Nazanin is currently a postdoctoral research fellow at Harvard Medical School and Mass General Hospital. Nazanin received her PhD in Industrial Engineering and Operations Research from the University of Massachusetts (UMass) Amherst. She also holds an MS in Electrical and Computer Engineering from UMass Amherst. Her research focuses on disease modeling, control, and optimization. During her Ph.D., she closely collaborated with the HIV division at the CDC where she developed a sequential decision-making model to control HIV at a national level using reinforcement learning algorithms.
While at the ITA, Dr. Khatami worked with Dr. Mohammad Jalali (MJ) at ITA to develop machine learning models to address opioid crisis in the US. She also worked with Dr. Krishna Reddy at the MGH Medical Practice Evaluation Center (MPEC) to develop a tuberculosis transmission module for people with HIV.
Selected Publications
Khatami, Seyedeh Nazanin; Gopalappa, Chaitra
Deep reinforcement learning framework for controlling infectious disease outbreaks in the context of multi-jurisdictions Journal Article
In: Math Biosci Eng, vol. 20, no. 8, pp. 14306–14326, 2023, ISSN: 1551-0018.
@article{pmid37679137,
title = {Deep reinforcement learning framework for controlling infectious disease outbreaks in the context of multi-jurisdictions},
author = {Seyedeh Nazanin Khatami and Chaitra Gopalappa},
doi = {10.3934/mbe.2023640},
issn = {1551-0018},
year = {2023},
date = {2023-06-01},
journal = {Math Biosci Eng},
volume = {20},
number = {8},
pages = {14306--14326},
abstract = {In the absence of pharmaceutical interventions, social distancing and lockdown have been key options for controlling new or reemerging respiratory infectious disease outbreaks. The timely implementation of these interventions is vital for effectively controlling and safeguarding the economy.Motivated by the COVID-19 pandemic, we evaluated whether, when, and to what level lockdowns are necessary to minimize epidemic and economic burdens of new disease outbreaks. We formulated the question as a sequential decision-making Markov Decision Process and solved it using deep Q-network algorithm. We evaluated the question under two objective functions: a 2-objective function to minimize economic burden and hospital capacity violations, suitable for diseases with severe health risks but with minimal death, and a 3-objective function that additionally minimizes the number of deaths, suitable for diseases that have high risk of mortality.A key feature of the model is that we evaluated the above questions in the context of two-geographical jurisdictions that interact through travel but make autonomous and independent decisions, evaluating under cross-jurisdictional cooperation and non-cooperation. In the 2-objective function under cross-jurisdictional cooperation, the optimal policy was to aim for shutdowns at 50 and 25% per day. Though this policy avoided hospital capacity violations, the shutdowns extended until a large proportion of the population reached herd immunity. Delays in initiating this optimal policy or non-cooperation from an outside jurisdiction required shutdowns at a higher level of 75% per day, thus adding to economic burdens. In the 3-objective function, the optimal policy under cross-jurisdictional cooperation was to aim for shutdowns of up to 75% per day to prevent deaths by reducing infected cases. This optimal policy continued for the entire duration of the simulation, suggesting that, until pharmaceutical interventions such as treatment or vaccines become available, contact reductions through physical distancing would be necessary to minimize deaths. Deviating from this policy increased the number of shutdowns and led to several deaths.In summary, we present a decision-analytic methodology for identifying optimal lockdown strategy under the context of interactions between jurisdictions that make autonomous and independent decisions. The numerical analysis outcomes are intuitive and, as expected, serve as proof of the feasibility of such a model. Our sensitivity analysis demonstrates that the optimal policy exhibits robustness to minor alterations in the transmission rate, yet shows sensitivity to more substantial deviations. This finding underscores the dynamic nature of epidemic parameters, thereby emphasizing the necessity for models trained across a diverse range of values to ensure effective policy-making.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In the absence of pharmaceutical interventions, social distancing and lockdown have been key options for controlling new or reemerging respiratory infectious disease outbreaks. The timely implementation of these interventions is vital for effectively controlling and safeguarding the economy.Motivated by the COVID-19 pandemic, we evaluated whether, when, and to what level lockdowns are necessary to minimize epidemic and economic burdens of new disease outbreaks. We formulated the question as a sequential decision-making Markov Decision Process and solved it using deep Q-network algorithm. We evaluated the question under two objective functions: a 2-objective function to minimize economic burden and hospital capacity violations, suitable for diseases with severe health risks but with minimal death, and a 3-objective function that additionally minimizes the number of deaths, suitable for diseases that have high risk of mortality.A key feature of the model is that we evaluated the above questions in the context of two-geographical jurisdictions that interact through travel but make autonomous and independent decisions, evaluating under cross-jurisdictional cooperation and non-cooperation. In the 2-objective function under cross-jurisdictional cooperation, the optimal policy was to aim for shutdowns at 50 and 25% per day. Though this policy avoided hospital capacity violations, the shutdowns extended until a large proportion of the population reached herd immunity. Delays in initiating this optimal policy or non-cooperation from an outside jurisdiction required shutdowns at a higher level of 75% per day, thus adding to economic burdens. In the 3-objective function, the optimal policy under cross-jurisdictional cooperation was to aim for shutdowns of up to 75% per day to prevent deaths by reducing infected cases. This optimal policy continued for the entire duration of the simulation, suggesting that, until pharmaceutical interventions such as treatment or vaccines become available, contact reductions through physical distancing would be necessary to minimize deaths. Deviating from this policy increased the number of shutdowns and led to several deaths.In summary, we present a decision-analytic methodology for identifying optimal lockdown strategy under the context of interactions between jurisdictions that make autonomous and independent decisions. The numerical analysis outcomes are intuitive and, as expected, serve as proof of the feasibility of such a model. Our sensitivity analysis demonstrates that the optimal policy exhibits robustness to minor alterations in the transmission rate, yet shows sensitivity to more substantial deviations. This finding underscores the dynamic nature of epidemic parameters, thereby emphasizing the necessity for models trained across a diverse range of values to ensure effective policy-making.
Khatami, Seyedeh N.; Gopalappa, Chaitra
A reinforcement learning model to inform optimal decision paths for HIV elimination. Journal Article
In: Mathematical biosciences and engineering : MBE, vol. 18, iss. 6, pp. 7666–7684, 2021, ISSN: 1551-0018.
@article{Khatami2021,
title = {A reinforcement learning model to inform optimal decision paths for HIV elimination.},
author = {Seyedeh N. Khatami and Chaitra Gopalappa},
url = {https://pubmed.ncbi.nlm.nih.gov/34814269/},
doi = {10.3934/mbe.2021380},
issn = {1551-0018},
year = {2021},
date = {2021-09-01},
journal = {Mathematical biosciences and engineering : MBE},
volume = {18},
issue = {6},
pages = {7666--7684},
abstract = {The 'Ending the HIV Epidemic (EHE)' national plan aims to reduce annual HIV incidence in the United States from 38,000 in 2015 to 9300 by 2025 and 3300 by 2030. Diagnosis and treatment are two most effective interventions, and thus, identifying corresponding optimal combinations of testing and retention-in-care rates would help inform implementation of relevant programs. Considering the dynamic and stochastic complexity of the disease and the time dynamics of decision-making, solving for optimal combinations using commonly used methods of parametric optimization or exhaustive evaluation of pre-selected options are infeasible. Reinforcement learning (RL), an artificial intelligence method, is ideal; however, training RL algorithms and ensuring convergence to optimality are computationally challenging for large-scale stochastic problems. We evaluate its feasibility in the context of the EHE goal. We trained an RL algorithm to identify a 'sequence' of combinations of HIV-testing and retention-in-care rates at 5-year intervals over 2015-2070 that optimally leads towards HIV elimination. We defined optimality as a sequence that maximizes quality-adjusted-life-years lived and minimizes HIV-testing and care-and-treatment costs. We show that solving for testing and retention-in-care rates through appropriate reformulation using proxy decision-metrics overcomes the computational challenges of RL. We used a stochastic agent-based simulation to train the RL algorithm. As there is variability in support-programs needed to address barriers to care-access, we evaluated the sensitivity of optimal decisions to three cost-functions. The model suggests to scale-up retention-in-care programs to achieve and maintain high annual retention-rates while initiating with a high testing-frequency but relaxing it over a 10-year period as incidence decreases. Results were mainly robust to the uncertainty in costs. However, testing and retention-in-care alone did not achieve the 2030 EHE targets, suggesting the need for additional interventions. The results from the model demonstrated convergence. RL is suitable for evaluating phased public health decisions for infectious disease control.},
keywords = {},
pubstate = {ppublish},
tppubtype = {article}
}
The 'Ending the HIV Epidemic (EHE)' national plan aims to reduce annual HIV incidence in the United States from 38,000 in 2015 to 9300 by 2025 and 3300 by 2030. Diagnosis and treatment are two most effective interventions, and thus, identifying corresponding optimal combinations of testing and retention-in-care rates would help inform implementation of relevant programs. Considering the dynamic and stochastic complexity of the disease and the time dynamics of decision-making, solving for optimal combinations using commonly used methods of parametric optimization or exhaustive evaluation of pre-selected options are infeasible. Reinforcement learning (RL), an artificial intelligence method, is ideal; however, training RL algorithms and ensuring convergence to optimality are computationally challenging for large-scale stochastic problems. We evaluate its feasibility in the context of the EHE goal. We trained an RL algorithm to identify a 'sequence' of combinations of HIV-testing and retention-in-care rates at 5-year intervals over 2015-2070 that optimally leads towards HIV elimination. We defined optimality as a sequence that maximizes quality-adjusted-life-years lived and minimizes HIV-testing and care-and-treatment costs. We show that solving for testing and retention-in-care rates through appropriate reformulation using proxy decision-metrics overcomes the computational challenges of RL. We used a stochastic agent-based simulation to train the RL algorithm. As there is variability in support-programs needed to address barriers to care-access, we evaluated the sensitivity of optimal decisions to three cost-functions. The model suggests to scale-up retention-in-care programs to achieve and maintain high annual retention-rates while initiating with a high testing-frequency but relaxing it over a 10-year period as incidence decreases. Results were mainly robust to the uncertainty in costs. However, testing and retention-in-care alone did not achieve the 2030 EHE targets, suggesting the need for additional interventions. The results from the model demonstrated convergence. RL is suitable for evaluating phased public health decisions for infectious disease control.
Baker, Erin D.; Khatami, Seyedeh Nazanin
The levelized cost of carbon: a practical, if imperfect, method to compare CO2 abatement projects Journal Article
In: Climate Policy, vol. 19, no. 9, pp. 1132-1143, 2019.
@article{EDBaker2019,
title = {The levelized cost of carbon: a practical, if imperfect, method to compare CO2 abatement projects},
author = {Erin D. Baker and Seyedeh Nazanin Khatami},
url = {https://doi.org/10.1080/14693062.2019.1634508},
doi = {10.1080/14693062.2019.1634508},
year = {2019},
date = {2019-01-01},
journal = {Climate Policy},
volume = {19},
number = {9},
pages = {1132-1143},
publisher = {Taylor \& Francis},
keywords = {},
pubstate = {published},
tppubtype = {article}
}