Improving the radiologist-CAD interaction: designing for appropriate trust.

Computer-aided diagnosis (CAD) has great potential to improve radiologists' diagnostic performance. However, the reported performance of the radiologist-CAD team is lower than what might be expected based on the performance of the radiologist and the CAD system in isolation. This indicates that the interaction between radiologists and the CAD system is not optimal. An important factor in the interaction between humans and automated aids (such as CAD) is trust. Suboptimal performance of the human-automation team is often caused by an inappropriate level of trust in the automation. In this review, we examine the role of trust in the radiologist-CAD interaction and suggest ways to improve the output of the CAD system so that it allows radiologists to calibrate their trust in the CAD system more effectively. Observer studies of the CAD systems show that radiologists often have an inappropriate level of trust in the CAD system. They sometimes under-trust CAD, thereby reducing its potential benefits, and sometimes over-trust it, leading to diagnostic errors they would not have made without CAD. Based on the literature on trust in human-automation interaction and the results of CAD observer studies, we have identified four ways to improve the output of CAD so that it allows radiologists to form a more appropriate level of trust in CAD. Designing CAD systems for appropriate trust is important and can improve the performance of the radiologist-CAD team. Future CAD research and development should acknowledge the importance of the radiologist-CAD interaction, and specifically the role of trust therein, in order to create the perfect artificial partner for the radiologist. This review focuses on the role of trust in the radiologist-CAD interaction. The aim of the review is to encourage CAD developers to design for appropriate trust and thereby improve the performance of the radiologist-CAD team.

Visual metaphors on anaesthesia monitors do not improve anaesthetists' performance in the operating theatre.

BACKGROUND: Previous research using a metaphorical anaesthesia monitor, where dimensions of rectangles proportionally represent 30 patient variable values, showed improved performance in diagnosing adverse events compared with the standard monitor. Steady-state values were represented by a frame around each rectangle. We developed a similar metaphorical anaesthesia interface, but instead of presenting four relatively simple complications, we presented 10 complications of various levels of difficulty. Our simplified monitor presented variables that anaesthetists and trainees suggested as being essential for diagnosis. METHODS: Thirty-two anaesthetists and anaesthesia trainees participated in the monitoring task. Three types of monitors were presented: standard monitor, metaphorical monitor, and metaphorical monitor with trend arrows emphasizing the direction of change. The subjects were presented with screenshots of the three monitor types displaying anaesthesia-related complications. They were asked to indicate treatment method and diagnosis for the displayed complication. RESULTS: No significant differences were found in time to diagnosis and accuracy between the metaphorical and standard monitor. There were also no differences between trend and no-trend monitors. Forty per cent of the complications were identified incorrectly. CONCLUSIONS: Visual metaphors on anaesthesia monitors do not improve anaesthetists' performance in the operating theatre. Since all complications in this study were identifiable based on monitor values alone, it seems feasible to develop a decision support system (DSS) based on these values. We suggest that a DSS could support the anaesthetist by calling attention to diagnoses that may not be considered.

Testing the effects of hypnotics on memory via the telephone: fact or fiction?

The two benzodiazapines used in this experiment, namely midazolam and flunitrazepam, have both been shown to have effects on memory processing in laboratory studies. In spite of the potential hazards involved in real life testing, it should be possible to replicate such findings in everyday environments and it is argued that a successful replication would be a very meaningful extension to the existing laboratory data. The present study was successful in producing significant "hangover" effects in healthy volunteers using a novel "user-friendly" telephone testing technique. Compared to placebo, the two hypnotics reduced speed of processing in tasks which required retrieval from long-term semantic memory (semantic verification) and the manipulation of material in working memory (syntactic reasoning). We suggest that this new method offers the potential for carrying out large-scale psychopharmacological studies with real patients and achieves a meaningful step forward in the search for ecological validity.