Computerized clinical decision support systems, or CDSS, represent a paradigm shift in healthcare today. CDSS are used to augment clinicians in their complex decision-making processes. Since their first use in the 1980s, CDSS have seen a rapid evolution. They are now commonly administered through electronic medical records and other computerized clinical workflows, which has been facilitated by increasing global adoption of electronic medical records with advanced capabilities. Despite these advances, there remain unknowns regarding the effect CDSS have on the providers who use them, patient outcomes, and costs. There have been numerous published examples in the past decade(s) of CDSS success stories, but notable setbacks have also shown us that CDSS are not without risks. In this paper, we provide a state-of-the-art overview on the use of clinical decision support systems in medicine, including the different types, current use cases with proven efficacy, common pitfalls, and potential harms. We conclude with evidence-based recommendations for minimizing risk in CDSS design, implementation, evaluation, and maintenance.

Background and Aims: CD71 + erythroid cells are enriched during pregnancy with immuno suppressive properties. We investigated the frequency and functionality of CD71 + erythroid cells in peripheral blood, cord blood, and placenta of inflammatory bowel disease [IBD] patients versus healthy controls [HCs]. We aimed to determine their role in IBD pathogenesis during pregnancy. Methods: Peripheral blood was collected at preconception, the first, second and third trimesters, and postpartum. Cord blood and placental tissues were collected at the time of birth. Cells from different specimens were subjected to immunephenotyping and functional assays. CD71 + erythroid cells were purified for quantitative polymerase chain reaction [qPCR] analysis. Using an allogeneic mouse model of pregnancy, the effects of CD71 + erythroid cells depletion on intestinal homeostasis and dysbiosis was studied. Results: IBD patients had lower CD71 + erythroid cells during pregnancy compared with HCs. Placenta and cord blood CD71 + erythroid cells from IBD patients exhibited impaired functionality and expressed lower inhibitory molecules including VISTA, TGFβ, and reactive oxygen species [ROS]. Lower CD71 + erythroid cells were correlated with reduced regulatory T cells and increased immuneactivation in IBD patients. Depletion of CD71 + erythroid cells in an allogeneic pregnancy model resulted in upregulation of TLRs, IL6, and CXCL1, and enhanced production of TNFα, in intestinal tissues. In contrast, TGF β gene expression was reduced. Excessive inflammatory response in the gut [e.g. TNFα] affects intestinal integrity and CD71 + erythroid cells impact on the gut's bacterial composition. Conclusions: Reduced frequency and/or impaired functionality of CD71 + erythroid cells during pregnancy may predispose IBD patients to a more proinflammatory milieu in their gastrointestinal tract, characterised by lower Tregs, higher IL6, and TNFα, and dysbiosis.

High-frequency (10-MHz) sonography demonstrated a cervical mass or lymphadenopathy, or both, during postoperative follow-up of 52 patients who had undergone surgery for thyroid cancer. Percutaneous biopsy with ultrasonographic (US) guidance was performed in all 52 masses, 44 of which were nonpalpable. Malignant cells were obtained in 29 biopsies, and the results of 20 biopsies were negative, yielding benign lymphocytes only. Results in three biopsies were nondiagnostic due to hypocellular specimens. Therefore, 94% of biopsy results (49) of 52) were confidently assigned as either positive (56%) or negative (38%) for malignancy. There were no complications. High-frequency sonography can demonstrate clinically occult thyroid bed tumor recurrence and lymph node metastases. US-guided biopsy is an accurate and safe technique to confirm or exclude malignancy in patients at high risk of recurrence of thyroid cancer.

Background and Aims: For women with inflammatory bowel disease [IBD], it is not very well known how IBD or IBD treatment affects their breast milk components. We aimed to investigate whether breast milk composition differs in healthy control [HC] versus IBD mothers in terms of antibodies, cytokines, and metabolite,s to identify potential impact of IBD breast milk on neonatal immune system. Methods: Breast milk specimens from HC [n = 17] and IBD [n = 31 for Crohn's disease [CD]; and n = 41 for ulcerative colitis [UC]; were collected at 3 and 6 months postpartum [PP3] and [PP6], respectively. Faecal samples were also collected. Cytokines and immunoglobulins [IgA/IgG/IgE] were analysed by multiplex Meso Scale Discovery [MSD] and commercial kits. Moreover, breast milk metabolites were analysed by 1 H nuclear magnetic resonance [NMR]. Results: We found that breast milk from IBD mothers showed significantly lower levels of IgA, sugar metabolite [lactose], and 2-aminobutyrate. In contrast, we observed that breast milk from mothers with IBD had increased levels of pro-inflammatory cytokines and higher energy metabolites [lactate and succinate] than milk from healthy mothers. In addition, we noticed that the type of treatment [5-aminosalicylic acid versus biologics] influenced the milk cytokines and metabolites profile. Conclusions: The reduction in immunoprotective components of IBD breast milk such as sIgA and lactose theoretically may modulate the potential protective effects of breastfeeding. On the other hand, presence of higher levels of pro-inflammatory cytokines, lactate, and succinate may predispose the offspring to an inflammatory condition or impact on the gut microbiome. Better understanding of the role of succinate in infants and its potential effects on microbiome or mucosal immunity merits further investigations.

Endoscopic evaluation to reliably grade disease activity, detect complications including cancer and verification of mucosal healing are paramount in the care of patients with ulcerative colitis (UC); but this evaluation is hampered by substantial intra- and interobserver variability. Recently, artificial intelligence methodologies have been proposed to facilitate more objective, reproducible endoscopic assessment. In a first step, we compared how well several deep learning convolutional neural network architectures (CNNs) applied to a diverse subset of 8000 labeled endoscopic still images derived from HyperKvasir, the largest multi-class image and video dataset from the gastrointestinal tract available today. The HyperKvasir dataset includes 110,079 images and 374 videos and could (1) accurately distinguish UC from non-UC pathologies, and (2) inform the Mayo score of endoscopic disease severity. We grouped 851 UC images labeled with a Mayo score of 0–3, into an inactive/mild (236) and moderate/severe (604) dichotomy. Weights were initialized with ImageNet, and Grid Search was used to identify the best hyperparameters using fivefold cross-validation. The best accuracy (87.50%) and Area Under the Curve (AUC) (0.90) was achieved using the DenseNet121 architecture, compared to 72.02% and 0.50 by predicting the majority class (‘no skill’ model). Finally, we used Gradient-weighted Class Activation Maps (Grad-CAM) to improve visual interpretation of the model and take an explainable artificial intelligence approach (XAI).