Predicting COVID-19 outcomes from clinical and laboratory parameters in an intensive care facility during the second wave of the pandemic in South Africa

Allwood, Brian; Koegelenberg, Coenraad F. N.; Ngah, Veranyuy D.; Sigwadhi, Lovemore N.; Irusen, Elvis; Lalla, Usha; Yalew, Anteneh; Tamuzi, Jacques L.; Allister, Marli Mc; Zemlin, Annalise E.; Jalavu, Thumeka P.; Erasmus, Rajiv T; Chapanduka, Zivanai C.; Matsha, Tandi E.; Fwemba, Isaac; Zumla, Alimuddin; Nyasulu, Peter

doi:10.1016/j.ijregi.2022.03.024

Cited by 12 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Histopathological results from SARS and covid-19 were diffuse alveolar damage with fibrin-rich hyaline membranes and multiple multinucleated giant cells. Suboptimal wound healing causes more severe scarring and fibrosis than other forms of ARDS (10). This pathogenesis is the basis for determining Brixia's scoring in covid-19 cases.…”

Section: Discussionmentioning

confidence: 99%

Chest imaging of COVID-19 patients amongst diverse vaccination status: A comparative study using Brixia Score

Hanafi¹,

Maryetty²,

Widiastuti³

2022

GSC Adv. Res. Rev.

View full text Add to dashboard Cite

Background: Covid-19 vaccination has reached more than 132 million people in Indonesia since its first outbreak in March 2020. However; its effects on immunity are still lack of evidence. Covid-19 cases reached a significant increase in June 2021 and decreased in November 2021. In early 2022; it again recorded an increase. Seeing this phenomenon; this study investigates the differences of Covid-19 Patients’ severity levels over their vaccination status. Objective: This study examines the differences of severity level of chest x-ray imaging in covid-19 patients treated at Dr. Moewardi Hospital in three periods of time. Methods: A total of 89 covid-19 cases were collected from 3 different vaccination status: (1) 30 non-vaccinated patients (group A); (2) 30 patients treated for covid-19 after 1-3 months post-vaccination (group B); (3) 29 treated for covid-19 after more than 6 months post-vaccination (group C). Patients with type-II diabetes mellitus; heart failure or autoimmune disease were excluded. Severity level is based on chest x-ray examination by calculating the Brixia score by 3 examiners. All assessment results were analysed using the Kruskall-Wallis test followed by the Mann-Whitney post-hoc test. Results: A total of 8 male (26.7%) and 22 female (73.3%) patients in group B had lower Brixia scores with mean score 2.94 + 0.25 compared to 29 patients (55% male and 45% female) in group C with mean score 4.90 + 0.27 with a significant difference (p = 0.001). The Brixia score with the highest average was found in group A (non-vaccinated) with mean value 5.77 + 0.31 showing a significant difference from groups B and C (p<0.05). Conclusion: Vaccine administration status showed different Brixia scores; whereas longer duration from vaccination showed higher score. Unvaccinated patients recorded the most severe condition. Booster vaccination is strongly recommended to obtain the best immunity level.

show abstract

Section: Discussionmentioning

confidence: 99%

Chest imaging of COVID-19 patients amongst diverse vaccination status: A comparative study using Brixia Score

Hanafi¹,

Maryetty²,

Widiastuti³

2022

GSC Adv. Res. Rev.

View full text Add to dashboard Cite

show abstract

“…Out of 60 reviewed articles, 16 were eligible for data extraction (Table 2). All 16 articles were conducted in Africa, 1 [19] of them in Nigeria, 2 [20,34] in Egypt, 2 [21,30] in Ethiopia, 1 [22] in South Africa, 2 [23,24] in Uganda, 4 in DRC, [25,26,32,33] 1 [27] in Ghana, 2 [28,29] in Guinea, 1 [29] in Burkina Faso, 1 [31] in Niger. Of these, 5 [19,25,27,32,33] articles were published in 2020, 4 [28,29,31,34] in 2021, and 7 [20][21][22][23][24]26,30] in 2022.…”

Section: Characteristics Of Included Studiesmentioning

confidence: 99%

“…All 16 articles were conducted in Africa, 1 [19] of them in Nigeria, 2 [20,34] in Egypt, 2 [21,30] in Ethiopia, 1 [22] in South Africa, 2 [23,24] in Uganda, 4 in DRC, [25,26,32,33] 1 [27] in Ghana, 2 [28,29] in Guinea, 1 [29] in Burkina Faso, 1 [31] in Niger. Of these, 5 [19,25,27,32,33] articles were published in 2020, 4 [28,29,31,34] in 2021, and 7 [20][21][22][23][24]26,30] in 2022. The total sample size in the present systematic review and meta-analysis was 12,297 participants, predominantly men.…”

Section: Characteristics Of Included Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Risk factors for death in hospitalized COVID-19 patients in Africa: A systematic review and meta-analysis

Riziki Ghislain,

Muzumbukilwa,

Magula

2023

Medicine

View full text Add to dashboard Cite

Background: The coronavirus disease 2019 has quickly spread worldwide since it first appeared in Wuhan, China, in late 2019. The most affected country in Africa was South Africa. This study aimed to identify the risk factors for death in hospitalized COVID-19 patients in Africa. Methods: We conducted a systematic review following the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines. We searched articles from the following database: PubMed, Embase, Cochrane Library, Medline, and COVID-19 Research Database. We used Google Scholar for gray literature. The language used in this article was English. The last search was conducted on January 15, 2023. Pooled HRs, or ORs, and 95% confidence intervals, were calculated separately to identify the risk factors for death in hospitalized COVID-19 patients. Heterogeneity was assessed by Cochran’s Q statistic and the I 2 test. The Egger test was used to assess publication bias. Subgroup analysis was performed to determine the source of heterogeneity. Data analysis was performed using Stata version 17. A P value < .05 was considered significant. Results: A total of 16,600 articles were obtained from the database search; finally, 16 articles met the inclusion criteria and were eligible for data extraction. The analysis revealed that the pooled prevalence of mortality in hospitalized COVID-19 patients was 13.9%. Advanced age was a significant risk factor for death in hospitalized COVID-19 patients, with the pooled coronavirus mortality HR and OR being 3.73 (95% CI: 2.27–5.19) and 1.04 (95% CI: 1.02–1.06), respectively. In addition, male gender (pOR 1.23; 95% CI: 1.07–1.40), patients with diabetes mellitus (DM) (pOR 1.26; 95% CI: 1.01–1.51), hypertension (HTN) (pOR 1.56; 95% CI: 1.27–1.85), chronic kidney disease (CKD) (pHR 5.43; 95% CI: 0.18–10.67), severe or critical conditions (pOR 9.04; 95% CI: 3.14–14.94) had a significantly increased risk of coronavirus-related mortality. The main limitations of the present study stem from the predominant use of published studies, which could introduce publication bias. Conclusion: According to this study, advanced age, male gender, hypertension, diabetes mellitus, chronic kidney disease, and severe or critical condition were clinical risk factors associated with death outcomes in hospitalized COVID-19 patients in Africa.

show abstract

“…The effect of the COVID-19 pandemic on healthcare systems all over the world has been devastating [1]. As a result, various clinical intervention methods have been employed in the detection, diagnosis, and prognosis of COVID-19 cases, including clinical/laboratory methods and medical image-based diagnosis [2][3]. Lately, the use of Artificial Intelligence (AI) methods for tackling the challenges of COVID-19 has received significant attention.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-based Prediction of Treatment Outcome of Patients with COVID-19 and Comorbidities: A South African Cohort Study

Daramola

Kavu

Kotze

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Background: As a result of the COVID-19 pandemic, various clinical intervention methods and AI methods have been employed in the detection, diagnosis, and prognosis of COVID-19 cases. However, limited instances of applying AI to the prognosis of COVID-19 cases in Africa have been reported in the literature. Thus, case studies on the application of machine learning to guide for decision-making on the treatment of COVID-19 cases in Africa are essential. Methods: We applied three machine learning (ML) algorithms: Deep Multi-layer Perceptron (Deep MLP), Extreme Boosted Trees (XGBoost) and Support Vector Machines (SVM) for predicting the outcome of intensive care patients of COVID-19 with comorbidities in a South African hospital. We compared the performance and interpretability of the three ML models when cross-validation (CV) and principal component analysis (PCA) were applied for the prognosis of COVID-19 mortality risk. Results: We found that Deep MLP had the best overall performance when CV and SMOTE were applied without PCA (F1=0.92; AUC = 0.94), followed by SVM (F1=0.83; AUC=0.82). We found that the performance of both SVM and MLP can be enhanced through CV without PCA. XGBoost (F1= 0.81; AUC = 0.79) performed best when none of CV, PCA or SMOTE was applied. XGBoost is not affected by CV and performs worse with PCA. From the model predictions, we identified Length of stay in the hospital, Duration in ICU, Time to ICU from Admission, Days discharged or death, D-dimer (blood clotting factor), and blood pH as the six most critical variables for the prediction of mortality or survival of the COVID-19 patients. We also found other variables: Age at admission, Pf Ratio (PaO2/FiO2 ratio), TropT, Ferritin, ventilation, CRP, and Symptom of Acute respiratory distress syndrome (ARDS) associated with the severity and fatality of COVID-19 cases. Conclusions: This study demonstrates how ML can be applied to identify variables that have prognostic value in the treatment and management of critically ill COVID-19 patients. The findings also reveal the effect of CV and PCA when predicting clinical outcomes of COVID-19 cases

show abstract

Predicting COVID-19 outcomes from clinical and laboratory parameters in an intensive care facility during the second wave of the pandemic in South Africa

Cited by 12 publications

References 35 publications

Chest imaging of COVID-19 patients amongst diverse vaccination status: A comparative study using Brixia Score

Chest imaging of COVID-19 patients amongst diverse vaccination status: A comparative study using Brixia Score

Risk factors for death in hospitalized COVID-19 patients in Africa: A systematic review and meta-analysis

Machine Learning-based Prediction of Treatment Outcome of Patients with COVID-19 and Comorbidities: A South African Cohort Study

Contact Info

Product

Resources

About