AI-clinician collaboration via disagreement prediction: A decision pipeline and retrospective analysis of real-world radiologist-AI interactions.

Clinical decision support tools can improve diagnostic performance or reduce variability, but they are also subject to post-deployment underperformance. Although using AI in an assistive setting offsets many concerns with autonomous AI in medicine, systems that present all predictions equivalently fail to protect against key AI safety concerns. We design a decision pipeline that supports the diagnostic model with an ecosystem of models, integrating disagreement prediction, clinical significance categorization, and prediction quality modeling to guide prediction presentation. We characterize disagreement using data from a deployed chest X-ray interpretation aid and compare clinician burden in this proposed pipeline to the diagnostic model in isolation. The average disagreement rate is 6.5%, and the expected burden reduction is 4.8%, even if 5% of disagreements on urgent findings receive a second read. We conclude that, in our production setting, we can adequately balance risk mitigation with clinician burden if disagreement false positives are reduced.

Pulmonary Health Effects of Indoor Volatile Organic Compounds-A Meta-Analysis.

Volatile organic compounds (VOCs) are commonly found in consumer products, including furniture, sealants and paints. Thus, indoor VOCs have become a public health concern, especially in high-income countries (HICs), where people spend most of their time indoors, and indoor and outdoor air exchange is minimal due to a lack of ventilation. VOCs produce high levels of reaction with the airway epithelium and mucosa membrane and is linked with pulmonary diseases. This paper takes a stock of the literature to assess the strength of association (measured by effect size) between VOCs and pulmonary diseases with the focus on asthma and its related symptoms by conducting a meta-analysis. The literature was searched using the PubMed database. A total of 49 studies that measured VOCs or VOC types and pulmonary health outcomes were included in the analysis. The results of these studies were tabulated, and standard effect size of each study was computed. Most studies were conducted in high-income countries, including France (n = 7), Japan (n = 7) and the United States (n = 6). Our analysis suggests that VOCs have a medium-sized effect on pulmonary diseases, including the onset of asthma (effect size (or Cohen's d) ~0.37; 95% confidence interval (CI) = 0.25-0.49; n = 23) and wheezing (effective size ~0.26; 95% CI = 0.10-0.42; n = 10). The effect size also varied by country, age and disease type. Multiple stakeholders must be engaged in strategies to mitigate and manage VOC exposure and its associated pulmonary disease burden.