Maximiliano Mollura

Mr. Maximiliano Mollura

Politecnico di Milano, Milan, Lombardy, Italy
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
1 July 2022 in JAMA
Verified
Journal Article
Open access
PDF file
EAElena Azzolini
Elena Azzolini
RLRiccardo Levi
Riccardo Levi
RSRiccardo Sarti
Riccardo Sarti
CPChiara Pozzi
Chiara Pozzi
MMMaximiliano Mollura
Maximiliano Mollura
MRMaria Rescigno
Maria Rescigno
Survivors of COVID-19 may present with long-lasting symptoms.1 Some factors have been associated with the development of post-COVID conditions (also referred to as “long COVID”),2 including hospitalization.3 A study of older US veterans showed 15% reduction of long COVID after vaccination; however, study limitations included the low number of women and suboptimal vaccination schedules.4

25 October 2021 in Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
Verified
Journal Article
Open access
MMMaximiliano Mollura
Maximiliano Mollura
LLLi-Wei H. Lehman
Li-Wei H. Lehman
RMRoger G. Mark
Roger G. Mark
RBRiccardo Barbieri
Riccardo Barbieri
A massive amount of multimodal data are continuously collected in the intensive care unit (ICU) along each patient stay, offering a great opportunity for the development of smart monitoring devices based on artificial intelligence (AI). The two main sources of relevant information collected in the ICU are the electronic health records (EHRs) and vital sign waveforms continuously recorded at the bedside. While EHRs are already widely processed by AI algorithms for prompt diagnosis and prognosis, AI-based assessments of the patients’ pathophysiological state using waveforms are less developed, and their use is still limited to real-time monitoring for basic visual vital sign feedback at the bedside. This study uses data from the MIMIC-III database (PhysioNet) to propose a novel AI approach in ICU patient monitoring that incorporates features estimated by a closed-loop cardiovascular model, with the specific goal of identifying sepsis within the first hour of admission. Our top benchmark results (AUROC = 0.92, AUPRC = 0.90) suggest that features derived by cardiovascular control models may play a key role in identifying sepsis, by continuous monitoring performed through advanced multivariate modelling of vital sign waveforms. This work lays foundations for a deeper data integration paradigm which will help clinicians in their decision-making processes. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.

25 June 2022 in Journal of Endocrinological Investigation
Verified
Journal Article
Closed access
PDF file
EBE. Biamonte
E. Biamonte
RLR. Levi
R. Levi
FCF. Carrone
F. Carrone
WVW. Vena
W. Vena
ABA. Brunetti
A. Brunetti
GMG. Mazziotti
G. Mazziotti

21 September 2022 in American Journal of Audiology
Verified
Journal Article
Open access
MLMarta Lenatti
Marta Lenatti
PMPedro A. Moreno-Sánchez
Pedro A. Moreno-Sánchez
EPEdoardo M. Polo
Edoardo M. Polo
MMMaximiliano Mollura
Maximiliano Mollura
RBRiccardo Barbieri
Riccardo Barbieri
APAlessia Paglialonga
Alessia Paglialonga
Purpose: The aim of this study was to analyze the performance of multivariate machine learning (ML) models applied to a speech-in-noise hearing screening test and investigate the contribution of the measured features toward hearing loss detection using explainability techniques. Method: Seven different ML techniques, including transparent (i.e., decision tree and logistic regression) and opaque (e.g., random forest) models, were trained and evaluated on a data set including 215 tested ears (99 with hearing loss of mild degree or higher and 116 with no hearing loss). Post hoc explainability techniques were applied to highlight the role of each feature in predicting hearing loss. Results: Random forest (accuracy = .85, sensitivity = .86, specificity = .85, precision = .84) performed, on average, better than decision tree (accuracy = .82, sensitivity = .84, specificity = .80, precision = .79). Support vector machine, logistic regression, and gradient boosting had similar performance as random forest. According to post hoc explainability analysis on models generated using random forest, the features with the highest relevance in predicting hearing loss were age, number and percentage of correct responses, and average reaction time, whereas the total test time had the lowest relevance. Conclusions: This study demonstrates that a multivariate approach can help detect hearing loss with satisfactory performance. Further research on a bigger sample and using more complex ML algorithms and explainability techniques is needed to fully investigate the role of input features (including additional features such as risk factors and individual responses to low-/high-frequency stimuli) in predicting hearing loss.

12 October 2023 in IEEE Journal of Translational Engineering in Health and Medicine
Verified
Journal Article
Open access
EPEdoardo M. Polo
Edoardo M. Polo
AFAndrea Farabbi
Andrea Farabbi
MMMaximiliano Mollura
Maximiliano Mollura
APAlessia Paglialonga
Alessia Paglialonga
Luca MainardiLuca Mainardi
Luca Mainardi
RBRiccardo Barbieri
Riccardo Barbieri
The study of emotions through the analysis of the induced physiological responses gained increasing interest in the past decades. Emotion-related studies usually employ films or video clips, but these stimuli do not give the possibility to properly separate and assess the emotional content provided by sight or hearing in terms of physiological responses. In this study we have devised an experimental protocol to elicit emotions by using, separately and jointly, pictures and sounds from the widely used International Affective Pictures System and International Affective Digital Sounds databases. We processed galvanic skin response, electrocardiogram, blood volume pulse, pupillary signal and electroencephalogram from 21 subjects to extract both autonomic and central nervous system indices to assess physiological responses in relation to three types of stimulation: auditory, visual, and auditory/visual. Results show a higher galvanic skin response to sounds compared to images. Electrocardiogram and blood volume pulse show different trends between auditory and visual stimuli. The electroencephalographic signal reveals a greater attention paid by the subjects when listening to sounds compared to watching images. In conclusion, these results suggest that emotional responses increase during auditory stimulation at both central and peripheral levels, demonstrating the importance of sounds for emotion recognition experiments and also opening the possibility toward the extension of auditory stimuli in other fields of psychophysiology. Clinical and Translational Impact Statement- These findings corroborate auditory stimuli’s importance in eliciting emotions, supporting their use in studying affective responses, e.g., mood disorder diagnosis, human-machine interaction, and emotional perception in pathology.

28 July 2022 in Frontiers in Immunology
Verified
Journal Article
Open access
MRMaria Elena Romero-Ibarguengoitia
Maria Elena Romero-Ibarguengoitia
AGArnulfo González-Cantú
Arnulfo González-Cantú
CPChiara Pozzi
Chiara Pozzi
RLRiccardo Levi
Riccardo Levi
MMMaximiliano Mollura
Maximiliano Mollura
MRMaria Rescigno
Maria Rescigno
Background: Scarce information exists in relation to the comparison of seroconversion and adverse events following immunization (AEFI) with different SARS-CoV-2 vaccines. Our aim was to correlate the magnitude of the antibody response to vaccination with previous clinical conditions and AEFI.Methods: A multicentric comparative study where SARS-CoV-2 spike 1-2 IgG antibodies IgG titers were measured at baseline, 21-28 days after the first and second dose (when applicable) of the following vaccines: BNT162b2 mRNA, mRNA-1273, Gam-COVID-Vac, Coronavac, ChAdOx1-S, Ad5-nCoV and Ad26.COV2. Mixed model and Poisson generalized linear models were performed.Results: We recruited 1867 individuals [52 (SD 16.8) years old, 52% men]. All vaccines enhanced anti-S1 and anti-S2 IgG antibodies over time (p<0.01). The highest increase after the first and second dose was observed in mRNA-1273 (p<0.001). There was an effect of previous SARS-CoV-2 infection; and an interaction of age with previous SARS-CoV-2 infection, Gam-COVID-Vac and ChAdOx1-S (p<0.01). There was a negative correlation of Severe or Systemic AEFI (AEs) of naïve SARS-CoV-2 subjects with age and sex (p<0.001); a positive interaction between the delta of antibodies with Gam-COVID-Vac (p=0.002). Coronavac, Gam-COVID-Vac and ChAdOx1-S had less AEs compared to BNT162b (p<0.01). mRNA-1273 had the highest number of AEFIs. The delta of the antibodies showed an association with AEFIs in previously infected individuals (p<0.001).Conclusions: The magnitude of seroconversion is predicted by age, vaccine type and SARS-CoV-2 exposure. AEs are correlated with age, sex, and vaccine type. The delta of the antibody response only correlates with AEs in patients previously exposed to SARS-CoV-2.Registration number: ClinicalTrials.gov, identifier NCT05228912.