Using Integrated City Data and Machine Learning to Identify and Intervene Early on Housing-Related Public Health Problems

Substandard housing and the risk of COVID-19 infection and disease severity: A retrospective cohort study

In this study we examine associations between substandard housing and the risk of COVID-19 infection and severity during the first year of the pandemic by linking individual-level housing and clinical datasets. Residents of Chelsea, Massachusetts who were tested for COVID-19 at any Mass General Brigham testing site and who lived at a property that had received a city housing inspection were included (N = 2873). Chelsea is a densely populated city with a high prevalence of substandard housing. Inspected properties with housing code violations were considered substandard; inspected properties without violations were considered adequate. COVID-19 infection was defined as any positive PCR test, and severe disease defined as hospitalization with COVID-19. We used a propensity score design to match individuals on variables including age, race, sex, and income. In the severity model, we also matched on ten comorbidities. We estimated the risk of COVID-19 infection and severity associated with substandard housing using Cox Proportional Hazards models for lockdown, the first phase of reopening, and the full study period. In our sample, 32% (919/2873) of individuals tested positive for COVID-19 and 5.9% (135/2297) had severe disease. During lockdown, substandard housing was associated with a 48% increased risk of COVID-19 infection (95%CI 1.1-2.0, p = 0.006). Through Phase 1 reopening, substandard housing was associated with a 39% increased infection risk (95%CI 1.1-1.8, p = 0.020). The difference in risk attenuated over the full study period. There was no difference in severe disease risk between the two groups. The increased risk, observed only during lockdown and early reopening - when residents were most exposed to their housing - strengthens claims that substandard housing conveys higher infection risk. The results demonstrate the value of combining cross-sector datasets. Existing city housing data can be leveraged 1) to identify and prioritize high-risk areas for future pandemic response, and 2) for longer-term housing solutions.

The application of artificial intelligence in health policy: a scoping review

BACKGROUND

Policymakers require precise and in-time information to make informed decisions in complex environments such as health systems. Artificial intelligence (AI) is a novel approach that makes collecting and analyzing data in complex systems more accessible. This study highlights recent research on AI's application and capabilities in health policymaking.

METHODS

We searched PubMed, Scopus, and the Web of Science databases to find relevant studies from 2000 to 2023, using the keywords "artificial intelligence" and "policymaking." We used Walt and Gilson's policy triangle framework for charting the data.

RESULTS

The results revealed that using AI in health policy paved the way for novel analyses and innovative solutions for intelligent decision-making and data collection, potentially enhancing policymaking capacities, particularly in the evaluation phase. It can also be employed to create innovative agendas with fewer political constraints and greater rationality, resulting in evidence-based policies. By creating new platforms and toolkits, AI also offers the chance to make judgments based on solid facts. The majority of the proposed AI solutions for health policy aim to improve decision-making rather than replace experts.

CONCLUSION

Numerous approaches exist for AI to influence the health policymaking process. Health systems can benefit from AI's potential to foster the meaningful use of evidence-based policymaking.