At the intersection of neuroscience, statistics, and artificial intelligence, Rahul Biswas is redefining how we understand and treat neurological disease. As a Postdoctoral Scholar at UCSF’s Department of Neurology and founder of Kaneva Consulting, Biswas combines cutting-edge research with practical applications that bridge the gap between scientific insight and real-world impact. His work focuses on AI-driven neural data analysis and causal inference, aiming to shift healthcare from reactive diagnosis to proactive, personalized intervention. In this conversation, Biswas discusses the founding of Kaneva, the future of AI in brain health, and why clarity, compassion, and curiosity will shape the next decade of innovation.
What inspired you to launch Kaneva Consulting, and how does your academic background shape the way you approach industry problems?
Kaneva Consulting was created out of a desire to make high-quality statistical problem-solving more accessible across disciplines. As data became more central in research and decision-making, I found myself frequently supporting colleagues and collaborators who needed help making sense of complex datasets. That experience naturally evolved into something larger. My academic background in statistics and neuroscience shaped the way I work: focused, methodical, and grounded in clarity over complexity. Kaneva reflects that approach, combining analytical depth with practical relevance to help teams turn data into meaningful, actionable insights.
You work at the intersection of AI, causal inference, and neuroscience—how do you see these disciplines converging to change the way we diagnose and treat neurological diseases?
The convergence of AI, causal inference, and neuroscience is shifting healthcare from reactive treatment to proactive and personalized care. Rather than relying on late-stage symptoms or generalized diagnostic labels, we are now building models that can detect early changes in brain connectivity and predict how a patient might respond to different treatments. AI enables us to process vast and complex neural datasets, neuroscience provides insight into how brain circuits function, and causal inference allows us to go beyond pattern recognition to uncover the underlying drivers of disease. For example, in Alzheimer’s research, we can now analyze fMRI time series data to identify causal disruptions in memory-related networks before clinical symptoms fully emerge. This makes it possible to intervene earlier and tailor treatment strategies based on each individual’s brain dynamics. These advances open the door to more accurate diagnostics, earlier interventions, and more effective therapies grounded in how the brain actually works.
Can you share an example of a real-world challenge that Kaneva Consulting helped solve through customized analytics? What was the impact?
A health technology client approached us with wearable data that was high-dimensional, noisy, and difficult to interpret. Their existing models gave inconsistent results, which impacted user trust. We developed a customized analytics pipeline that addressed signal artifacts, identified stable biomarkers, and allowed the team to segment users based on physiological stress responses. This not only improved the clarity of the platform’s insights but also increased user retention and strengthened partnerships with clinical collaborators who now had greater confidence in the product.
Your work spans both scientific research and business strategy. How do you balance rigor and innovation in projects that demand both?
I see rigor and innovation as mutually reinforcing. Rigor ensures the foundation is solid, while innovation opens the door to new solutions. In every project, I start with a clear problem definition and apply methods that are statistically sound and aligned with the context. From there, I look for creative ways to adapt or extend those methods to deliver new value. Whether I am working on a neural data analysis or a strategic business model, I hold the same standard. Solutions must be both reliable and relevant.
Mentorship seems to be a priority for you—what advice do you give to early-career researchers looking to transition into entrepreneurial or consulting roles?
Recognize that your research training has already equipped you with valuable skills. Your ability to analyze complex problems, work with uncertainty, and communicate insights is highly applicable outside academia. The key is to shift your mindset from academic depth to practical impact. Learn how to present your work in a way that matters to decision-makers. Build relationships beyond your field, volunteer for interdisciplinary projects, and explore consulting opportunities to gain experience. Most importantly, do not wait for perfect readiness. Start small, stay curious, and grow with each opportunity.
In your experience, what are the biggest misconceptions companies have when it comes to applying AI to complex data, like brain imaging or biomedical signals?
One common misconception is that large volumes of data will automatically produce useful results. In practice, biomedical signals are often noisy, variable, and highly structured in time, which makes standard AI approaches less reliable. Another issue is the overuse of black-box models without understanding the system being modeled. Success in these domains requires more than algorithms. It demands careful attention to preprocessing, domain knowledge, and collaboration with subject matter experts. Interpretable and causally meaningful insights are more valuable than flashy but opaque predictions.
How has volunteering with the Brahma Kumaris influenced your perspective on leadership, especially in the high-pressure world of tech and science?
Volunteering with the Brahma Kumaris has shaped my understanding of leadership as an inner discipline rooted in self-respect, clarity, and kindness. In fast-paced environments, it is easy to become reactive. But with reflection and spiritual grounding, I am better able to lead with purpose and calm. I believe leadership is about inspiring rather than directing, being a friend rather than a boss, and helping others feel equal and capable. If I am stronger in a particular area, it is my responsibility to raise others up to that level or beyond. Leadership is not about control, but about service, dignity, and creating space for growth. This mindset helps me stay steady, even in uncertain or high-pressure environments.
Looking ahead, what emerging trends in computational neuroscience or AI do you think will define the next decade of innovation in healthcare?
The most urgent need I see is to turn complex brain data into practical tools that help clinicians detect and treat neurological conditions early, before symptoms become severe or irreversible. Today, diseases like Alzheimer’s are often diagnosed too late, and even when data is available, it does not always lead to clear clinical decisions. Causal AI can address this by helping us understand why certain brain changes are happening and what treatments are likely to help. Personalized brain models that integrate imaging, behavior, and genetics will support more targeted care. Human-centered AI tools, built in collaboration with clinicians, will ensure these insights are accessible and usable in real healthcare settings. These advances are moving us toward a future where people receive the right care at the right time, with greater precision and impact.
