AI for Global Health and Public Health

Modeling to Inform Disease Control, Screening, Treatment Policies, and Prevention Interventions

 

  

MOTIVATION

AI tools can be used to inform public health policy.  For example, predictive analytics can be used to identify risk factors for disease; and optimization frameworks (whether single stage or repeated) can be used to identify when to screen or treat disease, or which risk groups to target given limited resources. Optimization frameworks can also be used to channel limited resources towards at-risk individuals to improve their adherence to healthy habits. We describe several projects and potential project areas below.

CURRENT PROJECTS

Improving Maternal and
Child Health Outcomes in
Partnership with ARMMAN

Maternal and Child Health

This project Improving Maternal and Child Health Outcomes in Partnership with ARMMAN aims at using AI for improving Maternal and Child Health Outcomes by predicting which beneficiaries are at a risk of dropping out from automated health information delivery programs. 

Learning Loss Functions for Predict-then-Optimize

Predict-then-Optimize (PtO) is a framework for using machine learning to perform decision-making under uncertainty. As the name suggests, it proceeds in two steps—first, you make predictions about the uncertain quantities of interest and then, second, you make the required decisions assuming that these predictions are accurate. However, these decisions are only optimal if the input predictions are accurate. To evaluate the quality of our decisions for a given prediction, we check how well they would perform on the ground truth values of the quantities of interest (from the dataset) as opposed to the predictions. Let’s use an example to make all these different steps in the PtO pipeline concrete.

HIV Prevention
Among Homeless Youth

The HIV Prevention Among Homeless Youth project focuses on the development of decision support systems for homeless youth drop-in center staff, who need to find the most influential homeless youth to raise awareness about HIV (and other STDs) among their peers, and to drive the homeless youth community towards safer behaviors.

PREVIOUS WORK

Algorithmic Social Interventions for Social Work and Public Health

Combatting COVID-19

Coronavirus

The COVID-19 outbreak has caused an unprecedented global reaction with countries taking drastic steps to combat the pandemic. Mathematical modeling and multi-agent based analysis of the pandemic allows better understanding of the disease spread and may help inform policy at the national and regional level. We use tools and modeling techniques from AI to help understand the situation better and design aids that may help policymakers design better solutions in the fight against this pandemic. Read more about Teamcore's efforts to stop the spread of COVID-19.

  

Using Machine Learning
& Multi-Agent Planning
to Fight Tuberculosis

Tuberculosis Health Post

Fighting and Preventing Tuberculosis in India

Tuberculosis is one of the top 10 killers in the world and is especially prevalent in India. AI can help across the entire pipeline of care, from decision support tools for planning active screening routes, to predictive algorithms for resource constrained health workers to deliver targeted interventions to patients.

  

Using Social Networks
for Prevention Interventions

Click here to read more on this initiative.

Two young men

Substance abuse prevention among homeless youth

Research has consistently documented levels of cocaine, heroin, methamphetamine, alcohol, and marijuana use and abuse among these adolescents that far exceed that of housed adolescents.  This Social Networks and Substance Abuse Prevention for Homeless Youth project aims to use algorithms to determine the best group formations to prevent regular use of hard drugs among homeless youth.

 

Army officer with a young child

Suicide prevention among active duty military and homeless youth

One of the fundamental questions facing social science is how social networks and the cognitions people have about their networks affect their mental states and mental health.  AI techniques present an opportunity to dynamically model social networks and the messages transmitted across those networks to create predictive models of influence unavailable with standard statistical techniques.  View Predictive Modeling for Early Identification of Suicidal Thinking.

  

  

PROJECT
PARTICIPANTS

Sze-chuan Suen
Milind Tambe
Bryan Wilder
Han Ching Ou
Dana Goldman
Eric Rice
Carl Castro
Anthony Fulginiti
Anamika Barman-Adhikari
Aditya Mate

Phebe Vayanos
Aida Rahmattalabi
Jackson A. Killian
Maimuna Majumder
Marie Charpignon
Angel N. Desai
Shahin Jabbari
Andrew Perrault
Lily Xu
Shresth Verma

Aparna Taneja
Vineet Nair
Aparna Hegde
Neha Madhiwalla
Paula Rodriguez Diaz
Sonja Johnson-Yu
Sanket Shah

  

SPONSORS

California HIV/AIDS Research Program
The California HIV/AIDS Research Program (CHRP) logo

Army Research Office

  

RELATED
PUBLICATIONS

Aditya Mate*, Jackson A. Killian*, Haifeng Xu, Andrew Perrault, and Milind Tambe. 12/5/2020. “Collapsing Bandits and Their Application to Public Health Interventions.” In Advances in Neural and Information Processing Systems (NeurIPS) 12/5/2020. Vancouver, Canada. Publisher's VersionAbstract
We propose and study Collapsing Bandits, a new restless multi-armed bandit (RMAB) setting in which each arm follows a binary-state Markovian process with a special structure: when an arm is played, the state is fully observed, thus “collapsing” any uncertainty, but when an arm is passive, no observation is made, thus allowing uncertainty to evolve. The goal is to keep as many arms in the “good” state as possible by planning a limited budget of actions per round. Such Collapsing Bandits are natural models for many healthcare domains in which health workers must simultaneously monitor patients and deliver interventions in a way that maximizes the health of their patient cohort. Our main contributions are as follows: (i) Building on the Whittle index technique for RMABs, we derive conditions under which the Collapsing Bandits problem is indexable. Our derivation hinges on novel conditions that characterize when the optimal policies may take the form of either “forward” or “reverse” threshold policies. (ii) We exploit the optimality of threshold policies to build fast algorithms for computing the Whittle index, including a closed form. (iii) We evaluate our algorithm on several data distributions including data from a real-world healthcare task in which a worker must monitor and deliver interventions to maximize their patients’ adherence to tuberculosis medication. Our algorithm achieves a 3-order-of-magnitude speedup compared to state-of-the-art RMAB techniques, while achieving similar performance.
Evaluating COVID-19 Lockdown and Business-Sector-Specific Reopening Policies for Three US States
Jackson A. Killian, Marie Charpignon, Bryan Wilder, Andrew Perrault, Milind Tambe, and Maimuna S. Majumder. 8/24/2020. “Evaluating COVID-19 Lockdown and Business-Sector-Specific Reopening Policies for Three US States.” In KDD 2020 Workshop on Humanitarian Mapping. Publisher's VersionAbstract
Background: The United States has been particularly hard-hit by COVID-19, accounting for approximately 30% of all global cases and deaths from the disease that have been reported as of May 20, 2020. We extended our agent-based model for COVID-19 transmission to study the effect of alternative lockdown and reopening policies on disease dynamics in Georgia, Florida, and Mississippi. Specifically, for each state we simulated the spread of the disease had the state enforced its lockdown approximately one week earlier than it did. We also simulated Georgia's reopening plan under various levels of physical distancing if enacted in each state, making projections until June 15, 2020.

Methods: We used an agent-based SEIR model that uses population-specific age distribution, household structure, contact patterns, and comorbidity rates to perform tailored simulations for each region. The model was first calibrated to each state using publicly available COVID-19 death data as of April 23, then implemented to simulate given lockdown or reopening policies.

Results: Our model estimated that imposing lockdowns one week earlier could have resulted in hundreds fewer COVID-19-related deaths in the context of all three states. These estimates quantify the effect of early action, a key metric to weigh in developing prospective policies to combat a potential second wave of infection in each of these states. Further, when simulating Georgia’s plan to reopen select businesses as of April 27, our model found that a reopening policy that includes physical distancing to ensure no more than 25% of pre-lockdown contact rates at reopened businesses could allow limited economic activity to resume in any of the three states, while also eventually flattening the curve of COVID-19-related deaths by June 15, 2020.
Amulya Yadav, Leandro Marcolino, Eric Rice, Robin Petering, Hailey Winetrobe, Harmony Rhoades, Milind Tambe, and Heather Carmichael. 2015. “Preventing HIV Spread in Homeless Populations Using PSINET.” In Conference on Innovative Applications of Artificial Intelligence (IAAI-15).Abstract
Homeless youth are prone to HIV due to their engagement in high risk behavior. Many agencies conduct interventions to educate/train a select group of homeless youth about HIV prevention practices and rely on word-of-mouth spread of information through their social network. Previous work in strategic selection of intervention participants does not handle uncertainties in the social network’s structure and in the evolving network state, potentially causing significant shortcomings in spread of information. Thus, we developed PSINET, a decision support system to aid the agencies in this task. PSINET includes the following key novelties: (i) it handles uncertainties in network structure and evolving network state; (ii) it addresses these uncertainties by using POMDPs in influence maximization; (iii) it provides algorithmic advances to allow high quality approximate solutions for such POMDPs. Simulations show that PSINET achieves ∼60% more information spread over the current state-of-the-art. PSINET was developed in collaboration with My Friend’s Place (a drop-in agency serving homeless youth in Los Angeles) and is currently being reviewed by their officials.
Amulya Yadav, Ece Kamar, Barbara Grosz, and Milind Tambe. 2016. “HEALER: POMDP Planning for Scheduling Interventions among Homeless Youth (Demonstration).” In International conference on Autonomous Agents and Multiagent Systems.Abstract
Adaptive software agents like HEALER have been proposed in the literature recently to recommend intervention plans to homeless shelter officials. However, generating networks for HEALER’s input is challenging. Moreover, HEALER’s solutions are often counter-intuitive to people. This demo paper makes two contributions. First, we demonstrate HEALER’s Facebook application, which parses the Facebook contact lists in order to construct an approximate social network for HEALER. Second, we present a software interface to run human subject experiments (HSE) to understand human biases in recommendation of intervention plans. We plan to use data collected from these HSEs to build an explanation system for HEALER’s solutions.
Amulya Yadav, Hau Chan, Albert Jiang, Eric Rice, Ece Kamar, Barbara Grosz, and Milind Tambe. 2016. “POMDPs for Assisting Homeless Shelters - Computational and Deployment Challenges.” In AAMAS 2016 IDEAS Workshop.Abstract
This paper looks at challenges faced during the ongoing deployment of HEALER, a POMDP based software agent that recommends sequential intervention plans for use by homeless shelters, who organize these interventions to raise awareness about HIV among homeless youth. HEALER’s sequential plans (built using knowledge of social networks of homeless youth) choose intervention participants strategically to maximize influence spread, while reasoning about uncertainties in the network. In order to compute its plans, HEALER (i) casts this influence maximization problem as a POMDP and solves it using a novel planner which scales up to previously unsolvable real-world sizes; (ii) and constructs social networks of homeless youth at low cost, using a Facebook application. HEALER is currently being deployed in the real world in collaboration with a homeless shelter. Initial feedback from the shelter officials has been positive but they were surprised by the solutions generated by HEALER as these solutions are very counterintuitive. Therefore, there is a need to justify HEALER’s solutions in a way that mirrors the officials’ intuition. In this paper, we report on progress made towards HEALER’s deployment and detail first steps taken to tackle the issue of explaining HEALER’s solutions.
Leandro Soriano Marcolino, Aravind Lakshminarayanan, Amulya Yadav, and Milind Tambe. 2016. “Simultaneous Influencing and Mapping Social Networks (Extended Abstract).” In International Conference on Autonomous Agents and Multiagent Systems (AAMAS).Abstract
Influencing a social network is an important technique, with potential to positively impact society, as we can modify the behavior of a community. For example, we can increase the overall health of a population; Yadav et al. (2015) [4], for instance, spread information about HIV prevention in homeless populations. However, although influence maximization has been extensively studied [2, 1], their main motivation is viral marketing, and hence they assume that the social network graph is fully known, generally taken from some social media network. However, the graphs recorded in social media do not really represent all the people and all the connections of a population. Most critically, when performing interventions in real life, we deal with large degrees of lack of knowledge. Normally the social agencies have to perform several interviews in order to learn the social network graph [3]. These highly unknown networks, however, are exactly the ones we need to influence in order to have a positive impact in the real world, beyond product advertisement. Additionally, learning a social network graph is very valuable per se. Agencies need data about a population, in order to perform future actions to enhance their well-being, and better actuate in their practices [3]. As mentioned, however, the works in influence maximization are currently ignoring this problem. Each person in a social network actually knows other people, including the ones she cannot directly influence. When we select someone for an intervention (to spread influence), we also have an opportunity to obtain knowledge. Therefore, in this work we present for the first time the problem of simultaneously influencing and mapping a social network. We study the performance of the classical influence maximization algorithm in this context, and show that it can be arbitrarily low. Hence, we study a class of algorithms for this problem, performing an experimentation using four real life networks of homeless populations. We show that our algorithm is competitive with previous approaches in terms of influence, and is significantly better in terms of mapping.
Amulya Yadav, Hau Chan, Albert Xin Jiang, Haifeng Xu, Eric Rice, and Milind Tambe. 2016. “Using Social Networks to Aid Homeless Shelters: Dynamic Influence Maximization under Uncertainty.” In International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2016.Abstract
This paper presents HEALER, a software agent that recommends sequential intervention plans for use by homeless shelters, who organize these interventions to raise awareness about HIV among homeless youth. HEALER’s sequential plans (built using knowledge of social networks of homeless youth) choose intervention participants strategically to maximize influence spread, while reasoning about uncertainties in the network. While previous work presents influence maximizing techniques to choose intervention participants, they do not address three real-world issues: (i) they completely fail to scale up to real-world sizes; (ii) they do not handle deviations in execution of intervention plans; (iii) constructing real-world social networks is an expensive process. HEALER handles these issues via four major contributions: (i) HEALER casts this influence maximization problem as a POMDP and solves it using a novel planner which scales up to previously unsolvable realworld sizes; (ii) HEALER allows shelter officials to modify its recommendations, and updates its future plans in a deviation-tolerant manner; (iii) HEALER constructs social networks of homeless youth at low cost, using a Facebook application. Finally, (iv) we show hardness results for the problem that HEALER solves. HEALER will be deployed in the real world in early Spring 2016 and is currently undergoing testing at a homeless shelter.
Amulya Yadav, Aida Rahmattalabi, Ece Kamar, Phebe Vayanos, Milind Tambe, and Venil Loyd Noronha. 2017. “Explanations Systems for Influential Maximizations Algorithms.” In 3rd International Workshop on Social Influence Analysis.Abstract
The field of influence maximization (IM) has made rapid advances, resulting in many sophisticated algorithms for identifying “influential” members in social networks. However, in order to engender trust in IM algorithms, the rationale behind their choice of “influential” nodes needs to be explained to its users. This is a challenging open problem that needs to be solved before these algorithms can be deployed on a large scale. This paper attempts to tackle this open problem via four major contributions: (i) we propose a general paradigm for designing explanation systems for IM algorithms by exploiting the tradeoff between explanation accuracy and interpretability; our paradigm treats IM algorithms as black boxes, and is flexible enough to be used with any algorithm; (ii) we utilize this paradigm to build XplainIM, a suite of explanation systems; (iii) we illustrate the usability of XplainIM by explaining solutions of HEALER (a recent IM algorithm) among ∼200 human subjects on Amazon Mechanical Turk (AMT); and (iv) we provide extensive evaluation of our AMT results, which shows the effectiveness of XplainIM.