The development and implementation of artificial intelligence (AI) applications in health care contexts is a concurrent research and management question. Especially for hospitals, the expectations regarding improved efficiency and effectiveness by the introduction of novel AI applications are huge. However, experiences with real-life AI use cases are still scarce. As a first step towards structuring and comparing such experiences, this paper is presenting a comparative approach from nine European hospitals and eleven different use cases with possible application areas and benefits of hospital AI technologies. This is structured as a current review and opinion article from a diverse range of researchers and health care professionals. This contributes to important improvement options also for pandemic crises challenges, e.g., the current COVID-19 situation. The expected advantages as well as challenges regarding data protection, privacy, or human acceptance are reported. Altogether, the diversity of application cases is a core characteristic of AI applications in hospitals, and this requires a specific approach for successful implementation in the health care sector. This can include specialized solutions for hospitals regarding human–computer interaction, data management, and communication in AI implementation projects.

Artificial intelligence (AI) is gaining increasing interest in the field of medicine because of its capacity to process big data and pattern recognition. Cardiotocography (CTG) is widely used for the assessment of foetal well-being and uterine contractions during pregnancy and labour. It is characterised by inter- and intraobserver variability in interpretation, which depends on the observers’ experience. Artificial intelligence (AI)-assisted interpretation could improve its quality and, thus, intrapartal care. Cardiotocography (CTG) raw signals from labouring women were extracted from the database at the University Hospital of Bern between 2006 and 2019. Later, they were matched with the corresponding foetal outcomes, namely arterial umbilical cord pH and 5-min APGAR score. Excluded were deliveries where data were incomplete, as well as multiple births. Clinical data were grouped regarding foetal pH and APGAR score at 5 min after delivery. Physiological foetal pH was defined as 7.15 and above, and a 5-min APGAR score was considered physiologic when reaching ≥7. With these groups, the algorithm was trained to predict foetal hypoxia. Raw data from 19,399 CTG recordings could be exported. This was accomplished by manually searching the patient’s identification numbers (PIDs) and extracting the corresponding raw data from each episode. For some patients, only one episode per pregnancy could be found, whereas for others, up to ten episodes were available. Initially, 3400 corresponding clinical outcomes were found for the 19,399 CTGs (17.52%). Due to the small size, this dataset was rejected, and a new search strategy was elaborated. After further matching and curation, 6141 (31.65%) paired data samples could be extracted (cardiotocography raw data and corresponding maternal and foetal outcomes). Of these, half will be used to train artificial intelligence (AI) algorithms, whereas the other half will be used for analysis of efficacy. Complete data could only be found for one-third of the available population. Yet, to our knowledge, this is the most exhaustive and second-largest cardiotocography database worldwide, which can be used for computer analysis and programming. A further enrichment of the database is planned.

Individuals with SARS-CoV-2 infection and (pre-existing) diabetes, including pregnant women, present with more severe morbidity, as compared to non-diabetic subjects. To date, evidence is limited concerning the role of gestational diabetes (GDM) in severity of SARS-CoV-2 infection during pregnancy, or vice versa. The aim of our study was to investigate the prevalence of GDM in a SARS-CoV-2 infected pregnant population and evaluate risk factors for and from severe infection in these patients. A case-control study with prospective data collection for the case group and 1:2 matching with historical controls based on parity, BMI and ethnicity was conducted (n = 224). GDM screening was performed at 26 weeks’ gestation. Multivariate binary logistic regression analysis was performed to assess risk factors for GDM and inpatient COVID-19 management. 34.6% of the patients in the case group suffered from GDM, vs. 16.1% in the control group (p = 0.002). 35.7% patients were diagnosed with GDM after, vs. 33.3% before SARS-CoV-2 infection (OR (95%CI) 1.11(0.40–3.08), p = 0.84), with no correlation between time point of infection and GDM diagnosis. SARS-CoV-2 (OR (95%CI) 2.79 (1.42, 5.47), p = 0.003) and BMI (OR (95%CI) 1.12 (1.05, 1.19), p = 0.001) were significant independent risk factors for GDM. Data suggests that GDM increases the risk of infection in SARS-CoV-2 infected pregnant women. Meanwhile, SARS-CoV-2 during pregnancy might increase the risk of developing GDM. Vaccination and caution in using protective measures should be recommended to pregnant women, particularly when suffering from GDM.

Misoprostol vaginal insert for induction of labor has been recently reported to be superior to dinoprostone vaginal insert in a phase III trial, but has never been compared to vaginal misoprostol in another galenic form. The aim of this study was to compare misoprostol vaginal insert (MVI) with misoprostol vaginal tablets (MVT) for induction of labor in term pregnancies. In this retrospective cohort study we compared 200 consecutive women induced with 200-μg misoprostol 24-h vaginal insert (Misodel®) with a historical control of 200 women induced with Misoprostol 25-μg vaginal tablets (Cytotec®) every 4-6 h. Main outcomes variables included induction-to-delivery interval, vaginal delivery within 24-h, incidence of tachysystole, mode of delivery, and neonatal outcome. A subanalysis in the MVI group was performed in order to identify predictive factors for tachysistole and vaginal delivery within 24 h. The time from induction to vaginal delivery was 1048 ± 814 min in the MVI group and 1510 ± 1043 min in the MVT group (p < 0.001). Vaginal delivery within 24-h occurred in 127 (63.5%) patients of the MVI group and in 110 (55%) patients of the MVT group (p < 0.001). Tachysystole was more common in the MVI group (36% vs. 18%; p < 0.001). However, no significant predictors of uterine tachysystole in MVI group have been identified in crude and fully adjusted logistic regression models. Bishop score was the only predictor for vaginal delivery within 24 h (p < 0.001) in MVI group. Caesarean delivery rate (27% vs. 20%) and vaginal-operative deliveries (15.5% vs. 15.5%) did not differ significantly between the two groups. Neonatal outcomes were similar in both groups. MVI achieves a more vaginal delivery rate within 24 h and Tachysystole events compared to MVT. However, no differences in caesarean section, operative vaginal delivery, and neonatal outcomes are reported. No predictors of tachysistole after MVI administration have been identified. Bishop score and parity are the only predictors of vaginal delivery within 24 h after MVI administration.