ChatGPT: unlocking the potential of Artifical Intelligence in COVID-19 monitoring and prediction

BACKGROUND

The COVID-19 pandemic has had an unprecedent impact of everyday life with deleterious consequences on global health, economics, and society. Thus, accurate and timely information is critical for monitoring its spread and mitigating its impact. ChatGPT is a large language model chatbot with artificial intelligence, developed by OpenAI, that can provide both textual content and R code for predictive models. It may prove to be useful in analyzing and interpreting COVID-19-related data.

METHODS

This paper explores the application of ChatGPT to the monitoring of the COVID-19 pandemic, presenting R code for predictive models and demonstrating the model's capabilities in sentiment analysis, information extraction, and predictive modelling. We used the prediction models suggested by ChatGPT to predict the daily number of COVID-19 deaths in Italy. The prediction accuracy of the models was compared using the following metrics: mean squared error (MSE), mean absolute deviation (MAD) and root mean squared error (RMSE).

RESULTS

ChatGPT suggested three different predictive models, including ARIMA, Random Forest and Prophet. The ARIMA model outperformed the other two models in predicting the daily number of COVID-19 deaths in Italy, with lower MSE, MAD, and RMSE values as compared to the Random Forest and Prophet.

CONCLUSIONS

This paper demonstrates the potential of ChatGPT as a valuable tool in the monitoring of the pandemic. By processing large amounts of data and providing relevant information, ChatGPT has the potential to provide accurate and timely insights, and support decision-making processes to mitigate the spread and impact of pandemics. The paper highlights the importance of exploring the capabilities of artificial intelligence in the management of public emergencies and provides a starting point for future research in this area.

COVID-19 and alcohol consumption: recommendations in the Omicron era

In the early stages of the pandemic, the first reports began that alcohol consumption could increase the risk of becoming infected and worsening the prognosis disease. This is for two reasons: behavioral and socio-economic factors that characterize a part of this population can be the cause of viral spread and a direct or indirect negative action of ethanol on the immune system. The data used for the preparation of these recommendations are based on a detailed analysis of the scientific literature published before March 31, 2022 (Web of Science, Scopus, Google Scholar). Furthermore, in the process of developing this work, we consulted the guidelines/position papers of the Italian Society on Alcohol and of the World Health Organization. It has been confirmed that AC is in COVID-19 era a risky behavior and that AUD and substance use disorder (SUD) patients are certainly at greater risk of contracting infection and also of having a worse course. In light of what has been said, some recommendations can be made: correctly inform the general population that AC negatively interacts with COVID-19 infection; reducing the COVID-19 risk by advocating healthy lifestyle habits (smoke, diet, physical exercise, etc.) and preferential policies in population with comorbidities; implement actions that reduce the average consumption of alcohol by avoiding hazardous/harmful consumption. Abstention is better; identify alcohol consumption through a more in-depth alcohol history, using the AUDIT; AUDs patients are frail patients deserving a complete vaccination course; suggest a period of alcoholic abstention of at least thirty days before vaccination to be maintained for the following fifteen days; promoting health education campaigns for young people in order to promote vaccination culture and correct lifestyles.

COVID-19 Vaccination in Pediatrics: Was It Valuable and Successful?

BACKGROUND

The mass vaccination of children against coronavirus 2019 disease (COVID-19) has been frequently debated. The risk-benefit assessment of COVID-19 vaccination versus infection in children has also been debated.

AIM

This systematic review looked for answers to the question "was the vaccination of our children valuable and successful?".

METHODS

The search strategy of different articles in the literature was based on medical subject headings. Screening and selection were based on inclusion/exclusion criteria.

RESULTS AND DISCUSSION

The search results revealed that the majority of the reported adverse events after COVID-19 vaccination in pediatrics were mild to moderate, with few being severe. Injection site discomfort, fever, headache, cough, lethargy, and muscular aches and pains were the most prevalent side effects. Few clinical studies recorded significant side effects, although the majority of these adverse events had nothing to do with vaccination. In terms of efficacy, COVID-19 disease protection was achieved in 90-95% of cases for mRNA vaccines, in 50-80% of cases for inactivated vaccines, and in 58-92% of cases for adenoviral-based vaccines in children and adolescents.

CONCLUSIONS

Based on available data, COVID-19 immunizations appear to be safe for children and adolescents. Furthermore, multiple studies have proven that different types of vaccines can provide excellent protection against COVID-19 in pediatric populations. The efficacy of vaccines against new SARS-CoV-2 variants and the reduction in vaccine-related long-term adverse events are crucial for risk-benefit and cost-effectiveness assessments; therefore, additional safety studies are required to confirm the long-term safety and effectiveness of vaccinations in children.

Vaccines Against COVID-19: A Review

As a result of the COVID-19 pandemic, various joint efforts have been made to support the creation of vaccines. Different projects have been under development, of which some are in the clinical evaluation stage and others in are in phase III with positive results. The aim of this paper was to describe the current situation of the development and production of vaccines available to the population to facilitate future research and continue developing and proposing ideas for the benefit of the population. So, we carried out a systematic review using databases such as PubMed, ScienceDirect, SciELO, and MEDLINE, including keywords such as “vaccines,” “COVID-19,” and “SARS-CoV-2”. We reviewed the development and production of the anti-COVID vaccine and its different platforms, the background leading to the massive development of these substances, and the most basic immune aspects for a better understanding of their physiological activity and the immune response in those who receive the vaccine. We also analyzed immunization effects in populations with any medical or physiological conditions (such as immunosuppression, people with comorbidities, and pregnancy), as well as the response to immunization with heterologous vaccines and the hybrid immunity (the combination of natural immunity to SARS-CoV-2 with immunity generated by the vaccine). Likewise, we address the current situation in Mexico and its role in managing the vaccination process against SARS-CoV-2 at the national and international levels. There are still many clinical and molecular aspects to be described, such as the duration of active immunity and the development of immunological memory, to mention some of the most important ones. However, due to the short time since the global vaccination roll-out and that it has been progressive (not counting children and people with medical conditions), it is premature to say whether a second vaccination schedule will be necessary for the near future. Thus, it is essential to continue with health measures.

A Nomogram-Based Prediction for Severe Pneumonia in Patients with Coronavirus Disease 2019 (COVID-19)

Background

The outbreak of a novel coronavirus disease 2019 (COVID-19) is currently ongoing worldwide. A proportion of COVID-19 patients progress rapidly to acute respiratory failure.

Objective

We aimed to build a model to predict the risk of developing severe pneumonia in patients with COVID-19 in the early stage.

Methods

Data from patients who were confirmed to have COVID-19 and were admitted within 7 days from the onset of respiratory symptoms were retrospectively collected. The patients were classified into severe and non-severe groups according to the presence or absence of severe pneumonia during 1–2 weeks of follow-up. The clinical characteristics and laboratory indicators were screened by cross-validation based on LASSO regression to build a prediction model presented by a nomogram. The discrimination and stability, as well as the prediction performance of the model, were analysed.

Results

The neutrophil–lymphocyte ratio, monocyte counts, eosinophil percentage, serum lactate dehydrogenase level and history of diabetes mellitus were collected for the model. Bootstrap resampling showed the apparent C-statistics, and the brier scores were 0.929 and 0.098. The optimism of the C-statistics and brier score was 0.0172 and −0.019, respectively. The adjusted C-statistics and brier score were 0.9108 and 0.1169, respectively. The optimal cut-off value of the total nomogram score was determined to be 119 according to the maximal Youden index. The sensitivity, specificity, positive predictive value, and negative predictive value for differentiating the presence and absence of severe pneumonia were 83%, 89%, 74%, and 94%, respectively.

Conclusion

In our study, the neutrophil–lymphocyte ratio, monocyte counts, eosinophil percentage, serum lactate dehydrogenase level and history of diabetes mellitus showed great discrimination and stability for the prediction of the presence of severe pneumonia and were selected for the model.

COVID-19: a user's guide, status of the art and an original proposal to terminate viral recurrence

The world is now entering its 9^th month of combat against a pandemic of deadly pneumonia. Started out from China in December 2019, the disease has been declared as caused by infection with a so far unknown RNA Coronavirus of the respiratory family, then named severe acute respiratory syndrome coronavirus SARS-CoV-2. In the absence of a vaccine, and with scientists still struggling for an effective therapy, COVID-19 (the SARS-dependent syndrome) carries up to now, a death toll of more than 590,000 (July 18,2020) undermining jobs and finance of contemporary society in all continents. Social distancing, the only measure hitherto shown to restrain virus spread, has been progressively loosened from May 2020 in some countries, leaving us in the fear of repeat attacks from the unchecked virus. We discuss the problem and propose to tentatively boost the antivirus cell machinery by using lab-made viral mimics to engage cell receptors.

Clinical stability and in-hospital mortality prediction in COVID-19 patients presenting to the Emergency Department

BACKGROUND

The Novara-COVID score was developed to help the emergency physician to decide which Coronavirus disease (COVID) patient required hospitalization at Emergency Department (ED) presentation and to which intensity of care. We aimed at evaluating its prognostic role.

METHODS

We retrospectively collected data of COVID patients admitted to our ED between March 16 and April 22, 2020. The Novara-COVID score was systematically applied to all COVID patients since its introduction in clinical practice and adopted to decide patients' destination. The ability of the Novara-COVID score to predict in-hospital clinical stability and in-hospital mortality were evaluated through multivariable logistic regression and cox regression hazard models, respectively.

RESULTS

Among the 480 COVID patients admitted to the ED, 338 were hospitalized: the Novara-COVID score was 0-1 in 49.7%, 2 in 24.6%, 3 in 15.4% and 4-5 in 10.3% of patients. Novara-COVID score values of 3 and 4-5 were associated with lower clinical stability with adjusted odds ratios of 0.28 (0.13-0.59) and 0.03 (0.01-0.12), respectively. When in-hospital mortality was evaluated, a significant difference emerged between scores of 0-1 and 2 vs. 3 and 4-5. In particular, the death adjusted hazard ratio for Novara-COVID scores of 3 and 4-5 were 2.6 (1.4-4.8) and 8.4 (4.7-15.2), respectively.

CONCLUSIONS

The Novara-COVID score reliably predicts in-hospital clinical instability and mortality of COVID patients at ED presentation. This tool allows the emergency physician to detect patients at higher risk of clinical deterioration, suggesting a more aggressive therapeutic management from the beginning.

Pattern of emergency department referral during the Covid-19 outbreak in Italy

BACKGROUND

The coronavirus disease (COVID-19) outbreak is putting the European National Health Systems under pressure. Interestingly, Emergency Department (ED) referrals for reasons other than Covid-19 seem to have declined steeply. In the present paper, we aimed to verify how the Covid-19 outbreak changed ED referral pattern.

METHODS

We retrospectively reviewed the clinical records of patients referred to the ED of a University Hospital in Northern Italy from 1st March to 13th April 2020. We compared the following data with those belonging to the same period in 2019: number of EDs accesses, rate of hospital admission, frequencies of the most common causes of ED referral, priority codes of access.

RESULTS

The number of ED referrals during the Covid-19 outbreak was markedly reduced when compared to the same period in 2019 (3059 vs. 5691;-46.3%). Conversely, the rate of hospital admission raised from 16.9% to 35.4% (p<0.0001), with a shift toward higher priority codes of ED admission. In 2020, we observed both a reduction of the number of patients referred for both traumatic (513, 16.8% vs. 1544, 27.1%; χ2=118.7, p<0.0001) and non-traumatic (4147 vs. 2546) conditions. Among the latter, suspected Covid-19 accounted for 1101 (43.2%) accesses.

CONCLUSIONS

The Covid-19 pandemic completely changed the pattern of ED referral in Italy, with a marked reduction of the accesses to the hospitals. This could be related to a limited exposure to traumas and to a common fear of being infected during EDs in-stay. This may limit the misuse of EDs for non- urgent conditions, but may also delay proper referrals for urgent conditions.