early prediction
Recently Published Documents


TOTAL DOCUMENTS

2045
(FIVE YEARS 796)

H-INDEX

71
(FIVE YEARS 9)

2022 ◽  
Vol 3 ◽  
Author(s):  
Elham Jamshidi ◽  
Amirhossein Asgary ◽  
Nader Tavakoli ◽  
Alireza Zali ◽  
Soroush Setareh ◽  
...  

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.


2022 ◽  
Author(s):  
Annika R. P. Schneider ◽  
Carolin V. Schneider ◽  
Kai Markus Schneider ◽  
Vanessa Baier ◽  
Steffen Schaper ◽  
...  

Author(s):  
Koki Nakanishi ◽  
Mitsuro Kanda ◽  
Chie Tanaka ◽  
Shigeomi Takeda ◽  
Katsuhito Tanaka ◽  
...  

2022 ◽  
Vol 22 (1) ◽  
Author(s):  
Elham Shaarbaf Eidgahi ◽  
Malihe Nasiri ◽  
Nourossadat Kariman ◽  
Nastaran Safavi Ardebili ◽  
Masoud Salehi ◽  
...  

Abstract Background Gestational Diabetes Mellitus (GDM) is an underlying cause of maternal and newborn morbidity and mortality all around the world. Timely diagnosis of GDM plays an important role in reducing its adverse consequences and burden. This study aimed to determine diagnostic accuracy of multiple indicators in complete blood count (CBC) test for early prediction of GDM. Methods In this prospective cohort study, the data from 600 pregnant women was analyzed. In the study sample, the two-step approach was utilized for the diagnosis of GDM at 24–28 weeks of gestation. We also used the repeated measures of hemoglobin (Hb), hematocrit (Hct), fasting blood sugar (FBS) and red blood cell count (RBC) in the first and early second trimesters of pregnancy as the longitudinal multiple indicators for early diagnosis of GDM. The classification of pregnant women to GDM and non-GDM groups was performed using a statistical technique based on the random-effects modeling framework. Results Among the sample, 49 women (8.2%) were diagnosed with GDM. In the first and early second trimester of pregnancy, the mean HcT, Hb and FBS of women with GDM was significantly higher than non-GDMs (P < 0.001). The concurrent use of multiple longitudinal data from HcT, Hb, RBC and FBS in the first and early second trimester of pregnancy resulted in a sensitivity, specificity and area under the curve (AUC) of 87%, 70% and 83%, respectively, for early prediction of GDM. Conclusions In general, our findings showed that the concurrent use of repeated measures data on Hct, Hb, FBS and RBC in the first and early second trimester of pregnancy might be utilized as an acceptable tool to predict GDM earlier in pregnancy.


Author(s):  
Siran Lin ◽  
YuBing Peng ◽  
Yuzhen Xu ◽  
Wei Zhang ◽  
Jing Wu ◽  
...  

H1N1 is the most common subtype of influenza virus circulating worldwide and can cause severe disease in some populations. Early prediction and intervention for patients who develop severe influenza will greatly reduce their mortality. In this study, we conducted a comprehensive analysis of 180 PBMC samples from three published datasets from the GEO DataSets. Differentially expressed gene (DEG) analysis and weighted correlation network analysis (WGCNA) were performed to provide candidate DEGs for model building. Functional enrichment and CIBERSORT analyses were also performed to evaluate the differences in composition and function of PBMCs between patients with severe and mild disease. Finally, a risk score model was built using lasso regression analysis, with six genes (CX3CR1, KLRD1, MMP8, PRTN3, RETN and SCD) involved. The model performed moderately in the early identification of patients that develop severe H1N1 disease.


Sign in / Sign up

Export Citation Format

Share Document