Background: Timely identification of deteriorating COVID-19 patients is needed to guide changes in clinical management and admission to intensive care units (ICUs). There is significant concern... Show moreBackground: Timely identification of deteriorating COVID-19 patients is needed to guide changes in clinical management and admission to intensive care units (ICUs). There is significant concern that widely used Early warning scores (EWSs) underestimate illness severity in COVID-19 patients and therefore, we developed an early warning model specifically for COVID-19 patients. Methods: We retrospectively collected electronic medical record data to extract predictors and used these to fit a random forest model. To simulate the situation in which the model would have been developed after the first and implemented during the second COVID-19 `wave' in the Netherlands, we performed a temporal validation by splitting all included patients into groups admitted before and after August 1, 2020. Furthermore, we propose a method for dynamic model updating to retain model performance over time. We evaluated model discrimination and calibration, performed a decision curve analysis, and quantified the importance of predictors using SHapley Additive exPlanations values. Results: We included 3514 COVID-19 patient admissions from six Dutch hospitals between February 2020 and May 2021, and included a total of 18 predictors for model fitting. The model showed a higher discriminative performance in terms of partial area under the receiver operating characteristic curve (0.82 [0.80-0.84]) compared to the National early warning score (0.72 [0.69-0.74]) and the Modified early warning score (0.67 [0.65-0.69]), a greater net benefit over a range of clinically relevant model thresholds, and relatively good calibration (intercept = 0.03 [- 0.09 to 0.14], slope = 0.79 [0.73-0.86]). Conclusions: This study shows the potential benefit of moving from early warning models for the general inpatient population to models for specific patient groups. Further (independent) validation of the model is needed. Show less
Background: Reporting individual clinical and patient-reported outcomes to patients during consultations may add to patients' disease knowledge and activation and stimulate Shared Decision Making ... Show moreBackground: Reporting individual clinical and patient-reported outcomes to patients during consultations may add to patients' disease knowledge and activation and stimulate Shared Decision Making (SDM). These outcomes can be presented over time in a clear way by the means of dashboarding. We aimed to systematically develop a Chronic Kidney Disease (CKD) dashboard designed to support consultations, test its usability and explore conditions for optimal use in practice. Methods: For development a participatory approach with patients and healthcare professionals (HCPs) from three hospitals was used. Working groups and patient focus groups were conducted to identify needs and inform the dashboard's design. Usability was tested in patient interviews. A focus group with HCPs was held to identify conditions for optimal use of the dashboard in daily practice. Results: A dashboard was developed for CKD patients stage 3b-4 visualizing both clinical and patient-reported outcomes over time for use during consultations and accessible for patients at home. Both HCPs and patients indicated that the dashboard can: motivate patients in their treatment by providing feedback on outcomes over time; improve consultation conversations by enhanced preparation of both HCPs and patients; better inform patients, thereby facilitating shared decision making. HCPs and patients both stated that setting a topic agenda for the consultation together is important in effectively discussing the dashboard during consultations. Moreover, the dashboard should not dominate the conversation. Lastly, findings of the usability tests provided design requirements for optimal user-friendliness and clarity. Conclusions: Dashboarding can be a valuable way of reporting individual outcome information to patients and their clinicians as findings suggest it may stimulate patient activation and facilitate decision making. Co-creation with patients and HCPs was essential for successful development of the dashboard. Gained knowledge from the co-creation process can inform others wishing to develop similar digital tools for use in clinical practice. Show less