Computer-aided detection in computed tomography colonography: current status and problems with detection of early colorectal cancer

Automation bias: a systematic review of frequency, effect mediators, and mitigators

Automation bias (AB)--the tendency to over-rely on automation--has been studied in various academic fields. Clinical decision support systems (CDSS) aim to benefit the clinical decision-making process. Although most research shows overall improved performance with use, there is often a failure to recognize the new errors that CDSS can introduce. With a focus on healthcare, a systematic review of the literature from a variety of research fields has been carried out, assessing the frequency and severity of AB, the effect mediators, and interventions potentially mitigating this effect. This is discussed alongside automation-induced complacency, or insufficient monitoring of automation output. A mix of subject specific and freetext terms around the themes of automation, human-automation interaction, and task performance and error were used to search article databases. Of 13 821 retrieved papers, 74 met the inclusion criteria. User factors such as cognitive style, decision support systems (DSS), and task specific experience mediated AB, as did attitudinal driving factors such as trust and confidence. Environmental mediators included workload, task complexity, and time constraint, which pressurized cognitive resources. Mitigators of AB included implementation factors such as training and emphasizing user accountability, and DSS design factors such as the position of advice on the screen, updated confidence levels attached to DSS output, and the provision of information versus recommendation. By uncovering the mechanisms by which AB operates, this review aims to help optimize the clinical decision-making process for CDSS developers and healthcare practitioners.

Efficacy of computer-aided diagnosis in lung cancer screening with low-dose spiral computed tomography: receiver operating characteristic analysis of radiologists' performance

PURPOSE

The aim of this study was to evaluate the efficacy of a computer-aided diagnosis (CAD) system we developed that can also respond to subsolid nodules, for lung cancer screening using low-dose spiral computed tomography (LDCT).

MATERIALS AND METHODS

The institutional review board approved this study. A total of 30 positive cases (including 15 lung cancer cases) that needed further examination and 30 negative cases were used for the observer performance study. Three thoracic radiologists, five general radiologists, and three residents participated in this study in which they first read the original CT image on its own and then reassessed the same image with the assistance of CAD. Radiologists' performance was evaluated using receiver operating characteristic (ROC) analysis.

RESULTS

The Az values without and with CAD were 0.872 and 0.910 for the thoracic radiologists, 0.864 and 0.924 for general radiologists, and 0.875 and 0.837 for residents, respectively. The detection accuracy improved significantly for the thoracic and general radiologists with our CAD system; however, no statistically significant difference between without or with CAD was seen for residents.

CONCLUSION

This CAD system is beneficial in the detection of pulmonary nodules on LDCT when used by experienced radiologists.

Flat lesions in CT colonography

Flat lesions have been a source of controversy because of concerns that CT colonography (CTC) is insensitive in detecting these lesions, yet they may harbor a high incidence of advanced neoplasia. The wide variation in the reported incidence of flat lesions may in part be due to the lack of a uniform definition of "flat", and in fact in many prior reports the inclusion criteria for flat are not even clearly specified. Emphasis on the more recent CTC literature suggests that when limited the target lesion to neoplasia (adenomas or adenocarcinoma), the incidence of flat lesions is low and most can be detected by CTC. Using fecal tagging and careful attention to the proper methods of searching for flat lesions with both 3D and 2D techniques can maximize the detection of flat lesions at CTC. Computer-aided detection may be helpful.