Difficult diagnosis in the ICU: making the right call but beware uncertainty and bias

Abstract

Dealing with an uncertain or missed diagnosis is commonplace in the intensive care unit setting. Affected patients are subject to a potential decrease in quality of care and a greater risk of a poor outcome. The diagnostic process is a complex task that starts with information gathering, followed by integration and interpretation of data, hypothesis generation and, finally, confirmation of a (hopefully correct) diagnosis. This may be particularly challenging in the patient who is critically ill where a good history may not be forthcoming and/or clinical, laboratory and imaging features are non-specific. The aim of this narrative review is to analyse and describe common causes of diagnostic error in the intensive care unit, highlighting the multiple types of cognitive bias, and to suggest a diagnostic framework. To inform this review, we performed a literature search to identify relevant articles, particularly those pertinent to unclear diagnoses in patients who are critically ill. Clinicians should be cognisant as to how they formulate diagnoses and utilise debiasing strategies. Multidisciplinary teamwork and more time spent with the patient, supported by effective and efficient use of electronic healthcare records and decision support resources, is likely to improve the quality of the diagnostic process, patient care and outcomes.

Clinical tests for confirming tracheal intubation or excluding oesophageal intubation: a diagnostic test accuracy systematic review and meta‐analysis

“…The performance characteristics described in the two articles reporting this technique appear to be similar to that of the oesophageal detector device. However, this is based on only two studies, both conducted in non-human and anchoring [68,69]. as the majority of the included studies are old, while the small number of studies did not allow us to quantitatively test for it.…”

“…When the clinician finally examines the capnograph, their perception has already been framed wrongly by preconceived notions that the tube has been placed correctly. Thus, their pre‐test confidence is high and if the capnograph does not show sustained exhaled carbon dioxide there is an increased risk of erroneous interpretation of the capnograph through confirmation bias, premature closure and anchoring [68, 69].…”

Prediction of Complications and Prognostication in Perioperative Medicine: A Systematic Review and PROBAST Assessment of Machine Learning Tools

“…Progress has been made in understanding the limitations of human cognition, but significant gaps still remain. 147 We therefore recommend adopting a human-centered design approach in conjunction with a continuous artificial intelligence development cycle with the aim of enhancing clinician performance.…”

Global Dissipative Examination of Delayed Memristive Inertial Neural Networks with Uncertain Parameters

“…So, it is vital to study the time delay of the system with the involvement of uncertain in the parameters of the system. As an example of practical, the difficult diagnosis in the ICU due to the uncertain or missed diagnosis was investigated in [8] which impacts the importance. Stability of the memristor based delayed fractional-order Cohen-Grosberg NNs with time delays and uncertainities are discussed in [9].…”