosing to adopt a digital consumer-centric mindset that complements its traditionally vigorous product marketing sales model.

[![Digitalizing Self-Care to Empower Patients](//images.ctfassets.net/iqo3fk8od6t9/7wrEubeEKuCAgb3g68cmEA/520ff73a7fceec4fa8f913cbf3d3e92d/JCB-ID-Banner-Ads-4-22-1024x256.png)](https://www.impetusdigital.com/2022/03/01/fireside-chat-with-jonathon-carr-brown/)

## How Healthily can help pharma companies? 

Healthily can help both over-the-counter and prescription pharmaceutical companies overcome these marketing challenges with its consumer-centric approach.

We know that whether you’re promoting an over-the-counter or a prescription drug, the approach should be the same. We recommend pharma companies focus on the following.

- personalisation
- customer experience
- multiple channels

The mantra should be ‘the right product, at the right time, for the right user, in the right media.’

__Visit our [business page](https://www.livehealthily.com/discover/business) to find out more, or [get in touch](https://lp.livehealthily.com/get-in-touch) to speak to an expert.__

## The Healthy ecosystem improves the healthcare experience

Our content expertise, smart condition checkers and smart symptom checking technology can be configured to deliver real value to healthcare professionals and consumers. This means companies play an important part in the overall healthcare experience, not just at the point of sale or prescription.

The approach using content and AI can be used for all conditions, targeting awareness and adherence. 

The Healthily app can also be customised so that users track drug-taking and other complementary nutritional, activity, mental health and sleep regimes, linking the pharmaceutical brand to the overall wellness of the consumer.

### Case study: Healthily and Walmart Health and Wellness   

Multinational retail giant Walmart saw the value of this multi-pronged approach and teamed-up with Healthily to help consumers understand whether they’re more likely to have a cold, flu or COVID-19. 

[The pilot](https://www.walmart.com/cp/Medicine-Cabinet/976798) has seen high conversion rates because the consumer receives information at their point of need. After all, the Healthily mantra is to provide medically safe health information that helps anyone, anywhere decide the best next steps for their health needs.

### Case study: Healthily and Numan partnership

Numan, the digital healthcare company for men, has found new customers at low prices by leveraging the Healthily digital health marketing team with great success and market-leading conversion rates.

### Case study: Healthily and Merck partnership

The Healthily partnership with Merck has allowed the multinational pharmaceutical company to position itself at the start of a consumer’s journey with its [Thyroid Aware campaign](https://www.livehealthily.com/blog/how-healthily-helped-merck-make-users-thyroid-aware). 

This website breaches no regulatory guidelines and tells consumers what they need to know about hypothyroidism (an underactive thyroid) and hyperthyroidism (an overactive thyroid), using Healthily AI technology (to inform users of the probability of having either condition).

[![Download AI whitepaper | The Chatbot Will See You Now - on any platform](//images.ctfassets.net/iqo3fk8od6t9/7cU1cJJ09DWhuwwVXJvKvw/6b1a9b4964dcbb1147cf12bc50da9ef8/AI_Whitepaper_Desktop_CTA_1400x488.jpg)](https://lp.livehealthily.com/ai-whitepaper)

## The Healthily approach 

While the regulatory frameworks won’t soften, the role pharma companies play in informing, alerting and educating consumers can be developed comfortably using the innovative Healthily digital approach.

This approach is formulated using the best AI solutions and products combined with medically verified content created by our content team. Healthily has all the digital credentials needed to jump-start a pharmaceutical company’s content marketing and deliver rich digital experiences.

## Future-proofing with customer-first digital innovation

Those businesses that embrace the power of digital innovation and a customer-first business model will succeed in building more effective interactions, deeper loyalty and lasting brand preference. 

The key is to understand that the 2 biggest questions consumers want answered are: ‘what do I need to know?’ and ‘what do I need to do next?’

## Focus on the user, not the drugs

Despite the squeeze of cost control, regulatory restrictions and global competition, the marketing world of pharma will adapt going forward to focus on the user.

Healthily gives pharma companies a headstart in health management, self-care and prevention allowing them to:

- build relationships with people suffering from conditions
- engage with people already using their drugs

By inserting itself throughout the value chain, pharma can build trust and loyalty with consumers and move away from traditional direct sales techniques. 

The industry can focus on outcomes, use behavioural insights to target consumers and leverage appropriate channels. 

## Get in touch
__Want to know more about how Healthily can help with your pharma marketing challenges. Visit our [business page](https://www.livehealthily.com/discover/business) to find out more, or [get in touch](https://lp.livehealthily.com/get-in-touch) to speak to an expert.__

[![CTA - AI Health Solutions for Business, Get in touch](//images.ctfassets.net/iqo3fk8od6t9/5i1Q3aMKhVdc3ePrE2PoHP/e930bcfdfeb9745d5c1e8c9a8ee1ce25/B2B_CTA_Desktop_CTA_1400x488__1_.jpg)](https://www.livehealthily.com/discover/business)

Regulations on pharmaceutical marketing are sensible but challenging. With content expertise and intelligent health tech, we help companies deliver real value to healthcare professionals and consumers.

I often get asked what’s the ‘why’ behind our mission of helping a billion people ‘find their health’.

The question comes in two parts: why a billion and what does ‘find your health’ actually mean?

The answers are simple. 

## One billion searches

One billion is the number of people who [search for health information](https://www.telegraph.co.uk/technology/2019/03/10/google-sifting-one-billion-health-questions-day/) on Google every day – and it was the number that motivated myself and [Henrik Pettersen](https://www.linkedin.com/in/henrik-b-pettersen-26311a87/) to found Healthily in 2014. 

Every day one billion people seek precision, but find  generic health information instead. The Healthily mission is to challenge that paradigm. 

We use smart tech to understand what your individual health problem or question is so that we can deliver a completely personalised service. Once we know what you’re looking for, we share tailored, relevant, medically-validated information. And then we guide you on the action to take – your best next steps.

## Find your health 

We want to help a billion people find the information, products and services they need, quickly and safely, so they can take control of their health – find their health.

![Why Healthily is on a mission to help a billion people find their health](//images.ctfassets.net/iqo3fk8od6t9/5E5hat6SndDTGvqLj11GBD/2f88ecf7f09a356aa1e0d327c819edd8/Matteo_Image_AR_1.91.1_02.jpg)

Unlike traditional search engines and magazine-style health websites, which can leave the user with decisions and choices to make, Healthily uses data and advanced algorithms to tailor recommendations and information for the individual, and therefore helps them decide what best next steps to take.

Every day we get a little closer to helping one billion people find their health with Healthily – why not find yours?<br><br>

## Medically-verified information with our Smart Symptom Checker
Taking into account users' symptoms, symptom combinations and influencing factors like age and lifestyle, our [Smart Symptom Checker](https://www.livehealthily.com/symptom-checker) provides everything they need to review symptoms, receive advice on the next best steps and find relevant health information. [Find out more](https://www.livehealthily.com/discover/business). 

## AI Health Solutions for Business

If you're interested in helping your users navigate their own health needs with award-winning digital health technology, AI symptom checking, assessments and triage. 

__Visit our [business page](https://www.livehealthily.com/discover/business) to find out more, or [get in touch](https://lp.livehealthily.com/talk-to-an-expert) to speak to an expert.__

[![Download AI whitepaper | The Chatbot Will See You Now - on any platform](//images.ctfassets.net/iqo3fk8od6t9/7cU1cJJ09DWhuwwVXJvKvw/6b1a9b4964dcbb1147cf12bc50da9ef8/AI_Whitepaper_Desktop_CTA_1400x488.jpg)](https://lp.livehealthily.com/ai-whitepaper)


We recently spoke to Matteo Berlucchi, CEO & Co-Founder at Healthily, to share why we're on a mission to help a billion people find their health

It is unlikely that grand predictions of AI replacing doctors will come true in our lifetimes - at Healthily, we certainly hope they don’t. But there is a strong case for their collaboration, particularly if outcomes include improved patient care, system efficiency and reduced human error. 

In a new and insightful [article for Forbes Technology Council](https://www.forbes.com/sites/forbestechcouncil/2022/01/25/how-ai-could-predict-medical-conditions-and-revive-the-healthcare-system), Rena Christina Tabata outlines where AI and medical professionals can dovetail for the benefit of both patients and healthcare systems.  

As Tabata points out, Medical AI is already showing that it can detect traditionally difficult to identify or diagnose conditions. 

At Healthily, we have designed our Smart Symptom Checker to focus on symptoms and influencing factors rather than probable conditions. This means we can look beyond seemingly innocuous symptoms and detect symptom combinations or influencing factors that might signify early signs of cancer. Though results might surprise users, being less probable doesn’t make them impossible.  

__Looking for [AI health solutions](https://www.livehealthily.com/discover/business) for your business? [Get in touch](https://lp.livehealthily.com/talk-to-an-expert) to speak to an expert.__

## Smart Symptom Checkers
As smart symptom checkers have almost infinitely extensible datasets, we will evolve to include external factors such as social determinants and lifestyle models. For instance, smoking is already an influencing factor in the Healthily algorithm.

This may lead to early presentation and diagnosis, significant increases in life expectancy, and a reduction in healthcare spending in the long run.

For Tabata, deciding when a model is ready to be released to the big wild world is complex. 

We would agree. After six years of development, Healthily launched the first AI [Smart Symptom Checker](https://www.livehealthily.com/symptom-checker) in 2015, and while there would have been benefits to waiting longer, at some point, you have to allow actual users to play to learn how to keep improving your product. 

As a result, we’ve been able to identify how users describe symptoms (rather than, say, pointing to a pain point) and interpret conclusions from their final report. We can establish what further questions we need to ask to understand conditions and how to improve our user experience fully - and our technology and intelligence grows. 

At Healthily, we take the development of our AI as seriously as a pharmaceutical company takes the development of a drug. This is difficult for digital investors who are used to a culture of moving fast and breaking things. But in medical AI, we can’t afford to break things, as it could lead to loss of life.

## Will people ever trust AI chatbots? 

As Tabata points out, trust in non-human digital assessment is the main barrier to their acceptance - no matter how good it is.

The gold standard of face-to-face medical consultation is embedded in developed societies and coveted in emerging economies. Many emerging economies have swiftly jumped to mobile money, but mobile health is a trickier selling proposition.

Another pertinent question Tabata asks is what margin of error would we accept? It probably should be at a similar rate to that of humans, but the issue is we don’t actually know what the human error rate is in primary care assessments. Soon Healthily will publish a literature review paper looking at studies of medical fallibility - and in truth, the research base in primary care is pretty sketchy. 

__Looking for [AI health solutions](https://www.livehealthily.com/discover/business) for your business? [Get in touch](https://lp.livehealthily.com/talk-to-an-expert) to speak to an expert.__

## What are we testing against?
Healthily can now match GPs on vignette tests (mini-medical stories). Still, we often get marked down in academic studies because our symptom checker has asked more questions than the GP, elicited more information, and concluded it differs from a pre-ordained test answer.

Imperial College London’s Self-Care Research Unit currently has a paper in peer review that looks at this issue and concludes that the current process for testing AI symptom checkers is flawed for this and other reasons.

That said, we need a benchmark for safety. At Healthily, we have arbitrarily decided that we need to be 98% safe to attain any form of trust with our users. We mean 98% of the time, our triage advice will be appropriate or over-cautious. We are [currently at 97%](https://www.livehealthily.com/blog/why-safety-is-paramount-in-digital-health) according to internal testing, so we still have work to do.

## How do Healthily users find the AI experience?

Currently, our users tell us they find the symptom checker and final report useful and helpful - mainly because it eases worries about symptoms and helps decide what next steps they should take. The final report is also a helpful discussion tool if they need to see a pharmacist or doctor. So it seems trust can be established if the [Healthily Smart Symptom Checker](https://www.livehealthily.com/discover/business) is clear that is it a triage for the best next steps, not a replacement for healthcare professional support.

## Healthily AI solutions for your business
Could award-winning digital health technology, AI symptom checking, assessments and triage from Healthily help your customers, sales or process efficiency? You could help your users understand faster whether their next steps should be self-care, doctor care or urgent attention, or use our AI triage and reports to pre-screen patients for an online consultation. 

__Visit our [business page](https://www.livehealthily.com/discover/business) to find out more, or [get in touch](https://lp.livehealthily.com/talk-to-an-expert) to speak to an expert.__

[![Download AI whitepaper | The Chatbot Will See You Now - on any platform](//images.ctfassets.net/iqo3fk8od6t9/7cU1cJJ09DWhuwwVXJvKvw/6b1a9b4964dcbb1147cf12bc50da9ef8/AI_Whitepaper_Desktop_CTA_1400x488.jpg)](https://lp.livehealthily.com/ai-whitepaper)

Medical professionals are empowering patients and healthcare systems with the help of technology.


When it comes to supporting health with digital technology, the goal is to find the best next steps to every user’s problem. 

At Healthily, we’ve worked hard to reach those quality next steps by developing a self-assessment tool that improves continuously with the help of AI. The result: a tool that gives users everything they need to review symptoms, find relevant health information and advice on the best next steps

## But how did we get here?

We’ve used three types of logic to understand your needs. These might be used alone, or in combination, it depends on the problem at hand. When designing the Healthily self-assessment tool, it became clear that each of these types of logic has benefits and limitations, so understanding each one has been key.

## Logic type 1: Rules

Conditional ‘if-then’ logic has a clear advantage when you need to ensure something happens 100% of the time. But this certainty comes with a major downside: lack of flexibility and scalability. Complex chains of ‘if-this-happens-then-that-happens’ quickly become unmanageable and end up creating logic loopholes.

So we use these rules when we need certainty – and to ensure our recommendations are safe. For example, if a user mentions ‘blood in vomit’ this triggers a rule that the user will be told to visit A&E in their assessment report.

## Logic type 2: Bayesian inference

This is a method of statistical inference, named after its developer Reverend Thomas Bayes. He died in 1761 before he could publish his work, but it’s now widely recognised as an approach to complex problems where new information is constantly changing the probability of the outcome.

We use Bayesian logic to estimate the probability of a condition being the cause of the symptoms reported. The logic can also acknowledge personal factors like a history of smoking or diabetes.

The strength of this approach is in its mathematical foundations. Unlike digital software, the human brain is not well-versed in the language of statistical analysis - tricks of perception will often lead to misinterpretation. While we absolutely do not believe the tool can replace a doctor, we are confident that we can triage users (i.e. advise on the best next steps) consistently and effectively. 

[![Download AI whitepaper | The Chatbot Will See You Now - on any platform](//images.ctfassets.net/iqo3fk8od6t9/7cU1cJJ09DWhuwwVXJvKvw/6b1a9b4964dcbb1147cf12bc50da9ef8/AI_Whitepaper_Desktop_CTA_1400x488.jpg)](https://lp.livehealthily.com/ai-whitepaper)

Another advantage of Bayesian Inference is that it requires a clearly defined set of data in order to reach decisions, which means these can be traced and explained. To get this data, we enlisted the help of doctors to create symptom and condition profiles based on medical evidence. This makes Healthily an augmented intelligence app rather than an artificial intelligence (AI) one. 

Early experiments using AI to learn from data sets created unsafe results because the full list of symptoms were not present in the data. The AI  would miss the signs of a heart attack.  over a certain age with chest pain all had heart attacks and people with pain down their left arm had a muscle strain. We concluded it is much safer - as we know what the symptoms of diseases are - to tell the AI rather than let it guess. 

Thanks to this approach it is always possible to replicate the results of an outcome because we know why the AI is asking the questions and what condition data sets it is attempting to narrow down its focus on. It’s very important to be able to justify why one option was chosen over another. In other words, the tool is not a ‘black box’ –we understand why decisions have been made.

## Logic type 3: Machine Learning (ML)

The last piece of our logic puzzle is ML - what some describe as pure AI. 

If you have a lot of unstructured ‘fuzzy’ data, ML is a very powerful tool for labelling information as it’s very good at recognising situations and patterns. Kenneth Cukier, author of Big Data, explains that ML can tell you the ‘what’ but not the ‘why’. 

You may have noticed that Healthily is the only self-assessment tool that doesn’t force the user to pick a symptom from a list. Instead we have a free text box which allows you to tell our chatbot DOTTM what the problem is. That’s great from a user perspective, but it means Healthily needs to understand what you’re talking about. This can be tricky, as you might be typing in a medical problem or simply just chatting. 

To tackle this, we use ML to extract concepts and understand if they are medical or not. First, we spellcheck your answers using a checker that has been enhanced by our medical team. Then we examine the colloquialisms and turn them into medical concepts, so something like ‘I pee every hour’ becomes ‘frequent urination’. We then use our own ontology system to classify medical concepts found in the input.

We also use ML to determine user intent: do they want information about a condition or do they want an assessment of their symptoms? We have to be able to understand the difference between ‘I have a headache’ and ‘can I use painkillers for my headache if I am pregnant?’ These are clearly two very different cases which must be dealt with in different ways. Once we determine intent we can use our search engine to find the best information from our medical library, or start asking questions about the user's symptoms using our Bayesian Inference engine.

## Augmented intelligence - what it means in practise
We describe what we do as augmented intelligence because we have created an algorithm which is neither exclusively ML nor Bayesian, but which uses the principles of Information Theory, developed by Claude Shannon, to mathematically evaluate which questions would provide the most useful information. 

If you know the children’s game “guess the animal” you will know that your brain will start with questions that give the highest amount of differentiating information: asking if the animal is a mammal is more useful and more likely to receive a positive answer than asking if the animal lives in Madagascar.

Our question selection algorithm also flags if any of the symptoms, symptom combinations or possible conditions described indicate  an emergency. The emphasis on “triage” – understanding what the users best next steps could be – rather than the most probable conditions sets us apart from our competition. 

It also makes us safer. In an independent study by Imperial College in association with the Royal College of GPs our advice to the user was found to [be safe 99%](https://www.livehealthily.com/blog/why-safety-is-paramount-in-digital-health) of the time. 

Healthily has been pioneering the personalisation of health information with AI since 2015. Our approach is very pragmatic: we identify a problem and then look for the best technologies to solve it. 

__Do your customers need help understanding their health conditions using smart AI? [Get in touch](https://lp.livehealthily.com/get-in-touch) and we'll arrange a call with an expert__

[![Download AI whitepaper | The Chatbot Will See You Now - on any platform](//images.ctfassets.net/iqo3fk8od6t9/7cU1cJJ09DWhuwwVXJvKvw/6b1a9b4964dcbb1147cf12bc50da9ef8/AI_Whitepaper_Desktop_CTA_1400x488.jpg)](https://lp.livehealthily.com/ai-whitepaper)

*Your MD is the previous name for Healthily


How our technology check symptoms, provides health information and improves with machine learning.

*Martin Cansdale, Chief Scientist at Healthily explains the science behind the Healthily Smart Symptom Checker and why Healthily uses Bayesian inference.*

The Artificial Intelligence (AI) behind the Healthily Smart Symptom Checker has been continuously updated and refined over the last 6 years. But some of the decisions made in developing the first version of the AI are as important now as they were in 2015, in particular the use of Bayesian techniques to predict the cause of a user’s symptoms.

## What is Bayesian inference?
Bayesian inference is a method of updating our beliefs in the probability of an event or hypothesis, based on new information we observe.

Imagine you’re sitting indoors with no view of a window and you want to estimate how likely it is to be raining. You might start by thinking about how often it rains where you are, perhaps taking into account the time of year, and come up with an initial probability of 10%.

Next, you think back to the weather that morning when there were dark clouds. You estimate that there are dark clouds on about 90% of days when it rains and only 40% of days when it doesn’t rain. You use this information – that the clouds you observed are much more likely to be seen on a rainy day than a dry day – to update your estimate for the chances of rain. After doing the Bayesian calculations, you find that this is now 20%.

Finally, you look at someone coming in the door and see that they’re carrying a wet umbrella. This wouldn’t surprise you if it was raining – you estimate that 80% of people  would be using an umbrella when it’s raining – but would if it was a dry day. You also give a generous 1% chance of someone carrying a wet umbrella on a dry day – perhaps a water main has burst outside.

You feed this new information into your Bayesian calculations. Because it would be so surprising to see someone with a wet umbrella on a dry day, this changes your estimate a lot – now you think there’s more than a 95% chance that it’s raining.

At Healthily, we can use the same approach to update our estimates of the probabilities of different conditions that could be causing a user’s symptoms. With each symptom a user tells us about, we can update the estimates based on how often each condition causes that symptom.

## Why did we choose a Bayesian approach?
The merits of using Bayesian methods can be seen by comparing it with two other approaches we could have used, Machine Learning and Decision Trees.

Machine Learning takes a set of training data and uses this to train a model to make decisions. Models range from the extremely simple to large and sophisticated neural networks. Depending on the complexity of the problem and the model being used, the amount of training data needed can vary from a few dozen examples to tens of millions.

There are no shortages of models we could have tried. The difficulty is in finding suitable training data. While Machine Learning has been applied to Electronic Health Records (EHRs), this isn’t a suitable source for us. It’s important that the data used to train a model reflects the situation in which the model will be used.

For us, this means data on the same population that will use our Smart Symptom Checker. EHRs can provide data for patients in primary care or hospital settings, but this is different to the pre-primary care situation in which our symptom checker is intended to be used. A symptom could be highly indicative of a particular condition among patients who have been to see a primary care doctor or been referred to hospital for treatment, but of much less significance among people who’ve not yet made the decision to seek medical attention. 

A large proportion of people with conditions suitable for self-care will decide to stay at home or visit a pharmacy rather than a doctor, so information on their symptoms will never make it into their health records.

A second approach would be to construct a Decision Tree. This is in essence a flowchart – perhaps with multiple starting points for each symptom a user could present with – that directs the flow of questions, with different routes for each possible answer the user could give. 

Decision Trees can be created automatically through Machine Learning, but this would run into the same problems as other Machine Learning algorithms for finding suitable data. They can also be curated manually, using available clinical data and the expertise of clinicians.

Manual curation of a Decision Tree, however, becomes more difficult and time consuming as the problem becomes more complex. Our symptom checker contains hundreds of medical conditions, hundreds of symptoms each with a number of different attributes, and various factors linked to the user’s age, gender, and medical history. Mapping these out in a Decision Tree would require hundreds of starting points and an unmanageable number of possible paths to take. Adding a new symptom or condition to the system would require a time-consuming reevaluation of the whole tree.

This complexity would be required just to allow the user to start with a single symptom. Our chat interface allows users to choose any combination of symptoms, making the problem even less surmountable for a Decision Tree.

And so we chose a Bayesian approach, allowing users to take an individual path through a consultation with our Smart Symptom Checker, based on what they have told us about themselves, and the symptoms they come to us with. By supplementing this Bayesian approach with rules on clinical best practice, we have developed a world-class symptom checker. The provision of safe and accurate advice on what may be causing the user’s symptoms, and what they should do next, empowers people to take control of their own health.

__You can read more about the [Healthily Smart Symptom Checker](https://www.livehealthily.com/symptom-checker), and other features available via our Chat API, in our white paper,[The Chatbot Will See You Now - on any platform](//assets.ctfassets.net/iqo3fk8od6t9/08pX2xBSPIjHltvLkv6YG/c3f139de4d6777d4af934c53b8dae204/Healthily-AI-whitepaper_The-chatbot-will-see-you-now.pdf)

[![Download AI whitepaper | The Chatbot Will See You Now - on any platform](//images.ctfassets.net/iqo3fk8od6t9/7cU1cJJ09DWhuwwVXJvKvw/6b1a9b4964dcbb1147cf12bc50da9ef8/AI_Whitepaper_Desktop_CTA_1400x488.jpg)](//assets.ctfassets.net/iqo3fk8od6t9/08pX2xBSPIjHltvLkv6YG/c3f139de4d6777d4af934c53b8dae204/Healthily-AI-whitepaper_The-chatbot-will-see-you-now.pdf)


Martin Cansdale, Chief Scientist at Healthily explains the science behind the Healthily Smart Symptom Checker and why Healthily uses Bayesian inference.

What Artificial Intelligence (AI) approaches are best for healthcare? 

The menopause will affect more than half of the world’s population, but it’s often a taboo subject. The average person still knows very little about what happens physically during this time, or the effect menopause can have on mental health.

But things are beginning to change. And October is World Menopause Awareness Month – a time to draw attention to a huge transition that so many of us go through.

To mark this, we caught up with the Healthily Chief Medical Officer, [Maureen Baker CBE](/team/prof-maureen-baker), to get her thoughts on some of your most common menopause questions:

__1. Why do my breasts feel sore during menopause? __

Breast tissue is very sensitive to hormones, including oestrogen. During the menopause, your hormone levels can vary a lot and may become unpredictable, which can cause [breast pain.](/menopause/menopause-sore-breasts-nipples) This should generally settle down over time, as your hormones stabilise. 

__2. Can menopause affect your sleep? __

Menopause can cause [sleep problems](/menopause/menopause-insomnia), and for a variety of reasons. First, sleep patterns tend to change as you get older. You’ll sleep for a shorter time, with less deep sleep, which means sleep quality tends to get worse. 

Second, the majority of people who go through the menopause get hot flushes – and these can also happen at night, causing night sweats. Night sweats can make you overheat and sweat a lot, to the extent that you may need to frequently change your night clothes or bedding. 

Some people are also more prone to [anxiety](/menopause/menopause-and-anxiety) and/or depression during the menopause, which can get in the way of good sleep.

__3. How can I stop hot flushes without taking hormone replacement therapy (HRT)?__

There are a number of lifestyle changes you can try instead of [HRT](https://www.livehealthily.com/menopause/how-to-stop-hot-flushes-without-hrt). Getting enough exercise can improve your mood and your sleep, which may reduce your symptoms. Cutting down on caffeine and alcohol, as well as spicy food, may also help. And smoking is known to make symptoms worse.

At night, focus on keeping yourself as cool as possible – choose loose clothing and light bedding, and open a window to keep your bedroom well-ventilated. 

There are also some prescription medicines for hot flushes that you and your doctor could consider, such as clonidine and paroxetine. 

__4. Is it common to gain weight during menopause, and why does this happen? __

[Weight gain](/menopause/menopause-weight-gain-is-it-bad-for-my-health-and-what-can-i-do-about-it) is a common symptom of menopause, but not an inevitable one. Your body changes as you age and you have a lower muscle mass, which makes it easier to gain weight. On top of this, menopause can stop you from getting a good night’s sleep, which can be a factor when it comes to weight gain. 

__5. Are there any supplements you recommend taking during menopause?__

A number of products are marketed as being able to help with menopausal symptoms, but there’s no good evidence that they’re effective. 

A well-balanced, varied diet should give you all the essential vitamins and minerals you need. Having said that, some health authorities recommend taking vitamin D supplements, especially during winter months, when there’s little sunlight.

__6. Can menopause cause nausea? __

Some people do report [nausea as a menopausal symptom](/menopause/can-menopause-cause-nausea), which is likely to be caused by your hormone levels going up and down. 

__7. Is it normal to get itchy skin during menopause? __

[Itchy skin is a commonly reported menopause symptom](/menopause/itchy-skin). Lower levels of hormones such as oestrogen can lead to your skin becoming dry and itchy. 

Another common problem is genital itching caused by vaginal dryness. This can be treated with hormone cream or with a non-hormonal vaginal lubricant or moisturiser.

__8. What are the most common symptoms during perimenopause? __

Everyone’s menopause experience is different, but in the time leading up to it (perimenopause), periods often change from their previous pattern. They can become heavier and more painful, or lighter and less frequent. 

Breast tenderness is common with perimenopause, as are hot flushes and night sweats. Disturbed sleep is also reported frequently, as are mood swings. 

__9. How would you advise someone to prepare for menopause? __

Make sure you’re getting regular exercise and eating a good and varied diet. If you smoke, this is a good time to think about quitting. It’s often harder to stop smoking when other things, such as menopausal symptoms, are going on. 

__10. What are the biggest misconceptions about menopause? __

That everyone gets horrible symptoms. In fact, they are mostly mild, and some people have no symptoms at all. 

Many people worry that menopause will cause low sex drive (libido), and that sex will become difficult or uncomfortable. Vaginal dryness can be an underlying cause here, but generally, this is easily treated. 

One important concern around the menopause is about the safety of HRT, especially in relation to breast cancer. The risk is small, and often, the benefits outweigh the risks. But talk to your doctor about it before you make any decisions.

Find out more about all things [menopause](https://www.livehealthily.com/menopause/summary), including some [unusual symptoms to look out for](https://www.livehealthily.com/menopause/8-unusual-menopause-symptoms-to-look-out-for).


Check your health, manage 100s of conditions, track your progress and much more.