Search

Background: Digitalization is currently revolutionizing health care worldwide. A promising technology in this context is artificial intelligence (AI). The application of AI can support health care providers in their daily work in various ways. The integration of AI is particularly promising in clinical decision support systems (CDSSs). While the opportunities of this technology are numerous, the problems should not be overlooked., Objective: This study aimed to identify challenges and barriers in the context of AI-based CDSSs from the perspectives of experts across various disciplines., Methods: Semistructured expert interviews were conducted with different stakeholders. These included representatives of patients, physicians and caregivers, developers of AI-based CDSSs, researchers (studying AI in health care and social and health law), quality management and quality assurance representatives, a representative of an ethics committee, a representative of a health insurance fund, and medical product consultants. The interviews took place on the web and were recorded, transcribed, and subsequently subjected to a qualitative content analysis based on the method by Kuckartz. The analysis was conducted using MAXQDA software. Initially, the problems were separated into "general," "development," and "clinical use." Finally, a workshop within the project consortium served to systematize the identified problems., Results: A total of 15 expert interviews were conducted, and 309 expert statements with reference to problems and barriers in the context of AI-based CDSSs were identified. These emerged in 7 problem categories: technology (46/309, 14.9%), data (59/309, 19.1%), user (102/309, 33%), studies (17/309, 5.5%), ethics (20/309, 6.5%), law (33/309, 10.7%), and general (32/309, 10.4%). The problem categories were further divided into problem areas, which in turn comprised the respective problems., Conclusions: A large number of problems and barriers were identified in the context of AI-based CDSSs. These can be systematized according to the point at which they occur ("general," "development," and "clinical use") or according to the problem category ("technology," "data," "user," "studies," "ethics," "law," and "general"). The problems identified in this work should be further investigated. They can be used as a basis for deriving solutions to optimize development, acceptance, and use of AI-based CDSSs., International Registered Report Identifier (irrid): RR2-10.2196/preprints.62704., (©Godwin Denk Giebel, Pascal Raszke, Hartmuth Nowak, Lars Palmowski, Michael Adamzik, Philipp Heinz, Marianne Tokic, Nina Timmesfeld, Frank Brunkhorst, Jürgen Wasem, Nikola Blase. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 03.02.2025.)

Purpose: There is evidence that lower activity of the RAF/MEK/ERK network is associated with positive outcomes in mild and moderate courses of COVID-19. The effect of this cascade in COVID-19 sepsis is still undetermined. Therefore, we tested the hypothesis that activity of the RAF/MEK/ERK network in COVID-19-induced sepsis is associated with an impact on 30-day survival., Methods: We used biomaterial from 81 prospectively recruited patients from the multicentric CovidDataNet.NRW-study cohort (German clinical trial registry: DRKS00026184) with their collected medical history, vital signs, laboratory parameters, microbiological findings and patient outcome. ERK activity was measured by evaluating ERK phosphorylation using a Proximity Ligation Assay., Results: An increased ERK activity at 4 days after diagnosis of COVID-19-induced sepsis was associated with a more than threefold increased chance of survival in an adjusted Cox regression model. ERK activity was independent of other confounders such as Charlson Comorbidity Index or SOFA score (HR 0.28, 95% CI 0.10-0.84, p = 0.02)., Conclusion: High activity of the RAF/MEK/ERK network during the course of COVID-19 sepsis is a protective factor and may indicate recovery of the immune system. Further studies are needed to confirm these results., Competing Interests: Declarations. Ethics approval and consent to participate: The study was approved by the Ethics Committee of the Medical Faculty of the University of Bochum (Ruhr-University Bochum, registry number 18–6606-BR, German clinical trial registry: DRKS00026184). Informed consent forms were available for all included patients or their respective legal representatives, if patients were unable to provide informed consent at the time of study inclusion. Competing interests: The authors declare that they have no competing interests. Consent for publication: Not applicable., (© 2024. The Author(s).)

Background: Artificial intelligence (AI)-based clinical decision support systems (CDSS) have been developed for several diseases. However, despite the potential to improve the quality of care and thereby positively impact patient-relevant outcomes, the majority of AI-based CDSS have not been adopted in standard care. Possible reasons for this include barriers in the implementation and a nonuser-oriented development approach, resulting in reduced user acceptance., Objective: This research project has 2 objectives. First, problems and corresponding solutions that hinder or support the development and implementation of AI-based CDSS are identified. Second, the research project aims to increase user acceptance by creating a user-oriented requirement profile, using the example of sepsis., Methods: The research project is based on a multimethod approach combining (1) a scoping review, (2) focus groups with physicians and professional caregivers, and (3) semistructured interviews with relevant stakeholders. The research modules mentioned provide the basis for the development of a (4) survey, including a discrete choice experiment (DCE) with physicians. A minimum of 6667 physicians with expertise in the clinical picture of sepsis are contacted for this purpose. The survey is followed by the development of a requirement profile for AI-based CDSS and the derivation of policy recommendations for action, which are evaluated in a (5) expert roundtable discussion., Results: The multimethod research project started in November 2022. It provides an overview of the barriers and corresponding solutions related to the development and implementation of AI-based CDSS. Using sepsis as an example, a user-oriented requirement profile for AI-based CDSS is developed. The scoping review has been concluded and the qualitative modules have been subjected to analysis. The start of the survey, including the DCE, was at the end of July 2024., Conclusions: The results of the research project represent the first attempt to create a comprehensive user-oriented requirement profile for the development of sepsis-specific AI-based CDSS. In addition, general recommendations are derived, in order to reduce barriers in the development and implementation of AI-based CDSS. The findings of this research project have the potential to facilitate the integration of AI-based CDSS into standard care in the long term., International Registered Report Identifier (irrid): DERR1-10.2196/62704., (©Pascal Raszke, Godwin Denk Giebel, Carina Abels, Jürgen Wasem, Michael Adamzik, Hartmuth Nowak, Lars Palmowski, Philipp Heinz, Silke Mreyen, Nina Timmesfeld, Marianne Tokic, Frank Martin Brunkhorst, Nikola Blase. Originally published in JMIR Research Protocols (https://www.researchprotocols.org), 30.01.2025.)

Background: Sepsis remains a leading cause of mortality in intensive care units. Understanding the dynamics of the plasma proteome of patients with sepsis is critical for improving prognostic and therapeutic strategies., Methods: This prospective, multicentre observational cohort study included 363 patients with sepsis recruited from five university hospitals in Germany between March 2018 and April 2023. Plasma samples were collected on days 1 and 4 after sepsis diagnosis, and proteome analysis was performed using mass spectrometry. Classical statistical methods and machine learning (random forest) were employed to identify proteins associated with 30-day survival outcomes., Findings: Out of 363 patients, 224 (62%) survived, and 139 (38%) did not survive the 30-day period. Proteomic analysis revealed significant differences in 87 proteins on day 1 and 95 proteins on day 4 between survivors and non-survivors. Additionally, 63 proteins were differentially regulated between day 1 and day 4 in the two groups. The identified protein networks were primarily related to blood coagulation, immune response, and complement activation. The random forest classifier achieved an area under the receiver operating characteristic curve of 0.75 for predicting 30-day survival. The results were compared and partially validated with an external sepsis cohort., Interpretation: This study describes temporal changes in the plasma proteome associated with mortality in sepsis. These findings offer new insights into sepsis pathophysiology, emphasizing the innate immune system as an underexplored network, and may inform the development of targeted therapeutic strategies., Funding: European Regional Development Fund of the European Union. The State of North Rhine-Westphalia, Germany., Competing Interests: Declaration of interests AZ received payments for grants, lectures or consulting from Baxter BioMerieux, Bayer, AM Pharma, Novartis, RenalGuard, Alexion, Baxter, Paion and Viatris. JCK received funding from Danaher Beacon. AZ has leadership or fiduciary role in IARS, DIVI and DGAI. ME is employee of Ruhr-University Bochum., (Copyright © 2024 The Author(s). Published by Elsevier B.V. All rights reserved.)