Interacting With COVID-19: How Population Behavior, Feedback and Memory Shaped Recurrent Waves of the Epidemic

Until the approval of vaccines at the end of 2020, societies relied on non-pharmaceutical interventions (NPIs) in order to control the COVID-19 pandemic. Spontaneous changes in individual behavior might have contributed to or counteracted epidemic control due to NPIs. For example, the population compliance to NPIs may have varied over time as people developed 'epidemic fatigue' or altered their perception of the risk and severity of COVID-19. Whereas official measures are well documented, the behavioral response of the citizens is harder to capture. We propose a mathematical model of the societal response, taking into account three main effects: the citizen response dynamics, the authorities' NPIs, and the occurrence of unpreventable events that significantly alter the virus transmission rate. A key assumption is that a society has a waning memory of the epidemic effects, which reflects on both the severity of the authorities' NPIs and on the citizens' compliance to the prescribed rules. This, in turn, feeds back onto the transmission rate of the disease, such that a higher number of hospitalizations decreases the probability of transmission. We show that the model is able to reproduce the COVID-19 dynamics in terms of hospital admissions for several European countries during 2020 over surprisingly long time scales. Also, it is capable of capturing the effects of disturbances (for example the emergence of new virus variants) and can be exploited for implementing control actions to limit such effects. A possible application, illustrated in this letter, consists of exploiting the estimations based on the data of one country, to predict and control the evolution in another country, where the virus spreading is still in an earlier phase. © 2017 IEEE.

Combining simulation and machine learning for the management of healthcare systems

The growing research trends in the field of artificial intelligence have largely impacted the healthcare sector. Thanks to the high predictive power of machine learning approaches, new tools to support the clinical decision-making can be designed. However, since the demand for healthcare services is complex and highly changing, as it is affected by external unpredictable factors such as the CoViD-19, the reliability and robustness of such predictive tools is highly dependent on their capability of varying and adapting the forecasting in accordance with variations in environmental factors and health needs. In this work, we propose a combined simulation and machine learning approach to study the robustness and adaptability of predictive tools for healthcare management. Discrete event simulation is employed to simulate a generic healthcare service. The patients' length of stay (LOS) is monitored as a performance indicator of the care process. Three machine learning algorithms have been tested to predict the LOS in different simulated scenarios obtained by varying the level of demand for the healthcare service. The predictability of the tested algorithms has been studied in terms of mean errors. Preliminary results suggest that abrupt changes in the healthcare demand have a negative impact on the performance of the machine learning algorithms, which are not prone to adapt decisions to the surrounding environment. The design of novel intelligent health system, which aim to integrate artificial intelligence tools in the clinical decision-making process, should take into account these limitations. In this sense the use of simulation can be beneficial in the assessment of the new generation of decision support systems in healthcare. © 2022 IEEE.

Interacting with COVID-19: How population behavior, feedback and memory shaped recurrent waves of the epidemic

Until the approval of vaccines at the end of 2020, societies relied on non-pharmaceutical interventions (NPIs) in order to control the COVID-19 pandemic. Spontaneous changes in individual behavior might have contributed to or counteracted epidemic control due to NPIs. For example, the population compliance to NPIs may have varied over time as people developed “epidemic fatigue" or altered their perception of the risk and severity of COVID-19. Whereas official measures are well documented, the behavioral response of the citizens is harder to capture. We propose a mathematical model of the societal response, taking into account three main effects: the citizen response dynamics, the authorities’NPIs, and the occurrence of unpreventable events that significantly alter the virus transmission rate. A key assumption is that a society has a waning memory of the epidemic effects, which reflects on both the severity of the authorities’NPIs and on the citizens’compliance to the prescribed rules. This, in turn, feeds back onto the transmission rate of the disease, such that a higher number of hospitalizations decreases the probability of transmission. We show that the model is able to reproduce the COVID-19 dynamics in terms of hospital admissions for several European countries during 2020 over surprisingly long time scales. Also, it is capable of capturing the effects of disturbances (for example the emergence of new virus variants) and can be exploited for implementing control actions to limit such effects. A possible application, illustrated in the paper, consists of exploiting the estimations based on the data of one country, to predict and control the evolution in another country, where the virus spreading is still in an earlier phase. IEEE

Bus Passenger Load Prediction: Challenges from an Industrial Experience

In times of ongoing pandemic outbreak, public transportation systems organisation and operation have been significantly affected. Among others, the necessity to implement in-vehicle social distancing has fostered new requirements, such as the possibility to know in advance how many people will likely be on a public bus at a given stop. This is very relevant for both potential passengers waiting at a stop, and for decision makers of a transit company, willing to adapt the operational planning. Within the domain of data-driven Intelligent Transportation Systems (ITS), some research activities are being conducted towards Bus Passenger Load (BPL) predictions, with contrasting results. In this paper we report on an academic/industrial experience we conducted to predict BPL in a major Italian city, using real-world data. In particular, we describe the difficulties and challenges we had to face in the data processing and mining steps, due to multiple data sources, with noisy data. As a consequence, in this paper we highlight to the ITS community the need of more advanced techniques and approaches suitable to support the instantiation of a data analytic pipeline for BPL prediction. © 2022, Springer Nature Switzerland AG.

Automatic Measurement of Acquisition for COVID-19 Related Information

This paper investigates data representation and extraction procedures for the management of domain-specific information regarding COVID-19 information. To integrate among different data sources, including data contained in COVID-19 related clinical texts written in natural language, Natural Language Processing (NLP) techniques and the main tools available for this purpose were studied. In particular, we use an NLP pipeline implemented in python to extract relevant information taken from COVID-19 related literature and apply lexicometric measures on it. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.