Your browser is old and is not supported. Upgrade for better security.
Wefunder logo

Invest in SelfDecode

AI platform that provides personalised health recommendations based on DNA, labs and environment.

Exclusive
Friends Invest First
Public Launch on Feb 7 @ 12:00 PM ET
05
day
22
hour
39
min
14
sec
INVESTMENT TERMS
 $52.498M  $49.989M pre-money valuation Priced Round
Early Bird Bonus: The first $500K of investments will be at $2.70 per share and a $49.989M pre-money valuation
$1K, $5K, $10K, $25K
LEAD INVESTOR
Founder of Ornament Health
Being investor in the first round and seeing the progress the team and Joe made so far makes me believe that this company is there to bring a change.                                                                                         
Pitch Video
Investor Panel

Highlights

1
$8M raised (mid 2021). ~2.7M in revenue in 2021.
2
Recurring Revenue: Predictable revenue stream from subscription sales model. Est$447 Lifetime Value of a Customer (LTV).
3
Large Margins & Scalable: High Avg Order Value of $254 - Low Cost of Goods Sold of ~$20 = $234 Gross Profit/Customer.
4
Highly Rated: 4.8 Trustpilot score, 98% retention rate, 75 Net Promoter Score (Q4 2021).
5
Growth Potential: Digital health market will be worth $639B by 2026 & medical apps market size is growing at 23%/yr.
6
Professional Experience: Team of 88 is composed of highly skilled scientists, MDs, PhDs, NDs and software engineers.
7
Operational Excellence: Bootstrapped to multimillion dollar revenue with only small seed investments (totaling $450K).
8
Accumulated Intellectual Property over 5 years. Proven B2C & B2B business models.

Our Team

Growing up, I suffered from inflammation, brain fog, fatigue, digestive problems, anxiety, depression, & other issues that caused me to rack up medical bills. Finally, I started studying my genes and found solutions that actually worked to get rid of my health issues. I knew if personalized healthcare could work for me, it could work for others.

Easy to use, affordable, and on-demand AI doctor

SelfDecode provides users with an integrated AI platform that provides personalized health recommendations based on a combination of your DNA, labs, and environmental factors.

In addition to providing a direct-to-consumer service, SelfDecode has signed 26+ business contracts licensing its technology to a variety of health companies as of January 2023.

Founded in 2016 with a mission to make precision medicine standard in the healthcare industry, the SelfDecode platform provides all the tools an individual or practitioner needs to understand risk factors and build a personalized action plan for optimal wellness.

Users are provided with comprehensive genetic reports about their health predispositions, lab test analysis and tracking tools and lifestyle assessments to get the fullest picture of their health. Based on these results, SelfDecode provides personalized diet, supplement and lifestyle recommendations.

This is in major contrast to the one-size-fits-all approach to health in traditional medicine, in which healthcare strategies are developed for the average person, with much less consideration for our unique characteristics and risk factors. 

The problem with conventional medicine & consumer health habits

Typically, when a person has a health problem, they immediately visit Google looking for answers. However, the information they find is generic and they can’t really understand what will, or won’t, actually work for them.

The fact of the matter is that it’s not possible to find out the root cause of health issues, or identify optimal solutions, without utilizing personal health data, such as genetics, labs, or environmental data. 

Even when a sick person visits a doctor, very little of this data is actually used to treat the issues. Doctors don’t have the time to analyze millions of data points, so they typically rely on treating symptoms.

Each issue is treated separately and people often end up on dozens of medications, none of which treat the root cause of their issues.

The SelfDecode difference

SelfDecode provides a solution that is different from both conventional medicine and other direct-to-consumer health services.

Unlike doctors, SelfDecode is able to analyze billions of pieces of information with artificial intelligence and machine learning to produce polygenic risk scores and personalized recommendations. That way, we can help consumers uncover the underlying cause of their health issues and give them a comprehensive plan to address their problems with specific supplements, diets, and lifestyle changes.

SelfDecode is the only company in the world as of January 2023 that provides cutting-edge ancestry-adjusted polygenic risk scoring direct to the consumer.

We are also the only company that offers truly personalized health recommendations based on a person's genes and other personal health data. While other companies provide risk analysis, their recommendations are generic and they do not use an integrative approach that takes all relevant health data points into consideration.

In fact, we’ve been setting ourselves apart from the competition for quite a while.

When you sign up for a membership with SelfDecode, you get:

  • More than 83 million genetic variants analyzed through a process called genetic imputation using AI and machine learning to provide the most accurate risk and recommendations analysis.
  • Natural supplement, diet and lifestyle suggestions based on your genes, labs and environment that you can implement right away.
  • Prioritized recommendations based on our analysis of all the relevant genes instead of one gene at a time.
  • Explanations about why we make each recommendation so that you can understand the science behind the suggestion (everything is supported with peer-reviewed scientific studies with references linked!).
  • Privacy and security - we never give away or sell your data.

The science behind SelfDecode: Integrative & data-driven

The human genome consists of about 7 billion pieces of information. On top of that, there are thousands of lab tests, diets and other environmental factors that impact your health and what works best for you.

In order to make the best health decisions, you must take all of these factors into account. Otherwise, you end up addressing individual problems or symptoms without looking at the whole picture. The problem is that there is just too much information for any human to analyze.

That’s why SelfDecode is solving this problem with artificial intelligence and machine learning.

We use the latest techniques in AI including Deep Learning, Bayesian Machine learning, and Hyperdimensional Computing for imputation and our genetic models.

That's why we're able to analyze 83 million SNPs (versus a typical 23andme kit that analyzes 650K SNPs) so that we get the most complete picture of your DNA.

In addition to genetics, we’re using advanced algorithms that will allow us to consider all relevant health data points, such as your labs and lifestyle factors, to make better predictions and recommendations so that you can become the best and healthiest version of yourself.

Who built SelfDecode? A highly qualified team of professionals

In order to build SelfDecode, we brought together a diverse team of 88 trained scientists, engineers, MDs, PhDs and skilled professionals to create something that’s never existed before.

The team consisted of 41 software architects and engineers, and 38 scientists with PhDs, MDs and Masters degrees. In addition, we have highly skilled professionals in product development, design, marketing, finance, operations, customer support, and human resources.

The process wasn’t easy, but in the end we were able to select the best people out of 53,000 applicants to bring together the world-class team responsible for building SelfDecode.

Scientific Innovations: Improved Models = Better Accuracy

Our team has successfully built genetic ancestry and imputation models that consistently outperform today’s state-of-the-art models.

These are critical components in providing cutting edge polygenic risk scoring. In addition, our core algorithm for these polygenic scores significantly outperforms others, which will be released in a paper that we are working on publishing with the prestigious Scripps Institute.

Two of these reasons that genetics is not in mainstream medicine today is because of ancestry and imputation.

When you have a diverse population like the US, the same variants will not be accurate for a person of Chinese, Nigerian, Spanish and Norwegian descent. You can't create a test and say that it only works for northern Europeans, etc.

To solve this problem, as a first step, you need to accurately compute ancestry. There are currently 3 companies that have reasonable Ancestry based on our research - 23andme, Ancestry and MyHeritage.

All of these are multi billion dollar companies, and one reason is because ancestry is not easy to predict well.

Our algorithm outperforms their algorithms, and we plan on licensing our ancestry to our B2B partners and others who want cutting edge ancestry.

As far as imputation, whole‐genome sequencing fully captures genetic variation but remains prohibitively expensive and commercially unviable for larger datasets. Instead, the overwhelming majority rely on cost-effective genotyping arrays which capture a sparser set of variants. However, looking at 700k variants can't give you even close to a full picture. Genotype imputation then fills in the gaps, using the array variants as a scaffold, by inferring missing variants from a relevant reference panel. The accuracy of imputation, therefore, is crucial for all downstream applications.

Below, you can see the results from the tests that compare our models (Orchestra and Selphi) to the leading industry standards. It's important to note that most other consumer companies don't use ancestry and imputation in their prediction models at all, or they use methods that are inferior to what is being tested here.

Fig.1: Orchestra vs. state of the art LAI methods. (a) Percent recall and precision for ancestry deconvolution by FLARE (navy), Gnomix (light blue), RFmix (green) and Orchestra (red) across 6 generations of admixture. Each generation is represented with a star shape. The number of points on the star corresponds to the number of generations (0 - 6). Orchestra outperforms other methods in the 1000 Genomes Project (1KGP) dataset with 16 populations (left) and our larger custom data panel with 35 populations (right). Accuracy (%) per population for the 16 populations in the 1KGP dataset (b) and the 35 populations in the larger custom dataset (c). Populations are ordered by mean accuracy across all methods (cross). Overall accuracy for each reference panel is shown on the right.

As seen above, Orchestra markedly outperforms other leading ancestry methods in both non-admixed (generation 0) and admixed samples (generations 1-6). It has ~15% better overall recall and ~14% better overall precision than the next best model. It also retains high accuracy across all tested populations, with a remarkable ability to distinguish between closely related ancestries. Orchestra achieves an accuracy of over 75% for 100% populations within the 1KGP dataset and for 75% of populations within the custom data panel. The other models struggle with about a third of the populations, where their accuracy falls below 50%.

Fig. 2: Accuracy of Selphi vs. state of the art Imputation methods. Imputation errors across chromosomes 1-22 for Beagle 5.4 (blue), Impute 5 (magenta), Minimac 4 (Yellow) and Selphi (Green) for different minor allele frequencies (MAFs) (a) and in different superpopulations (b). Target and reference samples are obtained from the 1000 Genomes Project (1KGP) 30x reference panel. Errors are shown as deviations from the average number of errors across all 4 methods. Selphi outperforms all other methods for all minor allele frequencies and all four super populations. Selphi is in particular better at imputing rare variants (MAF < 1%).

As seen above, Selfie outperforms leading imputation methods across all allele frequencies, performing exceedingly well for rare variants, where all other models struggle. This is of importance because rare variants are more likely to be of medical significance. Selphi also performs better in all tested super populations: Africans, East and South Asians, and Europeans.

B2B Growth & High Return on Marketing Spend

In 2022, SelfDecode averaged a 13:1 return on every dollar spent on marketing.

However, we looked at the landscape and saw that there are quite a few direct-to-consumer companies in genetics, but none of them were using up-to-date methods because of the difficulty in building the core technology.

We could have just continued with our V1 technology and had a profitable business without improving it, but then it would never make it into mainstream healthcare.

It takes longer to do something correctly to begin with, but the results are much better in the long run. That is why we raised and why we are raising again.

For the past two years, we have utilized the additional funds from revenue and our previous raise to improve our core technology, which allowed us to create the best genetic analysis models currently available, as evidenced above. Additionally, we:

  • Optimized our AI and machine learning technology to provide clinical-grade Polygenic Risk Scores
  • Combined genetics with conventional labs and self-assessments within SelfDecode health reports
  • Implemented Ancestry-Informed Polygenic Risk Scoring Models
  • Improve our genetic file analysis to impute over 83 million SNPs with 99.7% accuracy, outperforming academic and commercial models by 22%

Because of our advancements in our technology and valuable consumer-ready software, SelfDecode has massive B2B potential. Already in the last year, we were able to secure 26+ B2B partnerships with an estimated value of $69M over the next 5 years.

Throughout the year, we also worked on improving the product, dialing in our subscription offers, and introducing targeted and relevant upsells to our customers, nearly doubling the average lifetime value from $247 to $447.

Since 2021, we’ve grown our active subscribers by more than 150%. Additionally, SelfDecode was named a winner in Similarweb’s #Digital100 for 2023. With a website growth rate of 120.5%, we’ve been included in the company’s annual ranking of the fastest-growing digital companies.

A look inside SelfDecode

What’s next for SelfDecode? Goals for 2023 & beyond

SelfDecode will continue adding features and product offerings for their B2C and B2B subscription products.

B2B Business

As of Q4 2022, we have signed 25+ partners to license our technology out to other companies in the personalized health space.

Including:

  • Direct to consumer genetics companies
  • Direct to consumer lab testing companies
  • Supplement companies that want to integrate precision health
  • Health apps or devices that want to integrate precision health

B2B Subscription Product for integrative Health Practitioners

  • Client management system (2023)
  • Integrative client reports & health recommendations (2023)

B2C Product Expansion

  • Comprehensive health reports that combine multiple PRS into one report (current)
  • Expansion of our recommendations feature (2023)
  • Precision Health Forum - connects patients with similar conditions, genetics and labs (2023)

Long-term goals (2023-2025)

  • Utilize our large user database to dramatically improve predictions and recommendations
  • Conduct health economic study
  • Partner with corporations to reduce healthcare costs via preventative treatments.
  • Provide clinical decision support system to medical providers - tools that allow doctors to make better decisions
  • Create a laboratory developed test so that doctors can start ordering the tests in hospitals
  • Conduct clinical trials for FDA approval for patented diagnostic tests

      Market Growth Potential

      SelfDecode has entered the health industry at just the right time.

      It's quite clear that polygenic risk scoring will be part of the clinical healthcare market. What isn't clear is how soon it's going to happen - but we believe in the next 1-2 years.

      Since we are the industry leader in this space, we think we are poised to get a big share of the market and grow with the market.

      Consumers are looking for digital solutions for their healthcare now more than ever before. In fact, the Accenture 2020 Digital Health Consumer Survey showed that 62% of consumers are open to using digital health services.

      With 6 in 10 adults having at least one chronic disease that can be impacted by lifestyle choices, the consumer need for personalized and data-driven health recommendations is apparent. GMI Insights reported that the digital health market is expected to grow to over $639 billion by 2026.

      People aren’t just looking for ways to solve their current health problems. They are looking for strategies to effectively prevent diseases and conditions. Grand View Research predicts that the preventive healthcare technologies and services market will be worth $432 billion by 2024. Combined with the fact that the mobile medical apps market size is growing at a compound rate of 23% per year (Emergen Research), and SelfDecode is poised to provide a growing market with just the right product at exactly the right time.

      We also believe that consumers don't just want generic solutations, but they are starting to demand real personalization when making health decisions.

      SelfDecode is poised to not only market its own consumer platform, but to be a provider for other consumer platforms and functional healthcare providers who want to integrate genomics into their practice.

      Meet the founder: Joe Cohen's Story

      Our customers are happier, healthier & they love us

      Overview