Change in eating habits after 2 years of pandemic restrictions among adolescents living in a city in northern Italy: results of the COALESCENT Observational Study (Change amOng ItAlian adoLESCENTs).

Background: Lockdown measures during the recent pandemic, due to the novel COVID-19, affected several other aspects of lifestyle, but little is known about their long-term impact, especially among adolescents. Our study aimed to assess the long-term consequences of changes in diet, exercise and screen activity levels, sleep quality, smoke, smartphone addiction and emotional distress among a sample of Italian adolescents, 2 years after the beginning of the pandemic. Methods: We submitted an online survey to high-school students in the province of Brescia, a city in Northern Italy, investigating changes in food consumption and in physical and screen activities, cooking skills, sleep duration and quality, emotional distress, smartphone addiction and nutrition knowledge. We assigned an Eating Habit Index (EHI) score from 0 to 54, reflecting a current worsening (lower score) or improvement (higher score) in overall diet quality, compared with the pre-pandemic period. The χ2 test or Fisher's exact probability test and Mann-Whitney test were used as appropriate; a binary logistic regression model was carried out, with EHI score≥33 as the dependent variable. Results: We collected 1686 questionnaires. Consumption of healthy foods increased, as it was for ultraprocessed foods (UPFs). EHI score>33 (75° percentile value) was associated with female gender (OR 1.81, p<0.0001), better nutrition knowledge (OR 1.54, p=0.001), better cooking skills (OR 1.43, p=0.01), lower consumption of UPFs before the pandemic (OR 2.19, p<0.0001), self-perception of healthier diet quality (OR: 4.05, p<0.0001) and no smartphone addiction (OR: 1.35, p=0.02). Conclusions: Considering the profound impact of lifestyle on both physical and mental health, our results could be relevant to understand how to promote healthy eating practices among young people.

Fat Fraction Extracted from Whole-Body Magnetic Resonance (WB-MR) in Bone Metastatic Prostate Cancer: Intra- and Inter-Reader Agreement of Single-Slice and Volumetric Measurements.

BACKGROUND: This study evaluates the repeatability and reproducibility of fat-fraction percentage (FF%) in whole-body magnetic resonance imaging (WB-MRI) of prostate cancer patients with bone metastatic hormone naive disease. METHODS: Patients were selected from the database of a prospective phase-II trial. The treatment response was assessed using the METastasis Reporting and Data System for Prostate (MET-RADS-P). Two operators identified a Small Active Lesion (SAL, <10 mm) and a Large Active Lesion (LAL, ≥10 mm) per patient, performing manual segmentation of lesion volume and the largest cross-sectional area. Measurements were repeated by one operator after two weeks. Intra- and inter-reader agreements were assessed via Interclass Correlation Coefficient (ICC) on first-order radiomics features. RESULTS: Intra-reader ICC showed high repeatability for both SAL and LAL in a single slice (SS) and volumetric (VS) measurements with values ranging from 0.897 to 0.971. Inter-reader ICC ranged from 0.641 to 0.883, indicating moderate to good reproducibility. Spearman's rho analysis confirmed a strong correlation between SS and VS measurements for SAL (0.817) and a moderate correlation for LAL (0.649). Both intra- and inter-rater agreement exceeded 0.75 for multiple first-order features across lesion sizes. CONCLUSION: This study suggests that FF% measurements are reproducible, particularly for larger lesions in both SS and VS assessments.

Adenoid Cystic carcinoma of minor salivary glands (AdCCmSG): a multidisciplinary update.

INTRODUCTION: Adenoid cystic carcinoma of minor salivary glands (AdCCmSG) represents a 'rarity in the rarity,' posing a clinical challenge in lack of standardized, evidence-based recommendations. At present, AdCCmSG management is mostly translated from major salivary gland cancers (MSGCs). Ideally, AdCCmSG diagnostic-therapeutic workup should be discussed and carried out within a multidisciplinary, high-expertise setting, including pathologists, surgeons, radiation oncologists and medical oncologists. AREAS COVERED: The present review provides an overview of epidemiology and pathologic classification. Moreover, the most recent, clinically relevant updates in the treatment of AdCCmSG (Pubmed searches, specific guidelines) are critically discussed, aiming to a better understanding of this rare pathologic entity, potentially optimizing the care process, and offering a starting point for reflection on future therapeutic developments. EXPERT OPINION: The management of rare cancers is often hindered by limited data and clinical trials, lack of evidence-based guidelines, and hardly represented disease heterogeneity, which cannot be successfully tackled with a 'one-size-fits-all' approach. Our goal is to address these potential pitfalls, providing an easy-to-use, updated, multidisciplinary collection of expert opinions concerning AdCCmSG management as of today's clinical practice. We will also cover the most promising future perspectives, based on the potential therapeutic targets highlighted within AdCCmSG's molecular background.

A Pathophysiological Approach to Spontaneous Orbital Meningoceles: Case Report and Systematic Review.

BACKGROUND: Spontaneous orbital cephaloceles are a rare condition. The purpose of this study is to provide a description of a clinical case and to carry out a systematic literature review. METHODS: A systematic review of the English literature published on the Pubmed, Scopus, and Web of Science databases was conducted, according to the PRISMA recommendations. RESULTS: A 6-year-old patient was admitted for right otomastoiditis and thrombosis of the sigmoid and transverse sinuses, as well as the proximal portion of the internal jugular vein. Radiological examinations revealed a left orbital mass (22 × 14 mm) compatible with asymptomatic orbital meningocele (MC) herniated from the superior orbital fissure (SOF). The child underwent a right mastoidectomy. After the development of symptoms and signs of intracranial hypertension (ICH), endovascular thrombectomy and transverse sinus stenting were performed, with improvement of the clinical conditions and reduction of the orbital MC. The systematic literature review encompassed 29 publications on 43 patients with spontaneous orbital MC. In the majority of cases, surgery was the preferred treatment. CONCLUSIONS: The present case report and systematic review highlight the importance of ICH investigation and a pathophysiological-oriented treatment approach. The experiences described in the literature are limited, making the collection of additional data paramount.

CT and MR anatomy of the larynx and hypopharynx.

Imaging of the larynx and hypopharynx is frequently requested to assess the extent of neoplasms beyond the field of view of endoscopic evaluation. The combination of optical and cross-sectional imaging allows tumors to be classified according to AJCC/UICC guidelines. A thorough understanding of laryngeal and hypopharyngeal anatomy is crucial to guide the radiological eye along the possible pathways of the spread of diseases and to guide differential diagnoses. Computed tomography (CT) has been the first cross-sectional imaging technique used to evaluate the larynx and hypopharynx; its spatial resolution combined with volumetric capability and the use of injectable contrast medium made CT the working horse in the assessment of neoplastic and inflammatory diseases. In the last two decades, magnetic resonance (MR) supported CT in the most challenging cases, when the optimal contrast resolution due to the multisequence portfolio is needed to assess the neoplastic involvement of laryngeal cartilages, paraglottic space(s), and extra laryngeal spread. The aim of this paper is to give a comprehensive radiological overview of larynx and hypopharynx complex anatomy, combining in vivo images, anatomical sections, and images of ex vivo specimens.

Computer-aided designed 3D-printed polymeric scaffolds for personalized reconstruction of maxillary and mandibular defects: a proof-of-concept study.

PURPOSE: To investigate the potential reconstruction of complex maxillofacial defects using computer-aided design 3D-printed polymeric scaffolds by defining the production process, simulating the surgical procedure, and explore the feasibility and reproducibility of the whole algorithm. METHODS: This a preclinical study to investigate feasibility, reproducibility and efficacy of the reconstruction algorithm proposed. It encompassed 3 phases: (1) scaffold production (CAD and 3D-printing in polylactic acid); (2) surgical simulation on cadaver heads (navigation-guided osteotomies and scaffold fixation); (3) assessment of reconstruction (bone and occlusal morphological conformance, symmetry, and mechanical stress tests). RESULTS: Six cadaver heads were dissected. Six types of defects (3 mandibular and 3 maxillary) with different degree of complexity were tested. In all case the reconstruction algorithm could be successfully completed. Bone morphological conformance was optimal while the occlusal one was slightly higher. Mechanical stress tests were good (mean value, 318.6 and 286.4 N for maxillary and mandibular defects, respectively). CONCLUSIONS: Our reconstructive algorithm was feasible and reproducible in a preclinical setting. Functional and aesthetic outcomes were satisfactory independently of the complexity of the defect.

Prognostic Value of Anteroposterior Extension in Oral Tongue and Floor Squamous Cell Carcinoma.

Importance: The tongue and oral floor represent the most involved subsite by oral cancer, and there are no reported systems to classify anteroposterior tumor extension with prognostic effect. In other cancers, the anterior vs posterior tumor extension is a relevant prognostic factor. Objective: To establish whether anterior vs posterior tumor extension may represent a prognostic factor in oral tongue and floor squamous cell carcinoma (OTFSCC). Design, Setting, and Participants: This was a retrospective cohort study of patients who underwent surgery for OTFSCC from January 1, 2010, to December 31, 2021, at 2 tertiary-level academic institutions in Italy (University of Padua and University of Brescia). Patients eligible for the study had histologically proven primary OTFSCC; underwent surgery-based, curative treatment; and had available preoperative contrast-enhanced imaging. Exposures: Four anatomical lines were designed to assess tumor extension: (1) chin-palate line (CPL), (2) chin-basion line, (3) Stensen duct line, and (4) lingual septum line. Preoperative imaging was re-evaluated, and tumor extension was classified as either anterior or posterior according to the lines. Main Outcomes and Measures: Overall survival and time to recurrence (TTR) were evaluated according to tumor extension. These outcomes were reported as 5-year survival rates with 95% CIs. Results: Of the 133 patients included, 79 (59.4%) were male, and the mean (SD) age was 62.7 (15.4) years. The 5-year TTR difference was higher for posterior vs anterior OTFSCC classified according to CPL (21.0%; 95% CI, 8.3%-33.7%), Stensen duct line (15.5%; 95% CI, 1.0%-30.0%), and lingual septum line (17.2%; 95% CI, 2.2%-32.3%). Overall survival analysis showed similar results. At the multivariable analysis on TTR, N status (adjusted hazard ratio [HR], 3.0; 95% CI, 1.2-7.1) and anteroposterior classification according to CPL (adjusted HR, 7.1; 95% CI, 0.9-54.6) were the variables associated with the highest adjusted HRs. Conclusions and Relevance: In this cohort study, OTFSCC with a posterior extension to the CPL was associated with a higher risk of recurrence and death. This analysis suggests that the poor prognosis conveyed by the posterior tumor extension is independent of other relevant prognosticators except for the burden of nodal disease. This estimate is not precise and does not allow for definitive clinically important conclusions; therefore, further prospective studies are necessary to confirm these data.

Cooking Skills, Eating Habits and Nutrition Knowledge among Italian Adolescents during COVID-19 Pandemic: Sub-Analysis from the Online Survey COALESCENT (Change amOng ItAlian adoLESCENTs).

BACKGROUND: Cooking skills (CS) have the potential to improve self-care behaviours and healthy development among adolescents. The COVID-19 pandemic has affected lifestyles worldwide, and the present study aims to investigate the level of CS after the pandemic, as well as its associations with nutrition knowledge and eating behaviours among a cohort of Italian adolescents. METHODS: We submitted an online survey about lifestyle changes to students aged 13-21 years during the pandemic. Based on overall culinary abilities, we divided respondents into high, medium and low CS. Worsening or improvement in diet quality was detected by assigning an eating habit index (EHI; 0-54). RESULTS: Out of the 1686 questionnaires collected, 21.5%, 63.6% and 14.9% reported high, medium and low CS, respectively. The EHI scores were statistically higher among students who were able to cook more than 20 recipes compared to those reporting no cooking abilities (30.2 ± 5.9 vs. 26.6 ± 5.7; p = 0.0001). High CS significantly correlated with better EHI (OR 1.44; p = 0.009), lower consumption of ultra-processed food (OR 1.80; p < 0.0001) and better nutrition knowledge (OR 1.42; p = 0.007). CONCLUSIONS: Adolescents with good CS showed better nutrition knowledge and healthier eating habits, including lower consumption of ultra-processed foods. Projects aimed to improve CS in adolescents can therefore promote healthier development.

COVID-19 Pneumonia with Migratory Pattern in Agammaglobulinemic Patients: A Report of Two Cases and Review of Literature.

X-linked agammaglobulinemia (XLA) is a primary immunodeficiency characterized by marked reduction in serum immunoglobulins and early-onset infections. Coronavirus Disease-2019 (COVID-19) pneumonia in immunocompromised patients presents clinical and radiological peculiarities which have not yet been completely understood. Very few cases of agammaglobulinemic patients with COVID-19 have been reported since the beginning of the pandemic in February 2020. We report two cases of migrant COVID-19 pneumonia in XLA patients.

Magnetic resonance diagnosis of laryngeal chondritis after transoral laser microsurgery for laryngeal cancer.

Objective: Laryngeal chondritis (LC) is a rare complication of carbon dioxide transoral laser microsurgery (CO2 TOLMS) for laryngeal tumours and can pose a diagnostic challenge. Its magnetic resonance (MR) features have not been previously described. This study aims to characterise a cohort of patients who developed LC after CO2 TOLMS and describe its clinical and MR findings. Methods: Clinical records and MR images of all patients presenting with LC after CO2 TOLMS between 2008 and 2022 were reviewed. Results: Seven patients were analysed. Timing of LC diagnosis ranged from 1 to 8 months after CO2 TOLMS. Four patients were symptomatic. Abnormal endoscopic findings included suspected tumour recurrence in 4 patients. MR documented focal or extensive signal changes involving the thyroid lamina and para-laryngeal space with T2 hyperintensity, T1 hypointensity and intense contrast enhancement (n = 7), and minimally reduced mean apparent diffusion coefficient (ADC) values (1.0-1.5 x 10-3 mm2/s) (n = 6). A favourable clinical outcome was achieved in all patients. Conclusions: LC after CO2 TOLMS has a distinctive MR pattern. When tumour recurrence cannot be confidently excluded based on imaging, antibiotic therapy, close clinical and radiological follow-up and/or biopsy are recommended.

AI-Based Automated Lipomatous Tumor Segmentation in MR Images: Ensemble Solution to Heterogeneous Data.

Deep learning (DL) has been proposed to automate image segmentation and provide accuracy, consistency, and efficiency. Accurate segmentation of lipomatous tumors (LTs) is critical for correct tumor radiomics analysis and localization. The major challenge of this task is data heterogeneity, including tumor morphological characteristics and multicenter scanning protocols. To mitigate the issue, we aimed to develop a DL-based Super Learner (SL) ensemble framework with different data correction and normalization methods. Pathologically proven LTs on pre-operative T1-weighted/proton-density MR images of 185 patients were manually segmented. The LTs were categorized by tumor locations as distal upper limb (DUL), distal lower limb (DLL), proximal upper limb (PUL), proximal lower limb (PLL), or Trunk (T) and grouped by 80%/9%/11% for training, validation and testing. Six configurations of correction/normalization were applied to data for fivefold-cross-validation trainings, resulting in 30 base learners (BLs). A SL was obtained from the BLs by optimizing SL weights. The performance was evaluated by dice-similarity-coefficient (DSC), sensitivity, specificity, and Hausdorff distance (HD95). For predictions of the BLs, the average DSC, sensitivity, and specificity from the testing data were 0.72 [Formula: see text] 0.16, 0.73 [Formula: see text] 0.168, and 0.99 [Formula: see text] 0.012, respectively, while for SL predictions were 0.80 [Formula: see text] 0.184, 0.78 [Formula: see text] 0.193, and 1.00 [Formula: see text] 0.010. The average HD95 of the BLs were 11.5 (DUL), 23.2 (DLL), 25.9 (PUL), 32.1 (PLL), and 47.9 (T) mm, whereas of SL were 1.7, 8.4, 15.9, 2.2, and 36.6 mm, respectively. The proposed method could improve the segmentation accuracy and mitigate the performance instability and data heterogeneity aiding the differential diagnosis of LTs in real clinical situations.

Microsurgical transcranial approaches to the posterior surface of petrosal portion of the temporal bone: quantitative analysis of surgical volumes and exposed areas.

Different microsurgical transcranial approaches (MTAs) have been described to expose the posterior surface of the petrous bone (PPB). A quantitative, anatomical comparison of the most used MTAs, for specific areas of the PPB, is not available. Anatomical dissections were performed on five formalin-fixed, latex-injected cadaver heads (10 sides). Six MTAs were analyzed: Kawase approach (KWA), retrosigmoid approach (RSA), retrosigmoid approach with suprameatal extension (RSAS), retrolabyrinthine approach (RLA), translabyrinthine approach (TLA), and transcochlear approach (TCA). Surgical volumes and exposed areas of each approach were quantified with a dedicated neuronavigation system (ApproachViewer, part of GTx-Eyes II, University Health Network, Toronto, Canada) and adjuvant software (ITK-SNAP and Autodesk Meshmixer 3.5). Areas and volumes were compared using linear mixed models. TCA provided the best exposure of Trautmann's triangle and the retromeatal, suprameatal, meatal, and premeatal regions. RSAs provided the best exposure of the inframeatal region, with RSAS gaining significant exposure of the suprameatal region. KWA had the highest surgical volume, and RLA the lowest. Transpetrosal approaches offer the widest exposure of PPB proportionally to their invasiveness. Retrosigmoid approaches, which get to the studied region through a postero-lateral path, are paramount for the exposure of the inframeatal and suprameatal region and, given the adequate exposure of the remaining PPB, represent an effective approach for the cerebellopontine angle (CPA). These anatomical findings must be considered with approach-related morbidity and the pathological features in order to choose the most appropriate approach in clinical practice.

The Oculomotor Cistern and Its Role in the Management of Pituitary Lesions: An Anatomical, Radiographic, and Clinical Scoping Review.

BACKGROUND: The oculomotor cistern (OMC) is a cerebrospinal fluid space bound by meningeal layers that surrounds the oculomotor nerve as it crosses the oculomotor triangle to reach the lateral wall of the cavernous sinus at the level of the anterior clinoid process. Although several anatomical and radiological studies are available, its anatomy and relationship with pituitary adenomas (PAs) are still matter of discussion. OBJECTIVE: The aim of the study is to provide an updated and focused overview of the OMC, highlighting the different perspectives and descriptions from anatomical, radiological, and clinical points of view. METHODS: A scoping review was conducted up to 29th October 2022, according to PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) criteria. PubMed, Web of Science, Scopus databases, and correlated citations were investigated. RESULTS: Of the 562 records identified, 22 were included in the present analysis. There were 13, 5, and 4 anatomo-surgical, radiological, and clinical studies, respectively. Though there is general consensus on its definition, data are variable on different features of OMC. Defects or absence of dural layers adjacent to the oculomotor nerve were described in only 4 papers. The transition from meningeal to neural layers is still unclear. PAs with OMC involvement are poorly studied and have unique clinical characteristics. To date, 21 patients have been described; the reported prevalence of OMC involvement by PAs ranges from 4.1% to 14.6%. CONCLUSIONS: Clarifying the OMC features with further systematic studies may not only broaden theoretical knowledge but also have implications on endoscopic transnasal pituitary surgery.

Deep learning to detect significant coronary artery disease from plain chest radiographs AI4CAD.

BACKGROUND: The predictive role of chest radiographs in patients with suspected coronary artery disease (CAD) is underestimated and may benefit from artificial intelligence (AI) applications. OBJECTIVES: To train, test, and validate a deep learning (DL) solution for detecting significant CAD based on chest radiographs. METHODS: Data of patients referred for angina and undergoing chest radiography and coronary angiography were analysed retrospectively. A deep convolutional neural network (DCNN) was designed to detect significant CAD from posteroanterior/anteroposterior chest radiographs. The DCNN was trained for severe CAD binary classification (absence/presence). Coronary angiography reports were the ground truth. Stenosis severity of ≥70% for non-left main vessels and ≥ 50% for left main defined severe CAD. RESULTS: Information of 7728 patients was reviewed. Severe CAD was present in 4091 (53%). Patients were randomly divided for algorithm training (70%; n = 5454) and fine-tuning/model validation (10%; n = 773). Internal clinical validation (model testing) was performed with the remaining patients (20%; n = 1501). At binary logistic regression, DCNN prediction was the strongest severe CAD predictor (p < 0.0001; OR: 1.040; CI: 1.032-1.048). Using a high sensitivity operating cut-point, the DCNN had a sensitivity of 0.90 to detect significant CAD (specificity 0.31; AUC 0.73; 95% CI DeLong, 0.69-0.76). Adding to the AI chest radiograph interpretation angina status improved the prediction (AUC 0.77; 95% CI DeLong, 0.74-0.80). CONCLUSION: AI-read chest radiographs could be used to pre-test significant CAD probability in patients referred for suspected angina. Further studies are required to externally validate our algorithm, develop a clinically applicable tool, and support CAD screening in broader settings.

Residual Lung Abnormalities in Survivors of Severe or Critical COVID-19 at One-Year Follow-Up Computed Tomography: A Narrative Review Comparing the European and East Asian Experiences.

The literature reports that there was a significant difference in the medical impact of the coronavirus disease (COVID-19) pandemic between European and East Asian countries; specifically, the mortality rate of COVID-19 in Europe was significantly higher than that in East Asia. Considering such a difference, our narrative review aimed to compare the prevalence and characteristics of residual lung abnormalities at one-year follow-up computed tomography (CT) after severe or critical COVID-19 in survivors of European and East Asian countries. A literature search was performed to identify articles focusing on the prevalence and characteristics of CT lung abnormalities in survivors of severe or critical COVID-19. Database analysis identified 16 research articles, 9 from Europe and 7 from East Asia (all from China). Our analysis found a higher prevalence of CT lung abnormalities in European than in Chinese studies (82% vs. 52%). While the most prevalent lung abnormalities in Chinese studies were ground-glass opacities (35%), the most prevalent lung abnormalities in European studies were linear (59%) and reticular opacities (55%), followed by bronchiectasis (46%). Although our findings required confirmation, the higher prevalence and severity of lung abnormalities in European than in Chinese survivors of COVID-19 may reflect a greater architectural distortion due to a more severe lung damage.

Salvage surgery in recurrent sinonasal cancers: Proposal for a prognostic model based on clinicopathologic and treatment-related parameters.

BACKGROUND: Evidence on survival and major prognosticators after salvage surgery in recurrent sinonasal cancers (SNC) is limited. METHODS: A retrospective, single-center study of recurrent SNC treated with salvage surgery between 1997 and 2019 was conducted. Univariate and multivariable analyses were performed to define a prognostic score for overall survival (OS). RESULTS: One hundred and eighteen patients were included. Recurrent SNC originated mostly in the naso-ethmoidal box (67.8%) and were mainly epithelial (76.2%), high-grade (49.2%), and locally advanced (rpT4, 60.1%) malignancies. Negative margins were achieved in 56.6% of cases. Two- and 5-year OS were 71.7% and 56%, respectively. The prognostic model included treatment modality for primary tumor, histology, rpT class, margin status, perineural invasion, and adjuvant radiotherapy and stratified patients into three prognostic groups (5-year OS: 84.4%, 44.9%, and 0%, respectively). CONCLUSIONS: Treatment of recurrent SNC can result in good long-term survival estimates with limited morbidity. Our score can provide excellent prognostic stratification.

Machine learning for prediction of in-hospital mortality in coronavirus disease 2019 patients: results from an Italian multicenter study.

BACKGROUND: Several risk factors have been identified to predict worse outcomes in patients affected by SARS-CoV-2 infection. Machine learning algorithms represent a novel approach to identifying a prediction model with a good discriminatory capacity to be easily used in clinical practice. The aim of this study was to obtain a risk score for in-hospital mortality in patients with coronavirus disease infection (COVID-19) based on a limited number of features collected at hospital admission. METHODS AND RESULTS: We studied an Italian cohort of consecutive adult Caucasian patients with laboratory-confirmed COVID-19 who were hospitalized in 13 cardiology units during Spring 2020. The Lasso procedure was used to select the most relevant covariates. The dataset was randomly divided into a training set containing 80% of the data, used for estimating the model, and a test set with the remaining 20%. A Random Forest modeled in-hospital mortality with the selected set of covariates: its accuracy was measured by means of the ROC curve, obtaining AUC, sensitivity, specificity and related 95% confidence interval (CI). This model was then compared with the one obtained by the Gradient Boosting Machine (GBM) and with logistic regression. Finally, to understand if each model has the same performance in the training and test set, the two AUCs were compared using the DeLong's test. Among 701 patients enrolled (mean age 67.2 ±â€Š13.2 years, 69.5% male individuals), 165 (23.5%) died during a median hospitalization of 15 (IQR, 9-24) days. Variables selected by the Lasso procedure were: age, oxygen saturation, PaO2/FiO2, creatinine clearance and elevated troponin. Compared with those who survived, deceased patients were older, had a lower blood oxygenation, lower creatinine clearance levels and higher prevalence of elevated troponin (all P < 0.001). The best performance out of the samples was provided by Random Forest with an AUC of 0.78 (95% CI: 0.68-0.88) and a sensitivity of 0.88 (95% CI: 0.58-1.00). Moreover, Random Forest was the unique model that provided similar performance in sample and out of sample (DeLong test P = 0.78). CONCLUSION: In a large COVID-19 population, we showed that a customizable machine learning-based score derived from clinical variables is feasible and effective for the prediction of in-hospital mortality.