[Use of AI-based applications by hospital staff: task profiles and qualification requirements]. / Einsatz von KI-basierten Anwendungen durch Krankenhauspersonal: Aufgabenprofile und Qualifizierungsbedarfe.

BACKGROUND: Artificial intelligence (AI) is becoming increasingly important for the future development of hospitals. To unlock the large potential of AI, job profiles of hospital staff members need to be further developed in the direction of AI and digitization skills through targeted qualification measures. This affects both medical and non-medical processes along the entire value chain in hospitals. The aim of this paper is to provide an overview of the skills required to deal with smart technologies in a clinical context and to present measures for training employees. METHODS: As part of the "SmartHospital.NRW" project in 2022, we conducted a literature review as well as interviews and workshops with experts. AI technologies and fields of application were identified. RESULTS: Key findings include adapted and new task profiles, synergies and dependencies between individual task profiles, and the need for a comprehensive interdisciplinary and interprofessional exchange when using AI-based applications in hospitals. DISCUSSION: Our article shows that hospitals need to promote digital health literacy skills for hospital staff members at an early stage and at the same time recruit technology- and AI-savvy staff. Interprofessional exchange formats and accompanying change management are essential for the use of AI in hospitals.

Topic modeling revisited: New evidence on algorithm performance and quality metrics.

Topic modeling is a popular technique for exploring large document collections. It has proven useful for this task, but its application poses a number of challenges. First, the comparison of available algorithms is anything but simple, as researchers use many different datasets and criteria for their evaluation. A second challenge is the choice of a suitable metric for evaluating the calculated results. The metrics used so far provide a mixed picture, making it difficult to verify the accuracy of topic modeling outputs. Altogether, the choice of an appropriate algorithm and the evaluation of the results remain unresolved issues. Although many studies have reported promising performance by various topic models, prior research has not yet systematically investigated the validity of the outcomes in a comprehensive manner, that is, using more than a small number of the available algorithms and metrics. Consequently, our study has two main objectives. First, we compare all commonly used, non-application-specific topic modeling algorithms and assess their relative performance. The comparison is made against a known clustering and thus enables an unbiased evaluation of results. Our findings show a clear ranking of the algorithms in terms of accuracy. Secondly, we analyze the relationship between existing metrics and the known clustering, and thus objectively determine under what conditions these algorithms may be utilized effectively. This way, we enable readers to gain a deeper understanding of the performance of topic modeling techniques and the interplay of performance and evaluation metrics.

Giving voice to all patients: On patients at the margins and their intention and perceived ability to complain.

BACKGROUND: It is now widely established that health care organizations are well advised not only to identify and act upon the concerns of all patient groups but also to encourage and enable them to voice their concerns in the first place. That said, research has begun to reveal that patients differ substantially in their readiness to complain, with many deciding to remain silent even after experiencing severe adverse events. Little research has explored whether patients at the margins (e.g., elderly, disabled, or mentally ill patients) are more likely to remain silent. PURPOSE: We examined the extent to which patients' social (being elderly or poorly educated), physical (having a permanent impairment such as deafness, blindness, or a chronic physical condition), and mental marginality (having a mental illness or learning disability) is associated with their intention and perceived ability to complain. METHODOLOGY: We matched survey and patient record data for hospital inpatients treated in the English National Health Service in 2007. We then computed two-stage probit selection models to estimate the cross-sectional association between patients' social, physical, and mental marginality and their intention (Stage 1, N1 = 58,062) and perceived ability to complain (Stage 2, N2 = 3,765). FINDINGS: Only 6.47% of all patients intended to complain. Of these, only 10.41% indicated that hospital staff provided them with all the information they needed to complain. An additional 14.70% reported to have received at least some of the information needed for this purpose. Patients above 80 not only exhibited significantly lower intentions to complain than their mid-aged counterparts (-1.16%) but also felt considerably less well informed to file a complaint (-5.45%). Similarly, patients suffering from blindness or a severe vision impairment showed a significantly lower perceived ability to complain (-5.20%). PRACTICE IMPLICATIONS: Patients at the margins, especially elderly patients and those with a severe vision impairment, will often remain silent and require special attention, if health care organizations are to listen to-and learn from-the voices of all patients. Our results indicate the need for inclusive complaint procedures designed to fuel organizational learning. Dedicated roles such as case managers and complaint officers might help to make such feedback channels accessible to all patients.

Fighting MRSA Infections in Hospital Care: How Organizational Factors Matter.

OBJECTIVE: To identify factors associated with methicillin-resistant Staphylococcus aureus (MRSA) bloodstream infections at the level of the hospital organization. DATA SOURCES: Data from all 173 acute trusts in the English National Health Service (NHS). STUDY DESIGN: A longitudinal study based on trust-level panel data for the 5-year period from April 2004 to March 2009. Fixed effects negative binominal and system generalized method of moment models were used to examine the effect of (i) patient mix characteristics, (ii) resource endowments, and (iii) infection control practices on yearly MRSA counts. DATA COLLECTION: Archival and staff survey data from multiple sources, including Public Health England, the English Department of Health, and the Healthcare Commission, were merged to form a balanced panel dataset. PRINCIPAL FINDINGS: MRSA infections decrease with increases in general cleaning (-3.52 MRSA incidents per 1 standard deviation increase; 95 percent confidence interval: -6.61 to -0.44), infection control training (-3.29; -5.22 to -1.36), hand hygiene (-2.72; -4.76 to -0.68), and error reporting climate (-2.06; -4.09 to -0.04). CONCLUSIONS: Intensified general cleaning, improved hand hygiene, additional infection control training, and a climate conducive to error reporting emerged as the factors most closely associated with trust-level reductions in MRSA infections over time.