Prediction of diagnosis and prognosis of COVID-19 disease by blood gas parameters using decision trees machine learning model: a retrospective observational study

Huyut, Mehmet Tahir; Üstündağ, Hilal

doi:10.4103/2045-9912.326002

Cited by 38 publications

(17 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the researches discussed above, decision tree based algorithms were showing advantages. Both research examples have visualized how good the models perform with testing set of data as well as important features for diagnosing the disease [11,13].…”

Section: Discussionmentioning

confidence: 99%

“…This indicates that if patients had their ionized calcium value in blood test lower or equal to 1.110 mM, they should be taken extra care of, and as shown in Fig. 2, prediction had 53.9% correctness according to the boundary value [13]. The next step for the model was to detect the disease, and at this point the most efficient predictor was carboxyhemoglobin value.…”

Section: In Detecting and Preventing Diseasementioning

confidence: 98%

“…As promising the result showed, there were still limitations due to the selfreporting nature of the symptoms, which could be biased, and lack of detailed information regards of some features like how long a person had contact with an infected [11]. Another research was focusing on blood gas test result to diagnose COVID-19 disease, where the team applied Chi-square automatic interaction detection (CHAID) decision tree algorithm as assistant [13]. This particular technique did not require parameters and variables could be qualitative and quantitative; moreover, it was able to deal with a large and complex dataset [14].…”

Section: In Detecting and Preventing Diseasementioning

confidence: 99%

“…Following with indicators such as pH, sodium, hematocrit and methemoglobin values, the prediction would achieve a high accuracy. Still, this model had limitations since the source of data was limited and biased due to factors such as the season was different when data collected [13].…”

Section: In Detecting and Preventing Diseasementioning

confidence: 99%

See 3 more Smart Citations

Machine learning for medical processing: algorithms and analysis

Zhang

2023

International Conference on Modern Medicine and Global Health (ICMMGH 2023)

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: In Detecting and Preventing Diseasementioning

confidence: 98%

Section: In Detecting and Preventing Diseasementioning

confidence: 99%

Section: In Detecting and Preventing Diseasementioning

confidence: 99%

See 2 more Smart Citations

Machine learning for medical processing: algorithms and analysis

Zhang

2023

International Conference on Modern Medicine and Global Health (ICMMGH 2023)

View full text Add to dashboard Cite

“…The aim of the Huyut M.T. et al research was to evaluate the diagnosis and prognosis of COVID-19 based on blood gas data by applying a chi-square automatic interaction detector (CHAID) decision tree model [42]. The decision tree, constructed with five key variables, demonstrated an overall classification accuracy of 68.2%.…”

Section: Discussionmentioning

confidence: 99%

A Novel COVID-19 Diagnosis Approach Utilizing a Comprehensive Set of Diagnostic Information (CSDI)

Zhunissova,

Dzierżak,

Omiotek

et al. 2023

JCM

View full text Add to dashboard Cite

The aim of the study was to develop a computerized method for distinguishing COVID-19-affected cases from cases of pneumonia. This task continues to be a real challenge in the practice of diagnosing COVID-19 disease. In the study, a new approach was proposed, using a comprehensive set of diagnostic information (CSDI) including, among other things, medical history, demographic data, signs and symptoms of the disease, and laboratory results. These data have the advantage of being much more reliable compared with data based on a single source of information, such as radiological imaging. On this basis, a comprehensive process of building predictive models was carried out, including such steps as data preprocessing, feature selection, training, and evaluation of classification models. During the study, 9 different methods for feature selection were used, while the grid search method and 12 popular classification algorithms were employed to build classification models. The most effective model achieved a classification accuracy (ACC) of 85%, a sensitivity (TPR) equal to 83%, and a specificity (TNR) of 88%. The model was built using the random forest method with 15 features selected using the recursive feature elimination selection method. The results provide an opportunity to build a computer system to assist the physician in the diagnosis of the COVID-19 disease.

show abstract

Advances in Point‐Of‐Care Testing for Emergency Response, Infectious Diseases, and Critical Care — Novel Technologies, Practice Standards, and Improved Outcomes

Füzéry¹,

Kost²,

Tran³

2022

Encyclopedia of Analytical Chemistry

View full text Add to dashboard Cite

We present strategies for point‐of‐care testing ( POCT ) that pave the way for diagnostic portals from homes to intensive care. Now well recognized worldwide by the public and professionals alike, POCT has become ubiquitous. Its scope encompasses mobile field rescue, emergency rooms, and hospital intensive care, where rapid test results help stabilize critically ill patients. We introduce novel technologies and insights for effective application of POCT, including identifying infectious pathogens. We chronicle the discovery of the clinical significance of ionized calcium, the ‘fifth electrolyte,’ an obligatory whole‐blood analyte. We tabulate outcomes associated with whole‐blood analysis, which has progressed significantly across the globe. Progressively endemic, coronavirus disease 2019 is catapulting POCT to new heights. This striking expansion calls for more practical know‐how among laboratorians and public health officials, careful planning of POC strategies in healthcare small‐world networks, and support by national guidelines and policies, especially in limited‐resource settings. Technical, clinical, and cultural advances predict exponential growth as the world embraces faster, smaller, and smarter connected diagnostic decision making where it counts the most, at points of need. This POC paradigm shift means learning novel principles and appreciating new standards for POC devices used on ambulances for emergency rescue, so we start there.

show abstract

Prediction of diagnosis and prognosis of COVID-19 disease by blood gas parameters using decision trees machine learning model: a retrospective observational study

Cited by 38 publications

References 26 publications

Machine learning for medical processing: algorithms and analysis

Machine learning for medical processing: algorithms and analysis

A Novel COVID-19 Diagnosis Approach Utilizing a Comprehensive Set of Diagnostic Information (CSDI)

Advances in Point‐Of‐Care Testing for Emergency Response, Infectious Diseases, and Critical Care — Novel Technologies, Practice Standards, and Improved Outcomes

Contact Info

Product

Resources

About