Symptom Prediction and Mortality Risk Calculation for COVID-19 Using Machine Learning

Jamshidi, Elham; Asgary, Amirhossein; Tavakoli, Nader; Zali, Alireza; Dastan, Farzaneh; Daaee, Amir; Badakhshan, Mohammadtaghi; Esmaily, Hadi; Jamaldini, Seyed Hamid; Safari, Saeid; Bastanhagh, Ehsan; Maher, Ali; Babajani, Amirhesam; Mehrazi, Maryam; Kashi, Mohammad Ali Sendani; Jamshidi, Masoud; Sendani, Mohammad Hassan; Rahi, Sahand Jamal; Mansouri, Nahal

doi:10.3389/frai.2021.673527

Cited by 20 publications

(9 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A number of studies have investigated the risk factors affecting COVID-19 infections (34,35). Elevated inflammatory cytokines such as interleukin-6 (IL-6), granulocyte colonystimulating factor (G-CSF), interferon gamma-induced protein 10 (IP-10), and interferon (IFN)-γ have been proposed as poor prognostic factors for COVID-19 patients (36)(37)(38)(39).…”

Section: Discussionmentioning

confidence: 99%

Using Machine Learning to Predict Mortality for COVID-19 Patients on Day 0 in the ICU

Jamshidi

Asgary

Tavakoli

et al. 2022

Front. Digit. Health

Self Cite

View full text Add to dashboard Cite

Rationale: Given the expanding number of COVID-19 cases and the potential for new waves of infection, there is an urgent need for early prediction of the severity of the disease in intensive care unit (ICU) patients to optimize treatment strategies.Objectives: Early prediction of mortality using machine learning based on typical laboratory results and clinical data registered on the day of ICU admission.Methods: We retrospectively studied 797 patients diagnosed with COVID-19 in Iran and the United Kingdom (U.K.). To find parameters with the highest predictive values, Kolmogorov-Smirnov and Pearson chi-squared tests were used. Several machine learning algorithms, including Random Forest (RF), logistic regression, gradient boosting classifier, support vector machine classifier, and artificial neural network algorithms were utilized to build classification models. The impact of each marker on the RF model predictions was studied by implementing the local interpretable model-agnostic explanation technique (LIME-SP).Results: Among 66 documented parameters, 15 factors with the highest predictive values were identified as follows: gender, age, blood urea nitrogen (BUN), creatinine, international normalized ratio (INR), albumin, mean corpuscular volume (MCV), white blood cell count, segmented neutrophil count, lymphocyte count, red cell distribution width (RDW), and mean cell hemoglobin (MCH) along with a history of neurological, cardiovascular, and respiratory disorders. Our RF model can predict patient outcomes with a sensitivity of 70% and a specificity of 75%. The performance of the models was confirmed by blindly testing the models in an external dataset.Conclusions: Using two independent patient datasets, we designed a machine-learning-based model that could predict the risk of mortality from severe COVID-19 with high accuracy. The most decisive variables in our model were increased levels of BUN, lowered albumin levels, increased creatinine, INR, and RDW, along with gender and age. Considering the importance of early triage decisions, this model can be a useful tool in COVID-19 ICU decision-making.

show abstract

Section: Discussionmentioning

confidence: 99%

Using Machine Learning to Predict Mortality for COVID-19 Patients on Day 0 in the ICU

Jamshidi

Asgary

Tavakoli

et al. 2022

Front. Digit. Health

Self Cite

View full text Add to dashboard Cite

show abstract

“…In general the prevalence of COVID-19 symptoms differ depending on the studied population. For example, in an Iranian study of 23,749 patients from 74 hospitals in Teheran, the most prevalent symptoms were cough (50.51%), respiratory distress (43.55%), muscular pain or fatigue (38.94%), gastrointestinal problems (10.4%) and headache (4.72%) ( 35 ). A Chinese meta-analysis of 38 studies with 3,062 patients found these to be fever (80.4%), cough (63.1%) and fatigue (46.0%) but not anosmia or ageusia ( 36 ).…”

Section: Discussionmentioning

confidence: 99%

The prevalence of symptoms and its correlation with sex in polish COVID-19 adult patients: Cross-sectional online open survey

et al. 2023

View full text Add to dashboard Cite

BackgroundThe understanding and treatment of COVID-19 has improved rapidly since December 2019 when SARS-CoV-2 was sequenced. However most papers on its symptomatology focus on hospitalized patients and address only a limited number of major presentations. Although differences depending on sex of COVID-19 patients have been previously confirmed (higher ICU admission and higher death rate for men), no publication has focused on sex-related differences in COVID-19 symptomatology.ObjectiveThe aim of the study was to present a reliable list of COVID-19 symptoms and identify any differences in symptom prevalence depending on sex.MethodsA sample of Polish patients suffering from COVID-19 were surveyed using a cross-sectional anonymous online survey in Polish available on a web-based surveying platform (Survey Monkey). The survey included 20 questions asking about COVID-19 symptoms, days of occurrence (from day 1 until day 14 and “15 days or more”) and patient characteristics including sex, age, height, weight, place of residence and type of therapy received during COVID-19. The survey was made available during the third COVID-19 wave in Poland. The link to the survey was distributed across social networks. Participation was open to anyone willing, without any incentives. The data was analyzed statistically.ResultsSurvey responses were collected from 2,408 participants (56.9% women) aged 18–90 (42 ± 12), 84.7% living in cities, who took part in the study between December 2020 and February 2021. Out of 54 predefined symptoms, the three most prevalent were fatigue (reported by 87.61% respondents), anosmia (73.74%) and headache (69.89%). Women were found to be more symptomatic than men, 31 symptoms occurred more often in women (including anosmia, headache and myalgias, p < 0.05). Subfebrility, fever and hemoptysis were more prevalent in men. Twelve symptoms (incl. hypothermia, sneezing and nausea) lasted longer in women than men (p < 0.05). Fatigue, cough, nasal dryness, xerostomia and polydipsia were the longest lasting symptoms of COVID-19 (lasted over 14 days).ConclusionOur study presents a wide range of symptoms, which may enable better recognition of COVID-19, especially in an outpatient setting. Understanding these differences in the symptomatology of community and hospitalized patients may help diagnose and treat patients faster and more accurately. Our findings also confirmed differences in symptomatology of COVID-19 between men and women, which may lay the foundation for a better understanding of the different courses of this disease in the sexes. Further studies are necessary to understand whether a different presentation correlates with a different outcome.

show abstract

“…Till now, several general characteristics and diseased elements such as sex, age, high blood pressure, diabetes, chronic lung infection, dermatologic infection, endocrine and hepatobiliary complications, and cardiovascular manifestation are considered among the main risk factor observed during clinical managements of COVID-19 (Jordan et al, 2020;Yang et al, 2020;Jamshidi et al, 2021).…”

Section: Viral Manifestationsmentioning

confidence: 99%

Interplay of Nutrition and Psychoneuroendocrineimmune Modulation: Relevance for COVID-19 in BRICS Nations

Mehta

Ratre

Sharma³

et al. 2021

Front. Microbiol.

View full text Add to dashboard Cite

The consequences of COVID-19 are not limited to physical health deterioration; the impact on neuropsychological well-being is also substantially reported. The inter-regulation of physical health and psychological well-being through the psychoneuroendocrineimmune (PNEI) axis has enduring consequences in susceptibility, treatment outcome as well as recuperation. The pandemic effects are upsetting the lifestyle, social interaction, and financial security; and also pose a threat through perceived fear. These consequences of COVID-19 also influence the PNEI system and wreck the prognosis. The nutritional status of individuals is also reported to have a determinative role in COVID-19 severity and convalescence. In addition to energetic demand, diet also provides precursor substances [amino acids (AAs), vitamins, etc.] for regulators of the PNEI axis such as neurotransmitters (NTs) and immunomodulators. Moreover, exaggerated immune response and recovery phase of COVID-19 demand additional nutrient intake; widening the gap of pre-existing undernourishment. Mushrooms, fresh fruits and vegetables, herbs and spices, and legumes are few of such readily available food ingredients which are rich in protein and also have medicinal benefits. BRICS nations have their influences on global development and are highly impacted by a large number of confirmed COVID-19 cases and deaths. The adequacy and access to healthcare are also low in BRICS nations as compared to the rest of the world. Attempt to combat the COVID-19 pandemic are praiseworthy in BRICS nations. However, large population sizes, high prevalence of undernourishment (PoU), and high incidence of mental health ailments in BRICS nations provide a suitable landscape for jeopardy of COVID-19. Therefore, appraising the interplay of nutrition and PNEI modulation especially in BRICS countries will provide better understanding; and will aid in combat COVID-19. It can be suggested that the monitoring will assist in designing adjunctive interventions through medical nutrition therapy and psychopsychiatric management.

show abstract

Symptom Prediction and Mortality Risk Calculation for COVID-19 Using Machine Learning

Cited by 20 publications

References 28 publications

Using Machine Learning to Predict Mortality for COVID-19 Patients on Day 0 in the ICU

Using Machine Learning to Predict Mortality for COVID-19 Patients on Day 0 in the ICU

The prevalence of symptoms and its correlation with sex in polish COVID-19 adult patients: Cross-sectional online open survey

Interplay of Nutrition and Psychoneuroendocrineimmune Modulation: Relevance for COVID-19 in BRICS Nations

Contact Info

Product

Resources

About