GCGiuseppe Costa

Giuseppe Costa

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Giuseppe Costa has a total of 92 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Multimorbidity Analysis of Hospitalized Patients With COVID-19 in Northwest Italy: Longitudinal Study Using Evolutionary Machine Learning and Health Administrative Data

    by Dayana Benny, Mario Giacobini, Alberto Catalano, Giuseppe Costa, Roberto Gnavi, Fulvio Ricceri

    Background: Multimorbidity is a significant public health concern, characterized by the coexistence and interaction of multiple preexisting medical conditions. This complex condition has been associated with an increased risk of COVID-19. Individuals with multimorbidity who contract COVID-19 often face a significant reduction in life expectancy. The postpandemic period has also highlighted an increase in frailty, emphasizing the importance of integrating existing multimorbidity details into epidemiological risk assessments. Managing clinical data that include medical histories presents significant challenges, particularly due to the sparsity of data arising from the rarity of multimorbidity conditions. Also, the complex enumeration of combinatorial multimorbidity features introduces challenges associated with combinatorial explosions. Objective: This study aims to assess the severity of COVID-19 in individuals with multiple medical conditions, considering their demographic characteristics such as age and sex. We propose an evolutionary machine learning model designed to handle sparsity, analyzing preexisting multimorbidity profiles of patients hospitalized with COVID-19 based on their medical history. Our objective is to identify the optimal set of multimorbidity feature combinations strongly associated with COVID-19 severity. We also apply the Apriori algorithm to these evolutionarily derived predictive feature combinations to identify those with high support. Methods: We used data from 3 administrative sources in Piedmont, Italy, involving 12,793 individuals aged 45-74 years who tested positive for COVID-19 between February and May 2020. From their 5-year pre–COVID-19 medical histories, we extracted multimorbidity features, including drug prescriptions, disease diagnoses, sex, and age. Focusing on COVID-19 hospitalization, we segmented the data into 4 cohorts based on age and sex. Addressing data imbalance through random resampling, we compared various machine learning algorithms to identify the optimal classification model for our evolutionary approach. Using 5-fold cross-validation, we evaluated each model’s performance. Our evolutionary algorithm, utilizing a deep learning classifier, generated prediction-based fitness scores to pinpoint multimorbidity combinations associated with COVID-19 hospitalization risk. Eventually, the Apriori algorithm was applied to identify frequent combinations with high support. Results: We identified multimorbidity predictors associated with COVID-19 hospitalization, indicating more severe COVID-19 outcomes. Frequently occurring morbidity features in the final evolved combinations were age>53, R03BA (glucocorticoid inhalants), and N03AX (other antiepileptics) in cohort 1; A10BA (biguanide or metformin) and N02BE (anilides) in cohort 2; N02AX (other opioids) and M04AA (preparations inhibiting uric acid production) in cohort 3; and G04CA (Alpha-adrenoreceptor antagonists) in cohort 4. Conclusions: When combined with other multimorbidity features, even less prevalent medical conditions show associations with the outcome. This study provides insights beyond COVID-19, demonstrating how repurposed administrative data can be adapted and contribute to enhanced risk assessment for vulnerable populations.


  • La metrica di salute per guidare e valutare le innovazioni nel PNRR

    by Giuseppe Costa

    Key Words: health inequalities, metric, integrated community care ABSTRACT Among the dimensions of well-being, health is the one perceived as most important by individuals and communities. It is also easier to measure. The distribution of health in the population may therefore be the most useful metric for identifying problems and looking for solutions. Particularly eloquent is the search for health inequalities, because they show that someone has done better than someone else and that change is possible by improving living conditions and access to care for all. Therefore, the metric of unequal health can be the key to activating a change, to be proposed to the local community and to the professionals who build the new Community Houses. Autore per corrispondenza: giuseppe.costa@unito.it

  • Open Access

    A Multimorbidity Analysis of Hospitalized Patients With COVID-19 in Northwest Italy: Longitudinal Study Using Evolutionary Machine Learning and Health Administrative Data (Preprint)

    by Dayana Benny, Mario Giacobini, Alberto Catalano, Giuseppe Costa, Roberto Gnavi, Fulvio Ricceri

    BACKGROUND Multimorbidity is a significant public health concern, characterized by the coexistence and interaction of multiple preexisting medical conditions. This complex condition has been associated with an increased risk of COVID-19. Individuals with multimorbidity who contract COVID-19 often face a significant reduction in life expectancy. The postpandemic period has also highlighted an increase in frailty, emphasizing the importance of integrating existing multimorbidity details into epidemiological risk assessments. Managing clinical data that include medical histories presents significant challenges, particularly due to the sparsity of data arising from the rarity of multimorbidity conditions. Also, the complex enumeration of combinatorial multimorbidity features introduces challenges associated with combinatorial explosions. OBJECTIVE This study aims to assess the severity of COVID-19 in individuals with multiple medical conditions, considering their demographic characteristics such as age and sex. We propose an evolutionary machine learning model designed to handle sparsity, analyzing preexisting multimorbidity profiles of patients hospitalized with COVID-19 based on their medical history. Our objective is to identify the optimal set of multimorbidity feature combinations strongly associated with COVID-19 severity. We also apply the Apriori algorithm to these evolutionarily derived predictive feature combinations to identify those with high support. METHODS We used data from 3 administrative sources in Piedmont, Italy, involving 12,793 individuals aged 45-74 years who tested positive for COVID-19 between February and May 2020. From their 5-year pre–COVID-19 medical histories, we extracted multimorbidity features, including drug prescriptions, disease diagnoses, sex, and age. Focusing on COVID-19 hospitalization, we segmented the data into 4 cohorts based on age and sex. Addressing data imbalance through random resampling, we compared various machine learning algorithms to identify the optimal classification model for our evolutionary approach. Using 5-fold cross-validation, we evaluated each model’s performance. Our evolutionary algorithm, utilizing a deep learning classifier, generated prediction-based fitness scores to pinpoint multimorbidity combinations associated with COVID-19 hospitalization risk. Eventually, the Apriori algorithm was applied to identify frequent combinations with high support. RESULTS We identified multimorbidity predictors associated with COVID-19 hospitalization, indicating more severe COVID-19 outcomes. Frequently occurring morbidity features in the final evolved combinations were age>53, R03BA (glucocorticoid inhalants), and N03AX (other antiepileptics) in cohort 1; A10BA (biguanide or metformin) and N02BE (anilides) in cohort 2; N02AX (other opioids) and M04AA (preparations inhibiting uric acid production) in cohort 3; and G04CA (Alpha-adrenoreceptor antagonists) in cohort 4. CONCLUSIONS When combined with other multimorbidity features, even less prevalent medical conditions show associations with the outcome. This study provides insights beyond COVID-19, demonstrating how repurposed administrative data can be adapted and contribute to enhanced risk assessment for vulnerable populations.

  • Open Access

    Addressing health inequalities in Europe: key messages from the Joint Action Health Equity Europe (JAHEE)

    by Raffaella Bucciardini, Pi Zetterquist, Tuulia Rotko, Vania Putatti, Benedetta Mattioli, Paola De Castro, Federica Napolitani, Anna Maria Giammarioli, Bernadette N. Kumar, Charlott Nordström, et al.

    Health inequalities within and between Member States of the European Union are widely recognized as a public health problem as they determine a significant share of potentially avoidable mortality and morbidity. After years of growing awareness and increasing action taken, a large gap still exists across Europe in terms of policy responses and governance. With the aim to contribute to achieve greater equity in health outcomes, in 2018 a new Joint Action, JAHEE, (Joint Action Health Equity Europe) was funded by the third EU Health Programme, with the main goal of strengthening cooperation between participating countries and of implementing concrete actions to reduce health inequalities. The partnership led by Italy counted 24 countries, conducting actions in five policy domains: monitoring, governance, healthy living environments, health systems and migration, following a three-step implementation approach. Firstly, specific Policy Frameworks for Action (PFA) collecting the available evidence on what practice should be done in each domain were developed. Second, different Country Assessments (CAs) were completed to check the country’s adherence to the recommended practice in each domain. The gap between the expected policy response (PFA) and the present policy response (CA) guided the choice of concrete actions to be implemented in JAHEE, many of which are continuing even after the end of JA. Final recommendations based on the best results achieved during JAHEE were elaborated and agreed jointly with the representatives of the involved Ministries of Health. The JAHEE initiative represented an important opportunity for the participating countries to work jointly, and the results show that almost all have increased their level of action and strengthened their capacities to address health inequalities.


  • Open Access

    COVID-19 and Health Outcomes in People with Multiple Sclerosis: A Population-Based Study in Italy

    by Roberto Gnavi, Ilenia Eboli, Paolo Emilio Alboini, Sandra D’alfonso, Roberta Picariello, Giuseppe Costa, Maurizio Leone

    People with multiple sclerosis (PWMS) are at high risk of being affected by the disruption of health services that occurred during the COVID-19 pandemic months. The aim of this study was to evaluate the effect of the pandemic on the health outcomes of PWMS. PWMS and MS-free residing in Piedmont (north-west of Italy) were identified from electronic health records and linked with the regional COVID-19 database, the hospital-discharge database, and the population registry. Both cohorts (9333 PWMS and 4,145,856 MS-free persons) were followed-up for access to swab testing, hospitalisation, access to the Intensive Care Unit (ICU), and death from 22 February 2020 to 30 April 2021. The relationship between the outcomes and MS was evaluated using a logistic model, which was adjusted for potential confounders. The rate of swab testing was higher in PWMS, but the positivity to infection was similar to that of MS-free subjects. PWMS had a higher risk of hospitalisation (OR = 1.74; 95% IC, 1.41–2.14), admission to ICU (OR = 1.79; 95% IC, 1.17–2.72), and a slight, albeit not statistically significant, increase in mortality (OR = 1.28; 95% IC, 0.79–2.06). Compared to the general population PWMS with COVID-19 had an increased risk of hospitalization and admission to the ICU; the mortality rate did not differ.

  • Open Access

    Multimorbidity and SARS-CoV-2–Related Outcomes: Analysis of a Cohort of Italian Patients

    by Alberto Catalano, Lucia Dansero, Winston Gilcrease, Alessandra Macciotta, Carlo Saugo, Luca Manfredi, Roberto Gnavi, Elena Strippoli, Nicolás Zengarini, Valeria Caramello, et al.

    Background: Since the outbreak of the COVID-19 pandemic, identifying the main risk factors has been imperative to properly manage the public health challenges that the pandemic exposes, such as organizing effective vaccination campaigns. In addition to gender and age, multimorbidity seems to be 1 of the predisposing factors coming out of many studies investigating the possible causes of increased susceptibility to SARS-CoV-2 infection and adverse outcomes. However, only a few studies conducted have used large samples. Objective: The objective is to evaluate the association between multimorbidity, the probability to be tested, susceptibility, and the severity of SARS-CoV-2 infection in the Piedmont population (Northern Italy, about 4 million inhabitants). For this purpose, we considered 5 main outcomes: access to the swab, positivity to SARS-CoV-2, hospitalization, intensive care unit (ICU) admission, and death within 30 days from the first positive swab. Methods: Data were obtained from different Piedmont health administrative databases. Subjects aged from 45 to 74 years and infections diagnosed from February to May 2020 were considered. Multimorbidity was defined both with the Charlson Comorbidity Index (CCI) and by identifying patients with previous comorbidities, such as diabetes and oncological, cardiovascular, and respiratory diseases. Multivariable logistic regression models (adjusted for age and month of infection and stratified by gender) were performed for each outcome. Analyses were also conducted by separating 2 age groups (45-59 and 60-74 years). Results: Of 1,918,549 subjects, 85,348 (4.4%) performed at least 1 swab, of whom 12,793 (14.9%) tested positive for SARS-CoV-2. Of these 12,793 subjects, 4644 (36.3%) were hospitalized, 1508 (11.8%) were admitted to the ICU, and 749 (5.9%) died within 30 days from the first positive swab. Individuals with a higher CCI had a higher probability of being swabbed but a lower probability of testing positive. We observed the same results when analyzing subjects with previous oncological and cardiovascular diseases. Moreover, especially in the youngest group, we identified a greater risk of being hospitalized and dying. Among comorbidities considered in the study, respiratory diseases seemed to be the most likely to increase the risk of having a positive swab and worse disease outcomes. Conclusions: Our study shows that patients with multimorbidity, although swabbed more frequently, are less likely to get infected with SARS-CoV-2, probably due to greater attention on protective methods. Moreover, a history of respiratory diseases is a risk factor for a worse prognosis of COVID-19. Nonetheless, whatever comorbidities affect the patients, a strong dose-response effect was observed between an increased CCI score and COVID-19 hospitalization, ICU admission, and death. These results are important in terms of public health because they help in identifying a group of subjects who are more prone to worse SARS-CoV-2 outcomes. This information is important for promoting targeted prevention and developing policies for the prioritization of public health interventions.


  • Open Access

    Could a fairer retirement age mitigate health inequalities? Evidence and decision-making

    by Chiara Ardito, Giuseppe Costa

    Could a fairer retirement age mitigate health inequalities? Evidence and decision-making


  • Open Access

    Improvements throughout the Three Waves of COVID-19 Pandemic: Results from 4 Million Inhabitants of North-West Italy

    by Valeria Caramello, Alberto Catalano, Alessandra Macciotta, Lucia Dansero, Carlotta Sacerdote, Giuseppe Costa, Franco Aprà, Aldo Tua, Adriana Boccuzzi, Fulvio Ricceri

    At the very beginning of the European spread of SARS-CoV-2, Piedmont was one of the most affected regions in Italy, with a strong impact on healthcare organizations. In this study, we evaluated the characteristics and outcomes of the COVID-19 patients in an entire region during the first three pandemic waves, identifying similarities and differences in the SARS-CoV-2 epidemic’s timeline. We collected the health-administrative data of all the Piedmont COVID-19 patients infected during the first three pandemic waves (1 March 2020–15 April 2020; 15 October 2020–15 December 2020; 1 March 2021–15 April 2021, respectively). We compared differences among the waves in subjects positive for SARS-CoV-2 and in patients admitted to ICU. Overall, 18.621 subjects tested positive during the first wave (405 patients/day), 144.350 (2366.4 patients/day) in the second, and 81.823 (1778.8 patients/day) in the third. In the second and third waves, we observed a reduction in median age, comorbidity burden, mortality in outpatients, inpatients, and patients admitted to ICU, in intubation, invasive ventilation and tracheostomy, and a parallel increase in the use of CPAP. Our study confirmed a trend towards younger and healthier patients over time but also showed an independent effect of the period on mortality and ICU admission. The appearance of new viral variants, the starting of vaccination, and organizational improvements in tracking, outpatients and inpatients management could have influenced these trends.