UMass Disease Modeling Lab

Disease Modeling Lab, PI: Chaitra Gopalappa

RECENT/ONGOING PROJECTS (corresponding publications HERE )

Quantifying nutrition health disparities and contributing factors

About half of cardiometabolic deaths in 2017 in the U.S., from cardiovascular diseases (CVD) and type-2 diabetes were associated with diet. Diet was also associated with other chronic conditions including hypertension, stroke, obesity, and some cancers. Extensive research motivates the need to move beyond individual and household factors influencing diet. Intersecting systemic and structural factors create disparities in nutrition availability (e.g., food deserts are places with insufficient nutritious food supply), affordability (e.g., variations in healthy food pricing relative to unhealthy food pricing), and access (e.g., transportation constraints to grocery store access) 7–11. Further, the intersection of social and structural factors, such as racism, discrimination, psychological stressors, influence individual dietary preferences and behaviors 3,5,12,13. To address these complex interactions, NIH recently proposed a Nutrition Health Disparities Research Framework, that outline factors into domains of influence: behavioral, physical/build environment, socio/cultural environment, and health care system; and levels of influence: individual, interpersonal, community, and societal. Our long-term research objective is to quantify the contribution of each factor to nutrition disparity. Factors include individual-level factors, e.g., socio-economic status, coping ability/stress, and physical activities, inter-personal factors, e.g., family dietary practices and culturally appropriate food, community-level factors, e.g., transportation access and food pricing disparities across census tracts, and system-level factors, e.g., differences in nutrition programs across cities and states4. The challenge is that there is no single dataset with all features. As factors vary by population, it will be critical to develop a method to quantify contributions by population, say census-tract, to design effective population-specific multi-level interventions. TEAM; TEAM

PLANNING: Center for multi-sectoral decision analytics for optimizing health outcomes

The center’s goal is to advance fundamental analytics and translational research to develop models for coordinated analyses of multi-sectoral decisions for a person-centered approach to optimizing health. Decision analytic models play a key role in informing decisions at both public agency and community care-provider levels. The typical silos approach to single-disease decision analyses leads to suboptimal decisions, as they overlook correlations between diseases, their common social determinants, and the mechanisms leading to co-occurrence of multiple diseases. The envisioned transformative shift to multi-sectoral decision analyses is a complex challenge that cannot be achieved through fragmented independent research projects.

The planning phase will focus on developing a systematic approach for development, coordination, and integration of activities along the pipeline of data to decisions, through convergent fundamental and translational research, workforce development, and innovation. This work is a collaborative effort between multidisciplinary researchers and partners from academic and non-academic institutes.

FUNDING: 2024 Large-Scale Integrative Research Award (LIRA), UMASS Amherst
MEDIA: Uncovering Pathways to Health Disparities

Network generation methods for large-scale simulation models

Agent-based network models(ABNM) are suitable for simulating individual-level dynamics of infectious diseases. However, as ABNM simulates a scaled-version of the full population, consisting of all infected and susceptible persons, they are computationally infeasible for studying certain questions in low prevalence, such as during new or re-emerging disease outbreaks, or slower spreading diseases such as HIV, Hepatistis C, or Tuberculosis. For e.g., simulating 100,000 nodes to represent the U.S. population would generate only 400 people with HIV. We developed an Evolving Contact Network Algorithm, combining network theories with machine learning, to simulate networks of only infected persons and immediate contacts and thus dynamically evolve the network as the infection spreads.

Cluster generation algorithm for early detection and response of infectious diseases

Molecular analyses, using nucleotide sequences of the virus from persons diagnosed with an infection, can identify clusters or groups of infections that are genetically very similar. Thus, they help detect disease outbreaks, measure growth, and rapidly respond if needed. However molecular analysis is limited to persons who are diagnosed and have a sequence, and thus, generate only partially observable sub-networks of full networks. We developed mathematical methods to generate clusters and the underlying full network, specifically, a cluster generation algorithm generates clusters replicative of those observed using molecular data and maps clusters to the full contact and transmisison network. Using molecular methods for early detection and the model for understanding true size of network could further help with rapid response and optimal response.

Modeling social determinants of health into disease prediction models

Typically, dynamic models of infectious diseases simulate behaviors and model transmissions and disease progression as functions of behaviors. However, social conditions are among key drivers of behaviors that increase risk of infection. We develop statistical machine learning methods to first model behaviors as functions of social conditions. The resulting model will help quantify disparities, determine social needs of affected populations, and evaluate equitable allocation of intervention resources.

Reinforcement learning (RL) algorithms for large-scale dynamic decision-making problems

Reinforcment learning algorithms are suitable for evaluation of optmial sequence of decisions for eliminating infectious disease epidemics. However, they are computationally burdensome, and when combined with computationally large simulation enviromnents, especially for noncovex problems, such as in infectious disease models, become impractical to use. Through suitable choice of proxy action and state space we signifcantly reduce the size of the problem and generate an action space that makes the problem convex.

Typically, in infectious disease analyses, we develop models specific to each disease and conduct intervention analyses related to that disease. However, social determinants are key drivers of infectious diseases, and thus, structural interventions are key for overall disease prevention. Therefore, joint modeling multiple related diseases, such as diseases with common modes of transmission, would help collectively evaluate strategies to strengthen overall public health efforts. However, given the vastly varying epidemiology of diseases, there is no one suitable simulation technique that is suitable. Agent-based network models are suitable for slower spreading diseases, whereas differntial equations based models are suitable for faster spreading diseases. We developed a new simulation technique that simulates persons with atleast one slow spreading disease in a network and all other persons including those with only fast spreading diseases in a compartmental model, with an evolving contact network algorithm maintaining the contact dyanmics between the two populations.

Decision analytic tools to inform national and global public health efforts

National and global public health strategic plans and guidelines inform allocation of public health resources to varying intervention programs. We develop national-level stochastic dynamic simulation models, for use by public health agencies, for identifying optimal intervention combinations. We have developed models for HIV, COVID, breast cancer, colorectal cancer, and cervical cancer.

Multi-agent reinforcement learning for infectious disease models

In the context of infectious diseases, intervention decisions are typically made by multiple independent agents, e.g., state or national jurisdictions, cooperatively or non-cooperatively, but in an environment (diseases) that naturally involves cross-jurisdictional interactions. In an optimization context, infectious disease models typically do not consider these dynamics or simulate single jursidictions in isolation ignoring jurisdictional interactions, or conduct specific scenario based evaluations in a non-optimization context. Though recent advances in RL such as in multi-agent reinforcement learning would be suitable to address this gap, MARL algorithms are computationally impractical to implement in a national or global context as computational complexity grows exponentially with number of agents (jursidictions). We aim to develop suitable alternative algorithms.

PREVIOUS WORK