Evaluation of different machine learning algorithms for predicting the length of stay in the emergency departments: a single-centre study.

Background: Recently, crowding in emergency departments (EDs) has become a recognised critical factor impacting global public healthcare, resulting from both the rising supply/demand mismatch in medical services and the paucity of hospital beds available in inpatients units and EDs. The length of stay in the ED (ED-LOS) has been found to be a significant indicator of ED bottlenecks. The time a patient spends in the ED is quantified by measuring the ED-LOS, which can be influenced by inefficient care processes and results in increased mortality and health expenditure. Therefore, it is critical to understand the major factors influencing the ED-LOS through forecasting tools enabling early improvements. Methods: The purpose of this work is to use a limited set of features impacting ED-LOS, both related to patient characteristics and to ED workflow, to predict it. Different factors were chosen (age, gender, triage level, time of admission, arrival mode) and analysed. Then, machine learning (ML) algorithms were employed to foresee ED-LOS. ML procedures were implemented taking into consideration a dataset of patients obtained from the ED database of the "San Giovanni di Dio e Ruggi d'Aragona" University Hospital (Salerno, Italy) from the period 2014-2019. Results: For the years considered, 496,172 admissions were evaluated and 143,641 of them (28.9%) revealed a prolonged ED-LOS. Considering the complete data (48.1% female vs. 51.9% male), 51.7% patients with prolonged ED-LOS were male and 47.3% were female. Regarding the age groups, the patients that were most affected by prolonged ED-LOS were over 64 years. The evaluation metrics of Random Forest algorithm proved to be the best; indeed, it achieved the highest accuracy (74.8%), precision (72.8%), and recall (74.8%) in predicting ED-LOS. Conclusions: Different variables, referring to patients' personal and clinical attributes and to the ED process, have a direct impact on the value of ED-LOS. The suggested prediction model has encouraging results; thus, it may be applied to anticipate and manage ED-LOS, preventing crowding and optimising effectiveness and efficiency of the ED.

The Safety Profile of COVID-19 Vaccines in Patients Diagnosed with Multiple Sclerosis: A Retrospective Observational Study.

In the current COVID-19 pandemic, patients diagnosed with multiple sclerosis (MS) are considered to be one of the highest priority categories, being recognized as extremely vulnerable people. For this reason, mRNA-based COVID-19 vaccines are strongly recommended for these patients. Despite encouraging results on the efficacy and safety profile of mRNA-based COVID-19 vaccines, to date, in frail populations, including patients diagnosed with MS, this information is rather limited. We carried out a retrospective observational study with the aim to evaluate the safety profile of mRNA-based COVID-19 vaccines by retrieving real-life data of MS patients who were treated and vaccinated at the Multiple Sclerosis Center of the Hospital A.O.R.N. A. Cardarelli. Three-hundred and ten medical records of MS patients who received the first dose of the mRNA-based COVID-19 vaccine were retrieved (63% female; mean age: 45.9 years). Of these patients, 288 also received the second dose. All patients received the Pfizer-BioNTech vaccine. Relapsing-Remitting Multiple Sclerosis (RRSM) was the most common form of MS. The Expanded Disability Status Scale (EDSS) values were <3.0 in 70% of patients. The majority of patients received a Disease Modifying Therapy (DMT) during the study period, mainly interferon beta 1-a, dimethyl fumarate, and natalizumab and fingolimod. Overall, 913 AEFIs were identified, of which 539 were after the first dose of the vaccine and 374 after the second dose. The majority of these AEFIs were classified as short-term since they occurred within the first 72 h. The most common identified adverse events were pain at injection site, flu-like symptoms, and headache. Fever was reported more frequently after the second dose than after the first dose. SARS-CoV-2 infection occurred in 3 patients after the first dose. Using historical data of previous years (2017−2020), the relapses' rate during 2021 was found to be lower. Lastly, the results of the multivariable analysis that assessed factors associated with the occurrence of AEFIs revealed a statistical significance for age, sex, and therapy with ocrelizumab (p < 0.05). In conclusion, our results indicated that Pfizer-BioNTech vaccine was safe for MS patients, being associated with AEFIs already detected in the general population. Larger observational studies with longer follow-up and epidemiological studies are strongly needed.

Case Report: A Novel Homozygous Missense Variant of FBN3 Supporting It Is a New Candidate Gene Causative of a Bardet-Biedl Syndrome-Like Phenotype.

Fibrillin proteins are extracellular matrix glycoproteins assembling into microfibrils. FBN1, FBN2, and FBN3 encode the human fibrillins and mutations in FBN1 and FBN2 cause connective tissue disorders called fibrillinopathies, affecting cardiovascular, dermal, skeletal, and ocular tissues. Recently, mutations of the less characterized fibrillin family member, FBN3, have been associated in a single family with Bardet-Biedl syndrome (BBS). Here, we report on a patient born from two first cousins and affected by developmental delay, cognitive impairment, obesity, dental and genital anomalies, and brachydactyly/syndactyly. His phenotype was very similar to that reported in the previous FBN3-mutated family and fulfilled BBS clinical diagnostic criteria, although lacking polydactyly, the most recurrent clinical feature, as the previous siblings described. A familial SNP-array and proband's WES were performed prioritizing candidate variants on the sole patient's runs of homozygosity. This analysis disclosed a novel homozygous missense variant in FBN3 (NM_032447:c.5434A>G; NP_115823:p.Ile1812Val; rs115948457), inherited from the heterozygous parents. This study further supports that FBN3 is a candidate gene for a BBS-like syndrome characterized by developmental delay, cognitive impairment, obesity, dental, genital, and skeletal anomalies. Anyway, additional studies are necessary to investigate the exact role of the gene and possible interactions between FBN3 and BBS proteins.

A case study to investigate the impact of overcrowding indices in emergency departments.

BACKGROUND: Emergency department (ED) overcrowding is widespread in hospitals in many countries, causing severe consequences to patient outcomes, staff work and the system, with an overall increase in costs. Therefore, health managers are constantly looking for new preventive and corrective measures to counter this phenomenon. To do this, however, it is necessary to be able to characterize the problem objectively. For this reason, various indices are used in the literature to assess ED crowding. In this work, we explore the use of two of the most widespread crowding indices in an ED of an Italian national hospital, investigate their relationships and discuss their effectiveness. METHODS: In this study, two of the most widely used indices in the literature, the National Emergency Department Overcrowding Scale (NEDOCS) and the Emergency Department Working Index (EDWIN), were analysed to characterize overcrowding in the ED of A.O.R.N. "A. Cardarelli" of Naples, which included 1678 clinical cases. The measurement was taken every 15 minutes for a period of 7 days. RESULTS: The results showed consistency in the use of EDWIN and NEDOCS indices as measures of overcrowding, especially in severe overcrowding conditions. Indeed, in the examined case study, both EDWIN and NEDOCS showed very low rates of occurrence of severe overcrowding (2-3%). In contrast, regarding differences in the estimation of busy to overcrowded ED rates, the EDWIN index proved to be less sensitive in distinguishing these variations in the occupancy of the ED. Furthermore, within the target week considered in the study, the results show that, according to both EDWIN and NEDOCS, higher overcrowding rates occurred during the middle week rather than during the weekend. Finally, a low degree of correlation between the two indices was found. CONCLUSIONS: The effectiveness of both EDWIN and NEDOCS in measuring ED crowding and overcrowding was investigated, and the main differences and relationships in the use of the indices are highlighted. While both indices are useful ED performance metrics, they are not always interchangeable, and their combined use could provide more details in understanding ED dynamics and possibly predicting future critical conditions, thus enhancing ED management.

Physiologic Range of Myocardial Mechano-Energetic Efficiency among Healthy Subjects: Impact of Gender and Age.

BACKGROUND: Myocardial mechano-energetic efficiency (MEE) is the capability of the left ventricle (LV) to convert the chemical energy obtained from the cardiac oxidative metabolism into mechanical work. The aim of present study was to establish normal non-invasive MEE and MEEi reference values. METHODS: In total, 1168 healthy subjects underwent physical examinations, clinical assessment, and standardized transthoracic echocardiographic (TTE) examination. MEE was obtained by TTE as the ratio between stroke volume (SV) and heart rate (HR): MEE = SV/HR [HR expressed in seconds (HR/60)]. Because MEE is highly related to left ventricular mass (LVM), MEE was then divided by LVM with the purpose of obtaining an estimate of energetic expenditure per unit of myocardial mass (i.e., indexed MEE, MEEi, mL/s/g). RESULTS: The mean values of MEE and MEEi in the overall population were 61.09 ± 18.19 mL/s; 0.45 ± 0.14, respectively. In a multivariable analysis, gender, body surface area (BSA), diastolic blood pressure, left atrial volume indexed to BSA, E/e' and tricuspid annular plane systolic excursion (TAPSE) were the independent variables associated with MEE, while age, gender, BSA and TAPSE were the independent variables associated with MEEi. CONCLUSIONS: The knowledge of age- and gender-based MEE and MEEi normal values may improve the global assessment of LV cardiac mechanics and serve as a reference to identify phenotypes at high risk of cardiovascular events.

Lean Management Approach for Reengineering the Hospital Cardiology Consultation Process: A Report from AORN "A. Cardarelli" of Naples.

BACKGROUND: Consultations with specialists are essential for safe and high-quality care for all patients. Cardiology consultations, due to a progressive increase in cardiology comorbidities, are becoming more common in hospitals prior to any type of treatment. The appropriateness and correctness of the request, the waiting time for delivery and the duration of the visit are just a few of the elements that can affect the quality of the process. METHODS: In this work, a Lean approach and Telemedicine are used to optimize the cardiology consultancy process provided by the Cardiology Unit of "Antonio Cardarelli" Hospital of Naples (Italy), the largest hospital in the southern Italy. RESULTS: The application of corrective actions, with the introduction of portable devices and telemedicine, led to a reduction in the percentage of waiting for counseling from 29.6% to 18.3% and an increase in the number of patients treated. CONCLUSIONS: The peculiarity of the study is to apply an innovative methodology such as Lean Thinking in optimizing the cardiology consultancy process, currently little studied in literature, with benefits for both patients and medical staff.

De Novo Mutation in KMT2C Manifesting as Kleefstra Syndrome 2: Case Report and Literature Review.

Diagnosis of pediatric intellectual disability (ID) can be difficult because it is due to a vast number of established and novel causes. Here, we described a full-term female infant affected by Kleefstra syndrome-2 presenting with neurodevelopmental disorder, a history of hypotonia and minor face anomalies. A systematic literature review was also performed. The patient was a 6-year-old Caucasian female. In the family history there was no intellectual disability or genetic conditions. Auxological parameters at birth were adequate for gestational age. Clinical evaluation at 6 months revealed hypotonia and, successively, delay in the acquisition of the stages of psychomotor development. Auditory, visual, somatosensory, and motor-evoked potentials were normal. A brain MRI, performed at 9 months, showed minimal gliotic changes in bilateral occipital periventricular white matter. Neuropsychiatric control, performed at 5 years, established a definitive diagnosis of childhood autism and developmental delay. Molecular analysis of the exome revealed a novel KMT2C missense variant: c.9244C > T (p.Pro3082Ser) at a heterozygous state, giving her a diagnosis of Kleefstra syndrome 2. Parents did not show the variant. Literature review (four retrieved eligible studies, 10 patients) showed that all individuals had mild, moderate, or severe ID; language and motor delay; and autism. Short stature, microcephaly, childhood hypotonia and plagiocephaly were also present. Conclusion. Kleefstra syndrome 2 is a difficult diagnosis of a rare condition with a high clinical phenotypic heterogeneity. This study suggests that it must be taken in account in the work-up of an orphan diagnosis of intellectual disability and/or autism spectrum disorder.

Preoperative Assessment and Management of Cardiovascular Risk in Patients Undergoing Non-Cardiac Surgery: Implementing a Systematic Stepwise Approach during the COVID-19 Pandemic Era.

Major adverse cardiac events, defined as death or myocardial infarction, are common causes of perioperative mortality and major morbidity in patients undergoing non-cardiac surgery. Reduction of perioperative cardiovascular risk in relation to non-cardiac surgery requires a stepwise patient evaluation that integrates clinical risk factors, functional status and the estimated stress of the planned surgical procedure. Major guidelines on preoperative cardiovascular risk assessment recommend to establish, firstly, the risk of surgery per se (low, moderate, high) and the related timing (elective vs. urgent/emergent), evaluate the presence of unstable cardiac conditions or a recent coronary revascularization (percutaneous coronary intervention or coronary artery bypass grafting), assess the functional capacity of the patient (usually expressed in metabolic equivalents), determine the value of non-invasive and/or invasive cardiovascular testing and then combine these data in estimating perioperative risk for major cardiac adverse events using validated scores (Revised Cardiac Risk Index (RCRI) or National Surgical Quality Improvement Program (NSQIP)). This stepwise approach has the potential to guide clinicians in determining which patients could benefit from cardiovascular therapy and/or coronary artery revascularization before non-cardiac surgery towards decreasing the incidence of perioperative morbidity and mortality. Finally, it should be highlighted that there is a need to implement specific strategies in the 2019 Coronavirus disease (COVID-19) pandemic to minimize the risk of transmission of COVID-19 infection during the preoperative risk assessment process.

Successful surgical repair of left ventricular pseudoaneurysm in a patient with subacute ST-elevation myocardial infarction.

We report a successful surgical repair of left ventricular pseudoaneurysm in a patient with subacute ST-elevation myocardial infarction (STEMI). In the case of expansion of the infarct related ventricular wall, early (within 24 hours) or late (3-5 days after STEMI) cardiac rupture should be always borne in mind in order to proceed to life saving prompt surgical repair.