The increasing availability of data, and the development of algorithms capable of making sense of that data, are hugely important to the creation of better public policy and superior decision-making, says Harvard Kennedy School Associate Professor of Public Policy Soroush Saghafian. Saghafian, whose expertise includes state-of-the-art methods in machine learning and big data, is the the founder and director of the Public Impact Analytics Science Lab (PIAS Lab), based at the Mossavar-Rahmani Center for Business and Government, which is devoted to advancing and applying the science of analytics for solving societal problems that can have public impact. Saghafian also serves as a faculty affiliate of the Harvard Data Science Initiative, Harvard Center for Health Decision Science, and Harvard PhD Program in Health Policy.
Q: What can “big data” and “machine learning” contribute to public policy, and how can they be harnessed responsibly?
The possibilities in using algorithms along with the availed data are endless, and the potential impact on public lives is beyond limits. But, like many other technological advancements, advanced analytics science tools can be used in a positive or negative way. Naturally the main public fears about them are around potential misuses. However, the possibilities for positive uses and solving societal problems are also vast.
Policy decisions are naturally complex and extremely challenging. The AI and machine learning branches of analytics science are great tools because they allow us to move away from opinion-based solutions and instead adopt data-driven strategies. To harness them responsibly though, we must make use of them in specific ways. For example, we need to make sure they are not solely trained on data generated by human decision-makers, which, by nature, are often biased towards their own views.
Q: What is the data analytical research that you and PIAS Lab undertake? What are your methods and can you explain how “big data” and “machine learning” feed into them?
In my lab, we are collaborating with a variety of organizations to solve problems that can have public impact. We take a problem-driven approach, meaning that we make use of the best analytics science methods to most effectively address each unique problem. These tools come from various branches of analytics science, including operations research, machine learning and big data, decision science, statistics, and artificial intelligence, among others.
We have been using these tools to help hospitals, startups, public agencies in the United States and beyond, and private firms solving problems that have public impact. The tools and related collaborations with these entities have enabled us find the best ways to save lives, improve the quality of care delivered to patients, decrease healthcare expenditures, reduce existing inequalities, design superior policies, and make better use of technological advancements such as mobile health, smart devices, and telemedicine, among others.
“The possibilities in using algorithms along with the availed data are endless, and the potential impact on public lives is beyond limits.”
Q: What are the challenges to undertaking data analytical research? And where have these modes of analysis been successful?
The challenges are many, especially when you want to make a meaningful impact in one of the most complex sectors—the health care sector. The health care sector involves a variety of stakeholders, especially in the United States, where health care is extremely decentralized yet highly regulated, for example in the areas of data collections and data use. Analytics-based solutions that can help one part of this sector might harm other parts, making finding globally optimal solutions in this sector extremely difficult. Therefore, finding data-driven approaches that can have public impact is not a walk in the park.
Then there are various challenges in implementation. In my lab, we can design advanced machine learning and AI algorithms that have outstanding performance. But if they are not implemented in practice, or if the recommendations they provide are not followed, they won’t have any tangible impact.
In some of our recent experiments, for example, we found that the algorithms we had designed outperformed expert physicians in one of the leading U.S. hospitals. Interestingly, when we provided physicians with our algorithmic-based recommendations, they did not put much weight on the advice they got from the algorithms, and ignored it when treating patients, although they knew the algorithm most likely outperforms them.
We then studied ways of removing this obstacle. We found that combining human expertise with the recommendations provided by algorithms not only made it more likely for the physicians to put more weight on the algorithms’ advice, but also synthesized recommendations that are superior to both the best algorithms and the human experts.
We have also observed similar challenges at the policy level. For example, we have developed advanced algorithms trained on large-scale data that could help the Centers for Disease Control and Prevention improve its opioid-related policies. The opioid epidemic caused more than 556,000 deaths in the United States between 2000 and 2020, and yet the authorities still do not have a complete understanding of what can be done to effectively control this deadly epidemic. Our algorithms have produced recommendations we believe are superior to the CDC’s. But, again, a significant challenge is to make sure CDC and other authorities listen to these superior recommendations.
I do not want to imply that policymakers or other authorities are always against these algorithm-driven solutions—some are more eager than others—but I believe the helpfulness of algorithms is consistently underrated and often ignored in the practice.
Q: How do you think about the role of oversight and regulation in this field of new technologies and data analytical models?
Imposing appropriate regulations is important. There is, however, a fine line: while new tools and advancements should be guarded against misuses, the regulations should not block these tools from reaching their full potential.
As an example, in a paper that we published in the National Academy of Medicine in 2021, we discussed that the use of mobile health (mHealth) interventions (mainly enabled through advanced algorithms and smart devices) have been rapidly increasing worldwide as health care providers, industry, and governments seek more efficient ways of delivering health care. Despite the technological advances, increasingly widespread adoption, and endorsements from leading voices from the medical, government, financial, and technology sectors, these technologies have not reached their full potential.
Part of the reason is that there are scientific challenges that need to be addressed. For example, as we discuss in our paper, mHealth technologies need to make use of more advanced algorithms and statistical experimental designs in deciding how best to adapt the content and delivery timing of a treatment to the user’s current context.
However, various regulatory challenges remain—such as how best to protect user data. The Food and Drug Administration in a 2019 statement encouraged “the development of mobile medical apps (MMAs) that improve health care” but also emphasized its “public health responsibility to oversee the safety and effectiveness of medical devices—including mobile medical apps.” Balancing between encouraging new developments and ensuring that such developments abide by the well-known principle of “do no harm” is not an easy regulatory task.
At the end, what is needed are two-fold: (a) advancements in the underlying science, and (b) appropriately balanced regulations. If these are met, the possibilities for using advanced analytics science methods in solving our lingering societal problems are endless.
—
Banner art by gremlin/Getty Images