Treatment recommendations made by WFO and the tumor board were highly concordant for breast cancer cases examined. Breast cancer stage and patient age had significant influence on concordance, while receptor status alone did not. This study demonstrates that the AI clinical decision-support system WFO may be a helpful tool for breast cancer treatment decision making, especially at centers where expert breast cancer resources are limited.
New rapid growth economies, urbanization, health systems crises and “big data” are causing fundamental changes in social structures and systems including health. These forces for change have significant consequences for occupational and environmental medicine and will challenge the specialty to think beyond workers and workplaces as the principal locus of innovation for health and performance. These trends are placing great emphasis on upstream strategies for addressing the complex systems dynamics of the social determinants of health. The need to engage systems in communities for healthier workforces is a shift in orientation from worker and workplace centric to citizen and community centric. This change for occupational and environmental medicine requires extending systems approaches in the workplace to communities which are systems of systems and which require different skills, data, tools and partnerships.
PURPOSE The aim of the current study was to assess treatment concordance and adherence to National Comprehensive Cancer Network breast cancer treatment guidelines between oncologists and an artificial intelligence advisory tool. PATIENTS AND METHODS Study cases of patients (N = 1,977) who were at high risk for recurrence or who had metastatic disease and cell types for which the advisory tool was trained were obtained from the Chinese Society for Clinical Oncology cancer database (2012 to 2017). A cross-sectional observational study was performed to examine treatment concordance and guideline adherence among an artificial intelligence advisory tool and 10 oncologists with varying expertise—three fellows, four attending physicians, and three chief physicians. In a blinded fashion, each oncologist provided treatment advice on an average of 198 cases and the advisory tool on all cases (N = 1,977). Results are reported as rates and logistic regression odds ratios. RESULTS Concordance for the recommended treatment was 0.56 for all physicians and higher for fellows compared with chief and attending physicians (0.68 v 0.54; 0.49; P = .001). Concordance differed by hormone receptor subtype–TNM stage, with the lowest for hormone receptor–positive human epidermal growth factor receptor 2/neu-positive cancers (0.48) and highest for triple-negative breast cancers (0.71) across most TNM stages. Adherence to National Comprehensive Cancer Network guidelines was higher for oncologists compared with the advisory tool (0.96 v 0.82; P < .003) and lower for fellows compared with attending physicians (0.93 v 0.98; 0.96; P = .04). CONCLUSION Study findings reflect a complex breast cancer case mix, the limits of medical knowledge regarding optimum treatment, clinician practice patterns, and use of a tool that reflects expertise from one cancer center. Additional research in different practice settings is needed to understand the tool’s scalability and its impact on treatment decisions and clinical and health services outcomes.
A volunteer population of 266 current and former railroad workers was examined with posteroanterior and oblique chest roentgenograms, and a comprehensive occupational smoking history. Seventy-five percent of participants were over the age of 60, and 80% had fewer than 10 years of railroad-related asbestos exposure. Roentgenographic evidence of asbestosis was found in only six workers (2%), whereas 20% had one or more pleural changes. Radiological abnormalities were related to latency period, age, and occupation, but not to smoking habit. While selection factors qualify the results of this study, the findings support the exposure and suggest a past and future history of asbestos mortality and morbidity among steam era railway workers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.