Are Mortality and Acute Morbidity in Patients Presenting With Nonspecific Complaints Predictable Using Routine Variables?

Abstract

Objectives: Patients presenting to the emergency department (ED) with nonspecific complaints are difficult to accurately triage, risk stratify, and diagnose. This can delay appropriate treatment. The extent to which key medical outcomes are at all predictable in these patients, and which (if any) predictors are useful, has previously been unclear. To investigate these questions, we tested an array of statistical and machine learning models in a large group of patients and estimated the predictability of mortality (which occurred in 6.6% of our sample of patients), acute morbidity (58%), and presence of acute infectious disease (28.2%).Methods: To investigate whether the best available tools can predict the three key outcomes, we fed data from a sample of 1,278 ED patients with nonspecific complaints into 17 state-of-the-art statistical and machine learning models. The patient sample stems from a diagnostic multicenter study with prospective 30-day follow-up conducted in Switzerland. Predictability of the three key medical outcomes was quantified by computing the area under the receiver operating characteristic curve (AUC) for each model. Results:The models performed at different levels but, on average, the predictability of the target outcomes ranged between 0.71 and 0.82. The better models clearly outperformed physicians' intuitive judgments of how ill patients looked (AUC = 0.67 for mortality, 0.65 for morbidity, and 0.60 for infectious disease).Conclusions: Modeling techniques can be used to derive formalized models that, on average, predict the outcomes of mortality, acute morbidity, and acute infectious disease in patients with nonspecific complaints with a level of accuracy far beyond chance. The models also predicted these outcomes more accurately than did physicians' intuitive judgments of how ill the patients look; however, the latter was among the small set of best predictors for mortality and acute morbidity. These results lay the groundwork for further refining triage and risk stratification tools for patients with nonspecific complaints. More research, informed by whether the goal of a model is high sensitivity or high specificity, is needed to develop readily applicable clinical decision support tools (e.g., decision trees) that could be supported by electronic health records.ACADEMIC EMERGENCY MEDICINE 2015;22:1155-1163© 2015 by the Society for Academic Emergency Medicine E mergency physicians (EPs) frequently encounter patients with nonspecific complaints. These patients tend to report general feelings of weakness, discomfort, fatigue, or dizziness, but not more specific complaints. 1 They are often undertriaged (i.e., their initial risk assessments are too low), and the severity of the illness causing their nonspecific complaints is often misjudged. 2 These systematic misjudgments can result in delays in definitive treatment of the underlying cause of their nonspecific chief complaints.Improved triage, rapid diagnosis, timely treatment, and appropriate disposition decisions to the proper...

Ecological Rationality: Fast-and-Frugal Heuristics for Managerial Decision Making under Uncertainty

“…As a result, these strategies may be easier to adopt, more transparent, and more effective. Decision aids of this sort have been successfully developed in other fields, including medicine (e.g., Green & Mehr, 1997;Jenny et al, 2015) and the military (e.g., Keller & Katsikopoulos, 2016). Finally, the less-is-more principle can also be applied in job interview processes, given that, under many realistic conditions, one good interviewer may be better than two or more because adding less capable interviewers is likely to detract from the performance of the best one (Fific & Gigerenzer, 2014).…”

How should nonspecific complaints be defined? Comment to: “nonspecific complaints (NSCs) in the emergency department”

“…The rationale to focus on these patients is the lack of a standardized work-up, the high use of resources, and the risk of adverse outcomes [5][6][7][8]. All publications originating from the prospective multicenter Basel Nonspecific Complaints (BANC) cohorts used the above definition of NSCs [9][10][11][12], but other studies have used varying criteria to define NSCs [13]. There is an inherent difference regarding inclusion criteria between the studies considered by the present systematic review, e.g., some of the included studies were retrospective, and one study [14] has used a post-hoc classification of nonspecific complaints [15].…”

Disagreements between emergency patients and physicians regarding chief complaint – Patient factors and prognostic implications

“…This group of symptoms can be labelled “nonspecific”, as there is a very broad differential diagnosis in these presentations 13,25,35 . It was shown that the diagnostic accuracy in non‐specific complaints varies and can be very low, 36,37 while morbidity and mortality are high 25,37‐41 . The lower rate of reporting of non‐specific complaints by physicians could be because of complaint replacement or filtering of such complaints.…”