Artificial intelligence & machine learning

Generative AI has exploded into the mainstream. And Aily Labs, a Munich start-up with a Big Pharma veteran at the helm, is riding the wave with a plug-and-play decision intelligence app.

CEO and founder Bianca Anghelina, formerly head of global digital finance at Novartis, founded Aily after realizing how AI’s power could speed number-crunching tasks in her corporate role and free her up to focus on business strategy. With the goal of developing a tool that would work for other pharma companies, Aily became a reality in 2020, and its 200-person team now manages the app designed for large companies like Sanofi to incorporate AI in business functions across the organization. 

The company has been profitable since its first year, and last year saw a 500% increase in customer growth, according to company officials. It recently raised about $21 million in a series A round, its first outside infusion of capital since launch, in a market poised to reach $1.3 trillion globally by 2032. 

“My vision was to create the Apple of AI, and create an AI product which helps simplify work across the organization [and] across the value chain, because I saw the power of AI in connecting data across all functions and bridging the different data silos, which are pretty common in big organizations,” Anghelina said.

A simple formula

In a recent McKinsey survey, one-third of respondents said they already use generative AI for business, and 40% plan to boost their investment further to fuel productivity — a trend that’s revolutionizing how pharma companies work. But incorporating AI comes with hurdles, which Aily hopes to solve with its app, designed to be as friendly for non-techies as Spotify or Instagram. 

“It's basically a one-day integration from the moment we get the data,” Anghelina said. “You get the personalized insights based on your own company and a 360-degree view of the business.” 

The app offers predictions and insights to guide decisions such as gauging whether a phase 3 trial should get the green light, tracking inventory to avoid shortages and finding places to save, cut or optimize staffing. 

While AI brings advantages, it’s also known for its challenges, and Aily has systems in place to overcome them, Anghelina said. 

“We have a very robust AI brain where we validate AI and put it into action,” she said, pointing out that this helps avoid problems such as “hallucinations,” or false information.

Navigating a crowded field

The app format distinguishes the company in an increasingly crowded space, Anghelina said. It’s the first mobile app for decision intelligence in corporate circles, she said.

The app enables big companies to broadly incorporate AI in a way that would typically take them months or years to do on their own, Anghelina said. And they don’t have to keep pace with rapid-fire advances in the field — the app does it for them, Anghelina said.

Its most promising potential may be its predictive abilities, a capability Anghelina said they hope to continue enhancing. The technology may also leap into the virtual reality world, paired with Apple Vision Pro, ushering in a new era in which decision-makers collaborate in a multi-dimensional space, she said. The company is also making moves to expand beyond the life sciences ecosystem, she said. 

“It is really exciting to create a company, but also to create the next big revolution in terms of a technological transformation in how we work,” Anghelina said.

When you’re looking to make changes to biopharma clinical trials, one of the top minds in the industry could help you get there — by welcoming Robert Langer to its advisory board, that’s exactly what Lindus Health aims to do.

Langer, an MIT professor and co-founder of Moderna (in addition to a long list of successful biotechs), is the author of more than 1,500 scientific articles, holds more than 1,400 patents issued and pending, and is widely considered the most cited engineer in history.

Bringing Langer to the advisory board of a contract research organization like Lindus, which calls itself “the anti-CRO,” sets the company up to address some of the most pressing concerns in clinical research. Langer’s mind for biotech business also contributes to the ways he can help the company innovate to mitigate some of the risks associated with the CRO model.

Since the COVID-19 pandemic, traditional clinical trials have shifted to a more flexible approach, according to industry research from WCG. With clinical trial starts expected to rise in 2024 compared to the year before and new technologies emerging at a rapid clip, CROs are exploring ways to stay ahead of the curve.

A change is gonna come

Overall, Langer sees where CROs often fall short and where Lindus could make an impact in the industry.

“I think CROs haven’t changed much [in the last decade],” Langer said in an email interview. “There are some recent attempts to incorporate AI and virtual clinical trial techniques to increase efficiencies and expand reach of studies [but] in general CRO processes have remained unchanged.”

With massive success in the science and business of biopharma, Langer is notoriously modest and focused on the work. At Lindus, that work centers around removing bottlenecks in the clinical trial process with an end-to-end business model.

Langer isn’t the only big name with a hand in Lindus’ path forward — the company has raised more than $24 million from Peter Thiel and other tech and biopharma investors.

And one of the changes Lindus is trying to bring to the CRO table is a new financial model that positions drugmakers to share the risk of the clinical process.

“The incentives of CROs are currently totally misaligned with sponsors and with patients — CROs typically earn more money from projects that are delayed, due to their billable hour business model,” said Meri Beckwith, co-founder of Lindus, in an email.

Founded in 2021, Lindus gained insight from Langer on what would become the company’s driving business model. Beckwith said Langer was critical in shaping a model based on hitting clinical milestones so the CRO and the drugmaker are both locked in on the same goal. Milestones are also a way to share the risk since the contractor and the client are both in the same boat, Beckwith said.

“Sponsors are understandably risk-averse,” Beckwith said. “No one gets fired for hiring [CRO giant] IQVIA.”

Under one roof

Beyond a milestone-based financial model, Langer also sees the end-to-end nature of the clinical trial model as something that sets Lindus apart.

“By building their own robust tech platform and internal site capabilities, they have been able to streamline clinical trial execution,” Langer said.

For example, software that allows for quicker study configuration can help get a trial started. And since recruitment is often a narrow bottleneck for most studies, with most not recruiting on time, according to Langer, expanding the reach through virtual assistance and access to electronic medical records can grow the patient pool faster.

Lindus has also developed software that uses machine learning to write study protocols and capture data with AI monitors from beginning to end.

Langer’s role will be that of a biotech industry guru who can speak to many different facets and disease areas where Lindus is looking to innovate.

“[Langer]’s involvement will help us better design clinical trials, drawing on his wealth of experience from having been involved with dozens of pioneering life science companies,” Beckwith said, noting that Lindus is identifying market segments that work best with its model. “He has consistently been at the forefront of new modalities like gene therapy, tissue engineering and transdermal drug delivery.”

Diseases areas like diabetes where pharma companies have had a particularly difficult time developing novel drugs is where Langer could bring his expertise to find new solutions.

“I take a lot of what I’ve learned in the biotech and drug delivery space about the needs of these companies when looking to establish clinical evidence,” Langer said. “There are a lot of common threads with the types of issues that come up during clinical development that I am able to share.”

Sponsored content

By Domino

Several challenges prevent AI development in health and life sciences today, for example, minimal expertise, lack of data organization, unformulated strategies, and unstreamlined management. 

Pharma could “gain 39% incremental value from AI investments compared to other analytics techniques such as statistics and visualization.” Translating into “a 45-75% increase in EBITDA with double-digit gains in research, clinical trials, and commercial areas.”¹

From federated learning to train new models, to AI and ML-enhanced searches for new medicines and treatments, to making the business of health and life sciences more efficient, data science leaders are finding new ways to apply AI, machine learning, and other aspects of data science. Some cutting-edge companies, such as Evidation, are even basing their business models on using data from wearables and other mobile devices to improve users’ health.

In order to successfully transition to AI innovation, here are four main challenges your data science teams should be aware of. These challenges have been overcome by data scientist leaders at major life sciences companies with a collaborative AI and data analytics platform.

1. Heterogenous tools and data environments delay progress

Data scientists and researchers cannot easily access or incorporate new languages, tools and methods, and cloud and compute resources to move faster. Data scientists are more efficient when using preferred versus mandated tools. However, modern and legacy tools often live in separate systems, hindering access and collaboration with these tools. 

In addition, data and tool sprawl throttle access, scale, and collaboration. Siloed systems prevent standardization of best practices or reuse of machine learning models, workflows, and experiments, so work must be executed from scratch every time. Furthermore, replicated data in multiple systems is a workaround to make it accessible. However, this approach is costly and creates compliance risks with data sprawl.

2. Lost productivity and maximized redundancies due to limited collaboration between tech vs. non-tech users

Teams, tools, and data are in silos with non-standardized workflows within disconnected environments. Knowledge is difficult to share, and models are challenging to reuse and repurpose. Standardization and implementation of best practices are also challenging when multiple disparate systems are in usage.

3. Risks increase because of undiscoverable models, untraceable data, and unreproducible experiments

Reproducing experiments or model results is manual, is lost with system upgrades, often fails to reproduce models, and risks non-compliance, jeopardizing new drug approvals. Viewing, governing, reusing the best models, and detecting model degradation or bias is complex and risky in a decentralized environment. The possibility of releasing a model that does not perform as expected or involves biases is higher. In addition, audits require manual documentation, and experiments are not reproducible. Moving data to accommodate infrastructure impacts privacy and creates compliance risks.

4. Spend management and control of AI infrastructure costs

It can become time-consuming to optimize and manage costs across infrastructures – and it’s important to leverage AI in more places more often. For instance, a Kubernetes-based platform lets you host AI workloads anywhere – on-premises, cloud, hybrid, or multi-cloud – making it easier to optimize and manage costs across your infrastructures. Specifically, with a collaborative AI and data analytics platform – that includes granular visibility, reporting, and intelligent SaaS cost management features – budget owners can stop overspending before it starts.

Key takeaways

• AI/ML makes the business of health and life sciences more efficient.
• Data science leaders are finding new ways to apply AI, machine learning, and other aspects of data science. But, there are a few main AI challenges to be aware of. 
• Be on the lookout for heterogeneous tools and data environments that delay progress.
• A common pitfall is when teams, tools, and data are in silos with non-standardized workflows within disconnected environments.
• Unreproducible experiments and untraceable data result in greater risks.
• Budget owners must consider better management and control of AI infrastructure costs.
• A collaborative AI and data analytics platform can help to solve these challenges.

Explore these insightful AI and life sciences resources to learn more

• Optimizing your architecture for AI innovation
• Why a successful digital transformation demands a flexible SCE
• The data science innovator’s playbook (health and life sciences edition)
• 4 key strategies for modernizing drug discovery and pharma with AI
• Disrupting drug discovery and development with AI

References

¹ Henstock P. Artificial Intelligence in Pharma: Positive Trends but More Investment Needed to Drive a Transformation. Arch Pharmacol Ther. 2020

The FDA is due for “revolutionary” changes with how it regulates and leverages AI, according to the agency's commissioner, Dr. Robert Califf. Yet, as it looks to address its desire to do more with the technology, the agency is also grappling with a planned reorganization, a budget crisis and persistent challenges like drug shortages.

As the FDA weathers these storms with the aim to come out stronger, modernized and more reactive, its role with AI in pharma is still being defined. And because there’s growing proof AI modeling could alleviate drug shortages, it could also be a valuable tool for the FDA itself.

The pharma industry has been awaiting guidance on how the FDA will regulate AI even as it ramps up investment in AI tools for R&D. The federal agency is currently working on developing standards for the complex AI use cases in pharma that will provide guidance on the regulatory framework. Recent comments from Califf hint at how the regulatory role may shake out — and how the agency could leverage AI to advance its own capabilities.

Drawing the regulatory line

Pharma companies are already leveraging AI in drug discovery, and machine learning algorithms are currently being used to assess observational study and clinical trial data. Leveraging the technologies could bring safe and effective drugs to patients faster, improve health equity through broader access, enhance drug safety, increase manufacturing quality and more, the FDA said in its 2023 discussion paper about AI and drug manufacturing.

The agency is taking a risk-based approach to AI in drug development, hearing from stakeholders, and evaluating and managing the use of AI in the interest of public health, which has left pharma on hold for guidance, Califf explained during a webinar hosted by the Alliance for a Stronger FDA. 

“The development of the standards, like a lot of what the FDA does, should be a community activity, which gets a lot of input from all sectors, including patients,” he said. “But then the final writing it down and putting it in a rule or guidance is something the FDA should do. Then enacting it and keeping track of it would probably go back into consortia of some kind, because it is just too big and widespread for the FDA to do it all on its own.”

But as the FDA considers how it will regulate AI, there’s already a clear separation of roles, according to Califf. 

“I think a naive person may say, well, the FDA should be in there helping to regulate how people use AI to figure out what a target choice is — that is not our job,” Califf said. “Our job is to deal with what people bring forward to try to bring into development.”

FDA’s use of AI

Since returning at the helm of the FDA in 2022, Califf has been eager to fix the drug shortage crisis and the efforts could benefit from AI.

“[If] you think about the supply chain issues we are dealing with, there is so much progress that could be made with digital supply chains available to model what is going to happen,” Califf said. “I see this as transformative for the internal operations of the FDA.”

For the FDA to move forward with the technology in a meaningful way, investments are needed — and making upgrades can be a hard sell for an agency currently under budget pressures.

The FDA has asked for a 10% boost, totaling $7.2 billion, as part of the president’s fiscal year 2024 budget. So far, Congress hasn’t agreed on a long-term budget, and kicked the can down further down the road after passing a short-term spending bill in January to keep the government funded through March. The FDA is currently funded thanks to the stopgate measures that kept spending levels the same. 

For the agency charged with protecting public health, new upgrades to leverage the full potential of AI is a hard sell in the current budget climate.

“It is very hard to get Congress to give capital to make the changes that I think would be revolutionary,” Califf said. “So that is something for us to work on, is how to make that case. But it is not just AI; it is quantum computing now on the horizon.”

It’s not just the FDA’s potential use of AI being affected by budgeting — its regulatory role and oversight of the technology is also part of the equation.

The FDA already separates its role in regulating AI when it comes to medical devices, but predictive AI, which continues to accrue data and change over time, is more complex, Califf explained. And even without the agency’s ongoing budget woes, staffing for this heightened oversight isn’t likely to happen.

“There is a line of where FDA regulates or not,” Califf said. “That has been defined by Congress. FDA does not regulate the administrative functions, but when it involves patient safety, or there is significant risk, FDA is involved. But we would have to hire three or four times as many people to take on what is coming on.”

Despite significant pharma investments and lots of hype, using AI for drug discovery has shown mixed results so far. However, there’s one area where AI is already seeing success: Predicting the safety and efficacy of drugs, which has the potential to help patients find the right medication faster.

On the drug development side, using AI to test safety and efficacy promises to accelerate precision medicine and reduce animal testing. A handful of startups are working in this arena, including BioPhy, which uses predictive AI to zero in on endpoint outcomes in clinical drugs with more than 80% accuracy according to reports. And Quris-AI said its patient-on-a-chip platform accurately predicted which treatment caused drug-induced liver injury in a preclinical pilot study it conducted in partnership with Merck KGaA.

AI is also being used to predict safety and efficacy for drugs already on the market. In a recent example of this approach, researchers at the Amsterdam University Medical Center, used AI to help predict within a week whether Zoloft would work in patients with major depressive disorder.

That’s much faster than the six to eight weeks it usually takes to find out whether an antidepressant will be effective, the researchers said.

The study, published in the American Journal of Psychiatry, used an AI algorithm combined with a brain scan and clinical information to predict the effectiveness of Zoloft, one of the most commonly prescribed antidepressants, and found that a third of patients would respond to the drug. Using this method could help “prevent two-thirds of the number of 'erroneous' prescriptions of [Zoloft],” one of the researchers said in a press release.

Here are a few other ways researchers are tapping into the predictive powers of AI.

Chemotherapy resistance

Scientists at the University of California San Diego School of Medicine used a machine learning algorithm to predict when cancer will resist or respond to chemotherapy.

They tested the model on cervical cancer tumors and successfully forecast responses to cisplatin, one of the most common chemotherapy drugs. The model could identify which tumors were most at risk for treatment resistance and why. It also accurately identified tumors that responded to therapy.

They published their findings in the journal Cancer Discovery.

Response to immunotherapies

Researchers at GE HealthCare, Vanderbilt University Medical Center and the University Medicine Essen in Germany used GE HealthCare’s AI models to predict patient response to immunotherapies with 70% to 80% accuracy.

The AI models predicted both efficacy outcomes and the likelihood of an individual patient developing an adverse reaction. According to the researchers, this could enable precision medicine by helping prescribers choose the most appropriate treatment pathway sooner while helping patients avoid unnecessary side effects and cost.

GE HealthCare said it plans to commercialize the models for both drug development and clinical decision support.

Antibiotic resistance

A team at Oxford used AI combined with fluorescence microscopy to detect antimicrobial resistance within as little as 30 minutes. The models detected resistance reliably at least 10 times faster than the current “gold standard” clinical methods, which can often take several days.

The researchers said eventually, their model could identify whether cells in clinical samples are resistant to a range of antibiotics, and help create targeted antibiotic treatments.

Along with artificial intelligence has come plenty of hope and hype for its ability to sort through troves of molecules and data at super speed, shortening a clinical timeline to months as opposed to years. But can AI improve the dismal success rate of traditional drug identification methods?

Early AI wins have been promising — Insilico Medicine recently announced that an AI-identified anti-fibrotic small molecule inhibitor reached phase 2. But for every victory, there have also been flops. 

Exscientia deprioritized its cancer drug EXS-21546 after early-stage trials. BenevolentAI shelved its drug candidate for atopic dermatitis after seeing mixed results in a phase 2 trial. And Sumitomo Pharma saw its AI-identified treatment for schizophrenia, ulotaront, fall short of its primary endpoints in phase 3.

With these signposts along the way, it’s not yet clear if AI can improve upon traditional drug success rates, said Rahul Das, VP of AI and Life Science Solutions at Norstella. Between 2000 and 2015, only 14% of traditional drug candidates have ultimately hit their mark.

“We definitely know you can get a compound much faster using AI,” Das said, noting that, in some instances, the technology has shaved years off the process. “But then how they will perform in actual human clinical trials remains to be seen. Probably in two to three years, we will start seeing some of the results.”

While the future of AI-identified compounds remains murky, the technology is making a difference in other areas of drug development, Das said. 

“In clinical development we are already seeing the actual effect of AI, facilitating patient identification, faster recruitment, removing operational bottlenecks,” he said.” 

Drug companies use AI not only to flag promising compounds, but to identify and recruit patients who meet inclusion criteria for clinical trials, find high-performing sites to run trials and automate trial data. AI is also improving data collection and interpretation. 

“So now you can actually use that real-world data to identify which patients are responding and which patients are not responding to existing drugs,” Das said. Combined with biomarker data, this may make it easier to find the right drug for the right patient.

AI could also overcome one of the primary reasons people decline to participate in trials — the fear of receiving the placebo, Das said. 

“There is a concept called an external control arm, which is using real-world data to actually build a predictive model,” he said, noting that it allows investigators to treat all patients with the study drug while using computer models to predict how the control group would fare. 

As the industry awaits greater clarity as to whether AI-identified compounds are more successful, AI technology will continue to improve. 

“I believe we will continue to see a lot of benefits coming out of AI,” Das said. Even so, the industry should modulate its expectations. 

“Just because something has been designed by AI doesn't mean it's going to take away all the uncertainties,” Das said. “I don't think these failures are going to be just failures — they are actually going to feed future success.”

In the earliest days of the COVID-19 pandemic, doctors in China tried a barrage of drugs to quell the raging virus. In one Shenzhen hospital, treatments included combinations of up to eight antiviral, anti-inflammatory or immune-modulating drugs. But with no way of knowing how well different combinations would work, it was a trial-and-error approach.

Now, years later, a team of scientists at the University of California (UC) Riverside have followed up on these early medical practices and used machine learning to analyze how the various drug combinations performed — while also predicting which ones could keep further COVID-19 infections at bay.

In the study, which was published in Frontiers earlier this year, the researchers found that the efficacy of the different combinations often came down to factors such as a patient’s age or underlying risk factors.

And although these results were drawn from COVID-19 patients in China, they could have wider implications for healthcare, said Jiayu Liao, associate professor of bioengineering at UC Riverside and one of the study’s authors. In particular, the study demonstrated how machine learning — which excels at digesting reams of complex data — could improve and personalize treatments for conditions ranging from cancer to diabetes.

Testing treatments on the fly

When data for the study was first collected in April 2020, much of the research around COVID-19 focused on death rates. But doctors in Shenzhen recognized that more needed to be understood about why the virus recurred in some patients and not others.

With that goal in mind, the Chinese physicians gathered information on 417 hospitalized patients who were later sent to quarantine in government-run hotels after discharge and who all tested negative for COVID-19 twice before leaving the hospital. Within 28 days of leaving the hospital, 23% tested positive for COVID-19 again.

Because of the novelty of this situation in China, which required patients to quarantine following discharge, Liao said researchers at UC Riverside saw a novel opportunity to collect real-world data that showed disease recurrences rather than reinfections.

For the study, researchers used machine learning technology to turn the jumble of treatment information into an informative guide as to what COVID-19 treatments worked best. They didn’t discover a magic bullet. Some treatment combinations worked well in some subgroups of patients, but not in others, indicating the right approach varies by person.

“Many of the discoveries made biological or medical sense,” Liao said.

For example, older people did better with a combination of drugs that boosted their immune systems, because immune response becomes less robust as we age. The same was true for those with a body mass index in the obese range. In younger people, the most effective drugs did the opposite, tamping down an overzealous immune attack on the virus.

Other applications

While the COVID-19 landscape has changed substantially since 2020, Liao said there is still a need for better COVID-19 treatments and machine learning systems can dive into large bodies of treatment data to ferret out which drugs might be best for the job.

Another one of the study authors said the research team “pioneered” the technique to “generalize efficacy” for different subgroups of patients. And according to Liao, their methodology was “fairly general” and readily applicable to other studies either on COVID-19 or other diseases.

In fact, a separate review found that machine learning might help personalize treatments for chronic inflammatory diseases, such as autoimmune rheumatic diseases and other conditions caused by an immune system malfunction because the diseases are distinct, and affect various organs and systems.

The approach could also be particularly eye-opening in the U.S. where many diseases are treated using a single drug or therapy, but some conditions could benefit from a combination approach discovered by machine learning technology, Liao said.

Overall, the results are in line with the growing recognition that patients respond to medications differently and the general push toward increasing the use of pharmacogenomics testing. The search is also on for better biomarkers to help guide treatment decisions and machine learning could serve as yet another useful tool to bring personalized treatments to bear.

“In terms of the technology, it’s not that complicated,” said Liao. But how quickly machine learning technology is adopted will depend on whether people recognize its promise for this application.

Fears of AI replacing jobs hover over many industries as the technology matures. When ChatGPT hit the mainstream, concerns for professional obsolescence quickly escalated.

In pharma, AI has the potential to transform the way the industry engages with patient data and uses that information to provide thorough, personalized care. But many experts agree that the human component must remain the beating heart of AI-enabled models, using technology as a tool rather than a centerpiece.

For Miruna Sasu, CEO of COTA, which curates real-world data to improve cancer care, a healthy balance between trusting AI with complicated decisions related to research, diagnosis and treatment, and allowing for human oversight as the technology improves is critical.

“It’s checks and balances — what everybody wants me to say is that we’ll be human-free in two or three years, but what’s really going to happen is AI is going to help a curator identify where they need to look,” Sasu said. “It’s OK that Google gives me the wrong shopping advice, but one wrong move in this space and it could be someone’s life.”

The temptation to cut corners in the data curation industry is there, Sasu said, particularly around cost. Taking the human checks and balances out of the equation would lead to lower overhead but could also result in poorer outcomes.

“There is a lot of cost pressure, and because there are people actually reading these things, they’re not cheap,” Sasu said. “We’re all trying to do the right thing here, but there’s real pressure and it’s very sad when I see it happen — in this particular space, curation needs to be medically guided.”

But that doesn’t decrease the importance of AI in the future of oncology care, and COTA today announced the launch of a generative AI program called Vista that uses large-scale automated electronic health records to understand how cancer manifests in patients outside the clinic and how treatments can be improved to have a greater impact on patients’ lives.

The most important function of datasets like Vista is that the output is reliable, and COTA’s reputation as a curator hinges on that trustworthiness, Sasu said. Although the company is working with large language models from Google to train a model as a general physician — and potentially oncology specialists down the line — human context is still an important component.

For now, “the use and adoption of AI in clinical practice remains limited,” according to a study from the Royal College of Physicians. The researchers pointed out that many attempts at applying AI are aimed at forcing square pegs into round holes.

“We hold the view that AI amplifies and augments, rather than replaces, human intelligence,” the researchers said. “Hence, when building AI systems in healthcare, it is key to not replace the important elements of the human interaction in medicine but to focus it and improve the efficiency and effectiveness of that interaction.”

Sasu agreed that an AI model is only as useful as the context that surrounds it.

“Humans are never going to be able to be taken out of the context here because they’re the ones who provide the logic on top of the summary,” Sasu said. “The end goal here is to have an assistant that can help scour terabytes of data in just a few moments and answer questions that educated and trained people within each space can make sense of.”

Not J.A.R.V.I.S.

Fans of Marvel Studios’ Avengers saga might have a preconception of AI as Tony Stark’s snarky, ultra-intelligent computer system J.A.R.V.I.S., but Sasu said a fully autonomous system is unrealistic and impractical in the healthcare setting.

“I am not talking about J.A.R.V.I.S. here — this is an assist, and what we’re developing is an evidence-driven dataset that can be used to answer specific questions in therapeutic areas where there is enough data to do so,” Sasu said.

Even the most advanced AI program is worthless without data, she said.

“The first thing you need to do is build the data,” said Sasu, who worked with real-world evidence at pharma giants like J&J and Bristol Myers Squibb before leading COTA. “At BMS, we discovered several years ago that the problem isn’t necessarily the technology, but rather the data underlying the technology, and a lot of pharma companies struggle with this — you can have the best model in the world, and it’ll sit there useless without the data.”

And that’s where the human component comes in during AI’s data training stages. When the model makes a “choice” in diagnosis or treatment, for instance, based on a doctor’s written notes about a patient, that choice needs to be watched very carefully, Sasu said.

“COTA doesn’t develop general intelligence — we develop medical assistants,” Sasu said. “This is very fit for purpose, and when determining what’s happening to a patient, that’s a question that needs to be answered correctly.”

From data to care

Like many aspects of healthcare, technological advances are of little use if they don’t serve a practical purpose in patient care. Now, AI is beginning to play an important role in bringing the information gleaned from large datasets into patients’ lives, said Dr. Bobby Green, chief medical officer and co-founder of Thyme Care, a private company focused on helping patients navigate the cancer care landscape.

“I am a lot more optimistic and excited about AI today than I was a year ago,” Green said. “Prioritizing patients is No. 1, specifically around thinking about protocols and interventions — there is going to be a place for that.”

Green, who has a background in data research at the curation company Flatiron Health, said it’s about building “playbooks” for physicians and other caregivers to follow when applying that knowledge to a particular patient.

For example, if a patient has been prescribed a steroid for multiple myeloma, but that patient also has diabetes, the data from thousands of patients would tell the doctor how they should be monitoring blood sugar as a result of that treatment. But then there are the secondary parts of a patient’s life, like transportation difficulties, food insecurity, language comprehension or other factors that could affect how a physician needs to guide treatment. AI can distill that information for caregivers to follow, Green said.

“There are huge opportunities to summarize lots of information and lots of data and present that in a quick and easy way for nurses and the team [of care providers] to understand it,” Green said. “At a high level, it's always good to empower our care team, but at the same time, it's not going to replace them.”

Despite the promise of AI to help healthcare professionals and pharma companies get better at determining what’s right for the patients, there will always need to be a human component, Green said.

“AI is a part of that as a way to make people more efficient and better at what they do,” Green said. “But underlying that is the nuance around people.”