Integrative urban AI to expand coverage, access, and equity of urban data.

We consider the use of AI techniques to expand the coverage, access, and equity of urban data. We aim to enable holistic research on city dynamics, steering AI research attention away from profit-oriented, societally harmful applications (e.g., facial recognition) and toward foundational questions in mobility, participatory governance, and justice. By making available high-quality, multi-variate, cross-scale data for research, we aim to link the macrostudy of cities as complex systems with the reductionist view of cities as an assembly of independent prediction tasks. We identify four research areas in AI for cities as key enablers: interpolation and extrapolation of spatiotemporal data, using NLP techniques to model speech- and text-intensive governance activities, exploiting ontology modeling in learning tasks, and understanding the interaction of fairness and interpretability in sensitive contexts.

Computed tomographic coronary angiographic assessment of high-risk coronary anatomy in patients with suspected coronary artery disease and intermediate pretest probability.

BACKGROUND: It is unclear if computed tomographic coronary angiography (CTA), an evolving technique for the evaluation of coronary artery disease (CAD), can identify patients with high-risk coronary anatomy. METHODS: Among patients referred for invasive angiography at Hamilton Health Sciences (Hamilton, Ontario, Canada), those with an intermediate pretest probability (25%-60% likelihood of a significant stenosis) were prospectively identified using a multivariate risk score and were studied on a 64-detector Toshiba Aquilion scanner (Toshiba Medical Systems, Tokyo, Japan) before invasive angiography. Patients with high-risk anatomy (left main, 3-vessel CAD, or 2-vessel CAD involving the proximal left anterior descending artery) or at least 1 significant stenosis were identified on CTA and invasive angiography, and the results of these modalities were compared on a per patient basis. RESULTS: Eighty patients were enrolled in the study (mean age 56 +/- 9 years, male-female ratio 43:37). Nondiagnostic scan results were obtained in 5 patients (6%). By CTA, 13 patients had high-risk anatomy and 31 patients had at least 1 significant stenosis. For the per patient detection of high-risk anatomy, CTA had 100% sensitivity (95% CI 69%-100%), 95% specificity (95% CI 86%-95%), a positive likelihood ratio of 18.0 (95% CI 6.4-50.3), and a negative likelihood ratio of 0.05 (95% CI 0-0.072). Revascularization was performed in 100% of patients with high-risk anatomy on CTA, 83% with at least 1 significant stenosis on CTA, and 0% without a significant stenosis on CTA. CONCLUSION: In appropriately selected patients, CTA is a highly sensitive and specific technique for the detection of high-risk anatomy and maybe a valuable method for noninvasive risk stratification.