Improving Clinical Trials

8 Examples where Pharma is Using AI to Enhance Clinical Trials >> Pharma’s greatest use of AI is in drug development, but optimising clinical trials is an important and growing focus, as these recent examples illustrate 🔘 Bristol Myers Squibb extended its partnership with Medidata Solutions to enhance clinical trial management. BMS will adopt Medidata Clinical Data Studio and explore AI, advanced analytics, and data tools to optimize trial efficiency. This builds on their 2016 collaboration supporting cancer and other trials 🔘 Eisai US also partnered with Medidata Solutions on an AI-driven platform to streamline clinical trial management, reduce errors by 80%, and accelerate treatment development for cancer and Alzheimer's. The platform replaces spreadsheets with integrated data sources, aiming to improve patient experience and data accuracy 🔘 Eli Lilly and Company's Digital Health Hub in Singapore leverages AI tools like Magnol.AI to advance drug discovery for Alzheimer’s, autoimmune diseases, and cancer, while supporting Phase 1 clinical trials and real-time monitoring 🔘 AstraZeneca partnered with Immunai to enhance cancer drug trials using its AI platform, which maps the immune system. The collaboration leverages Immunai's machine learning and single-cell biology to improve clinical decision-making and accelerate immunotherapy development 🔘 AstraZeneca's new business Evinova launched, offering AI and health-tech solutions to enhance clinical trials, with support from Accenture and AWS 🔘 AbbVie collaborated with ConcertAI and Caris Life Sciences to enhance precision oncology by utilizing AI for clinical trials and patient enrollment. 🔘 Sanofi partnered with COTA to use real-world data and AI to enhance clinical trials for multiple myeloma, aiming to speed up the development and improve the design of future studies 🔘 Sanofi in collaboration with OpenAI and Formation Bio introduced Muse, an AI tool to streamline patient recruitment for clinical trials by identifying ideal profiles, generating materials, and ensuring regulatory compliance 👇Links to source articles in comments #DigitalHealth #Pharma #AI #ClinicalTrials

Clinical Research Needs a Reality Check, R3 Is Here Wake-Up Call: The new ICH-GCP R3 guidelines just dropped, and if you’re still running trials like it’s 2010, you’re already behind. R3 demands risk-based approaches, decentralized elements, and true patient-centricity. Yet, the industry keeps dragging its feet. Why? Because disruption is uncomfortable. What Needs to Change, Now: 1. Stop Wasting Time on Outdated Monitoring R3 prioritizes risk-based monitoring (RBM). If you’re still obsessed with 100% SDV, you’re part of the problem (minus some early phase oncology- if you know, you know). Solution: CRAs need to evolve into data-driven strategists. Equip yourself with skills in data analytics and centralized monitoring tools to spot trends before they become risks. Learn to read the signals, screen failure rates, dropout patterns, and query spikes tell a story. CRAs who identify these trends early will be the ones leading trials, not just monitoring them. 2. Decentralized Trials Are the Standard, Not a Nice-to-Have Still forcing patients into endless site visits? R3 says adapt or get left behind. Solution: Break into roles shaping the future: - Decentralized Trial Coordinator - Telehealth Study Manager - Remote Monitoring CRA 3. Patient-Centricity: Less Lip Service, More Action R3 is clear: trials must fit patients, not the other way around. Solution: Target roles like: Patient Engagement Lead, Design protocols around real lives. Your Next Move: Master R3: Knowledge of ICH-GCP R3 guidelines = competitive advantage. Target Future-Proof Roles: RBM specialists, DCT experts, and patient-centric strategists are the future of research. Think Like a Trendspotter: The best CRAs don’t just report data, they predict the next move. The Real Question: Are you disrupting the industry, or waiting to be replaced by those who will?

 My Clinical Trial Patient Fired Me for Following Protocol. And honestly? She was right. Let me explain. It was a Phase III oncology trial. The patient—let's call her Maria (not her real name for privacy)—had been with us for 6 months. Smart woman. Former teacher. Asked a lot of questions that made me think. But that Tuesday morning, she was different. ↳ "Rudy, I need to talk to you." ➡️ "Of course, Maria. What's going on?" ↳ "I'm done with this trial." My heart dropped. Not because of the paperwork. Not because of the metrics. But because I knew what was coming. "You keep reading from that binder," she said. "Every visit. Same script. Same questions. Like I'm not even here." She was right. I'd been so focused on following GCP to the letter that I'd forgotten something crucial: Behind every protocol is a person. Behind every data point is a story. Behind every consent form is trust. That moment changed how I approach clinical research forever. Yes, we need protocols. They protect patients. Yes, we need compliance. It ensures data integrity. Yes, we need standardization. It validates results. But here's what they don't teach you in clinical trials training: ✅ Protocols are guidelines, not scripts ✅ Compliance without compassion is just checking boxes ✅ The best CRCs know when to close the binder and open their hearts Maria didn't leave the trial. Because after she called me out, I did something different. I put down the protocol. Held her hands and looked her in the eye. And asked: "What do YOU need from me to feel heard?" We spent the next hour talking. Not about adverse events or dosing schedules. But about her grandkids. Her fears. Her hope that this trial might buy her more time. Then we went through the protocol—together. Me explaining why each step mattered. Her telling me how each step felt. She completed the trial. And taught me more about patient care than any SOP ever could. Here's what I learned: → Following protocol is non-negotiable → But HOW you follow it? That's where the magic happens → The moment you forget the human, you've failed—regardless of your compliance rate To my fellow CRCs and CRAs: Your patients aren't case numbers. They're people trusting you with their lives. Follow the protocol. But never forget to follow your humanity first. Have you ever had a moment where following the rules conflicted with doing what felt right? Drop a comment. Let's talk about it. Because in clinical research, the balance between compliance and compassion isn't just important—it's everything. P.S. Maria's doing well. Still sends me pictures of her grandkids. And yes, I documented everything properly. 😊 #ClinicalResearch #PatientCare #CRC #ClinicalTrials #HealthcareLeadership #PatientExperience #ClinicalResearchCoordinator

Can an # AI #Doctor partner with clinicians? Can we please move past the AI versus doctor/clinician comparisons in taking board exams.. solving diagnostically challenging cases... providing more empathetic on-line responses to patients...? and instead focus on improving patient care and their outcomes? The authors, Hashim Hayat, Adam Oskowitz et. al. at the University of California, San Francisco, of a recent study may be hinting at this: envisioning an agentic model (Doctronic) “used in sequence with a clinician” to expand access while letting doctors focus on high‑touch, high‑complexity care and supporting the notion that AI’s “main utility is augmenting throughput” rather than replacing clinicians (https://lnkd.in/e-y3CnuF)  In their study: ▪️ >100 cooperating LLM agents handled history evaluation, differential diagnosis, and plan development autonomously. ▪️ Performance was assessed with predefined LLM‑judge prompts plus human review. ▪️ Primary diagnosis matched clinicians in 81 % of cases and ≥1 of the top‑4 matched in 95 %—with no fabricated diagnoses or treatments. ▪️AI and clinicians produced clinically compatible care plans in 99.2 % of cases (496 / 500).  ▪️In discordant outputs, expert reviewers judged the AI superior 36 % of the time vs. 9 % for clinicians (remainder equivalent). Some key #healthcare AI concepts to consider: 🟢 Cognitive back‑up, in this study, the model identified overlooked guideline details (seen in the 36 % of discordant cases; the model used guidelines and clinicians missed). 🟢 Clinicians sense nuances that AI cannot perceive (like body‑language, social determinants). 🟢 Workflow relief , Automating history‑taking and structured documentation, which this study demonstrates is feasible, returns precious time to bedside interactions. 🟢 Safety net through complementary error profiles – Humans misdiagnose for different reasons than #LLMs; so using both enables cross‑checks that neither party could execute alone and may have a synergistic effect. Future research would benefit from designing trials that directly quantify team performance (clinician/team alone vs. clinician/team + AI) rather than head‑to‑head contests, aligning study structure with the real clinical objective—better outcomes through collaboration. Ryan McAdams, MD Scott J. Campbell MD, MPH George Ferzli, MD, MBOE, EMBA Brynne Sullivan Ameena Husain, DO Alvaro Moreira Kristyn Beam Spencer Dorn Hansa Bhargava MD Michael Posencheg Bimal Desai MD, MBI, FAAP, FAMIA Jeffrey Glasheen, MD Thoughts? #UsingWhatWeHaveBetter

I’ve worked in clinical research for almost a decade and I’d never heard this acronym until this week.... ICE = Ideas. Concerns. Expectations. Turns out, it’s one of the most powerful tools in patient care, and almost no one’s talking about it in clinical research. ICE is a framework clinicians use to understand what truly matters to patients, not just what’s medically required. And once I learned it, I couldn’t unsee it. In research, we talk a lot about: 🔹 Eligibility 🔹 Timelines 🔹 Compliance But how often do we stop to ask: 🧠 What does the participant think is happening? 😟 What are they worried about? 🎯 What outcome are they hoping for? Participants don’t enroll just for science. They enroll for: → Hope → Access → Understanding If we don’t ask about their ICE… we miss the very reasons they showed up. So next time you’re reviewing a protocol or prepping for a visit, ask: ✅ What hopes are they bringing into this trial? ✅ Are there unspoken fears we haven’t addressed? ✅ Does the process match the expectations we’ve set? Because ethical research doesn’t start with “eligible.” It starts with empathy. 💬 Ever used ICE in your work? How do you keep patient voice at the center? ♻️ Repost if you believe patient perspectives should shape the future of trials. 🔔 Follow Clinical Research Referral Club (CRRC) for more content on the real side of clinical research.

❗️Why Representation Matters in Clinical Trials❗️ Representation in clinical trials isn’t just about diversity—it’s about health equity. When clinical research lacks diversity, treatments may NOT be as effective for all populations, leading to disparities in healthcare outcomes. Black women, in particular, have been historically underrepresented in research, resulting in gaps in understanding how treatments impact us. Two barriers to participation are👇🏽 1️⃣ Medical Mistrust – Due to historical injustices like the Tuskegee Syphilis Study and unethical medical practices, many Black communities remain hesitant to participate in clinical trials. Rebuilding trust through transparency, community engagement, and Black-led research initiatives is essential. 2️⃣ Lack of Awareness & Accessibility – Many Black women are not informed about clinical trials or may not have access to research sites. Trials are often conducted in locations that are difficult to reach, and eligibility criteria may unintentionally exclude diverse participants. 👀So what can we do?👀 GET INFORMED & GET INVOLVED! We must bridge the gap by increasing education, trust, and access to clinical research. If you’re interested in learning more, check out these trusted resources: 🔹Black Women In Clinical Research ®– A network supporting Black women in research careers and increasing clinical trial awareness. www.bwicr.com✨ 🔹 CISCRP (Center for Information & Study on Clinical Research Participation) – Provides education on the clinical trial process.✨ 🔹 ResearchMatch.org – A platform that connects individuals with clinical trials they may qualify for.✨ Knowledge is power! Let’s take charge of our health by staying informed and advocating for inclusive research.✊🏽 ♻️ Share this post and help spread awareness! #RepresentationMatters #ClinicalTrials #HealthEquity #bwicr #clinicalresearch #clinicaltrials #bhm #diversity

A trio of ML / AI papers for improving different stages of the drug discovery chain Over the last few weeks we published three papers that cover several of the major phases of drug discovery. These papers provide a good view into the breadth of problems that a large pharma company is working on in the AI space. Our first paper [https://lnkd.in/di4td788] focuses on basic research and target identification. Sanofi is utilizing several novel technologies including spatial transcriptomic (ST). ST allows researchers to not only view the levels of genes within individual cells but also to determine where these cells are within the tissue and study the relationship between them. This information is critical for studies focused on oncology and immunology. We developed SpatialOne, an end to end platform for processing, visualization and analyzing Visium ST data. SpatialOne uses deep neural networks to integrate expression and image data and to derive insights on the activity at the molecular and cellular levels. While developed mainly for Sanofi’s scientist, the software is open source and available for the entire scientific community. The second paper [https://lnkd.in/dBr8WjfP] focuses on translational medicine, a key step for utilizing information from patients to further explore the efficacy and safety of potential therapeutics. A major challenge in such studies is related to the heterogenous nature of individuals. We developed an ML solution to integrate patient expression information over time and showed how it derives key mechanisms and patient subgroups for a number of different immunological diseases. Finally, for the clinical trial phase we developed methods that enable Sanofi scientists to integrate clinical trial data with Real World Data (RWD) [https://lnkd.in/dD93K9mZ]. Clinical studies collect detailed clinical information on the patients enrolled. However, once a drug is approved, we have much less information on the patients that receive it. Given the large number of patients receiving our treatments we would like to use information on the drug efficacy to determine who benefits the most from the drug and how we can make better. In a this paper we developed ML methods that can be used to integrate the two types of data to improve the ability to utilize RWD for future development. As usual, our work was done in close collaboration between the Digital, Research and Development teams at Sanofi including our Precision Medicine and Real World Data teams. Congratulations to all team members and looking forward to sharing more of the computational ML / AI tools we develop to bring the miracles of science to our patients. Michel Rider Matt Truppo Emanuele de Rinaldis Brandon Rufino Sachin Mathur Albert Pla Planas

🌟 Revolutionizing Clinical Trials with GenAI 🌟 This publication introduces a transformative framework for leveraging generative AI in clinical trials, addressing inefficiencies and biases to improve outcomes. 💡 The Challenge: Over 40% of clinical trials face significant flaws, wasting resources and delaying progress. Common issues include poor blinding, incomplete data, and inadequate diversity in participant selection. 🛠️ Proposed Solution: Develop Application-Specific Language Models (ASLMs) tailored for clinical trial design. These models, fine-tuned for the domain, can enhance protocol accuracy, reduce errors, and suggest best practices. 📋 Three-Phase Framework: 1️⃣ Regulatory Development: Agencies like the FDA create foundational ASLMs. 2️⃣ Customization: Health Technology Assessment bodies refine models for regional contexts. 3️⃣ Deployment: Researchers and trial designers access tools to improve protocols and submissions. 🌍 Key Benefits: ASLMs can address underrepresentation, predict safety issues, and ensure ethical, inclusive trials. They promise faster drug development, lower costs, and greater accuracy in trial outcomes. 🔗 Open Access and Collaboration: Advocates for open-source models to foster transparency, trust, and innovation, while maintaining rigorous oversight and validation. #GenerativeAI #ClinicalTrials #InnovationInMedicine #AIForGood #HealthcareTech #DiversityInTrials #MedicalInnovation #DrugDevelopment #EthicalAI #DigitalHealth

During the pandemic the overwhelming majority of cancer trials submitted to FDA as the basis of an approval included decentralized clinical trial (DCT) elements. "Key DCT elements included remote site monitoring (89%), telemedicine (68%), remote laboratory assessments (63%), and remote distribution of investigational products (58%). Main challenges encountered included institutional policies (83%), technology adoption (61%), and regulatory restrictions (56%)." Authors: Timil Patel, Pamela B., Craig Lipset, Sara Bristol Calvert, Sabrena Mervin-Blake, Vinit Nalawade, Paul Kluetz FDA | Clinical Trials Transformation Initiative (CTTI) | Decentralized Trials & Research Alliance (DTRA) AACR Journals https://lnkd.in/eythS-HU

I've touched on this issue before, but it cannot be spoken about enough: Equitable #ClinicalTrials lead to equitable treatments and solutions. But in a new article from Forbes, Jodi Akin, founder and CEO of Hawthorne Effect, points out that there continues to be "a very large accessibility problem." As Akin explains, everyone, even those who are already well represented in clinical trials, is better served by more accessible trials." But "sadly, so many barriers--economic, demographic, sociographic and more--remain in connecting patients with clinical trials." Not only do these barriers lead to clinical trials that often don't fully represent the patients who will actually use the product, Akin reminds us that "the ultimate costs are early deaths and poor health." The Hawthorne Effect is a healthcare start-up focused on fixing the issues around both clinical trial accessibility and diversity. The company's mission is "to deliver innovative, accessible, inclusive, clinical trials." Hawthorne's approach is to incorporate technology and a distributed network of medical professionals to enable trials to be conducted in the patient's home, avoiding hundreds of miles of travel to physical clinical trial sites. The "Hawthorne Heroes" network of providers also comes from patients' own communities, which leads to increased trust, a key factor in clinical trial participation. It looks like the work Hawthorne Effect is doing is already having an impact! A recent study showed that Akin's team was able to increase enrollment of Asian, Black, and Hispanic patients compared to typical industry averages. This is truly exciting to see and gives me hope that real progress is being made in this important part of healthcare. #FutureOfHealthcare #HealthEquity #Clinicaltrialdiversity