Bilal Khan's research explores the morphogenic space of substance use and addiction, viewing individuals and populations as adaptive, goal-finding systems operating within dynamic environments. His work lies at the intersection of mathematics, sociology, public health, and computation.

At the individual level, he develops artificial intelligence techniques that model ecological momentary assessment (EMA) and sensor data collected via mHealth platforms. These techniques are then engaged within new technologies to predict and respond to imminent shifts in craving, stress, and affect, enabling interventions that guide individuals toward stability and well-being by responding to their real-time goals and challenges.

At the population level, he uses network science and simulation to study how social structures and policy environments influence collective trajectories of addiction and recovery. His work conceptualizes addiction as a disruption of intrinsic goal-seeking processes, where competing feedback loops in social, structural, and behavioral domains can either hinder or support recovery. By modeling the interplay of peer influence, social norms, and policy interventions, he investigates how collective intelligence in technologically enhanced networks of various scales can operate to foster resilience and support sustainable recovery.

He is particularly interested in how transitions across the life course create opportunities for goal reorientation and behavioral shifts. This perspective allows him to explore the emergence of adaptive strategies at both individual and societal levels in response to evolving conditions and perspectives.

His integrative approach informs the design of personalized interventions and systemic policies that leverage the dynamic interplay of individual intentions, social networks, and structural environments to realign addiction trajectories toward recovery and well-being.