Association between Ustekinumab Trough Levels, Serum IL-22, and Oncostatin M Levels and Clinical and Biochemical Outcomes in Patients with Crohn's Disease.

Background: Ustekinumab (UST) has demonstrated effectiveness in treating patients with Crohn's disease. Monitoring treatment response can improve disease management and reduce healthcare costs. We investigated whether UST trough levels (TLs), serum IL22, and Oncostatin M (OSM) levels could be early indicators of non-response by analysing their correlation with clinical and biochemical outcomes in CD. Methods: Patients with CD initiating UST treatment from October 2018 to September 2020 were enrolled at six Italian centres for inflammatory bowel disease (IBD). Clinical and biochemical data were collected at four time points: baseline, second subcutaneous (SC) dose, fourth SC dose, and 52 weeks. TLs were measured during maintenance, at the second SC dose, and at the fourth SC dose. IL-22 and OSM serum levels were assessed at baseline and the second SC dose. We analysed whether TLs, IL22 levels, and OSM serum levels were associated with clinical response, clinical remission, biochemical remission, and endoscopic remission using the appropriate statistical tests. Results: Out of eighty-four initially enrolled patients, five were lost to follow-up, and eleven discontinued the drug before 52 weeks. At the 52-week time point, 47% achieved biochemical remission based on faecal calprotectin levels, and 61.8% achieved clinical remission. TLs at the second SC dose significantly correlated with biochemical remission at the same time point (p = 0.011). However, TLs did not correlate with clinical remission. Baseline OSM levels did not correlate with biochemical or clinical remission or response. IL22 levels notably decreased during UST therapy (p = 0.000), but its values did not correlate with biochemical or clinical remission. Conclusions: UST is an effective therapy for patients with CD. TLs measured at the second SC dose significantly correlated with biochemical remission, emphasising their potential role in treatment monitoring. Levels of OSM and IL-22, despite a significant decrease in the latter during therapy, did not exhibit correlations with clinical or biochemical outcomes in our study. Further studies are needed to confirm these findings.

Adaptive Machine Learning Approach for Importance Evaluation of Multimodal Breast Cancer Radiomic Features.

Breast cancer holds the highest diagnosis rate among female tumors and is the leading cause of death among women. Quantitative analysis of radiological images shows the potential to address several medical challenges, including the early detection and classification of breast tumors. In the P.I.N.K study, 66 women were enrolled. Their paired Automated Breast Volume Scanner (ABVS) and Digital Breast Tomosynthesis (DBT) images, annotated with cancerous lesions, populated the first ABVS+DBT dataset. This enabled not only a radiomic analysis for the malignant vs. benign breast cancer classification, but also the comparison of the two modalities. For this purpose, the models were trained using a leave-one-out nested cross-validation strategy combined with a proper threshold selection approach. This approach provides statistically significant results even with medium-sized data sets. Additionally it provides distributional variables of importance, thus identifying the most informative radiomic features. The analysis proved the predictive capacity of radiomic models even using a reduced number of features. Indeed, from tomography we achieved AUC-ROC 89.9 % using 19 features and 92.1 % using 7 of them; while from ABVS we attained an AUC-ROC of 72.3 % using 22 features and 85.8 % using only 3 features. Although the predictive power of DBT outperforms ABVS, when comparing the predictions at the patient level, only 8.7% of lesions are misclassified by both methods, suggesting a partial complementarity. Notably, promising results (AUC-ROC ABVS-DBT 71.8 % - 74.1 % ) were achieved using non-geometric features, thus opening the way to the integration of virtual biopsy in medical routine.

Artificial Intelligence Tools for the Diagnosis of Eosinophilic Esophagitis in Adults Reporting Dysphagia: Development, External Validation, and Software Creation for Point-of-Care Use.

BACKGROUND: Despite increased awareness of eosinophilic esophagitis (EoE), the diagnostic delay has remained stable over the past 3 decades. There is a need to improve the diagnostic performance and optimize resources allocation in the setting of EoE. OBJECTIVE: We developed and validated 2 point-of-care machine learning (ML) tools to predict a diagnosis of EoE before histology results during office visits. METHODS: We conducted a multicenter study in 3 European tertiary referral centers for EoE. We built predictive ML models using retrospectively extracted clinical and esophagogastroduodenoscopy (EGDS) data collected from 273 EoE and 55 non-EoE dysphagia patients. We validated the models on an independent cohort of 93 consecutive patients with dysphagia undergoing EGDS with biopsies at 2 different centers. Models' performance was assessed by area under the curve (AUC), sensitivity, specificity, and positive and negative predictive values (PPV and NPV). The models were integrated into a point-of-care software package. RESULTS: The model trained on clinical data alone showed an AUC of 0.90 and a sensitivity, specificity, PPV, and NPV of 0.90, 0.75, 0.80, and 0.87, respectively, for the diagnosis of EoE in the external validation cohort. The model trained on a combination of clinical and endoscopic data showed an AUC of 0.94, and a sensitivity, specificity, PPV, and NPV of 0.94, 0.68, 0.77, and 0.91, respectively, in the external validation cohort. CONCLUSION: Our software-integrated models (https://webapplicationing.shinyapps.io/PointOfCare-EoE/) can be used at point-of-care to improve the diagnostic workup of EoE and optimize resources allocation.

Enhancing COVID-19 CT Image Segmentation: A Comparative Study of Attention and Recurrence in UNet Models.

Imaging plays a key role in the clinical management of Coronavirus disease 2019 (COVID-19) as the imaging findings reflect the pathological process in the lungs. The visual analysis of High-Resolution Computed Tomography of the chest allows for the differentiation of parenchymal abnormalities of COVID-19, which are crucial to be detected and quantified in order to obtain an accurate disease stratification and prognosis. However, visual assessment and quantification represent a time-consuming task for radiologists. In this regard, tools for semi-automatic segmentation, such as those based on Convolutional Neural Networks, can facilitate the detection of pathological lesions by delineating their contour. In this work, we compared four state-of-the-art Convolutional Neural Networks based on the encoder-decoder paradigm for the binary segmentation of COVID-19 infections after training and testing them on 90 HRCT volumetric scans of patients diagnosed with COVID-19 collected from the database of the Pisa University Hospital. More precisely, we started from a basic model, the well-known UNet, then we added an attention mechanism to obtain an Attention-UNet, and finally we employed a recurrence paradigm to create a Recurrent-Residual UNet (R2-UNet). In the latter case, we also added attention gates to the decoding path of an R2-UNet, thus designing an R2-Attention UNet so as to make the feature representation and accumulation more effective. We compared them to gain understanding of both the cognitive mechanism that can lead a neural model to the best performance for this task and the good compromise between the amount of data, time, and computational resources required. We set up a five-fold cross-validation and assessed the strengths and limitations of these models by evaluating the performances in terms of Dice score, Precision, and Recall defined both on 2D images and on the entire 3D volume. From the results of the analysis, it can be concluded that Attention-UNet outperforms the other models by achieving the best performance of 81.93%, in terms of 2D Dice score, on the test set. Additionally, we conducted statistical analysis to assess the performance differences among the models. Our findings suggest that integrating the recurrence mechanism within the UNet architecture leads to a decline in the model's effectiveness for our particular application.

Comparison of drugs for active eosinophilic oesophagitis: systematic review and network meta-analysis.

BACKGROUND: There is currently no recommendation regarding preferred drugs for active eosinophilic oesophagitis (EoE) because their relative efficacy is unclear. We conducted an up-to-date network meta-analysis to compare proton pump inhibitors, off-label and EoE-specific topical steroids, and biologics in EoE. METHODS: We searched MEDLINE, Embase, Embase Classic and the Cochrane Central Register of Controlled Trials from inception to June 2023. We included randomised controlled trials (RCTs) comparing efficacy of all drugs versus each other, or placebo, in adults and adolescents with active EoE. Results were reported as pooled relative risks with 95% CIs to summarise effect of each comparison tested, with drugs ranked according to P score RESULTS: Seventeen RCTs were eligible for systematic review. Of these, 15 studies containing 1813 subjects with EoE reported extractable data for the network meta-analysis. For histological remission defined as ≤6 eosinophils/high-power field (HPF), lirentelimab 1 mg/kg monthly ranked first. For histological remission defined as ≤15 eosinophils/HPF, budesonide orally disintegrating tablet (BOT) 1 mg two times per day ranked first. For failure to achieve symptom improvement, BOT 1 mg two times per day and budesonide oral suspension (BOS) 2 mg two times per day were significantly more efficacious than placebo. For failure to achieve endoscopic improvement based on the EoE Endoscopic Reference Score, BOT 1 mg two times per day and BOS 1 mg two times per day or 2 mg two times per day were significantly more efficacious than placebo. CONCLUSIONS: Although this network meta-analysis supports the efficacy of most available drugs over placebo for EoE treatment, significant heterogeneity in eligibility criteria and outcome measures among available trials hampers the establishment of a solid therapeutic hierarchy.

Six-Food Elimination Diet Is Less Effective During Pollen Season in Adults With Eosinophilic Esophagitis Sensitized to Pollens.

INTRODUCTION: The role of inhaled and swallowed aeroallergens in treatment outcomes of adult patients with eosinophilic esophagitis (EoE) is unclear. We hypothesized that the pollen season contributes to the failure of the 6-food elimination diet (SFED) in EoE. METHODS: We compared outcomes of patients with EoE who underwent SFED during vs outside of the pollen season. Consecutive adult patients with EoE who underwent SFED and skin prick test (SPT) for birch and grass pollen were included. Individual pollen sensitization and pollen count data were analyzed to define whether each patient had been assessed during or outside of the pollen season after SFED. All patients had active EoE (≥15 eosinophils/high-power field) before SFED and adhered to the diet under the supervision of a dietitian. RESULTS: Fifty-eight patients were included, 62.0% had positive SPT for birch and/or grass, whereas 37.9% had negative SPT. Overall, SFED response was 56.9% (95% confidence interval, 44.1%-68.8%). When stratifying response according to whether the assessment had been performed during or outside of the pollen season, patients sensitized to pollens showed significantly lower response to SFED during compared with outside of the pollen season (21.4% vs 77.3%; P = 0.003). In addition, during the pollen season, patients with pollen sensitization had significantly lower response to SFED compared with those without sensitization (21.4% vs 77.8%; P = 0.01). DISCUSSION: Pollens may have a role in sustaining esophageal eosinophilia in sensitized adults with EoE despite avoidance of trigger foods. The SPT for pollens may identify patients less likely to respond to the diet during the pollen season.

GPU accelerated digital twins of the human heart open new routes for cardiovascular research.

The recruitment of patients for rare or complex cardiovascular diseases is a bottleneck for clinical trials and digital twins of the human heart have recently been proposed as a viable alternative. In this paper we present an unprecedented cardiovascular computer model which, relying on the latest GPU-acceleration technologies, replicates the full multi-physics dynamics of the human heart within a few hours per heartbeat. This opens the way to extensive simulation campaigns to study the response of synthetic cohorts of patients to cardiovascular disorders, novel prosthetic devices or surgical procedures. As a proof-of-concept we show the results obtained for left bundle branch block disorder and the subsequent cardiac resynchronization obtained by pacemaker implantation. The in-silico results closely match those obtained in clinical practice, confirming the reliability of the method. This innovative approach makes possible a systematic use of digital twins in cardiovascular research, thus reducing the need of real patients with their economical and ethical implications. This study is a major step towards in-silico clinical trials in the era of digital medicine.

Ambulatory pH-Impedance Findings Confirm That Grade B Esophagitis Provides Objective Diagnosis of Gastroesophageal Reflux Disease.

INTRODUCTION: The Lyon Consensus designates Los Angeles (LA) grade C/D esophagitis or acid exposure time (AET) >6% on impedance-pH monitoring (MII-pH) as conclusive for gastroesophageal reflux disease (GERD). We aimed to evaluate proportions with objective GERD among symptomatic patients with LA grade A, B, and C esophagitis on endoscopy. METHODS: Demographics, clinical data, endoscopy findings, and objective proton-pump inhibitor response were collected from symptomatic prospectively enrolled patients from 2 referral centers. Off-therapy MII-pH parameters included AET, number of reflux episodes, mean nocturnal baseline impedance, and postreflux swallow-induced peristaltic wave index. Objective GERD evidence was compared between LA grades. RESULTS: Of 155 patients (LA grade A: 74 patients, B: 61 patients, and C: 20 patients), demographics and presentation were similar across LA grades. AET >6% was seen in 1.4%, 52.5%, and 75%, respectively, in LA grades A, B, and C. Using additional MII-pH metrics, an additional 16.2% with LA grade A and 47.5% with LA grade B esophagitis had AET 4%-6% with low mean nocturnal baseline impedance and postreflux swallow-induced peristaltic wave index; there were no additional gains using the number of reflux episodes or symptom-reflux association metrics. Compared with LA grade C (100% conclusive GERD based on endoscopic findings), 100% of LA grade B esophagitis also had objective GERD but only 17.6% with LA grade A esophagitis ( P < 0.001 compared with each). Proton-pump inhibitor response was comparable between LA grades B and C (74% and 70%, respectively) but low in LA grade A (39%, P < 0.001). DISCUSSION: Grade B esophagitis indicates an objective diagnosis of GERD.

Efficacy of a Second PPI Course After Steroid-Induced Remission in Eosinophilic Esophagitis Refractory to Initial PPI Therapy.

INTRODUCTION: Eosinophilic esophagitis (EoE) requires maintenance therapy to avoid recurrence. We investigated the efficacy of a second course of proton pump inhibitors (scPPIs) to maintain steroid-induced histological remission (HR) in patients with EoE who had previously failed induction of remission with PPIs. METHODS: We retrospectively included 18 patients who achieved HR with topical steroids but could not be maintained on long-term topical steroids. Treatment outcomes were assessed after 12 weeks of scPPIs. RESULTS: Most of the patients (67%) maintained HR with high-dose PPI monotherapy at week 12. DISCUSSION: scPPIs might work as a maintenance strategy in primary PPI nonresponder EoE patients.

Chicago classification v4.0 protocol improves specificity and accuracy of diagnosis of oesophagogastric junction outflow obstruction.

BACKGROUND: Chicago classification version 4.0 (CCv4.0) introduced stringent diagnostic criteria for oesophagogastric junction outflow obstruction (EGJOO), in order to increase the clinical relevance of the diagnosis, although this has not yet been demonstrated. AIMS: To determine the prevalence of EGJOO using CCv4.0 criteria in patients with CCv3.0-based EGJOO, and to assess if provocative manoeuvres can predict a conclusive CCv4.0 diagnosis of EGJOO. METHODS: Clinical presentation, high resolution manometry (HRM) with rapid drink challenge (RDC), and timed barium oesophagogram (TBE) data were extracted for patients diagnosed with EGJOO as per CCv3.0 between 2018 and 2020. Patients were then re-classified according to CCv4.0 criteria, using clinically relevant symptoms (dysphagia and/or chest pain), and abnormal barium emptying at 5 min on TBE. Receiver operating characteristic (ROC) analyses identified HRM predictors of EGJOO. RESULTS: Of 2010 HRM studies, 144 (7.2%) fulfilled CCv3.0 criteria for EGJOO (median age 61 years, 56.9% female). Upon applying CCv4.0 criteria, EGJOO prevalence decreased to 1.2%. On ROC analysis, integrated relaxation pressure during RDC (RDC-IRP) was a significant predictor of a conclusive EGJOO diagnosis by CCv4.0 criteria (area under the curve: 96.1%). The optimal RDC-IRP threshold of 16.7 mm Hg had 87% sensitivity, 97.1% specificity, 95.7% negative predictive value and 91.3% positive predictive value for a conclusive EGJOO diagnosis; lower thresholds (10 mmHg, 12 mmHg) had better sensitivity but lower specificity. CONCLUSION: CCv4.0 criteria reduced the prevalence of EGJOO by 80%, thereby refining the diagnosis and identifying clinically relevant outflow obstruction. Elevated RDC-IRP can predict conclusive EGJOO per CCv4.0.

Improving Pediatric/Neonatology Residents' Newborn Resuscitation Skills With a Digital Serious Game: DIANA.

Background: Serious games, and especially digital game based learning (DGBL) methodologies, have the potential to strengthen classic learning methodology in all medical procedures characterized by a flowchart (e.g., neonatal resuscitation algorithm). However, few studies have compared short- and long-term knowledge retention in DGBL methodologies with a control group undergoing specialist training led by experienced operators. In particular, resident doctors' learning still has limited representation in simulation-based education literature. Objective: A serious computer game DIANA (DIgital Application in Newborn Assessment) was developed, according to newborn resuscitation algorithm, to train pediatric/neonatology residents in neonatal resuscitation algorithm knowledge and implementation (from procedure knowledge to ventilation/chest compressions rate). We analyzed user learning curves after each session and compared knowledge retention against a classic theoretical teaching session. Methods: Pediatric/neonatology residents of the Azienda Ospedaliera Universitaria Pisana (AOUP) were invited to take part in the study and were split into a game group or a control group; both groups were homogeneous in terms of previous training and baseline scores. The control group attended a classic 80 min teaching session with a neonatal trainer, while game group participants played four 20 min sessions over four different days. Three written tests (pre/immediately post-training and at 28 days) were used to evaluate and compare the two groups' performances. Results: Forty-eight pediatric/neonatology residents participated in the study. While classic training by a neonatal trainer demonstrated an excellent effectiveness in short/long-term knowledge retention, DGBL methodology proved to be equivalent or better. Furthermore, after each game session, DGBL score improved for both procedure knowledge and ventilation/chest compressions rate. Conclusions: In this study, DGBL was as effective as classic specialist training for neonatal resuscitation in terms of both algorithm memorization and knowledge retention. User appreciation for the methodology and ease of administration, including remotely, support the use of DGBL methodologies for pediatric/neonatology residents education.

Sensitivity analysis of an electrophysiology model for the left ventricle.

Modelling the cardiac electrophysiology entails dealing with the uncertainties related to the input parameters such as the heart geometry and the electrical conductivities of the tissues, thus calling for an uncertainty quantification (UQ) of the results. Since the chambers of the heart have different shapes and tissues, in order to make the problem affordable, here we focus on the left ventricle with the aim of identifying which of the uncertain inputs mostly affect its electrophysiology. In a first phase, the uncertainty of the input parameters is evaluated using data available from the literature and the output quantities of interest (QoIs) of the problem are defined. According to the polynomial chaos expansion, a training dataset is then created by sampling the parameter space using a quasi-Monte Carlo method whereas a smaller independent dataset is used for the validation of the resulting metamodel. The latter is exploited to run a global sensitivity analysis with nonlinear variance-based indices and thus reduce the input parameter space accordingly. Thereafter, the uncertainty probability distribution of the QoIs are evaluated using a direct UQ strategy on a larger dataset and the results discussed in the light of the medical knowledge.