Declaring Uncertainty: Using Quality Improvement Methods to Change the Conversation of Diagnosis

Abstract

BACKGROUND: Diagnostic uncertainty may be a sign that a patient’s working diagnosis is incorrect, but literature on proactively identifying diagnostic uncertainty is lacking. Using quality improvement methodologies, we aimed to create a process for identifying patients with uncertain diagnoses (UDs) on a pediatric inpatient unit and communicating about them with the interdisciplinary health care team. METHODS: Plan-do-study-act cycles were focused on interdisciplinary communication, structured handoffs, and integration of diagnostic uncertainty into the electronic medical record. Our definition of UD was as follows: “you wouldn’t be surprised if the patient had a different diagnosis that required a change in management.” The primary measure, which was tracked on an annotated run chart, was percentage agreement between the charge nurse and primary clinician regarding which patients had a UD. Secondary measures included the percentage of patient days during which patients had UDs. Data were collected 3 times daily by text message polls. RESULTS: Over 13 months, the percentage agreement between the charge nurse and primary clinician about which patients had UDs increased from a baseline of 19% to a median of 84%. On average, patients had UDs during 11% of patient days. CONCLUSIONS: We created a novel and effective process to improve shared recognition of patients with diagnostic uncertainty among the interdisciplinary health care team, which is an important first step in improving care for these patients.

Prevalence and Characteristics of Diagnostic Error in Pediatric Critical Care: A Multicenter Study*

“…Our study shows that an atypical presentation (clinical findings that do not easily fit a known illness script) and diagnostic uncertainty on admission can potentially be used as markers to identify critically ill children at risk for diagnostic error at the start of the diagnostic process, where diagnostic decision-making may be more amenable to intervention. This finding also supports efforts to improve diagnosis focusing on helping clinicians better recognize, communicate, and address diagnostic uncertainty (40–42).…”

Developing a machine learning model to detect diagnostic uncertainty in clinical documentation

“…Prior quality improvement work at our institution led to the development of an uncertain diagnosis (UD) label in our electronic health record (EHR) 15 . Without a firmly established definition in the literature, the team's operational definition for using the UD label in clinical practice has evolved over time, and currently is “the patient's symptoms are not fully explained by the working diagnosis.” This definition was one of several proposed definitions early in the quality improvement work but was used with several complementary definitions, including “you would not be surprised if the patient had a different diagnosis that required a change in management,” during our study period.…”

“…In the spirit of developing more systematic methods for identifying diagnostic uncertainty, this study aims to identify linguistic indicators of diagnostic uncertainty in clinical documentation by leveraging a unique population of hospitalized children prospectively identified by clinicians as having uncertain diagnoses. 15 Our hypothesis was that distinct linguistic patterns associated with uncertainty would be identified through natural language processing and linguistic analyses and enable the development of a machine learning model capable of detecting diagnostic uncertainty in clinical documentation. Natural language processing (NLP) is a combination of linguistics, computer science, and artificial intelligence and is the means by which computer programs can process and analyze unstructured text.…”

What the COVID-19 Pandemic Teaches Us About Pediatric Iatrogenic Risk

“…7 Diagnostic Error as a Source of Iatrogenic Harm to Children Although highlighted during the COVID-19 pandemic, diagnostic error is not new and is estimated to account for 5% to 15% of diagnoses. 9,10 Previous work has demonstrated that a significant number of admissions to pediatric intensive care units (PICUs) were due to iatrogenic events, with diagnostic error being identified as one area with potential for improvement. 11,12 Furthermore, diagnostic error has been identified as a priority research topic by the Children's Hospitals' Solutions for Patient Safety Network, with experts noting a lack of large, high-quality pediatric studies on the subject.…”