Rare disease market research needs a multifaceted approach

Caroline Mathie discusses some of the challenges in researching rare diseases, what the broader market can learn from observing these approaches, and the role of online research in particular. 

Earlier this year, England’s chief medical officer called for the ‘genomic dream’ of genome sequencing for all cancer and rare disease patients. Accelerated use of genome sequencing is allowing the identification of ever rarer diseases – a recent case in point being six children who were identified through an international database of genes and disease characteristics as having the same ASXL2 gene mutation. This answers two fundamental needs experienced by those with rare diseases; (1) knowing the cause of their problem and (2) the ability to share their experiences with others with the same condition. It also presents the industry with an opportunity to address the root cause of the disease through targeted therapies.




By March 2017, 49.7% of the world’s population had access to the internet (88% in North America and 77% in Europe) – figures that are growing rapidly. Unsurprisingly, this access is a valuable tool for researching rare diseases. In Germany alone, the Journal of Medical Internet Research (January 2017) identified 693 websites containing information on rare diseases, many of them provided by support groups/patient organisations, and showed that these are extremely valuable sources of information for patients and their families.

A high proportion of internet users engage with social media, including Facebook and Twitter, and there are many social media support groups for a wide range of rare and ultra-rare medical conditions. As genome-wide analyses, such as exome or whole-genome sequencing, become more commonplace, it is likely that the number of patient groups for rare diseases on social media will increase substantially.

Patient isolation: problem and opportunity

Having a rare disease can feel lonely, and rare disease patients are already fighting their isolation through social media, and by linking to others with the same condition. However, internet access also offers new opportunities in terms of specialist consultation, and patient education.

As new diseases are identified, ever more patients are forced to travel long distances for lengthy periods of time to specialised treatment centres. Each new disease may require a multi-disciplinary team, sparking the need for information and education for patients, carers and often other treating healthcare professionals (HCPs).

The use of the internet, to share information and for discussion, has become critical to both reduce the burden on health services and give patients the information they want at the time they want or need it. Forward-looking specialists are now looking at technological advances to enable at least some consultations with patients via video conferencing. However, though they may relieve logistical and time burdens for patients, fears have been expressed that they may be clinically risky and associated with significant technical, logistical and regulatory challenges.

Forums: opportunity and challenge

Patient forums are having a dramatic effect on the world of market research. They often emerge spontaneously after a small number of patients set up networks or communities to address their needs for information and to share experiences. These types of forums – and other, more established, groups – have been great tools for market researchers to gather information about the experiences of people with rare diseases, as they allow thorough observations of forum conversations. However, the forums may become hidden, as closed or invitation-only groups, if they become unwelcome targets for pharma and the healthcare industry. Thus, what could have been an opportunity for market researchers can turn into a frustrating difficulty.

Another problem with forums is that the industry itself has ethical and compliance concerns regarding too much contact with individual patients.

Nevertheless, the emergence and growth of patient forums suggest that the fabric of the rare disease market research world may have to change from ad hoc recruitment for interviews to a multi-prong approach which includes much longer term community observation.

Some solutions

All is not lost, however. When it comes to using online forums and communities for rare disease market research, we can, for example, set up our own ongoing network or community. To be effective, this requires knowledgeable and effective moderation – continuously – which is costly. However, it does provide the ability to address recruitment issues with a specific set of patients and, more importantly, facilitates an understanding of the longitudinal journeys of different patients and their families through listening to their views over time. The community also provides the ability to identify common points on the patient journey and the needs they have and the questions they are asking at each, to build a comprehensive picture of homogenous vs diverse or segmented needs.

Less costly, but effective, is to ask to join the specific closed communities as market researchers. Some forums allow this and some do not.

Patients can also be researched using standard approaches online, which, of course, come with the usual online issues. With rare diseases, questions around patient identification are more significant, as is making absolutely sure the patient really is a patient. Guaranteed security and compliance must also be in place. Finally, if clients are given access to listen to communities, specific patient identifiers need to be removed, and if it is a short term moderated community, any inputs or questions should not reveal the identity of patients.

Market research – a change in approach

As part of the market research industry we need to explore both a change in approach and, potentially, a change in the business relationship we have with our clients if rare disease market research is to be achieved successfully.

We also need to discuss our approach to dealing with duty of care issues up front, if we establish a long-term, moderated community.

Clearly there is also a role for traditional research approaches for these isolated patients using the web, such as teleweb interviews and Skype. Visual connection is also helpful to create rapport and reduce the sense of isolation.

In summary

The market research model for rare diseases is changing and to benefit from the richness of data produced by long-term patient communities, we need to think differently, set up relationships differently and consider not only the market research, security and compliance aspects, but also the ethical duty-of-care issues to sustain communities that may become important components of patients’ lives.

Gilead gains CAR-T approval, undercuts rival’s headline price

Gilead’s CAR-T cancer therapy has been approved in the US for an aggressive form of blood cancer, indicating the company’s $12 billion acquisition on Kite Pharma could pay off.GILEAD-outside-840x470

Priced at $373,000 per patient, Gilead’s Yescarta (axicabtagene ciloleucel) has just been approved by the FDA for adults with relapsed or refractory large B-cell lymphoma after two or more lines of systemic therapy.

Yescarta follows just six weeks after Novartis gained approval for the first ever CAR-T drug, Kymriah.

The two drugs won’t compete head to head immediately, as Kymriah is currently only approved in paediatric patients with acute lymphoblastic leukaemia (ALL), a smaller group than the broad licence for Yescarta covering B cell lymphoma.

This includes diffuse large B-cell lymphoma (DLBCL), primary mediastinal large B-cell lymphoma (PMBCL), high-grade B-cell lymphoma, and DLBCL arising from follicular lymphoma (transformed follicular lymphoma, or TFL).

These CAR-T (chimeric antigen receptor T-cell) therapies are remarkable because they offer the hope of a cure to at least some of these who receive the cell therapy. Kite’s pivotal trial shows that from 100 patients with large B-cell lymphoma, 72% responded to a single infusion, including 51% who then showed no sign of remaining cancer. The company says 44% of patients were still responding after six months, with 39% of these in complete remission.

This represents enormous progress in patients who would otherwise have died, and talk of a cure for these patients is not misplaced.  Nevertheless, Kite and Novartis hope to improve these percentages over time with next generation CAR-Ts.

These pioneering CAR-Ts involve harvesting the patient’s own T-cells, which are then genetically modified so that they can react to specific antigens on the surface of cancer cells, overcoming the cancer’s ability to hide from the body’s immune system.

This complicated and expensive process takes around 17 days ‘vein to vein’ time for Kite’s drug, slightly faster than Novartis’ current 22 days.

Yescarta’s headline price raised eyebrows when announced yesterday, as its substantially undercuts the $475,000 charged by Novartis for its first-to-market CAR-T, Kymriah.

However, the overall costs are closer than they first appear.  One reason is that Kite’s drug will cover a broader population, and it can therefore afford to offer a lower price. Another factor is that Gilead is not offering a refund if patients do not respond to treatment, unlike Novartis.

As only 17% of patients were not in remission after three months Novartis won’t be handing out that many refunds, but the strategy could mean that Kymriah is less costly overall than Yescarta.

Both drugs are expected to become blockbusters in the coming years, but sales will depend on a range of factors.

Cost will surely be a factor, as in the US and Europe, where Yescarta is also under review, healthcare systems are struggling to find ways to pay for expensive therapies.

And there are fearsome safety issues with CAR-Ts which have in clinical trials caused patients to develop cytokine release syndrome – when the body’s immune system goes into overdrive with potentially fatal consequences if not managed properly.

However Yescarta will carry a stronger boxed warning over the risks of cytokine release syndrome, unlike Kymriah.

Safety concerns arose around Kite’s drug in May when the company revealed a patient had died from cerebral oedema in a Yescarta clinical trial.

This had been the cause of a string of deaths involving a rival therapy developed by Juno Therapeutics, and forced the Celgene-partnered biotech to drop its lead product and switch focus to another further down the pipeline.

With other players such as Bluebird Bio also developing CAR-T therapies, it seems the age of cancer cell therapy is upon us.

Patient Engagement In Device Trials

Last week, the US Food and Drug Administration’s (FDA) Patient Engagement Advisory Committee (PEAC) met for the first time to look at ways to increase patient engagement in clinical trials for medical devices.

Owen Faris, clinical trials director at the Center for Devices and Radiological Health (CDRH), said the opportunity to engage with patients goes beyond using patient reported outcomes (PROs) and patient preference information (PPI) in regulatory decision-making.

According to Faris, patients should be engaged “at the very beginning when we’re thinking about what technologies need to be developed in the first place” and when designing preclinical and clinical studies.



Challenges and Opportunities

Throughout the meeting, participants and members of the PEAC brought up a number of challenges and barriers that patients face with clinical trials.

One of the biggest challenges raised is that many patients are not all well-informed about how clinical trials work or how to get involved with them.

As a potential solution, PEAC members said that a framework or roadmap should be developed to demystify the clinical trial process for patients. The committee also said that information about clinical trials and informed consent documents should be written in plain language to make it easier for patients to understand.

As for enrolling patients, Annie Saha, director of external expertise and partnerships at CDRH, said that clinical trial sponsors should engage with the institutions that people trust to recruit patients. “Go to the churches, go to the nonprofits, use the local affiliates of the nonprofits, go to social clubs, go to local clinics, don’t just try to use a primary care or academic medical center,” she said.

Inclusion and exclusion criteria were also discussed as a challenge to patients. One PEAC member, Cynthia Chauhan, said that clinical trials “should reflect the affected population,” noting that many minority groups are underrepresented in clinical trials and that restrictive inclusion and exclusion criteria can result in patients with comorbidities being left out.

When it comes to improving patient retention, PEAC members suggested reducing the frequency and length of visits, offering night and weekend hours to accommodate patients and their caregivers’ schedules, offering child-care and providing transportation to and from the trial center would make it easier for patients to continue with clinical trials.

PEAC members also suggested ways to improve how information from clinical trials is communicated to patients, such as sending a patient newsletter and providing final trial results in an easy-to-read format.

Apple patents Watch blood pressure monitoring tech

While its new line of smartphones dominates the headlines, Apple is continuing to push on with its healthcare ambitions, filing for a patent that would allow the Apple Watch to monitor blood pressure.



The patent, entitled “Wrist Worn Accelerometer for Pulse Transmit Time (PTT) Measurements of Blood Pressure”, describes technology that combines data gathered by two different sensors in the Watch.

The first data source is the Watch’s built-in heart rate sensor which can indicate a user’s pulse. The second data source is an accelerometer which, when placed against the heart, can detect the moment blood exits the left ventricle.

By timing the difference between the blood exiting the heart and reaching the wrist (the pulse transit time), blood pressure can be determined.


“Elevated blood pressure (aka hypertension) is a major risk factor for cardiovascular disease,” states the patent. “Timely detection of hypertension can help inhibit related cardiovascular damage via accomplishment of effective efforts in treating and/or controlling the subject’s hypertension.”

Current ambulatory and home blood pressure measurement approaches fail to provide continuous measurement of blood pressure, says the patent, whilst continuous measurement using a cuff can be disruptive to sleep patterns.

The news of the patent comes after last week’s listing of Apple as one of nine companies selected for the FDA’s Pre-Cert Program pilot.

Designed to streamline the approval of innovative solutions, the Program asks for less pre-market data for new tools from trusted ‘pre-certified’ companies, instead basing approval on post-market real-world evidence.

Interestingly, Apple CEO Tim Cook stated that the company did not want to include too many health-related sensors in the Watch back in 2015 due to complex regulatory approval systems. The time it would take for each new sensor to be approved would hinder the overall evolution of the Watch, said Cook.

But the company could see the new pilot programme as a way of both continuing to push its Watch into more health-focused territory whilst maintaining a decent technological evolutionary pace.

To market new drugs in India, global trials must include Indians


  • The move is expected to benefit clinical research organisations and hospitals operating in India
  • The decision has been taken keeping in mind the safety of the Indian patients


In a move to ensure efficacy of medicines sold in India, the drug regulator has made it mandatory for companies to include Indian patients in global clinical trials if they want to market in India a new drug developed outside the country.

The decision was taken in a recent technical committee meeting, headed by director general of health services Jagdish Prasad. The committee, which was formed following directions from the Supreme Court, has a mandate to supervise clinical trials on new chemical entities.

“Any firm intending to market a new drug which is being developed outside the country, should include Indian patients in the global clinical trial…,” the minutes of the meeting, reviewed by TOI, said.

The committee also decided that if proposal of such global clinical trials are already approved in ICH countries such as the US, Europe and Japan, then it will be reviewed on priority by the Indian drug regulator.

The ICH or International Council for Harmonisation of Technical Requirements for Pharmaceuticals for Human Use is a project that brings together the regulatory authorities of Europe, Japan and the United States and experts from the pharmaceutical industry in the three regions to discuss scientific and technical aspects of pharmaceutical product registration.

Clinical trial proposals approved by an ICH country will also be considered for approval by the Drugs Controller General of India (DCGI) without referring to subject expert committee, unless there is some specific reasons which should be recorded in writing.

“The decision has been taken in public interest keeping in mind the safety of Indian patients. It is important that drugs which are sold in the country are being tested on Indian subjects prior to their launch,” DCGI G N Singh said.

The move is expected to benefit clinical research organisations and hospitals operating in India. These organisations along with various hospitals conduct clinical trials or testing of drugs on human beings on behalf of pharmaceutical companies, mainly multinational drug makers.


Another Acquisition: Ergomed to acquire CRO PSR Group for €5.7M

Ergomed, a specialized pharmaceutical services and drug development company, announced the proposed acquisition of PSR Group, an international niche CRO specialized in orphan drug development. Ergomed has agreed to acquire 100% of the issued share capital of PSR Group for a total consideration of up to €5.7 million.


Dr. Dan Weng, Chief Executive Officer of Ergomed, said: “This acquisition aligns with the strategy laid out at IPO of seeking to grow our existing, profitable service business both organically and through strategic acquisitions, and specifically of becoming a leader in orphan drug development. We are looking forward to combining PSR’s specialist skills and Ergomed’s global infrastructure to rapidly develop this business based on our combined strengths. PSR has successfully demonstrated its leading capabilities in this area and its addition to the Group complements Ergomed’s existing highly-regarded orphan disease specialism. We welcome PSR’s team and are pleased to increase our capabilities in an under-served and growing area.”

Dr. Roger Legtenberg, Chief Executive Officer of PSR Group, added: “PSR welcomes the opportunity to expand its current services portfolio and geographical coverage by leveraging Ergomed’s international reach and complementary services. We will continue to make a significant contribution to the availability of new orphan drug treatments, improving the lives of patients and their families impacted by rare diseases. We look forward to joining the group and contributing to its growth and success.”

The Acquisition is consistent with Ergomed’s stated strategy to grow its existing, profitable services business both organically and through bolt on acquisitions. Ergomed has particular expertise in the development of orphan drugs as part of its profitable and fast growing CRO offering, which provides a full range of high quality contract research and trial management services across all phases of clinical development. PSR’s extensive expertise in orphan drug development will complement Ergomed’s services and will further strengthen Ergomed’s orphan drug development capability in addition to expanding its current services portfolio.

PSR, established in 1998, and based in the Netherlands, is a specialist orphan drug CRO and recognized as a leader in rare diseases. As part of the Acquisition, Ergomed will continue to grow PSR’s global orphan drug development business under the PSR brand and will remain focused on its two divisions: (1) PSR Orphan Experts, which is a leading expert in supporting biotech and pharma companies with their regulatory and clinical development of orphan drugs (c. 75% of revenues); and (2) PSR Pharma Resource, which complements PSR Orphan Experts as a niche staffing provider, focused on orphan drug specialised staff (c. 25% of revenues).

Orphan drug development is a specialist and growing field. Orphan diseases are severe, debilitating or even life-threatening conditions which affect fewer than 1 in 2000 people (EU definition) or fewer than 200,000 people in the US (US definition). Although patient numbers in individual indications are limited, there are a total of 30 million people worldwide suffering from rare diseases. The orphan drug market to target these diseases continues to grow and requires highly specialised providers due to the regulatory, logistical and operational complexities of conducting clinical trials in these indications. Due to their characteristics, combined with the rarity of the diseases, orphan drug clinical studies typically are complex and run in small patient cohorts with potentially faster market entry.

The Acquisition will bring together Ergomed’s global geographical footprint, including its presence in the MENA region, an area which is important for orphan drug development, and PSR’s significant expertise and strong brand. Ergomed believes the combination will have the scale and specialism to compete effectively in the global CRO market.

Ergomed has a track record of successful identification and integration of acquisitions and the Company continues to pursue opportunities to acquire services businesses which are consistent with its strategy of becoming the global leader in pharmacovigilance services, the leading CRO in orphan drug development and to strengthen its CRO network through geographic expansion and/or complementary service offerings.

The initial and contingent consideration will both be satisfied partly in cash and partly in new Ergomed ordinary shares. The initial share consideration will be satisfied through the issuance of 323,813 new Ordinary Shares in Ergomed at an issue price of 165 pence per share. The Initial Consideration Shares are subject to a 12 month hard lock-in and six month orderly market provision. Admission of the Initial Consideration Shares is expected to take place at 8.00 a.m. on 2 October 2017. The Acquisition is expected to be immediately accretive to Ergomed’s 2017 earnings per share.

The Acquisition is conditional only upon the placing agreement between the Company, Numis and N+1 Singer becoming unconditional and upon Admission. The Acquisition Agreement includes warranties and indemnities from certain of the sellers in favor of Ergomed. Claims by Ergomed against such sellers under the warranties and indemnities are subject to certain financial thresholds and caps and also, in the usual way, to matters disclosed by the sellers.

The Rise of Real-World Evidence

Healthcare has been shifting to a value-based, personalized paradigm,” says Brett Davis, general manager, ConvergeHEALTH by Deloitte. “Reimbursement pressures and the unsustainability of the cost trajectory we’ve been on has been driving everyone to get to more of an outcomes-based or value-based construct as opposed to a fee-for-service model.”


Personalization in medicine is driven by the convergence of our deepening understanding of genomics and our improving digital health technologies—the timing is right. Real-world data sources are combining with traditional data sources—clinical trials, electronic medical records, genomic data, insurance claims, streaming connected devices, social media, meteorological data, and patient reported data—to offer a wealth of possible applications. And now maturing technologies like machine learning and algorithmic methodologies can make sense of these big, noisy, complicated datasets. Together, these data sources and analytic technologies seek to answer what treatments work for whom, why, in what context, and at what cost.

And everyone wants in.

“Health payers are trying to use this data to decide what their reimbursement strategies should be; patients are going to increasingly have access to a lot of this data to make decisions and it will influence what they want to do,” Davis told me. “Obviously, health systems need to use this data to improve care pathways and clinical decisions. And then of course biopharmaceutical companies need to wrap their arms around, and figure out how to get access to and analyze this data.”

Regulatory Blessing

Real-world evidence brings with it a host of opportunities. Will more data help better design trials and find the right patient cohorts? Will more data better predict adverse events, and allow more nuanced safety and pharmacovigilance modeling? Will more data allow companies to better commercialize, price, and get reimbursed for their innovations?

“This is a tectonic shift for the pharmaceutical industry,” Davis said.

And in fact, biotech and pharma are being increasingly freed to use this data. In December 2016, the 21st Century Cures Act called for U.S. Food & Drug Administration to develop a framework and guidance for evaluating real-world evidence in the context of drug regulation to support approvals of new indications for previously approved drugs, and to support or fulfill post-approval study requirements.

FDA has been using real-world evidence for safety surveillance and development of drugs for rare diseases in which randomized controlled trials are impossible. And clinical trials commonly use real-world data to determine end-points, such as gathering deaths from the National Death Index or tumors from a tumor registry. But now the FDA is sending signals that broader use is appropriate and encouraged.

Using real-world evidence to answer questions about dosing regimens, long-term outcomes, and outcomes in various subpopulations “is preferable to having no evidence whatsoever,” wrote three FDA staff members including Janet Woodcock, director of FDA’s Center for Drug Evaluation and Research, in a Viewpoint article published in the Journal of the American Medical Association last month (doi:10.1001/jama.2017.9991).

Woodcock and her co-authors listed several ways real-world data can improve efficiency and cost-savings in clinical trials. “Real-world data may be used to aid in the design of a clinical trial by assisting in the selection of study sites that are more likely to enroll study participants, provide a basis for power calculations, provide a prior for a Bayesian statistical analysis, provide an external control group, and guide enrichment. Real-world data may also be used during the conduct of a trial to reduce duplication of data input such as baseline medical history, automated adverse event reporting, and end-point ascertainment.”

In remarks delivered to the National Academy of Sciences on September 19, Scott Gottlieb, Commissioner of Food and Drugs, further committed to expanding FDA’s use of real-world evidence.

“The FDA’s interest in advancing the adoption of RWE in support of its programs remains a top priority. And it’s a high priority of mine,” Gottlieb said. “We need to close the evidence gap between the information we use to make FDA’s decisions, and the evidence increasingly used by the medical community, by payers, and by others charged with making healthcare decisions.”

Drug discovery, development, clinical testing, and post-market use should be considered a continuum, Gottleib said. “No product is all risky and uncertain one day, and completely safe and effective the next.” So it makes sense to apply real-world evidence earlier in the drug development process. Gottleib also committed to publishing consensus definitions that relate to how different parts of FDA apply real-world data to regulatory considerations.

Paradigm Shift

With FDA’s blessing, companies can now pursue the application of real-world evidence with even greater energy. We are at a tipping point, Davis said, a shift from real-world data 1.0 to real-world data 2.0.

“What we’re really trying to do is have the real-world evidence and the clinical trial converge and have a much closer connection,” said Bill Fox, global CTO for healthcare and life sciences at MarkLogic. “That presents two kinds of opportunities for collaboration. One is internal, so you start to have parts of a business that weren’t tied together before, weren’t on the same page, weren’t necessarily working together start to work together, that it creates really important opportunities for collaboration in the market… [And] now a big pharma might be collaborating with a hospital system or a provider system, or patients directly in order to gather this real-world evidence from them.”

But new data types and data streams will do nothing but bog down the system without the next generation technologies to navigate them.

“Real world evidence is really sort of a lightning rod for digital transformation and for the way that these pharmas are doing business and the way that they think about their IT,” said Fox.

At Celgene, for instance, a company-wide information initiative has led to the creation of a new big data platform to manage real-world evidence. Celgene’s Synapse platform lets the company ask big picture questions that have the potential to drive the business in new ways. “There are certain types of studies that inform decisions at multiple stages of the pipeline,” said Patrick Loerch, senior director of data science at Celgene. For example, “building out treatment flows based on real world data. It’s getting an understanding of how a given disease is being treated in the real world, which is a question that informs decisions throughout the entire pipeline.” (Read more: Celgene’s Big Data IQ


Celgene is in good company. Last year, the Deloitte Center for Health Solutions surveyed 15 leading life sciences companies to understand the current state of their RWE capabilities. The results of the Real-World Evidence Benchmark were released late in 2016. Among the findings, the company discovered that over half of survey respondents plan to invest in their RWE programs to significantly increase their capability in this space.

The investments are broad. About 60% of companies surveyed are using the cloud to maximize their ability to store and analyze data. Whether relying on off or on-premises storage, companies are making software and platform investments to ensure the best use of RWE. There are staffing investments as well; companies are paying closer attention to improving their data science skills, seeking experts in statistics, machine learning, and computer science to generate insights from disparate data sources.

Data Dearth

But the technology is only half the battle; many in pharma and biotech don’t feel they have as much real world evidence as they’d like, and gaining access to the data is challenging. Sixty percent of Deloitte’s survey respondents reported their biggest challenge was gaining access to the real-world evidence they need.

“Pharma as an industry has spent billions of dollars collectively setting up the infrastructure for running clinical trials. But that infrastructure for clinical trials is somewhat useless to capture and manage real-world evidence, information, and data,” Davis said. In fact, the Deloitte survey respondents want real world data far before clinical trials. Nearly 50% of survey respondents believe that R&D is the biggest area of opportunity going forward to leverage real-world evidence.

So pharma and biotech are looking for partnerships with patient advocacy groups, health systems, and other parties capturing these data, Davis said, citing recent major partnerships like those between Amgen and Humana, Merck and Aetna.

Networks are also connecting more data by either disease area or geography. For example, the ORIEN Network—Oncology Research Information Exchange Network—started at Moffitt Cancer Center in 2006, but has now expanded to a network of over 15 cancer centers nationwide. ORIEN partners use a common protocol: Total Cancer Care, which provides a standard system for tracking patient molecular, clinical, and epidemiological data and follows the patient throughout his or her lifetime. Partners have access to one of the world’s largest clinically annotated cancer tissue repositories and data from more than 100,000 patients who have consented to the donation for research.

“For pharma, it is a little bit of a change in mindset. Historically pharma wants to own the data. The reality is in this new world of healthcare data being electronic… the concept of ownerships shouldn’t necessarily be focused on,” Davis said. “It’s access and use that are key.”

The Intelligent Trial: AI Comes To Clinical Trials

Artificial intelligence is revolutionizing health care and advancing the clinical trial process faster than any Hollywood AI robot could predict. Besides cutting costs, improving trial quality, and reducing trial times by almost half, AI is finding biomarkers and gene signatures that cause diseases, recruiting eligible clinical trial patients in minutes, reading volumes of text in seconds, and is on the cusp of breakthrough discoveries involving new diagnostic tools and treatments for Alzheimer’s disease, cancer, and other chronic and terminal illnesses.


Created in the 1950’s, AI is the ability of a computer or machine to simulate human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages. It is dependent upon three elements: massive amounts of data, sophisticated algorithms, and high performance parallel processors. One aspect, machine learning (ML), can rapidly assess multiple texts, graphs, and other data simultaneously.

The decreasing cost of computers and software, the increasing push for precision medicine, the abundant availability of an exponential amount of data, and the public’s impatience with the rising cost of drugs and medical care may contribute to the recent surge in AI adaptation and acceptance.

“This is not wizardry. It sounds like a mystical concept,” says Atul Butte, Director of UCSF’s Institute of Computational Health Sciences, Distinguished Professor of Pediatrics, and Executive Director for Clinical Informatics for the University of California Medical Schools and Medical Centers. “But in fact, you can go on Amazon and buy Machine Learning for Dummies for less than $20.” He cites logistical regression and “old-fashioned statistics” as examples simple machine learning. “We’ve always been using these techniques in trial designs.”

Artificial intelligence is an opportunity to personalize and optimize health care, says Trials.AI’s Product Manager Josh Stanley. “Trials are slow to progress; some researchers still use paper and pen. Their philosophy is, why change when it’s working? But it’s not. A huge percentage of trials fail, and a huge percentage don’t reach their recruitment and retention goals.”

Despite progress already made and promise ahead, many voices warn of potential negative consequences.

Pandora’s Box

For example, Tesla creator and Space-X CEO Elon Musk once said that AI is a “fundamental risk to the existence of human civilization,” and donated $10 million to the Future of Life Institute to run a global research program designed to keep AI beneficial to humanity. Physicist Stephen Hawking warned that AI “may be the best, or the worst thing, ever to happen to humanity” and later added that AI is “crucial to the future of our civilization and our species.”

Accenture estimates that AI will increase economic growth across 16 industries by 1.7% by 2035 and has the potential to increase productivity by 40%. A separate study done by researchers at Carnegie Mellon University and Albert Ludwig University in Germany, estimates that AI could cut the cost of drug discovery by about 70% (DOI: 10.7554/eLife.10047).

Unlike HAL, real-life artificial intelligence is not self-learning or self-aware. Humans must feed data, good and bad, successes and failures, into the software so it can learn patterns and experiences. “Before you have a [medical] case that needs to be fixed, it’s best to have given the computer 1000 or 10,000 more examples so it can learn,” says Butte. “Then when you have the 10,001st case, the computer now has a good guess of what went wrong. We have to teach computers, feed data, and let them discern the patterns.”

Trial Intelligence

Trials.AI’s Stanley says the role of AI is not to replace, but to augment and assist human intelligence, incorporate user-friendly efficiency, leverage data and make predictions in clinical trials to detect trends and outcomes. For example, AI can analyze operational data from historical cases, measure responses to drugs, predict site performances and use predictive criteria to determine whether taking a drug will result in a positive or negative outcome, whether the patient will drop out, and whether a trial will be successful. Clinicians can review a patient’s medical history and receive lab results within one system simultaneously. AI can ingest millions of words of text, molecules, genomic sequences, and images in minutes, aggregate the data and devise hypotheses beyond human ability. It does not argue dogmatic ideas, push personal theories, or maintain judgmental ideas.


Every year in the U.S., approximately 2 million patients participate in roughly 3000 clinical trials; six million patients are needed to meet U.S. recruitment goals. Consequently, up to 90% of trials are delayed or over budget. “The more patients who enroll in trials, the faster the pace of research and healthcare innovation in general,” says Wout Brusselaers, CEO and co-founder of Deep 6 AI, which uses AI to mine medical records to accelerate finding and recruiting patients for clinical trials.

Deep 6 AI’s software can find eligible patients for complex trials within minutes, depending upon the criteria. For example, in an early comparison search, a principal investigator using traditional recruitment methods to validate 23 eligible patients in six months for a biomarker for a non-small cell lung cancer trial. The Deep 6 AI software found and validated 58 eligible matches in less than 10 minutes. “We must find patients quickly,” says Brusselaers, “to develop cures faster.”

Researchers estimate that to hasten cures for cancer 25%-50% of cancer patients should be enrolled in trials. But, says former Vice President Joe Biden, “less than five percent of cancer patients enroll in a clinical trial often because patients and doctors don’t know what trials are available.”

That’s where AI comes in. Deep 6 AI, winner of the 2017 Accelerator Competition Enterprise and Smart Data category at the SXSW Conference and Festivals, uses Natural Language Processing (NLP) to read doctors’ notes, pathology reports, diagnoses, recommendations, and to detect hard-to-find lifestyle data, such as smoking and activity history. It then graphs this information and matches appropriate patients with clinical trial criteria, potentially reducing recruitment time from years to just days or weeks.

Brusselaers and his team compare these patient graphs to find common traits in symptoms and diseases and disease progression and patient outcome. “I can say, ‘Show me a patient that looks like this one.” When researchers isolate 10 common characteristics of Alzheimer’s patients, the software can find undiagnosed patients with the same traits. Brusselaers can then examine just how predictive of Alzheimer’s are these 10 conditions.

Another software program, called Fuzzy Matching, detects patients with undiagnosed symptoms and characteristics, such as cognitive decline or chronic pain. This allows sponsors who want to test new drugs for Alzheimer’s, chronic pain, and other disorders to find symptomatic, but undiagnosed, patients, and to offer these patients the chance to enroll in a trial they did not know about.

Using algorithms based on both historical and incoming data throughout a trial, AI can predict which patients have a higher chance of dropping out or not following protocols. Clinicians can track patients individually, and email or text them reminders to take medications at specific times, journal, submit forms, or keep appointments. “We keep them engaged to help them stay in the trial. This also makes it much easier to manage, especially if you have 5 or 6 trials going on simultaneously,” says Trials.AI’s Stanley. This also gives clinicians more time to strengthen communication with patients.

Electronic reminders and check-ins give rural patients who have Internet access but don’t live near major medical centers or trial sites a chance to participate in trials. This also saves them from stressful distance travelling and long waiting room queues. “We should all have the same access to cutting edge care,” says Wout Brusselaers. “It doesn’t have to be expensive.”

Intelligent Speed

The clinical trials managed by Trials.AI have increased protocol adherence and decreased lost time. In its first trial, AI retained 98% of patients, had one critical deviation throughout the entire trial, and continued to completion without interruptions. “This is a huge opportunity to shorten, maybe even cut in half time to market,” says Stanley. The program allows investigators to more easily monitor cross-country sites, to know which ones are underperforming, to proactively address problems early, and to measure data they otherwise would not have access to in real time.

It is also a chance to leverage what is known about genetic biomarkers, says Stanley. “We can test therapies against patient cohorts with different gene mutations, and monitor and drop cohorts from the trial that aren’t responding positively.”

Working in concert with human intelligence, AI identifies specific genetic markers in populations to develop drugs for individual patients. “Humans are good for seeing patterns, but have built-in biases,” says Stanley. “It can be overwhelming; humans can’t filter out the noise in data. AI can discover patterns in data. We then can go back and see if it’s actionable, if it’s a meaningful discovery.” Computers, not doctors, analyze the mountains of data producing personalized medicine.

Hospitals, pharma, CROs and other sponsors can use the software to find patients with specific diseases, genomics, mutations, or any other characteristics. Pharma or CROs see a different platform with aggregated results, exclusion and inclusion criteria. Although they don’t see personal information, they know where prospective patients are.

AI is “crucial” in determining if a patient is suffering anxiety, depression, Alzheimer’s disease, or other cognitive impairments, says Frank Rudzicz, co-founder and president of Toronto-based WinterLight Labs.

Traditional paper and pen testing methods for Alzheimer’s disease “are crude, and up to the person administering the test to judge whether a person passes or not,” says Rudzicz, also a scientist at the Toronto Rehabilitation Institute. Instead, the WinterLight Labs team uses quantifiable data from algorithms that measure thousands of variations in voice patterns, including pitch, frequency, amplitude, grammar idiosyncrasies, subject matter, and its emotional impact on the patient.

Deaths from Alzheimer’s disease have increased by 89% since 2000, according to the Alzheimer’s Association and, along with other dementias, are expected to cost the US $259 billion in 2017 and top $1 trillion by 2050.

“AI can hone in on very subtle, data-driven differences,” says Rudzicz. “This is beyond human perception. The input we get is the raw, direct measurements from the person as opposed to interpreted results. The patterns are in the data, and may not conform to a theoretical model a person came up with to describe a disease.”

For example, a depressed patient may use more personal pronouns and negative-sounding words. An Alzheimer’s patient replaces proper nouns (Aunt Elsie, TV remote) for pronouns (she, that) and hesitates more often between words. The software can then determine the average number of times a person uses negative words, find statistics related to a measure, and subsequently determine a patient’s positivity and negativity and whether he is at risk for depression. According to the National Alliance on Mental Illness (NAMI), depression is the leading cause of disabilities worldwide.


“We can’t predict what the most important measurement will be,” says Rudzicz. “That’s where the machine learning comes in. If the AI says a feature or obscure measure is important, and it can make accurate predictions on someone’s cognitive health, at some point we have to be satisfied that the machine found something we didn’t.”

WinterLight Labs is conducting pilot programs and clinical trials to test the software’s accuracy. It is not yet used to diagnose, due to complex regulatory processes, and instead maps and validates existing diagnoses. It is currently working with two pharma companies to screen and recruit eligible patients for Alzheimer’s disease trials, expediting the process, reducing patient drop-out rates, and hopefully slashing millions of dollars in costs. Rudzicz also hopes to use the software as a remote device to monitor and assess patients’ cognitive health from their homes, replacing stressful distance traveling and long waiting room lines.

Crowded Field

The list of companies using AI or partnering with companies already using it is growing exponentially. Deep 6 AI is partnering with Translational Drug Development (TD2) to recruit for an oncology clinical trial testing a new drug. The team is searching multiple hospitals to find patients with a rare form of cancer who have not yet begun therapy. American technology company NVIDIA teamed with the National Cancer Institute, the U.S. Department of Energy and national research laboratories to use AI in creating a common discovery platform for cancer called CANDLE. Goals include uncovering the genetic DNA and RNA of common cancers, predicting how patients will respond to treatments, how each patient’s cancer evolves, building a database of disease metastasis and recurrence, and getting new therapies to market faster.

Deep Genomics, another Toronto company, looks for patterns in genomic data to find causal relationships with specific diseases. It is in early-stage drug development for inherited diseases caused by a single genetic mutation, which affect about 350 million people globally.

BERG Health is using AI to analyze tissue samples, genomics, and other data pertinent to a disease, which has resulted in a potential new drug for topical squamous-cell carcinoma. It passed early safety and efficacy trials and is waiting for full-scale testing. The company also is financing Project Survival, a seven-year project to improve the efficiency and price-point of drug research.

Korea Pharmaceutical and Bio-pharma Manufacturers Association are collaborating to buy an AI platform that will be used by around 20 Korean pharma companies. IBM, Atomwise, and Insilico Medicine are forming research partnerships with universities and nonprofits. GKS and Lawrence Livermore National Laboratory will use AI for pharmaceutical R&D. England’s Benevolent AI has an exclusive rights agreement with Janssen, giving the AI company exclusive access to an undisclosed number of clinical-stage drug candidates.

Last year, A Chinese team won a $1 million contest aimed at automating the detection of lung cancer using algorithms that most accurately identified signs of the disease in low-dose computed tomography images. The winning algorithms will be released to the public for free, hoping to inspire future medical imaging innovation.

Learning Better Questions

What happens to all these millions of points of structured and unstructured data from biomarkers, genomics, wearable devices, EMR, social media, labs, and imaging? It isn’t all used immediately. Some researchers store raw data in the event that, after more research, unused data might answer an unresolved problem and find a cure. James Streeter, Global Vice President of Oracle Life Sciences Product Strategy, says some clinicians “want to collect data because they think the answer is in there somewhere. Some don’t know what they are looking for. They have a hypothesis but haven’t proven it.” If, for example, says Streeter, “we can predict from genomics when a person will get cancer, we need millions of points of data to eventually be able to figure it out.”

“Other companies have made great strides in artificial intelligence, but today’s companies don’t know what to ask it. If they don’t know which questions to ask, they won’t get an answer. We are barely touching the surface of what we can do with data,” says Streeter. “We don’t know all the challenges. Companies do a great job bringing data together, but if you don’t know what questions to ask, you can’t get answers.”

Finding answers, or deciphering what questions to ask, is one of the challenges facing the industry. Algorithms are not infallible and can still have biases; datasets may have inherent limitations or biases built into them by humans. “It’s still an art to develop methods and models to eliminate errors built into the subsystems,” says Bruce Palsulich, VP of product strategy at Oracle Health Sciences.

Is AI more successful with certain patients or diseases? What are the inherent unknowns? What don’t researchers know? These are all questions for data scientists. Will an over-reliance on machine learning really result in a lack of learned skills, as some posited in a Viewpoint published in JAMA? (DOI: doi:10.1001/jama.2017.7797)


“We can’t expect AI to be perfect,” says Oracle’s Streeter. “We may not be asking the right questions.” Computers are only as smart as the information fed to them. Basically, researchers don’t know yet what they need to know.

Brusselaers says it is important not to overpromise and to realistically manage user expectations. While AI strips weeks and months off traditional tedious recruitment practices, it also allows easier access to private health information. New tools and boundaries must be installed into the software to prevent nefarious intrusions. Human vigilance also reduces chances of errors. Brusselaers says, “We are big believers in synergistic relationships between artificial and human intelligence.”

AI and humans are reducing these errors together. The FDA receives about 12,000 serious adverse event reports annually per individual reviewer, up 15%-35%, says Oracle’s Palsulich. “The volume is so high that it will never be feasible to support that without having machines do that work for us.” Machine learning extracts meaningful attributes from documents, sometimes in seconds, such as adverse reactions across multiple trials in multiple populations, pharmacogenetics, results from markets where the drug was previously approved, and medical record observations, to determine which documents humans need to review.

Increased automation does not necessarily mean job losses. Teaching machines how to question may be the next phase of AI. “It’s still very basic and we still don’t have enough people in the industry with experience yet,” says Streeter.

Data scientists who know the different types of data available, how to do the analytics to find these answers, and how to find the questions that need to be asked, are in demand. Balancing data with regulatory needs is an industry challenge, says Streeter.

This is giving a new dimension to clinical healthcare. Some administrative and tech jobs that AI replicates will need to be retooled. But, there are new trade needs, covering the ethics of AI, data science, and teaching machines. Companies are looking for data scientists to help find questions and answers. The industry must find people to bring structured and unstructured data together to find the answers they need. “There aren’t too many scientists yet in the field,” says Streeter. “We know if we bring different kinds of data together, we can find answers.”

And that is the purpose of examining all this data: to find new drugs, new cures, and new hope. “We want to help doctors already overloaded with assessments and streamline a more accurate picture of cognitive health,” says Rudzicz. “We want to make the world a better place.”

Rho, Bracket, Hearst, And More: News From September 2017

September was full of exciting news in the clinical trial and healthcare community, including partnerships, products, and promotions from Rho, Bracket, Hearst, and more.


Hearst announced an equity investment in M2Gen one of the top comprehensive cancer centers in the United States. This partnership will help accelerate the discovery of innovative cancer therapies and improve care for patients nationwide. The collaboration will provide funding to expand the efforts of the nation’s first major data sharing network among leading cancer institutions. Press release

Rho announced it has plans to hire an additional 40 more team members as part of its growth expansion strategy in 2017. The open positions at Rho range from entry-level research associate or administrative assistant positions to seasoned professionals, including clinical research associates (CRAs) and senior. project managers.  The Chapel Hill-based CRO is also looking to fill more senior positions such as research scientists and a vice president of operations. Press release

Congenica announced a new customer partnership with the Coimbra Paediatric Hospital (CPH). Through this partnership, the hospital has licensed Congenica’s Sapientia software platform to perform analysis of whole-exome sequencing data and produce diagnostic reports for its In2Genome project. The €1.2 million ($1.4 million) project funded by Portugal2020Compete 2020, and European Structural and Investment, aims to revolutionize the diagnosis of rare genetic diseases through insights gained from population-wide genomic data. Initiated by The Medical Genetics Unit of CHUC, which is housed in CPH, the In2Genome project is a multidisciplinary consortium collaborating with Portuguese companies Coimbra Genomics and Genoinseq by Biocant. The project, which commenced in July 2017, is expected to run for two years. Press release

Marketware announced the close of $4.5 million Series B led by EPIC Ventures, and the appointment of Alex Obbard as the company’s CEO. Obbard brings more than 25 years’ experience in all areas of revenue and profit generation for technology organizations, with significant experience driving SaaS-based sales growth. Most recently, Obbard served as SVP of Sales at Solutionreach, the leader in patient relationship management with over 100,000 healthcare professionals and approximately 25,000 practices. “Not only does Alex have the relevant market experience and a track-record of growth but he has a contagious confidence,” said Nick Efstratis, Managing Director with EPIC Ventures, in a press release. “I have always enjoyed working with Marketware for their commitment to succeed and Alex’s placement as CEO will only continue to fuel the company’s momentum.” Obbard commented, “I’m excited and grateful for this opportunity. The Marketware team has accomplished so much, so quickly, establishing our solutions as the industry’s best physician relationship management and analytics platform. Our technology, positioning and people are unmatched and these funds will help launch us into the next stage of our development. The appointment comes at a momentous time as Marketware has also closed on a $4.5 million growth round of capital. This round of funding was led by EPIC Ventures with participation from Peak Ventures. EPIC maintains two seats on Marketware’s board of directors, signaling their strong commitment to building a world-class team and company. Press release

Bracket today welcomed Sam Whitaker as Chief Technology Officer (CTO) to its growing team. Whitaker joins Bracket’s leadership team bringing ten years of experience in clinical technology and global infrastructure innovation to the Company. Whitaker will be responsible for Bracket’s global product strategy, management and innovation, technology development and engineering including architecture, user experience (UX), user interface (UI) and IT support functions. Whitaker will leverage his ten years’ experience as co-founder and CEO of Greenphire, the first clinical technology to bring payment technology to the clinical environment. During his tenure at Greenphire, Whitaker invented and successfully commercialized the first clinical trial payment technologies. The web-based applications were built on top of a global technology infrastructure, which he and his team designed to support the unique needs of sponsors, clinical research organizations (CROs), and sites and scaled to support more than 500 clients globally. Press release

Bracket also introduced Amir Kalali as its Executive Advisor for Global Strategy. Kalali joins Bracket as a recognized leader in drug development methodology and technological innovation. Kalali will work with Bracket’s leadership to help identify innovative technologies to support the evolution of its integrated growth. In addition, Kalali will assist in the acceleration of growth in Bracket’s CNS product lines in other fields of medicine. Previously, Kalali was Global Head of the Neuroscience Center of Excellence at Quintiles, where he was responsible for the enterprise-wide strategy for neuroscience, encompassing drug development and healthcare services. Press release

mProve Health and Greenphire announced a partnership to provide patients with real-time access to ClinCard payment details via mProve’s engagement app, mPal. mPal is a robust, regulatory-compliant mobile solution for patients to receive study appointment and medication reminders, access their study visit schedule, documents, research site, and education materials, among other services such as the ability to request a lab courier pickup. Through this exclusive partnership, clinical trial participants who are receiving payments or reimbursements via the most widely accepted and adopted participant payment solution, ClinCard, can have real-time access to their balance and payment history directly through mPal. Adding ClinCard capabilities to the mPal app creates a single, mobile touchpoint for patients to access their study services, eliminating the need to use different systems. The combined solution will improve patients’ clinical trial experience and make it easier for them to fulfill study commitments. Press release

PureTech’s device could rival Saxenda in obesity market

A new non-invasive device from PureTech Health could help millions of overweight or obese people to slim down, allowing them to avoid surgery or prescription treatments.


Analysts believe it could also rival Novo Nordisk, the pharmaceutical company whose products are emerging as the biggest selling anti-obesity drugs.

Gelesis100 is a novel hydrogel that comes in a capsule, and when swallowed it swells up to provide the feeling of a full stomach and thereby reduce calorie intake.

Now trials of the device have shown it can help patients lose weight: 58% of adults achieving 5% or greater weight loss, versus 42% on placebo in its pivotal GLOW study.

Analysts Peel Hunt said in a broker note that this puts Gelesis second only to Novo Nordisk’s developmental GLP-1 drug semaglutide in the number of patients achieving weight loss.

The 58% of patients beat Novo’s already-marketed Saxenda (liraglutide) GLP-1 weight loss drug, where 36% of patients achieved the 5% weight loss target.

It also outperformed Orexigen’s Mysimba/Contrave weight loss drug, where around a quarter of patients in a phase 3 trial achieved the target.

Semaglutide came out top of the analysis, with 63% of patients in a phase 3 trial achieving the 5% weight loss target.

The company also argues the device has a favourable safety profile, as its active ingredients do not enter the bloodstream, thereby giving it a safety profile similar to placebo.

This would give it an edge on Saxenda, which produces nausea, diarrhoea, constipation, vomiting and hypoglycaemia in some patients, and requires a daily injection.

However the trial wasn’t all positive news: the device failed to hit its other co-primary endpoint, a placebo-adjusted weight loss target.

Analysts are suggesting this was caused by a high drop-out rate in the placebo arm, and are instead accentuating the device’s overall performance in weight loss.

The company plans to file Gelesis100 with the FDA in 2018 as a treatment for obesity.

In a separate note, analysts from Jefferies suggested peak sales of around $500 million, noting this is a conservative estimate given that Novo’s Saxenda could eventually produce sales in excess of $1 billion a year.

Visit Us On TwitterVisit Us On Google PlusVisit Us On LinkedinVisit Us On Facebook