Camilla Di Somma

Dr. Camilla Di Somma

Subintensive Care Unit and Respiratory Physiopathology Department Monaldi – Cotugno Hospital, Naples, Italy
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 October 2021 in Medicina
Verified
Journal Article
Open access
PDF file
GPGiorgio Emanuele Polistina
Giorgio Emanuele Polistina
MLMaurizia Lanza
Maurizia Lanza
CSCamilla Di Somma
Camilla Di Somma
AAanna annunziata
anna annunziata
GFGiuseppe Fiorentino
Giuseppe Fiorentino
Infection with severe acute respiratory syndrome coronavirus 2 causes coronavirus disease 2019 (COVID-19) which was revealed an official pandemic by the World Health Organization on 11 March 2020. The current pandemic, the third of this decade, is the worst in terms of suffering and deaths related. COVID-19 represents an unprecedented challenge for medical communities and patients around the world. High-resolution computed tomography of the chest (HRCT) is a fundamental tool in both management and diagnosis of the disease. Imaging plays an essential role in the diagnosis of all the manifestations of the disease and its complications and the correct use and interpretation of imaging tests are essential. Pneumomediastinum has been reported rarely in COVID-19 patients. We were one of the first groups to share our experiences in uncommon parenchymal complications of COVID-19 with spontaneous pneumothorax and pneumomediastinum, but also with new-onset bronchiectasis and cysts. A finding of pneumopericardium is also unusual. We hereby report a rare case of spontaneous pneumopericardium in a patient with COVID-19 pneumonia treated only with a high-flow nasal cannula (HFNC).

Verified
Journal Article
Open access
PDF file
AAanna annunziata
anna annunziata
SCSalvatore Cappabianca
Salvatore Cappabianca
Salvatore CapuozzoSalvatore Capuozzo
Salvatore Capuozzo
Nicola CoppolaNicola Coppola
Nicola Coppola
CSCamilla Di Somma
Camilla Di Somma
Carlo SansoneCarlo Sansone
Carlo Sansone
Hospital overcrowding, driven by both structural management challenges and widespread medical emergencies, has prompted extensive research into machine learning (ML) solutions for predicting patient length of stay (LOS) to optimize bed allocation. While many existing models simplify the LOS prediction problem to a classification task, predicting broad ranges of hospital days, an exact day-based regression model is often crucial for precise planning. Additionally, available data are typically limited and heterogeneous, often collected from a small patient cohort. To address these challenges, we present a novel multimodal ML framework that combines imaging and clinical data to enhance LOS prediction accuracy. Specifically, our approach uses the following: (i) feature extraction from chest CT scans via a convolutional neural network (CNN), (ii) their integration with clinically relevant tabular data from patient exams, refined through a feature selection system to retain only significant predictors. As a case study, we applied this framework to pneumonia patient data collected during the COVID-19 pandemic at two hospitals in Naples, Italy—one specializing in infectious diseases and the other general-purpose. Under our experimental setup, the proposed system achieved an average prediction error of only three days, demonstrating its potential to improve patient flow management in critical care environments.

5 September 2022 in Monaldi Archives for Chest Disease
Verified
Journal Article
Open access
PDF file
GPGiorgio Emanuele Polistina
Giorgio Emanuele Polistina
CSCamilla Di Somma
Camilla Di Somma
MFMartina Flora
Martina Flora
Alberto MaraoloAlberto Maraolo
Alberto Maraolo
NCNovella Carannante
Novella Carannante
GFGiuseppe Fiorentino
Giuseppe Fiorentino
The World Health Organization declared the Coronavirus Diseases 2019 (COVID-19) outbreak a global pandemic on March 11, 2020. COVID-19 had an impact on over 500 million people worldwide. According to the American Thoracic Society criteria, the respiratory spectrum of this disease ranges from mild illness to severe pneumonia, with the latter occurring in a not insignificant 15% of patients. A rapid increase in the incidence of COVID-19 pneumonia cases has been observed all over the world, resulting in a saturation of the Intensive Care Unit's capacity (ICUs). Because of this impressive outbreak, the ICU beds and invasive mechanical ventilators reached their capacity. Non-invasive supportive care has become an important option for keeping respiratory conditions under control. As a result, proper healthcare resource management was required to ensure adequate patient care. Respiratory Intensive Care Units (RICUs) have become a useful resource for managing complex patients due to a shortage of ICU capacity. This highlighted the importance of RICUs, where patients with moderate to severe respiratory failure can be treated with non-invasive respiratory support rather than being admitted to the ICU. The clinical outcomes and baseline characteristics of patients admitted to the RICU of Cotugno Hospital, a tertiary referral center in Naples (Italy), from January 2021 to October 2021 are described in this report.

6 September 2025 in Brain Sciences
Verified
Journal Article
Open access
PDF file
AAAnna Annunziata
Anna Annunziata
FSFrancesca Simioli
Francesca Simioli
GPGiorgio Emanuele Polistina
Giorgio Emanuele Polistina
AGAnna Michela Gaeta
Anna Michela Gaeta
MCMaria Cardone
Maria Cardone
GFGiuseppe Fiorentino
Giuseppe Fiorentino
Introduction: Myotonic dystrophies (DM) are progressive genetic disorders with multisystemic involvement, particularly affecting the muscular, respiratory, and neuropsychological systems. Myotonic dystrophy type 1 (DM1), or Steinert’s disease, may lead to severe respiratory complications, including sleep-disordered breathing and hypercapnia, often requiring noninvasive ventilation to manage respiratory failure. However, adherence to NIV remains a major challenge, often influenced by cognitive and psychological factors such as apathy and depression. This study aims to investigate the presence of depression and SDB in patients with DM1 initiating NIV, and to evaluate factors influencing adherence to ventilatory support. Materials and Methods: We selected 13 adult patients (≥18 years) with diagnosis of Steinert’s disease with respiratory impairment who needed to start respiratory support. Dysphagia was assessed in all patients at baseline by a videofluoroscopic swallow study. Beck’s Depression Inventory II was administered for measuring the severity of depression. The Montreal Cognitive Assessment was used as a screening tool to detect signs of neurocognitive disorders. We evaluated adherence to NIV. Results: The study population presented with sleep-disordered breathing, as indicated by a median apnea–hypopnea index (AHI) of 24 events per hour (IQR: 14.2–34.5) and an oxygen desaturation index (ODI) of 25 events per hour (IQR: 18–33). Adherence to NIV was obtained in seven patients. No difference in baseline lung function was observed. Adherent subjects had moderate hypercapnia at baseline; pCO2 was 52 vs. 49 mmHg. Non-adherent patients showed a higher prevalence of depression with a median BDI-II score of 18 vs. 6 in adherent patients. The findings highlight that psychological factors, especially depression, play a crucial role in adherence to NIV. Interestingly, depression was not linked to initial respiratory measurements but showed a significant association with nocturnal oxygen desaturation. This suggests that relying solely on clinical and respiratory assessments may not be adequate to predict or improve treatment adherence. Conclusions: Incorporating psychological evaluations and addressing mental health issues, such as depression, are essential steps to enhance NIV compliance and overall DM1 patient outcomes. A multidisciplinary approach combining respiratory and psycho-emotional interventions is crucial for effective disease management.