Problem framing is critical to developing risk prediction models because all subsequent development work and evaluation takes place within the context of how a problem has been framed and explicit documentation of framing choices makes it easier to compare evaluation metrics between published studies. In this work, we introduce the basic concepts of framing, including prediction windows, observation windows, window shifts and event-triggers for a prediction that strongly affects the risk of clinician fatigue caused by false positives. Building on this, we apply four different framing structures to the same generic dataset, using a sepsis risk prediction model as an example, and evaluate how framing affects model performance and learning. Our results show that an apparently good model with strong evaluation results in both discrimination and calibration is not necessarily clinically usable. Therefore, it is important to assess the results of objective evaluations within the context of more subjective evaluations of how a model is framed.

BackgroundPoint-of-care ultrasound (PoCUS) is spreading throughout Emergency Medicine, Critical Care and Pre-hospital Care. However, there is an underlying inherited conflict with the established specialties performing comprehensive examinations. It has been stated that PoCUS is disruptive innovation. If this is true the definition might open up for a new perspective on differentiating comprehensive ultrasound from PoCUS. PoCUS in the light of disruptive innovation is a different perspective on ultrasound that has not before been academically scrutinized.MethodsIn this paper we investigate if PoCUS is in fact disruptive innovation. This is done by comparative analysis with the point of departure in disruptive innovation theory known from the business world.ResultsWe find that a disruptive innovation process is happening. This new knowledge allows us to put forward advice for the stakeholders in the field of ultrasound. It also allows us to challenge the conventional pyramid of expertise used to describe different types of ultrasound. The perspective of this paper is mutual understanding of similarities and differences between conventional and point-of-care ultrasound. Only with this understanding the stakeholders can collaborate and use the full spectrum of ultrasound for the benefit of the patient.

Background: Point-of-Care ultrasound (POCUS) changes the management in specific groups of patients in the Emergency Department (ED). It seems intuitive that POCUS holds an unexploited potential on a wide variety of patients. However, little is known about the effect of ultrasound on the broad spectrum of unselected patients in the ED. This study aimed to identify the effect on the clinical management if POCUS was applied on unselected patients. Secondarily the study aimed to identify predictors of ultrasound changing management. Methods: This study was a blinded observational single center trial. A basic whole body POCUS protocol was performed in extension to the physical examination. The blinded treating physicians were interviewed about the presumptive diagnosis and plan for the patient. Subsequently the physicians were unblinded to the POCUS results and asked to choose between five options regarding the benefit from POCUS results. Results: A total of 403 patients were enrolled in this study. The treating physicians regarded POCUS examinations influence on the diagnostic workup or treatment as following: 1) No new information: 249 (61.8%), 2) No further action: 45 (11.2%), 3) Further diagnostic workup needed: 52 (12.9%), 4) Presumptive diagnosis confirmed 38 (9.4%), and 5) Immediate treatment needed: 19 (4.7%). Predictors of beneficial ultrasound were: (a) triage > 1, (b) patient comorbidities (cardiac disease, hypertension or lung disease), or (c) patients presenting with abdominal pain, dyspnea, or syncope. Conclusion: POCUS was found to be potentially beneficial in 27.0% of all patients. High triage score, known cardiac disease, hypertension, pulmonary diseases, a clinical presentation with abdominal pain, dyspnea, or syncope are predictors of this. Future research should focus on patient-important outcomes when applying POCUS on these patients.