Maximiliano Mollura | Politecnico di Milano (original) (raw)

inproceedings by Maximiliano Mollura

The role of Pulse Rate estimated from blood pressure pulse when used as a surrogate for Heart Rat... more The role of Pulse Rate estimated from blood pressure pulse when used as a surrogate for Heart Rate Variability (HRV) studies has been addressed under different conditions in healthy subjects. However, there is a lack of validation in studies involving patients admitted in the Intensive Care Unit (ICU). Therefore, our study aims at validating six different possible surrogates for the ECG-derived tachogram, estimated from the time interval series between successive onset (O), systolic (S) and diastolic (D) fiducial points extracted from arterial blood pressure (ABP) and photoplethysmogram (PPG) waveforms. The validation is performed by looking at the ability of such surrogates in providing comparable estimates of the most common HRV measures. Results show a high agreement between the ECG-derived and the ABP/PPG-derived series, with small biases. Results from sub-populations of patients that showed increases (and decreases) in such measures show a good ability of these surrogates in tracking autonomic changes. In addition, differently from PPGO and PPGS, ventilated and sedated subjects did not show differences in estimating HF power from PPGD, indicating diastolic time intervals as less affected by such procedures. In conclusion, HRV measures estimated from ABP or PPG can be reasonably used also in studies on ICU patients whenever ECG recordings are not available.

The latest extensive development of machine learning models in healthcare, and in particular thei... more The latest extensive development of machine learning models in healthcare, and in particular their application to data from the intensive care unit (ICU), is directed towards the main objective to help clinicians in making more timely diagnoses and efficient decisions. Many studies have been focused on the identification of Sepsis in a complex environment such as the ICU by using the data collected in electronic health records. However, only a few studies have investigated associations between the patients' continuously monitored vital signs and their Sepsis status. This work aims at demonstrating that machine learning algorithms considering measures extracted from 103 patients from the publicly available MIMIC-III clinical and waveform databases are able to adequately identify Sepsis just within the first hour of stay in the ICU. A bagged tree classifier showed AUC=0.86, Specificity=0.85 and Sensitivity=0.86 on the test set, when trained using only the information extracted from the recorded electrocardiogram and arterial blood pressure waveforms, showing that the information coming from waveform monitoring may help in detecting Sepsis within the first hour of ICU stay.

Septic Shock is a critical pathological state that affects patients entering the intensive care u... more Septic Shock is a critical pathological state that affects patients entering the intensive care unit (ICU). Many studies have been directed to characterize and predict the onset of the septic shock, both in ICU and in the Emergency Department employing data extracted from the Electronic Health Records. Recently, machine learning algorithms have been successfully employed to help characterize septic shock in a more objective and automatic fashion. Only a few of these studies employ information contained in the continuously recorded vital signs such as electrocardiogram and arterial blood pressure. In particular, we have devised a novel feature estimation procedure able to consider instantaneous dynamics related to cardiovascular control. This work aims at developing a short-term prediction algorithm for identifying patients experiencing septic shock among a population of 100 septic patients extracted from the MIMIC-III clinical and waveform database. Among all the results obtained from several trained machine learning models, the best performance reached an AUC on the test set equal to 0.93 (Accuracy=0.85, Sensitivity=0.89 and Specificity=0.82).

Human Robot Interaction has become a key point in the development of new robotic interfaces and c... more Human Robot Interaction has become a key point in the development of new robotic interfaces and controllers. In traditional control schemes for teleoperation, master devices are unaware of the user's arm dynamic characteristics, as well as of the complex motor control strategies adopted to perform the task. In this work, we propose a novel impedance controller to regulate the master device's dynamic properties based on the estimation of user's arm stiffness, with the aim of improving shared task performance. We developed a virtual planar reaching task, and we evaluated arm end-point stiffness's main axis changes in magnitude and direction using a non disruptive offline musculoskeletal model-based algorithm. Based on the stiffness modulation, the biomimetic variable impedance controller to adapt the master device's damping matrix. The direction of maximal damping was aligned with the estimated direction of maximal stiffness (Enhancing field), or to the perpendicular to the stiffness main axis (Isotropic field). The task performances under the biomimetic impedance controllers were tested and compared with the null damping condition. The results showed an increase in task performance, in terms of positional error and overshoots, with both biomimetic controllers. The analysis proved the potentiality of the biomimetic impedance modulation controller in terms of execution accuracy.

Papers by Maximiliano Mollura

IEEE open journal of engineering in medicine and biology, 2024

Goal: REM Sleep Behavior Disorder (RBD) is a REM parasomnia that is associated to high risk of de... more Goal: REM Sleep Behavior Disorder (RBD) is a REM parasomnia that is associated to high risk of developing ⍺synucleinopathies, as Parkinson's disease (PD) or dementia with Lewy bodies, over time. This study aims at investigating the presence of autonomic dysfunctions in RBD subjects, with and without PD, by assessing their sleep structure and autonomous nervous system activity along the different sleep stages. Methods: To this aim, an innovative framework combining a sleep transition model, by Markov chains, with an instantaneous assessment of autonomic state dynamics by statistical modeling of heart rate variability (HRV) dynamics through a point-process approach, was introduced. Results: In general, RBD groups showed lower HRV than controls across all sleep stages, as well as higher probabilities of transitioning towards lighter sleep stages. Subjects also affected by PD present an even lower HRV, but better sleep continuity. Conclusions: RBD patients suffer from sleep fragmentation and overall autonomic dysfunction, mainly due to lower autonomic activation across all sleep stages. Coexistence of PD seems to improve sleep quality, possibly due to a sleep-related relief of their symptoms.

Scientific data, Apr 11, 2024

Zenodo (CERN European Organization for Nuclear Research), Jul 5, 2023

Frontiers in Human Neuroscience, Jan 7, 2024

Scientific Reports, Nov 29, 2023

Due to the association between dysfunctional maternal autonomic regulation and pregnancy complica... more Due to the association between dysfunctional maternal autonomic regulation and pregnancy complications, tracking non-invasive features of autonomic regulation derived from wrist-worn photoplethysmography (PPG) measurements may allow for the early detection of deteriorations in maternal health. However, even though a plethora of these features-specifically, features describing heart rate variability (HRV) and the morphology of the PPG waveform (morphological features)exist in the literature, it is unclear which of these may be valuable for tracking maternal health. As an initial step towards clarity, we compute comprehensive sets of HRV and morphological features from nighttime PPG measurements. From these, using logistic regression and stepwise forward feature elimination, we identify the features that best differentiate healthy pregnant women from nonpregnant women, since these likely capture physiological adaptations necessary for sustaining healthy pregnancy. Overall, morphological features were more valuable for discriminating between pregnant and non-pregnant women than HRV features (area under the receiver operating characteristics curve of 0.825 and 0.74, respectively), with the systolic pulse wave deterioration being the most valuable single feature, followed by mean heart rate (HR). Additionally, we stratified the analysis by sleep stages and found that using features calculated only from periods of deep sleep enhanced the differences between the two groups. In conclusion, we postulate that in addition to HRV features, morphological features may also be useful in tracking maternal health and suggest specific features to be included in future research concerning maternal health. During pregnancy, continuous and finely tuned physiological changes occur to maintain maternal health while supporting the growing fetus 1. Adaptations in the maternal autonomic nervous system (ANS) are particularly important, given that the ANS regulates involuntary physiological processes such as respiration, blood pressure, and heart rate (HR), and is consequently essential to maintaining homeostasis throughout this physiologically dynamic period 2. In comparison to healthy pregnancies, altered maternal autonomic regulation has been found in women who develop pregnancy complications such as hypertensive disorders of pregnancy (HDP) or gestational diabetes mellitus (GDM), even as early as in the first trimester 3,4. While pregnancy complications are typically detected after the time window for clinical intervention has passed, earlier detection can improve maternal and perinatal outcomes by allowing for adequate management and treatment 5-7. Since dysfunctional maternal autonomic regulation has been found in women with pregnancy complications 3,4,8-11 , there is ongoing research into the potential of tracking maternal autonomic regulation to detect early deteriorations in maternal health 12-15. Autonomic regulation can be longitudinally assessed by tracking heart rate variability (HRV) via wearable HR monitors. Longitudinal HRV tracking might be measured

Studies in health technology and informatics, Oct 19, 2023

The WHISPER (Widespread Hearing Impairment Screening and PrEvention of Risk) platform was recentl... more The WHISPER (Widespread Hearing Impairment Screening and PrEvention of Risk) platform was recently developed for screening for hearing loss (HL) and cognitive decline in adults. It includes a battery of tests (a risk factors (RF) questionnaire, a language-independent speech-in-noise test, and cognitive tests) and provides a pass/fail outcome based on the analysis of several features. Earlier studies demonstrated high accuracy of the speech-in-noise test for predicting HL in 350 participants. In this study, preliminary results from the RF questionnaire (137 participants) and from the visual digit span test (DST) (78 participants) are presented. Despite the relatively small sample size, these findings indicate that the RF and DST may provide additional features that could be useful to characterize the overall individual profile, providing additional knowledge related to short-term memory performance and overall risk of HL and cognitive decline. Future research is needed to expand number of subjects tested, number of features analyzed, and the range of algorithms (including supervised and unsupervised machine learning) used to identify novel measures able to predict the individual hearing and cognitive abilities, also including components related to the individual risk.

Computing in Cardiology (CinC), 2012, Nov 25, 2023

Aims: Optimal reward formulation in Reinforcement Learning (RL) is still uncertain. The aim of th... more Aims: Optimal reward formulation in Reinforcement Learning (RL) is still uncertain. The aim of this study is to show that formulating a reward in RL for sepsis treatment using Mean Arterial Pressure (MAP) is a viable solution and can improve patient outcomes. Methods: The data were extracted from the MIMIC-III database. Patient data from 20,496 intensive care unit (ICU) stays were modeled with two different Markov Decision Processes that differed in reward formulation. The Mortality Model had a reward function linked only to 90-day mortality, and the Target MAP Model had an additional reward component that penalized the RL agent if the patient's MAP fell below 65 mmHg. Results: The Target MAP Model achieved the best results with a 95% lower bound (LB) of estimated policy value equal to 88.64 compared to 86.01 obtained from the Mortality Model despite having a more penalizing reward. The Target MAP Model in hypotensive patients uses less intravenous fluids and resorts more often to aggressive dosages of vasopressors. Conclusions: The results show that tying the reward to MAP is a viable approach, and the less sparse reward that comes with tying the reward to high temporal resolution cardiovascular features allows to evaluate single actions rather than the whole sequences of actions leading to the final outcome, allowing the RL agent to learn a better policy.

IEEE Journal of Translational Engineering in Health and Medicine

Scientific Reports, Apr 7, 2023

Physiologic dead space is a well-established independent predictor of death in patients with acut... more Physiologic dead space is a well-established independent predictor of death in patients with acute respiratory distress syndrome (ARDS). Here, we explore the association between a surrogate measure of dead space (DS) and early outcomes of mechanically ventilated patients admitted to Intensive Care Unit (ICU) because of COVID-19-associated ARDS. Retrospective cohort study on data derived from Italian ICUs during the first year of the COVID-19 epidemic. A competing risk Cox proportional hazard model was applied to test for the association of DS with two competing outcomes (death or discharge from the ICU) while adjusting for confounders. The final population consisted of 401 patients from seven ICUs. A significant association of DS with both death (HR 1.204; CI 1.019-1.423; p = 0.029) and discharge (HR 0.434; CI 0.414-0.456; p < 0.001) was noticed even when correcting for confounding factors (age, sex, chronic obstructive pulmonary disease, diabetes, PaO 2 /FiO 2 , tidal volume, positive end-expiratory pressure, and systolic blood pressure). These results confirm the important association between DS and death or ICU discharge in mechanically ventilated patients with COVID-19-associated ARDS. Further work is needed to identify the optimal role of DS monitoring in this setting and to understand the physiological mechanisms underlying these associations. Endothelial inflammatory damage and pulmonary microvascular dysfunction, resulting in microthrombosis and pulmonary vascular perfusion defects, are prominent features of acute respiratory distress syndrome (ARDS) associated with Coronavirus disease 2019 (COVID-19) 1,2. Although the contribution of pulmonary microthrombosis to the pathophysiology of ARDS is long-known 3,4 , the role of microangiopathy and and dysregulated lung perfusion appears even more relevant in COVID-19-associated ARDS as compared to other infectious causes of ARDS 5,6 .

Computing in Cardiology (CinC), 2012, Dec 31, 2022

IEEE EUROCON 2023 - 20th International Conference on Smart Technologies

The role of Pulse Rate estimated from blood pressure pulse when used as a surrogate for Heart Rat... more The role of Pulse Rate estimated from blood pressure pulse when used as a surrogate for Heart Rate Variability (HRV) studies has been addressed under different conditions in healthy subjects. However, there is a lack of validation in studies involving patients admitted in the Intensive Care Unit (ICU). Therefore, our study aims at validating six different possible surrogates for the ECG-derived tachogram, estimated from the time interval series between successive onset (O), systolic (S) and diastolic (D) fiducial points extracted from arterial blood pressure (ABP) and photoplethysmogram (PPG) waveforms. The validation is performed by looking at the ability of such surrogates in providing comparable estimates of the most common HRV measures. Results show a high agreement between the ECG-derived and the ABP/PPG-derived series, with small biases. Results from sub-populations of patients that showed increases (and decreases) in such measures show a good ability of these surrogates in tracking autonomic changes. In addition, differently from PPGO and PPGS, ventilated and sedated subjects did not show differences in estimating HF power from PPGD, indicating diastolic time intervals as less affected by such procedures. In conclusion, HRV measures estimated from ABP or PPG can be reasonably used also in studies on ICU patients whenever ECG recordings are not available.

The latest extensive development of machine learning models in healthcare, and in particular thei... more The latest extensive development of machine learning models in healthcare, and in particular their application to data from the intensive care unit (ICU), is directed towards the main objective to help clinicians in making more timely diagnoses and efficient decisions. Many studies have been focused on the identification of Sepsis in a complex environment such as the ICU by using the data collected in electronic health records. However, only a few studies have investigated associations between the patients' continuously monitored vital signs and their Sepsis status. This work aims at demonstrating that machine learning algorithms considering measures extracted from 103 patients from the publicly available MIMIC-III clinical and waveform databases are able to adequately identify Sepsis just within the first hour of stay in the ICU. A bagged tree classifier showed AUC=0.86, Specificity=0.85 and Sensitivity=0.86 on the test set, when trained using only the information extracted from the recorded electrocardiogram and arterial blood pressure waveforms, showing that the information coming from waveform monitoring may help in detecting Sepsis within the first hour of ICU stay.

Septic Shock is a critical pathological state that affects patients entering the intensive care u... more Septic Shock is a critical pathological state that affects patients entering the intensive care unit (ICU). Many studies have been directed to characterize and predict the onset of the septic shock, both in ICU and in the Emergency Department employing data extracted from the Electronic Health Records. Recently, machine learning algorithms have been successfully employed to help characterize septic shock in a more objective and automatic fashion. Only a few of these studies employ information contained in the continuously recorded vital signs such as electrocardiogram and arterial blood pressure. In particular, we have devised a novel feature estimation procedure able to consider instantaneous dynamics related to cardiovascular control. This work aims at developing a short-term prediction algorithm for identifying patients experiencing septic shock among a population of 100 septic patients extracted from the MIMIC-III clinical and waveform database. Among all the results obtained from several trained machine learning models, the best performance reached an AUC on the test set equal to 0.93 (Accuracy=0.85, Sensitivity=0.89 and Specificity=0.82).

Human Robot Interaction has become a key point in the development of new robotic interfaces and c... more Human Robot Interaction has become a key point in the development of new robotic interfaces and controllers. In traditional control schemes for teleoperation, master devices are unaware of the user's arm dynamic characteristics, as well as of the complex motor control strategies adopted to perform the task. In this work, we propose a novel impedance controller to regulate the master device's dynamic properties based on the estimation of user's arm stiffness, with the aim of improving shared task performance. We developed a virtual planar reaching task, and we evaluated arm end-point stiffness's main axis changes in magnitude and direction using a non disruptive offline musculoskeletal model-based algorithm. Based on the stiffness modulation, the biomimetic variable impedance controller to adapt the master device's damping matrix. The direction of maximal damping was aligned with the estimated direction of maximal stiffness (Enhancing field), or to the perpendicular to the stiffness main axis (Isotropic field). The task performances under the biomimetic impedance controllers were tested and compared with the null damping condition. The results showed an increase in task performance, in terms of positional error and overshoots, with both biomimetic controllers. The analysis proved the potentiality of the biomimetic impedance modulation controller in terms of execution accuracy.

IEEE open journal of engineering in medicine and biology, 2024

Goal: REM Sleep Behavior Disorder (RBD) is a REM parasomnia that is associated to high risk of de... more Goal: REM Sleep Behavior Disorder (RBD) is a REM parasomnia that is associated to high risk of developing ⍺synucleinopathies, as Parkinson's disease (PD) or dementia with Lewy bodies, over time. This study aims at investigating the presence of autonomic dysfunctions in RBD subjects, with and without PD, by assessing their sleep structure and autonomous nervous system activity along the different sleep stages. Methods: To this aim, an innovative framework combining a sleep transition model, by Markov chains, with an instantaneous assessment of autonomic state dynamics by statistical modeling of heart rate variability (HRV) dynamics through a point-process approach, was introduced. Results: In general, RBD groups showed lower HRV than controls across all sleep stages, as well as higher probabilities of transitioning towards lighter sleep stages. Subjects also affected by PD present an even lower HRV, but better sleep continuity. Conclusions: RBD patients suffer from sleep fragmentation and overall autonomic dysfunction, mainly due to lower autonomic activation across all sleep stages. Coexistence of PD seems to improve sleep quality, possibly due to a sleep-related relief of their symptoms.

Scientific data, Apr 11, 2024

Zenodo (CERN European Organization for Nuclear Research), Jul 5, 2023

Frontiers in Human Neuroscience, Jan 7, 2024

Scientific Reports, Nov 29, 2023

Due to the association between dysfunctional maternal autonomic regulation and pregnancy complica... more Due to the association between dysfunctional maternal autonomic regulation and pregnancy complications, tracking non-invasive features of autonomic regulation derived from wrist-worn photoplethysmography (PPG) measurements may allow for the early detection of deteriorations in maternal health. However, even though a plethora of these features-specifically, features describing heart rate variability (HRV) and the morphology of the PPG waveform (morphological features)exist in the literature, it is unclear which of these may be valuable for tracking maternal health. As an initial step towards clarity, we compute comprehensive sets of HRV and morphological features from nighttime PPG measurements. From these, using logistic regression and stepwise forward feature elimination, we identify the features that best differentiate healthy pregnant women from nonpregnant women, since these likely capture physiological adaptations necessary for sustaining healthy pregnancy. Overall, morphological features were more valuable for discriminating between pregnant and non-pregnant women than HRV features (area under the receiver operating characteristics curve of 0.825 and 0.74, respectively), with the systolic pulse wave deterioration being the most valuable single feature, followed by mean heart rate (HR). Additionally, we stratified the analysis by sleep stages and found that using features calculated only from periods of deep sleep enhanced the differences between the two groups. In conclusion, we postulate that in addition to HRV features, morphological features may also be useful in tracking maternal health and suggest specific features to be included in future research concerning maternal health. During pregnancy, continuous and finely tuned physiological changes occur to maintain maternal health while supporting the growing fetus 1. Adaptations in the maternal autonomic nervous system (ANS) are particularly important, given that the ANS regulates involuntary physiological processes such as respiration, blood pressure, and heart rate (HR), and is consequently essential to maintaining homeostasis throughout this physiologically dynamic period 2. In comparison to healthy pregnancies, altered maternal autonomic regulation has been found in women who develop pregnancy complications such as hypertensive disorders of pregnancy (HDP) or gestational diabetes mellitus (GDM), even as early as in the first trimester 3,4. While pregnancy complications are typically detected after the time window for clinical intervention has passed, earlier detection can improve maternal and perinatal outcomes by allowing for adequate management and treatment 5-7. Since dysfunctional maternal autonomic regulation has been found in women with pregnancy complications 3,4,8-11 , there is ongoing research into the potential of tracking maternal autonomic regulation to detect early deteriorations in maternal health 12-15. Autonomic regulation can be longitudinally assessed by tracking heart rate variability (HRV) via wearable HR monitors. Longitudinal HRV tracking might be measured

Studies in health technology and informatics, Oct 19, 2023

The WHISPER (Widespread Hearing Impairment Screening and PrEvention of Risk) platform was recentl... more The WHISPER (Widespread Hearing Impairment Screening and PrEvention of Risk) platform was recently developed for screening for hearing loss (HL) and cognitive decline in adults. It includes a battery of tests (a risk factors (RF) questionnaire, a language-independent speech-in-noise test, and cognitive tests) and provides a pass/fail outcome based on the analysis of several features. Earlier studies demonstrated high accuracy of the speech-in-noise test for predicting HL in 350 participants. In this study, preliminary results from the RF questionnaire (137 participants) and from the visual digit span test (DST) (78 participants) are presented. Despite the relatively small sample size, these findings indicate that the RF and DST may provide additional features that could be useful to characterize the overall individual profile, providing additional knowledge related to short-term memory performance and overall risk of HL and cognitive decline. Future research is needed to expand number of subjects tested, number of features analyzed, and the range of algorithms (including supervised and unsupervised machine learning) used to identify novel measures able to predict the individual hearing and cognitive abilities, also including components related to the individual risk.

Computing in Cardiology (CinC), 2012, Nov 25, 2023

Aims: Optimal reward formulation in Reinforcement Learning (RL) is still uncertain. The aim of th... more Aims: Optimal reward formulation in Reinforcement Learning (RL) is still uncertain. The aim of this study is to show that formulating a reward in RL for sepsis treatment using Mean Arterial Pressure (MAP) is a viable solution and can improve patient outcomes. Methods: The data were extracted from the MIMIC-III database. Patient data from 20,496 intensive care unit (ICU) stays were modeled with two different Markov Decision Processes that differed in reward formulation. The Mortality Model had a reward function linked only to 90-day mortality, and the Target MAP Model had an additional reward component that penalized the RL agent if the patient's MAP fell below 65 mmHg. Results: The Target MAP Model achieved the best results with a 95% lower bound (LB) of estimated policy value equal to 88.64 compared to 86.01 obtained from the Mortality Model despite having a more penalizing reward. The Target MAP Model in hypotensive patients uses less intravenous fluids and resorts more often to aggressive dosages of vasopressors. Conclusions: The results show that tying the reward to MAP is a viable approach, and the less sparse reward that comes with tying the reward to high temporal resolution cardiovascular features allows to evaluate single actions rather than the whole sequences of actions leading to the final outcome, allowing the RL agent to learn a better policy.

IEEE Journal of Translational Engineering in Health and Medicine

Scientific Reports, Apr 7, 2023

Physiologic dead space is a well-established independent predictor of death in patients with acut... more Physiologic dead space is a well-established independent predictor of death in patients with acute respiratory distress syndrome (ARDS). Here, we explore the association between a surrogate measure of dead space (DS) and early outcomes of mechanically ventilated patients admitted to Intensive Care Unit (ICU) because of COVID-19-associated ARDS. Retrospective cohort study on data derived from Italian ICUs during the first year of the COVID-19 epidemic. A competing risk Cox proportional hazard model was applied to test for the association of DS with two competing outcomes (death or discharge from the ICU) while adjusting for confounders. The final population consisted of 401 patients from seven ICUs. A significant association of DS with both death (HR 1.204; CI 1.019-1.423; p = 0.029) and discharge (HR 0.434; CI 0.414-0.456; p < 0.001) was noticed even when correcting for confounding factors (age, sex, chronic obstructive pulmonary disease, diabetes, PaO 2 /FiO 2 , tidal volume, positive end-expiratory pressure, and systolic blood pressure). These results confirm the important association between DS and death or ICU discharge in mechanically ventilated patients with COVID-19-associated ARDS. Further work is needed to identify the optimal role of DS monitoring in this setting and to understand the physiological mechanisms underlying these associations. Endothelial inflammatory damage and pulmonary microvascular dysfunction, resulting in microthrombosis and pulmonary vascular perfusion defects, are prominent features of acute respiratory distress syndrome (ARDS) associated with Coronavirus disease 2019 (COVID-19) 1,2. Although the contribution of pulmonary microthrombosis to the pathophysiology of ARDS is long-known 3,4 , the role of microangiopathy and and dysregulated lung perfusion appears even more relevant in COVID-19-associated ARDS as compared to other infectious causes of ARDS 5,6 .

Computing in Cardiology (CinC), 2012, Dec 31, 2022

IEEE EUROCON 2023 - 20th International Conference on Smart Technologies

Clinical Infectious Diseases

In an observational study, we analyzed 1,293 healthcare workers previously infected with SARS-CoV... more In an observational study, we analyzed 1,293 healthcare workers previously infected with SARS-CoV-2, of which 34.1% developed long COVID. Using a multivariate logistic regression model, we demonstrate that the likelihood of developing long COVID in infected individuals rises with the increasing of duration of infection and that three doses of the BNT162b2 vaccine are protective, even during the Omicron wave.

Scientific Reports

Physiologic dead space is a well-established independent predictor of death in patients with acut... more Physiologic dead space is a well-established independent predictor of death in patients with acute respiratory distress syndrome (ARDS). Here, we explore the association between a surrogate measure of dead space (DS) and early outcomes of mechanically ventilated patients admitted to Intensive Care Unit (ICU) because of COVID-19-associated ARDS. Retrospective cohort study on data derived from Italian ICUs during the first year of the COVID-19 epidemic. A competing risk Cox proportional hazard model was applied to test for the association of DS with two competing outcomes (death or discharge from the ICU) while adjusting for confounders. The final population consisted of 401 patients from seven ICUs. A significant association of DS with both death (HR 1.204; CI 1.019–1.423; p = 0.029) and discharge (HR 0.434; CI 0.414–0.456; p$$< 0.001$$ < 0.001 ) was noticed even when correcting for confounding factors (age, sex, chronic obstructive pulmonary disease, diabetes, PaO$$_{2}$$ 2 /F...

Lecture Notes in Computer Science, 2023