AI and urban design for health: Are large language models ethical advisers?
World-first study finds AI advice avoids obvious harm but is less consistent on community participation and human oversight
image:
ChatGPT-generated urban design advice avoided clear harm but showed gaps in community participation and transparent human oversight.
view moreCredit: faberdasher from Openverse | Image Source Link: https://openverse.org/image/6e1be61d-ab06-4d3c-89ea-2d8e22f7d27f?q=architect+designing+on+laptop&p=2
Large language models (LLMs) are increasingly being used to generate text-based advice across urban design, planning, and public health. In urban design, they can recommend changes to transportation infrastructure, land use, walkability, pedestrian environments, and greenspaces to support health. However, because these outputs can resemble expert advice, questions remain about whether they meet ethical expectations, including avoiding harm, treating neighborhoods fairly, involving communities, and recognizing human oversight.
Addressing this challenge, a research team led by Associate Professor Mohammad Javad Koohsari of the Urban Design Science for Health Laboratory at the Japan Advanced Institute of Science and Technology (JAIST), Japan, and Professor Koichiro Oka of the Faculty of Sport Sciences, Waseda University, Japan, examined the ethical properties of LLM-generated advice for modifying built environments to support human health. The researchers evaluated ChatGPT responses under different health pathways, neighborhood income contexts, and budget conditions. Their findings were made available online on August 10, 2026, and will be published in Volume 27 of the journal Developments in the Built Environment on October 01, 2026.
The team considered six health-related pathways: physical activity, dietary intake, social interaction, air pollution, traffic safety and crime, and noise. They created 18 prompts, with 12 covering higher-income and lower-income neighborhoods and six describing mixed-income neighborhoods under a budget constraint. Each prompt was run 10 times, producing 180 responses. The answers were assessed against four ethical criteria: non-maleficence, distributive justice, collective participation, and transparent oversight. Two co-authors independently coded all responses.
The results showed that non-maleficence was satisfied in all 180 answers, indicating that the model did not clearly recommend harmful or unsafe built environment changes. Distributive justice was satisfied in 110 of 120 evaluable units (91.7%), suggesting that lower-income contexts were rarely given weaker proposals. However, procedural criteria were met less consistently. Collective participation appeared in 109 of 180 answers (60.6%), while transparent oversight appeared in 136 of 180 answers (75.6%).
The differences were particularly clear in the mixed-income prompts that included a budget constraint. In the mixed-income, budget-constrained prompts, collective participation was present in 21 of 60 answers (35.0%), while transparent oversight appeared in 28 of 60 answers (46.7%). By comparison, these criteria were present in 73.3% and 90.0% of answers, respectively, in the non-budget-constrained prompt set. “Our findings show that ethical urban design for health depends not only on what physical changes are proposed, but also on how decisions are made, who is involved, and how uncertainty and human oversight are addressed,” Dr. Koohsari said.
These findings suggest that LLM-generated advice may reproduce some baseline ethical conventions in urban design, particularly harm avoidance and minimum distributive fairness, but may be less reliable on procedural concerns. LLMs could serve as an initial input for urban designers, planners, and public health professionals when considering health-supportive changes to streets, public spaces, transportation infrastructure, land use, and greenspaces. However, such outputs should not replace professional judgment or community participation, particularly when limited budgets require prioritization.
Overall, to the researchers' knowledge, this is the first study worldwide to examine the ethical properties of LLM-generated advice for urban design and health. The findings highlight the need to evaluate future tools not only by their design recommendations but also by whether they avoid harm, treat disadvantaged neighborhoods fairly, support community participation, and recognize human oversight. “With appropriate safeguards, LLMs could support more health-informed urban design while ensuring that important decisions remain grounded in professional expertise, community participation, and institutional processes,” Dr. Koohsari concludes.
***
Reference
DOI: https://doi.org/10.1016/j.dibe.2026.101007
Authors: Mohammad Javad Koohsari, Becky P.Y. Loo, Jing Zhao, Jiuling Li, Ying Long, Yi Lu, Koichiro Oka, and Andrew T. Kaczynski
About Japan Advanced Institute of Science and Technology, Japan
Founded in 1990 in Ishikawa prefecture, the Japan Advanced Institute of Science and Technology (JAIST) was the first independent national graduate university that has its own campus in Japan. Now, after 30 years of steady progress, JAIST has become one of Japan’s top-ranking universities. JAIST strives to foster capable leaders with a state-of-the-art education system where diversity is key; about 40% of its alumni are international students. The university has a unique style of graduate education based on a carefully designed coursework-oriented curriculum to ensure that its students have a solid foundation on which to carry out cutting-edge research. JAIST also works closely both with local and overseas communities by promoting industry–academia collaborative research.
Website: https://www.jaist.ac.jp/english/
About Associate Professor Mohammad Javad Koohsari from Japan Advanced Institute of Science and Technology, Japan
Dr. Mohammad Javad Koohsari is an Associate Professor and founder of the Urban Design Science for Health Laboratory at JAIST, Japan. He holds two PhDs in Urban Design and Health and Sport Sciences. He is also a Visiting Researcher at Waseda University, Japan and an Academic Affiliate at the Arnold School of Public Health, University of South Carolina. His research examines how urban spatial structure affects population health in the Asia–Pacific region using spatial analysis, epidemiological modelling, and AI. Recognized among the world’s top 2% most influential scientists, he has authored over 150 peer-reviewed publications and received 8,481 citations.
Funding information
N/A
Journal
Developments in the Built Environment
Method of Research
Content analysis
Subject of Research
Not applicable
Article Title
Ethical assessment of large language model-generated advisory text on designing the built environment for health
Article Publication Date
1-Oct-2026
Can AI help bridge the public health gap?
Ateneo researchers investigate cost-effectiveness of AI-assisted chest radiograph interpretation in isolated and disadvantaged FIlipino communities
image:
An AI-assisted chest x-ray highlighting areas for further review. Ateneo medical experts are looking into whether new imaging technologies could offer a cost-effective approach to TB screening for patients. The findings have significant implications on broader public healthcare delivery, particularly with regard to the accessibility and cost-efficiency of similar AI-assisted healthcare solutions.
view moreCredit: Chiu et al., 2026
In the Philippines, public healthcare remains inaccessible to many due to a variety of factors, including the high cost and limited availability of medical experts.
A new study by Ateneo researchers explores how artificial intelligence (AI) can help address this gap by looking at the cost-effectiveness of AI-assisted chest radiograph (X-ray) interpretation.
This is particularly vital for people with tuberculosis (TB), as finding the disease early can mean receiving the care they need before it becomes severe and causes irreversible damage. According to the World Health Organization, in 2024 alone an estimated 739,000 people in the Philippines developed tuberculosis, accounting for 6.8% of the 10.8 million TB cases worldwide.
As with most other diseases, early detection is essential. In geographically isolated or disadvantaged communities and rural health units, even if a patient is lucky enough to have an X-ray taken, waiting for a radiologist or teleradiology services to interpret it may take a long time. For some, that wait can mean another trip to a health facility, additional expenses, time away from work, or a missed opportunity for continued care.
Dr. Harold Chiu, Dr. Bryan Lao, and Dr. Gloanne Adolor developed a decision-analytic model based on a theoretical annual cohort of 1,000 presumptive TB patients undergoing chest radiography in rural health units. The analysis considered costs and outcomes over five years, including AI software and operating expenses, radiologist reading fees, and confirmatory GeneXpert testing.
Based on the study’s model-based projections, the AI-assisted strategy would entail an estimated annual cost of Php 877,330, compared with Php 1.14 million for manual interpretation. Divided across the 1,000 individuals screened, this translated to about Php 877 per person with AI-assisted interpretation, versus about Php 1,142 per person using manual interpretation. The use of AI promised to be economical.
Accessibility beyond efficiency
But the researchers suggest that the significance of AI goes beyond its capability to read an X-ray efficiently.
“For resource-constrained communities, the most important question is therefore not whether AI can outperform or assist an expert reader, but whether it can extend expert-level support to places where expertise is scarce in a way that is affordable, sustainable, and equitable,” the researchers said.
The researchers note that, if properly integrated into existing TB programs through portable digital X-rays and systems that can operate with limited connectivity, AI could help bring TB screening closer to underserved communities.
The goal, they emphasize, should not be to introduce another high-tech tool into healthcare, but to narrow existing geographic disparities.
Importance of local conditions
However, the findings also highlight the importance of local conditions. When a lower manual or teleradiology reading fee was used, or when diagnostic performance estimates from a Philippine scenario were applied, AI remained more effective but was no longer necessarily cost-saving.
The study is based on a theoretical cohort and assumptions about costs and diagnostic accuracy, while AI-assisted findings would still require confirmatory testing. Rather than immediate nationwide adoption, the researchers recommend starting with targeted pilot implementation in underserved rural health units, alongside local validation, quality assurance, monitoring, and budget assessment.
For a country that carries a significant share of the world’s tuberculosis burden and struggles to provide universal healthcare to its citizens, the question may ultimately be less about bringing the newest technology into healthcare and more about where that technology can help deliver expertise to meet the realities of people with the least access to it. — Danika Geronimo, Ateneo Research Communications
SOURCE: https://archium.ateneo.edu/gsb-pubs/87/
Harold Henrison Chiu, Bryan Christopher Lao, and Gloanne C. Adolor published their research, Cost-effectiveness evaluation of artificial intelligence-assisted chest radiograph interpretation for tuberculosis screening in rural health units in the Philippines, in the August 2026 issue of the BMC Health Services Research journal.
For interview requests and other information about the research, please contact Dr. Bryan Lao at bryan.christopher.lao@student.ateneo.edu and/or Dr. Harold Henrison Chiu at harold.henrison.chiu@student.ateneo.edu.
For other inquiries and concerns, please email media.research@ateneo.edu. Visit archium.ateneo.edu for more information about our latest research and innovations
Journal
BMC Health Services Research
Article Title
Cost-effectiveness evaluation of artificial intelligence-assisted chest radiograph interpretation for tuberculosis screening in rural health units in the Philippines
No comments:
Post a Comment