In the healthcare industry, data science, AI and ML enable us to deliver breakthrough innovations and help improve outcomes for patients faster and more efficiently than ever before. At J&J, we foster trust in AI by applying this technology ethically, prioritizing data privacy, security, fairness, transparency and responsible use. We believe that AI will play a central role in understanding and treating diseases, discovering and developing therapies, equipping healthcare providers with insights, and personalizing care for patients around the globe. Policies & Positions: Doing the right thing: AI & ethics
What excites me most when I consider the future of healthcare are the incredible possibilities to reimagine the ways we innovate and deliver care through technology. We must lead the way in advancing an AI-powered healthcare ecosystem, bringing together great science, technology, and people to transform health outcomes.”
Accelerating clinical trial enrollment through AI
AI is playing an increasingly important role in how we plan, execute and diversify our clinical trials. We have developed a platform that enables us to apply AI to large, de-identified real-world datasets to identify where patients who meet the criteria for our clinical trials are located geographically to help inform our clinical site footprint. The top 50% of sites ranked by our new model enrolled up to three times more patients than lower-ranked sites. We are currently leveraging this platform across approximately 50 clinical trials, with more expected in 2024 and beyond. An additional benefit of this platform is that it also helps us identify new locations where there is a high probability of enrolling diverse patients into our clinical trials. For example, at the end of 2023, enrollment of Black patients in five J&J multiple myeloma trials was more than twice the historical industry average where clinical and operational excellence was augmented by data science approaches (see also section: Research for healthier outcomes).
Using AI for precision disease assessment
We are deploying AI to identify ways of measuring disease onset and severity with an improved degree of precision. This helps us design trials, identify the right patients and measure the impact of our medicines more objectively. Examples include:
- Inflammatory bowel disease (IBD): The severity of disease in IBD is typically scored based on the worst “flare” in a patient’s colon, which underestimates variation between patients and improvements in overall mucosal health following treatment. To better measure and report the severity of ulcerative colitis (UC), we have developed AI-based computer vision models to quantify disease severity more objectively.
- Alzheimer’s disease: We are exploring the power of app-based technology to detect subtle changes in speech patterns, cognition and executive functioning to help identify individuals at the earliest stages of AD and more accurately track disease progression. As we prepare for an upcoming clinical trial slated for 2024, these approaches could enhance our ability to identify suitable participants and monitor the efficacy of potential treatments.
- Oncology: With external collaborators, we are developing algorithms to better quantify tumor burden across several types of cancer and measure the effects of treatment more accurately and rapidly. We are also developing AI-based models from ultra-high-resolution digital pathology slides to evaluate the tumor microenvironment automatically and quantitatively and better inform care decisions in the clinic.
Deploying next-generation digital tools
Landmark cross industry collaborations, led by UK Biobank and supported by J&J, are providing researchers with access to an unprecedented volume and depth of data to better understand the roles that genes and proteins play in disease. Two significant milestones in 2023 included a new dataset from the UK Biobank Pharma Proteomics Project (UKB-PPP) and the release of the final tranche of Whole Genome Sequencing of all half a million UK Biobank participants. These collaborations have helped unearth new possibilities for scientific research that could transform our understanding of complex diseases and how to treat them. Additionally, UK Biobank, with philanthropic contributions from J&J and other pharmaceutical companies, has launched a new fund to cover application fees for institute-affiliated researchers based in LMICs interested in accessing UK Biobank’s biomedical database to advance scientific discovery.
Helping medicines reach the right patients
Engagement.ai is a strategic, AI-driven analytics platform developed by J&J Innovative Medicine that uses extensive real-world healthcare data and interactions with customers to help advance the availability of our medicines and benefit more patients worldwide. Throughout 2023, the platform continued to expand to new countries and brands, with 6,500 field personnel using Engagement.ai to drive 7.5 million interactions with 300,000 HCPs across 14 major markets. These tailored insights are helping to inform HCPs as they consider treatment strategies for their patients, often much earlier in the patient treatment journey.
AI for anatomical renderings of the heart
Intracardiac echocardiography is a useful but operator-dependent tool for left atrial anatomical rendering during AFib ablation procedures. The CARTOSOUND FAM Module utilizes an AI-based imaging algorithm to overcome manual limitations by auto-generating the anatomy of the left atrium. This Module, part of the CARTO 3 System, can decrease the need for manual contouring, and can help electrophysiologists deliver more effective and efficient procedures and generate case data that may help further improve patient outcomes. Integrating the technology offers potential to streamline ablations used to treat AFib.
Driving precision surgery
Even the smallest individual differences in patient anatomy can change the ideal approach for surgery. In the case of total knee replacement, complementing expert surgeon technique with additional guidance and insights can help improve implant placements. J&J MedTech’s VELYS Enabling Technology Platform reveals real-time insights to empower patient-specific decisions with the goal to improve outcomes and deliver personalization at scale. For the VELYS Robotic-Assisted Solution for Total Knee Arthroplasty, the CT-free technology enables precise ATTUNE knee implant placement for each patient, equipping surgeons with the data needed to preserve the soft tissue envelope, predict joint stability and work toward returning knee function. With the CE mark obtained in 2023 and approval for use in 18 markets globally, more than 43,000 total knee replacement procedures have been performed using the system.
Guiding robotics to help diagnose lung cancer
Globally, there are more than 1.8 million lung cancer deaths per year, largely driven by late diagnosis.27 Early biopsy and diagnosis contribute to a higher lung cancer survival rate, but a majority of early-stage lung cancer lesions are difficult to access because they are deep in the lung. J&J MedTech’s MONARCH Platform for robotic-assisted bronchoscopy enables physicians to examine areas of the lung that are more difficult to access with conventional bronchoscopes, which can help support earlier lung cancer diagnosis. The flexible robotics system uses preoperative CT scans of the lungs to inform the procedure, but tracking objects in such a dynamic environment in real time can be complex. The Monarch R&D team uses AI and ML algorithms to develop and refine the Monarch Platform’s navigation, which helps physicians guide the bronchoscope during lung biopsy procedures and allows them to locate and biopsy a potential tumor more accurately.
Harnessing the power of AI in orthopaedics
We are empowering physicians with simplified surgical experiences though our VIRTUGUIDE AI Patient Matched Platform, which entered limited release in 2023 and automates patient analysis and correction to treat bone deformities of the foot and ankle. VIRTUGUIDE AI-powered software reduces the surgeon planning period from multiple weeks to a matter of days, enabling simpler procedures and fewer instruments.
27 WHO, https://www.who.int/news-room/fact-sheets/detail/lung-cancer, https://www.lung.org/research/state-of-lungcancer/key-findings.
