ABSTRACT
PURPOSE: The primary aim of the present study was to test the feasibility of predicting diagnostic errors in mammography by merging radiologists' gaze behavior and image characteristics. A secondary aim was to investigate group-based and personalized predictive models for radiologists of variable experience levels. METHODS: The study was performed for the clinical task of assessing the likelihood of malignancy of mammographic masses. Eye-tracking data and diagnostic decisions for 40 cases were acquired from four Radiology residents and two breast imaging experts as part of an IRB-approved pilot study. Gaze behavior features were extracted from the eye-tracking data. Computer-generated and BIRADS images features were extracted from the images. Finally, machine learning algorithms were used to merge gaze and image features for predicting human error. Feature selection was thoroughly explored to determine the relative contribution of the various features. Group-based and personalized user modeling was also investigated. RESULTS: Machine learning can be used to predict diagnostic error by merging gaze behavior characteristics from the radiologist and textural characteristics from the image under review. Leveraging data collected from multiple readers produced a reasonable group model [area under the ROC curve (AUC) = 0.792 ± 0.030]. Personalized user modeling was far more accurate for the more experienced readers (AUC = 0.837 ± 0.029) than for the less experienced ones (AUC = 0.667 ± 0.099). The best performing group-based and personalized predictive models involved combinations of both gaze and image features. CONCLUSIONS: Diagnostic errors in mammography can be predicted to a good extent by leveraging the radiologists' gaze behavior and image content.
Subject(s)
Diagnostic Errors , Eye Movements , Image Processing, Computer-Assisted/methods , Mammography/methods , Radiology , Adult , Aged , Aged, 80 and over , Artificial Intelligence , Decision Support Techniques , Feasibility Studies , Humans , Internship, Nonmedical , Middle Aged , Observer VariationABSTRACT
CONTEXT: Pompholyx (called dyshidrosis by some) is one of the most common conditions and its immune response is presently poorly understood. CASE REPORT: We describe a 58 year old African American female with a clinical history of rheumatoid arthritis and type II diabetes who presented a chronic five-year, itchy vesicular/blistering rash involving her hands and feet. A lesional skin biopsy was taken for hematoxylin and eosin (H & E) analysis. In addition, a multicolor direct immunofluorescence (MDIF) and immunohistochemistry (IHC) studies were performed. The major findings to be reported were: the H & E examination revealed spongiotic dermatitis and pompholix. IHC and MDIF studies demonstrated focally deposits of positive CD45, CD3, CD8, anti myeloperoxidase (MPO), and anti-human IgE, C3C, C3D and anti-human-fibrinogen within the epidermal spongiotic process, as well as around the blood vessels surrounding the inflammatory process especially at the sweat glands and respective ductus. The patient began mycophenolate mofetil therapy, with successful clearing of the palms and soles. CONCLUSION: The significance of our findings indicates a complex immunological process including complement, MPO and T-cell immune response. In addition, possibly a secondary allergic process for the presence of IgE immune response and possibly aggravation by application of other medicines. Further immunological studies on pompholyx are needed. (Abreu-Velez AM, Pinto FJ, Howard MS. North Am J Med Sci 2009; 1: 117-120).
