Prediction of in-hospital mortality rate in COVID-19 patients with diabetes mellitus using machine learning methods.

Background: Since its emergence in December 2019, until June 2022, coronavirus 2019 (COVID-19) has impacted populations all around the globe with it having been contracted by ~ 535 M people and leaving ~ 6.31 M dead. This makes identifying and predicating COVID-19 an important healthcare priority. Method and Material: The dataset used in this study was obtained from Shahid Beheshti University of Medical Sciences in Tehran, and includes the information of 29,817 COVID-19 patients who were hospitalized between October 8, 2019 and March 8, 2021. As diabetes has been shown to be a significant factor for poor outcome, we have focused on COVID-19 patients with diabetes, leaving us with 2824 records. Results: The data has been analyzed using a decision tree algorithm and several association rules were mined. Said decision tree was also used in order to predict the release status of patients. We have used accuracy (87.07%), sensitivity (88%), and specificity (80%) as assessment metrics for our model. Conclusion: Initially, this study provided information about the percentages of admitted Covid-19 patients with various underlying disease. It was observed that diabetic patients were the largest population at risk. As such, based on the rules derived from our dataset, we found that age category (51-80), CPR and ICU residency play a pivotal role in the discharge status of diabetic inpatients.

The Difference of COVID-19 Vaccination Attitude, Preventive Measures and Knowledge of SARS-COV-2 Between Diabetic Patients and Healthy Citizens in China.

Purpose: The outbreak of coronavirus disease has become an evolving global health crisis with wide-ranging implications. Clinical researches from several countries have reported greater morbidity and mortality from COVID-19 patients with diabetes. SARS-CoV-2/COVID-19 vaccines are currently the relatively effective means of prevention. The research was aimed to explore the attitudes of diabetic patients towards COVID-19 vaccine and the knowledge of COVID-19 related epidemiology and epidemic prevention. Methods: This case-control study was carried out in China via online and offline surveys. Knowledge questionnaire of COVID-19 and drivers of COVID-19 Vaccination Acceptance Scale (DrVac-COVID19S) were used to compare the difference of COVID-19 vaccination attitude, preventive measures, and knowledge of SARS-COV-2 between diabetic patients and healthy citizens. Results: The diabetic patients showed lower vaccination willingness and insufficient knowledge of the transmission route and common symptoms of COVID-19. Only 60.99% diabetic patients were willing to be vaccinated. Less than half of diabetics knew the COVID-19 spread by surface touch (34.04%) or aerosol (20.57%). The common symptoms like shortness of breath/ anorexia/ fatigue/ nausea/vomiting/diarrhea (34.04%) and panic and chest tightness (19.15%) were not well comprehend too. Diabetes patients shown lower report intentions when they contact a person infected with the virus (81.56%) or have any of the disease symptoms (74.47%). Values, knowledge, and autonomy assessed by the DrVac-COVID19S scale also showed negative attitude of vaccination in patients with diabetes. Also, patient with diabetes pay less attention to national (56.03%) and international (51.77%) COVID-19 updates. The willingness to attend COVID-19 lectures (27.66%) or read information leaflets (70.92%) was low. Conclusion: Vaccination is the effective available method for preventing the virus. Social and medical workers can increase the vaccination of diabetic patients through knowledge's popularization and patient's education based on the above differences.

A method for comparing multiple imputation techniques: A case study on the U.S. national COVID cohort collaborative.

Healthcare datasets obtained from Electronic Health Records have proven to be extremely useful for assessing associations between patients' predictors and outcomes of interest. However, these datasets often suffer from missing values in a high proportion of cases, whose removal may introduce severe bias. Several multiple imputation algorithms have been proposed to attempt to recover the missing information under an assumed missingness mechanism. Each algorithm presents strengths and weaknesses, and there is currently no consensus on which multiple imputation algorithm works best in a given scenario. Furthermore, the selection of each algorithm's parameters and data-related modeling choices are also both crucial and challenging. In this paper we propose a novel framework to numerically evaluate strategies for handling missing data in the context of statistical analysis, with a particular focus on multiple imputation techniques. We demonstrate the feasibility of our approach on a large cohort of type-2 diabetes patients provided by the National COVID Cohort Collaborative (N3C) Enclave, where we explored the influence of various patient characteristics on outcomes related to COVID-19. Our analysis included classic multiple imputation techniques as well as simple complete-case Inverse Probability Weighted models. Extensive experiments show that our approach can effectively highlight the most promising and performant missing-data handling strategy for our case study. Moreover, our methodology allowed a better understanding of the behavior of the different models and of how it changed as we modified their parameters. Our method is general and can be applied to different research fields and on datasets containing heterogeneous types.

COVID-19 and Diabetes Mellitus: From Pathophysiology to Clinical Management.

An increase in the severity of the coronavirus disease 2019 (COVID-19) was observed in patients infected with the acute severe metabolism syndrome coronavirus type 2 (SARS-CoV-2). Patients who have COVID-19 infection may also be more susceptible to hyperglycemia. When paired with other risk factors, hyperglycemia might alter immune and inflammatory responses, predisposing people to significant COVID-19 and perhaps deadly outcomes. Angiotensin-converting accelerator 2 (ACE2), a component of the renin-angiotensin-aldosterone system (RAAS), is the principal entry receptor for SARS-CoV-2; nevertheless, dipeptidyl enzyme 4 (DPP4) may potentially serve as a binding target. However, preliminary data did not indicate a substantial effect on the susceptibility to SARS-CoV-2 using glucose-lowering DPP4 inhibitors. Because of their pharmacologic characteristics, salt-glucose cotransporter 2 (SGLT2) inhibitors should not be advised for COVID-19 patients because they may have adverse effects. Currently, taking a hypoglycemic drug should be the most efficient way to manage acute glycemia. The majority of market proof is said to categorize two diabetes mellitus (DM) and fails to distinguish between the two primary categories of DM due to its widespread use. For grouping one DM and COVID-19, there is now some constrained proof available. Most of those findings are just preliminary, so further research will undoubtedly be required to determine the best course of action for DM patients.

Comparison of the Covid-19 Infection Severity in Known Diabetic Patients vs. Known Hypertensive Patients Admitted in A Tertiary Care Hospital in Peshawar

Objectives: To compare the severity of COVID-19 infection among known diabetic and known hypertensive patients who were admitted in a tertiary care hospital in Peshawar, Pakistan. Methodology: A cross-sectional clinical study was conducted for comparison in diabetic vs hypertensive patients in the department of medicine of Lady Reading Hospital, Peshawar during the period from April-June 2021. All the patients were admitted in COVID ward and COVID ICU, showed their full consent and active participation in this study. Along with patient's ECG and Echo report, a questionnaire based on Canadian categorization employed for angina grading and NYHA categorization to classify shortness of breath was used. Result(s): The mean age group taken for the sample was (n=140) with maximum age of 84 years. Majority were 102(72.9%) males and females were 38(27.1%). According to laboratory tests performed on patients of COVID-19 about 48(34.4%) of patients showed positive diabetes mellitus findings. Also, patients with positive hypertension found were 67(47.9%). The average stays of patients, at the hospital, was 15-40 days. About 58.3% of mortality was noted in patients with diabetes mellitus, a bulk of patients expired were from ICU-COVID-UNIT and 55.2% was the mortality rate in patients with positive hypertension according to our clinical findings and assessment. About 7.9% of COVID inpatients had cardiac infraction with severe condition and such patients who faced congestive heart failure expired. Almost 56(40%) of the patients were found with severe condition and 63(45%) were diagnosed with moderate condition during their stay at hospital. Conclusion(s): Regardless of age, gender and disease the death rate evaluated was 50%. Moreover, in diabetics and hypertensive patients there should be raised awareness for preventing the severity of disease. Copyright © 2022 Lahore Medical And Dental College. All rights reserved.

Knowledge, Attitudes, and Behaviors towards Proper Nutrition and Lifestyles in Italian Diabetic Patients during the COVID-19 Pandemic.

Prevention of diabetes mellitus is mainly based on a healthy lifestyle. The lockdown measures imposed during the COVID-19 pandemic resulted in major changes in daily life and social behavior, which may have an influence on diabetes self-management and glycemic control. The present work aims to assess the relationship between diabetic patients' knowledge, attitudes, and behaviors towards proper nutrition and lifestyles in order to plan strategies for educational intervention from a health literacy perspective. Attitudes, behaviors, and knowledge of diabetic patients attending the Diabetes and Metabolic Diseases Department of the Local Health Authority of Sassari (ASL1-SS) were assessed with a cognitive survey conducted from April to July 2022. Three hundred twenty-one questionnaires were administered during the survey period. Fifty-two percent of diabetic patients were female and 48% male, with a mean age of 61.1 ± 18.5 years and 62.0 ± 15.1 years, respectively. The overall level of knowledge about the role of food and proper nutrition with respect to the risk of diabetes and its complications appeared to be generally unsatisfactory and inadequate. Nonetheless, females showed a significantly higher level of knowledge than males (p < 0.0001). Moreover, knowledge was seen to decrease according to the age of the patients (p = 0.035). As for the possible impact played by the COVID-19 pandemic on lifestyles, it should be noted that about 70% of the respondents stated that they had maintained a reasonable dietary standard or even improved it throughout. Thus, the study underlines the need to improve the knowledge of diabetic subjects about nutrition and, in particular, their self-management, positively influencing behaviors and attitudes.

Investigation of Risk Factors for Hospitalization of COVID-19 Patients with Diabetes in Najaf, Iraq.

Preliminary findings indicate that patients with diabetes mellitus (DM) are at additional risk of infecting with COVID-19 caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which is associated with increased mortality in these patients. Hyperglycemia can affect inflammatory and immune responses, which leads patients to severe COVID-19 consequences. The present study investigated risk factors for hospitalized COVID-19 patients with DM in Najaf, Iraq. 127 patients with positive PCR tests were selected from Al-Hakeem Hospital and Al-Sadr Teaching Hospital. Demographic characteristics and laboratory data were collected to compare patients with and without DM. Chi-squared test followed by odds ratio calculations were used to investigate the risk factors associated with hospitalization of COVID-19 patients with or without DM in the ICU and RCU. Analysis of the relationship between risk factors indicated that age above 65 years, high BMI, hypertension, respiratory rate> 24 BPM, CVD, blood sugar> 180 mg/dl, D-dimer> 1000, ALT> 50 and AST> 40 U/L were independent risk factors for hospitalized COVID-19 patients with DM (P≤0.05). Therefore, investigating these factors may detect the risk of infection with COVID-19 in patients with DM in advance. Physicians should further consider risk factors to discover a targeted intervention to improve clinical efficacy.

Machine learning for optimizing healthcare resources

Optimizing healthcare resources is a major goal for any healthcare administrator. The significance of such a goal becomes very clear during pandemics. Access to such resources at the right time affects the quality of healthcare services and provides alternative treatments that can save patients’ lives. Achieving this goal becomes more challenging when there are large number of patients who have chronic diseases. Machine learning algorithms provide a very promising solution that can help healthcare administrators make the right decision at the right time. Machine learning model can predict the progress of pandemics, classify a patient with well-defined symptoms as contagious or not, and can also predict the number of patients who will be hospitalized in the future. This chapter shows how to utilize machine learning algorithms to create a models that can predict some of the key issues in healthcare systems. The discussion in the chapter relates to COVID-19 pandemic and highlights the solutions offered by machine learning in such scenarios. The chapter also highlights the significance of feature engineering and its impact on the accuracy of machine learning models. The chapter ends with two case studies. The first case study shows how to build a prediction model that can predict the number of diabetic patients who will visit certain hospitals in a specific geographic location in future years. The second case study analyzes health records during the COVID-19 pandemic. © 2021 Elsevier Inc. All rights reserved.

Invigorating diabetes care in a post-pandemic arena

Diabetes services have undergone significant changes during the pandemic. Anne Phillips highlights the opportunities this provides for improving care for people living with diabetes

Therapeutic interventions of remdesivir in diabetic and nondiabetic COVID-19 patients: A prospective observational study conducted on Pakistani population.

We aimed to investigate the interventions of remdesivir in both diabetic and nondiabetic individuals who were suffering from a severe infection of novel coronavirus disease (COVID-19). In this study, we aimed to explore the relationship between therapeutic effectiveness of remdesivir and complications of diabetes mellitus by observing the recovery period among diabetic and nondiabetic patients associated with COVID-19 infection. A total of 850 COVID-19 patients were recruited for this study, out of which 48% were diabetic and 52% were nondiabetics. The results of this study indicated that nondiabetic individuals administered with remdesivir recovered from COVID-19 within 10 days showing a 95% confidence interval (p < 0.01), while the diabetic individuals recovered in 15 days. Nondiabetic patients administered with remdesivir exhibited higher chances of clinical improvement at 15th day than those who were associated with diabetes. Remdesivir administration improved the levels of various biochemical parameters, such as C-reactive protein, lactate dehydrogenase, d-Dimer, and ferritin both in diabetic and nondiabetic patients. However, a significant improvement (p < 0.01) was seen in the level of biochemical parameters among nondiabetic patients as compared to that of diabetic patients administered with remdesivir treatment. In the end, it was concluded that remdesivir could be considered as a possible therapeutic agent in the treatment of COVID-19 both in diabetic and nondiabetic situations. However, diabetic patients showed a delayed recovery as compared with that of nondiabetic patients, in which the recovery rate was high.

Impact of Sitagliptin on Non-diabetic Covid-19 Patients.

OBJECTIVES: In coronavirus disease 2019 (Covid-19), SARS-CoV-2 may use dipeptidyl peptidase 4 (DPP4) as an entry-point in different tissues expressing these receptors. DPP4 inhibitors (DPP4Is), also named gliptins, like sitagliptin, have anti-inflammatory and antioxidant effects, thereby lessen inflammatory and oxidative stress in diabetic Covid-19 patients. Therefore, the present study aimed to illustrate the potential beneficial effect of sitagliptin in managing Covid-19 in non-diabetic patients. METHODS: A total number of 89 patients with Covid-19 were recruited from a single center at the time of diagnosis. The recruited patients were assigned according to the standard therapy for Covid-19 and our interventional therapy into two groups; Group A: Covid-19 patients on the standard therapy (n=40) and Group B: Covid-19 patients on the standard therapy plus sitagliptin (n=49). The duration of this interventional study was 28 days according to the guideline in managing patients with Covid-19. Routine laboratory investigations, serological tests, Complete Blood Count (CBC), C-reactive Protein (CRP), D-dimer, lactate dehydrogenase (LDH), and serum ferritin were measured to observed Covid-19 severity and complications. Lung Computed Tomography (CT) and clinical scores were evaluated. RESULTS: The present study illustrated that sitagliptin as an add-on to standard therapy improved clinical outcomes, radiological scores, and inflammatory biomarkers than standard therapy alone in non-diabetic patients with Covid-19 (P<0.01). CONCLUSION: Sitagliptin as an add-on to standard therapy in managing non-diabetic Covid-19 patients may have a robust beneficial effect by modulating inflammatory cytokines with subsequent good clinical outcomes.

COVID-19-specific diabetes worries amongst diabetic patients: The role of social support and other co-variates.

BACKGROUND: The COVID-19 pandemic has impacted every individual's life. It has been shown that mortality in people with underlying diseases including diabetes has been very high. The present study aimed to measure diabetes related worries (outcome) and their associations with social support and lifestyle (exposures) amongst people with diabetes during the COVID-19 pandemic. METHODS: An online cross-sectional survey was completed by 928 respondents (>18 years) between 15-11-2020 and 12-12-2020. The questionnaire comprised four sections: socio-demographic details, diabetic-related worries, social support, and behavioral changes due to COVID-19. Descriptive statistics, correlations and hierarchical regression analysis were performed in the study. RESULTS: Data from 928 respondents (51.61% male; mean age = 52.48 [SD = 11.76]; age range = 18-86 years) were analyzed. The mean score for COVID-19 specific diabetes worries was 3.13 out of 8. Hierarchical regression analysis showed that the mean COVID-19-specific diabetes worries score was significantly associated with lower age, cigarette smoking, perceived poor health status, presence of other diabetic complications. Lack of social support from family, friends, work colleagues and diabetes care team and also eating more than usual were also significantly associated with COVID-19 specific diabetes worry. CONCLUSIONS: Diabetes related worries were strongly associated with a lack of social support during the COVID-19 pandemic. The findings suggest the need of social support as well as improving knowledge and guidelines is important for people with diabetes during the COVID-19 pandemic.