Avoiding premature closure and reaching diagnostic accuracy: some key predictive factors

Krupat, Edward; Wormwood, Jolie B.; Schwartzstein, Richard M.; Richards, Jeremy B.

doi:10.1111/medu.13382

Cited by 29 publications

(18 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A diagnostic decision support system (DDSS) that supports the diagnostic process by generating differential diagnoses from observations provided [ 3 ] is expected to reduce diagnostic errors by reducing cognitive biases and reinforcing physicians’ knowledge. It is said that generating potential diagnoses is a rate-limiting step of differential diagnosis for novice diagnosticians [ 2 ], and their diagnostic accuracy was reported to be associated with the number of generated diagnoses [ 4 ]. Besides, using a simple differential diagnosis checklist, which could remind users of some missed diagnoses, was reported to improve the diagnostic accuracy of medical students [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

Effects of a Differential Diagnosis List of Artificial Intelligence on Differential Diagnoses by Physicians: An Exploratory Analysis of Data from a Randomized Controlled Study

Harada

Katsukura

Kawamura

et al. 2021

IJERPH

View full text Add to dashboard Cite

A diagnostic decision support system (DDSS) is expected to reduce diagnostic errors. However, its effect on physicians’ diagnostic decisions remains unclear. Our study aimed to assess the prevalence of diagnoses from artificial intelligence (AI) in physicians’ differential diagnoses when using AI-driven DDSS that generates a differential diagnosis from the information entered by the patient before the clinical encounter on physicians’ differential diagnoses. In this randomized controlled study, an exploratory analysis was performed. Twenty-two physicians were required to generate up to three differential diagnoses per case by reading 16 clinical vignettes. The participants were divided into two groups, an intervention group, and a control group, with and without a differential diagnosis list of AI, respectively. The prevalence of physician diagnosis identical with the differential diagnosis of AI (primary outcome) was significantly higher in the intervention group than in the control group (70.2% vs. 55.1%, p < 0.001). The primary outcome was significantly >10% higher in the intervention group than in the control group, except for attending physicians, and physicians who did not trust AI. This study suggests that at least 15% of physicians’ differential diagnoses were affected by the differential diagnosis list in the AI-driven DDSS.

show abstract

Section: Introductionmentioning

confidence: 99%

Effects of a Differential Diagnosis List of Artificial Intelligence on Differential Diagnoses by Physicians: An Exploratory Analysis of Data from a Randomized Controlled Study

Harada

Katsukura

Kawamura

et al. 2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…Previous studies on the diagnostic accuracy of clinical examination have found the performance of experienced physicians and students to be comparable [6]. Expert physicians are more often affected by multiple cognitive biases, such as confirmatory bias and premature closure, compared to students, who remain more open to new hypotheses and persist in collecting data [25,26]. Interestingly, while the diagnostic accuracy for individual physicians can be as low as 62.5%, there is a visible increase as the number of physicians involved increases (up to 85.6% for groups of nine physicians) [27].…”

Section: Discussionmentioning

confidence: 99%

A Bayesian Network Analysis of the Diagnostic Process and its Accuracy to Determine How Clinicians Estimate Cardiac Function in Critically Ill Patients: Prospective Observational Cohort Study

et al. 2019

View full text Add to dashboard Cite

BackgroundHemodynamic assessment of critically ill patients is a challenging endeavor, and advanced monitoring techniques are often required to guide treatment choices. Given the technical complexity and occasional unavailability of these techniques, estimation of cardiac function based on clinical examination is valuable for critical care physicians to diagnose circulatory shock. Yet, the lack of knowledge on how to best conduct and teach the clinical examination to estimate cardiac function has reduced its accuracy to almost that of “flipping a coin.”ObjectiveThe aim of this study was to investigate the decision-making process underlying estimates of cardiac function of patients acutely admitted to the intensive care unit (ICU) based on current standardized clinical examination using Bayesian methods.MethodsPatient data were collected as part of the Simple Intensive Care Studies-I (SICS-I) prospective cohort study. All adult patients consecutively admitted to the ICU with an expected stay longer than 24 hours were included, for whom clinical examination was conducted and cardiac function was estimated. Using these data, first, the probabilistic dependencies between the examiners’ estimates and the set of clinically measured variables upon which these rely were analyzed using a Bayesian network. Second, the accuracy of cardiac function estimates was assessed by comparison to the cardiac index values measured by critical care ultrasonography.ResultsA total of 1075 patients were included, of which 783 patients had validated cardiac index measurements. A Bayesian network analysis identified two clinical variables upon which cardiac function estimate is conditionally dependent, namely, noradrenaline administration and presence of delayed capillary refill time or mottling. When the patient received noradrenaline, the probability of cardiac function being estimated as reasonable or good P(ER,G) was lower, irrespective of whether the patient was mechanically ventilated (P[ER,G|ventilation, noradrenaline]=0.63, P[ER,G|ventilation, no noradrenaline]=0.91, P[ER,G|no ventilation, noradrenaline]=0.67, P[ER,G|no ventilation, no noradrenaline]=0.93). The same trend was found for capillary refill time or mottling. Sensitivity of estimating a low cardiac index was 26% and 39% and specificity was 83% and 74% for students and physicians, respectively. Positive and negative likelihood ratios were 1.53 (95% CI 1.19-1.97) and 0.87 (95% CI 0.80-0.95), respectively, overall.ConclusionsThe conditional dependencies between clinical variables and the cardiac function estimates resulted in a network consistent with known physiological relations. Conditional probability queries allow for multiple clinical scenarios to be recreated, which provide insight into the possible thought process underlying the examiners’ cardiac function estimates. This information can help develop interactive digital training tools for students and physicians and contribute toward the goal of further improving the diagnostic accuracy of clinical examination in ICU ...

show abstract

“…Functional MRI studies of clinicians during this process showed that highly salient diagnostic information, reducing uncertainty about the diagnosis, rapidly decreased monitoring activity in the frontoparietal attentional network and may contribute to premature diagnostic closure, an important cause of diagnostic errors (Melo et al, 2017). This may be considered a form of diagnosis or recognition related PE signal suppression analogous to the well know phenomenon of repetitive suppression (Blissett & Sibbald, 2017;Bunzeck & Thiel, 2016;Krupat et al, 2017).…”

Section: Core Features Of the Predictive Brain Modelmentioning

confidence: 99%

The predictive brain model in diagnostic reasoning

Lim

2021

TAPS

View full text Add to dashboard Cite

Introduction: Clinical diagnosis is a pivotal and highly valued skill in medical practice. Most current interventions for teaching and improving diagnostic reasoning are based on the dual process model of cognition. Recent studies which have applied the popular dual process model to improve diagnostic performance by “Cognitive De-biasing” in clinicians have yielded disappointing results. Thus, it may be appropriate to also consider alternative models of cognitive processing in the teaching and practice of clinical reasoning. Methods: This is critical-narrative review of the predictive brain model. Results: The theory of predictive brains is a general, unified and integrated model of cognitive processing based on recent advances in the neurosciences. The predictive brain is characterised as an adaptive, generative, energy-frugal, context-sensitive action-orientated, probabilistic, predictive engine. It responds only to predictive errors and learns by iterative predictive error management, processing and hierarchical neural coding. Conclusion: The default cognitive mode of predictive processing may account for the failure of de-biasing since it is not thermodynamically frugal and thus, may not be sustainable in routine practice. Exploiting predictive brains by employing language to optimise metacognition may be a way forward

show abstract

Avoiding premature closure and reaching diagnostic accuracy: some key predictive factors

Cited by 29 publications

References 36 publications

Effects of a Differential Diagnosis List of Artificial Intelligence on Differential Diagnoses by Physicians: An Exploratory Analysis of Data from a Randomized Controlled Study

Effects of a Differential Diagnosis List of Artificial Intelligence on Differential Diagnoses by Physicians: An Exploratory Analysis of Data from a Randomized Controlled Study

A Bayesian Network Analysis of the Diagnostic Process and its Accuracy to Determine How Clinicians Estimate Cardiac Function in Critically Ill Patients: Prospective Observational Cohort Study

The predictive brain model in diagnostic reasoning

Contact Info

Product

Resources

About