scholarly journals Laboratory Testing Implications of Risk-Stratification and Management of COVID-19 Patients

2021 ◽  
Vol 8 ◽  
Author(s):  
Caidong Liu ◽  
Ziyu Wang ◽  
Wei Wu ◽  
Changgang Xiang ◽  
Lingxiang Wu ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
High Risk ◽  
Risk Stratification ◽  
Random Sampling ◽  
Early Stage ◽  
Viral Pneumonia ◽  
Low Risk ◽  
Training Dataset ◽  
Support Vector ◽  
Testing Dataset

Objective: To distinguish COVID-19 patients and non-COVID-19 viral pneumonia patients and classify COVID-19 patients into low-risk and high-risk at admission by laboratory indicators.Materials and methods: In this retrospective cohort, a total of 3,563 COVID-19 patients and 118 non-COVID-19 pneumonia patients were included. There are two cohorts of COVID-19 patients, including 548 patients in the training dataset, and 3,015 patients in the testing dataset. Laboratory indicators were measured during hospitalization for all patients. Based on laboratory indicators, we used the support vector machine and joint random sampling to risk stratification for COVID-19 patients at admission. Based on laboratory indicators detected within the 1st week after admission, we used logistic regression and joint random sampling to develop the survival mode. The laboratory indicators of COVID-10 and non-COVID-19 were also compared.Results: We first identified the significant laboratory indicators related to the severity of COVID-19 in the training dataset. Neutrophils percentage, lymphocytes percentage, creatinine, and blood urea nitrogen with AUC >0.7 were included in the model. These indicators were further used to build a support vector machine model to classify patients into low-risk and high-risk at admission in the testing dataset. Results showed that this model could stratify the patients in the testing dataset effectively (AUC = 0.89). Our model still has good performance at different times (Mean AUC: 0.71, 0.72, 0.72, respectively for 3, 5, and 7 days after admission). Moreover, laboratory indicators detected within the 1st week after admission were able to estimate the probability of death (AUC = 0.95). We identified six indicators with permutation p < 0.05, including eosinophil percentage (p = 0.007), white blood cell count (p = 0.045), albumin (p = 0.041), aspartate transaminase (p = 0.043), lactate dehydrogenase (p = 0.002), and hemoglobin (p = 0.031). We could diagnose COVID-19 and differentiate it from other kinds of viral pneumonia based on these laboratory indicators.Conclusions: Our risk-stratification model based on laboratory indicators could help to diagnose, monitor, and predict severity at an early stage of COVID-19. In addition, laboratory findings could be used to distinguish COVID-19 and non-COVID-19.

scholarly journals Laboratory Testing Implications of Risk-Stratification and Management of COVID-19 Patients

2021 ◽  
Author(s):  
Caidong Liu ◽  
Ziyu Wang ◽  
Wei Wu ◽  
Changgang Xiang ◽  
Lingxiang Wu ◽  
...  
Keyword(s):  
High Risk ◽  
Risk Stratification ◽  
Early Stage ◽  
Case Series ◽  
Low Risk ◽  
Training Dataset ◽  
Support Vector ◽  
Machine Model ◽  
Testing Dataset ◽  
Probability Of Death

Abstract Objectives: To classify COVID-19 patients into low-risk and high-risk at admission by laboratory indicators.Design, Setting, and Patients: This is a case series of patients from a China healthcare system in Wuhan. In this retrospective cohort, 3563 patients confirmed COVID-19 pneumonia, including 548 patients in the training dataset, and 3015 patients in the testing dataset.Interventions: NoneMeasurements and Main Results:We first identified the significant laboratory indicators related to the severity of COVID-19 in the training dataset. Neutrophils percentage, lymphocytes percentage, creatinine, and blood urea nitrogen with AUC greater than 0.7 were included in the model. These indicators were further used to build a support vector machine model to classify patients into low-risk and high-risk at admission. Results showed that this model could stratify the patients in the testing dataset effectively (AUC=0.89). Moreover, laboratory indicators detected in the first week after admission were able to estimate the probability of death (AUC=0.95). Besides, we could diagnose COVID-19 and differentiated it from other kinds of viral pneumonia based on laboratory indicators (accuracy=0.97).Conclusions:Our risk-stratification model based on laboratory indicators could help to diagnose, monitor, and predict severity at an early stage of COVID-19.

scholarly journals Laboratory Testing Implications of Risk-Stratification and Management of COVID-19 Patients

2021 ◽  
Author(s):  
Caidong Liu ◽  
Ziyu Wang ◽  
Wei Wu ◽  
Changgang Xiang ◽  
Lingxiang Wu ◽  
...  
Keyword(s):  
High Risk ◽  
Risk Stratification ◽  
Early Stage ◽  
Case Series ◽  
Low Risk ◽  
Training Dataset ◽  
Support Vector ◽  
Machine Model ◽  
Testing Dataset ◽  
Probability Of Death

Abstract Aims: To classify COVID-19 patients into low-risk and high-risk at admission by laboratory indicators.Design, Setting, and Patients: This is a case series of patients from a China healthcare system in Wuhan. In this retrospective cohort, 3563 patients confirmed COVID-19 pneumonia, including 548 patients in the training dataset, and 3015 patients in the testing dataset.Interventions: NoneMeasurements and Main Results: We first identified the significant laboratory indicators related to the severity of COVID-19 in the training dataset. Neutrophils percentage, lymphocytes percentage, creatinine, and blood urea nitrogen with AUC greater than 0.7 were included in the model. These indicators were further used to build a support vector machine model to classify patients into low-risk and high-risk at admission. Results showed that this model could stratify the patients in the testing dataset effectively (AUC=0.89). Moreover, laboratory indicators detected in the first week after admission were able to estimate the probability of death (AUC=0.95). Besides, we could diagnose COVID-19 and differentiated it from other kinds of viral pneumonia based on laboratory indicators (accuracy=0.97).Conclusions: Our risk-stratification model based on laboratory indicators could help to diagnose, monitor, and predict severity at an early stage of COVID-19.

scholarly journals Laboratory Testing Implications of Risk-Stratification and Management of COVID-19 Patients

2020 ◽  
Author(s):  
Caidong Liu ◽  
Ziyu Wang ◽  
Wei Wu ◽  
Changgang Xiang ◽  
Lingxiang Wu ◽  
...  
Keyword(s):  
Risk Stratification ◽  
Support Vector Machine Model ◽  
Early Stage ◽  
Laboratory Data ◽  
Training Dataset ◽  
Support Vector ◽  
Machine Model ◽  
Testing Dataset ◽  
Risk Stratification Model ◽  
Probability Of Death

Abstract The progression from mild to critical illness is the main reason leading to the death of COVID-19 patients. Rapid risk-stratification at admission is important for precise management of COVID-19. Here, we developed a practical admission stratification model to predict the severity during hospitalization of COVID-19 patients using laboratory data from 3563 patients, including 548 patients in the training dataset, and 3015 patients in the testing dataset. We first identified the significant laboratory indicators related to the severity of COVID-19 in the training dataset. Neutrophils percentage (NEUT%), lymphocytes percentage (LYMPH%), creatinine (CREA), and blood urea nitrogen (BUN) with AUC greater than 0.7 were included in the model. These indicators were further used to build a support vector machine model to classify patients into low-risk and high-risk at admission. Results showed that this model could stratify the patients in the testing dataset effectively (AUC=0.89). Moreover, laboratory indicators detected in the first week after admission were able to estimate the probability of death (AUC=0.95). Besides, we could diagnose COVID-19 and differentiated it from other kinds of viral pneumonia based on laboratory indicators (accuracy=0.97). Our risk-stratification model based on laboratory indicators could help to diagnose, monitor, and predict severity at an early stage of COVID-19.

NeuroCS: A Tool to Predict Cleavage Sites of Neuropeptide Precursors

2020 ◽  
Vol 27 (4) ◽  
pp. 337-345 ◽  
Author(s):  
Ying Wang ◽  
Juanjuan Kang ◽  
Ning Li ◽  
Yuwei Zhou ◽  
Zhongjie Tang ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Characteristic Curve ◽  
Training Dataset ◽  
Support Vector ◽  
Feature Subset ◽  
Cleavage Sites ◽  
Accurate Identification ◽  
Testing Dataset ◽  
Optimal Feature Subset ◽  
Independent Testing Dataset

Background: Neuropeptides are a class of bioactive peptides produced from neuropeptide precursors through a series of extremely complex processes, mediating neuronal regulations in many aspects. Accurate identification of cleavage sites of neuropeptide precursors is of great significance for the development of neuroscience and brain science. Objective: With the explosive growth of neuropeptide precursor data, it is pretty much needed to develop bioinformatics methods for predicting neuropeptide precursors’ cleavage sites quickly and efficiently. Method : We started with processing the neuropeptide precursor data from SwissProt and NueoPedia into two sets of data, training dataset and testing dataset. Subsequently, six feature extraction schemes were applied to generate different feature sets and then feature selection methods were used to find the optimal feature subset of each. Thereafter the support vector machine was utilized to build models for different feature types. Finally, the performance of models were evaluated with the independent testing dataset. Results: Six models are built through support vector machine. Among them the enhanced amino acid composition-based model reaches the highest accuracy of 91.60% in the 5-fold cross validation. When evaluated with independent testing dataset, it also showed an excellent performance with a high accuracy of 90.37% and Area under Receiver Operating Characteristic curve up to 0.9576. Conclusion: The performance of the developed model was decent. Moreover, for users’ convenience, an online web server called NeuroCS is built, which is freely available at http://i.uestc.edu.cn/NeuroCS/dist/index.html#/. NeuroCS can be used to predict neuropeptide precursors’ cleavage sites effectively.

scholarly journals Quadratic tuned kernel parameter in Non-linear support vector machine (SVM) for agarwood oil compounds quality classification

2020 ◽  
Vol 17 (3) ◽  
pp. 1371
Author(s):  
Muhamad Addin Akmal Bin Mohd Raif ◽  
Nurlaila Ismail ◽  
Nor Azah Mohd Ali ◽  
Mohd Hezri Fazalul Rahiman ◽  
Saiful Nizam Tajuddin ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Confusion Matrix ◽  
Research Area ◽  
Training Dataset ◽  
Support Vector ◽  
Testing Dataset ◽  
Quality Classification ◽  
Kernel Parameter ◽  
Svm Model ◽  
Agarwood Oil

<span>This paper presents the analysis of agarwood oil compounds quality classification by tuning quadratic kernel parameter in Support Vector Machine (SVM). The experimental work involved of agarwood oil samples from low and high qualities. The input is abundances (%) of the agarwood oil compounds and the output is the quality of the oil either high or low. The input and output data were processed by following tasks; i) data processing which covers normalization, randomization and data splitting into two parts in which training and testing database (ratio of 80%:20%), and ii) data analysis which covers SVM development by tuning quadratic kernel parameter. The training dataset was used to be train the SVM model and the testing dataset was used to test the developed SVM model. All the analytical works are performed via MATLAB software version R2013a. The result showed that, quadratic tuned kernel parameter in SVM model was successful since it passed all the performance criteria’s in which accuracy, precision, confusion matrix, sensitivity and specificity. The finding obtained in this paper is vital to the agarwood oil and its research area especially to the agarwood oil compounds classification system.</span>

ABC-Gly: identifying protein lysine glycation sites with artificial bee colony algorithm

2019 ◽  
Vol 17 ◽  
Author(s):  
Yanqiu Yao ◽  
Xiaosa Zhao ◽  
Qiao Ning ◽  
Junping Zhou
Keyword(s):  
Support Vector Machine ◽  
Amino Acid ◽  
Artificial Bee Colony Algorithm ◽  
Artificial Bee Colony ◽  
Training Dataset ◽  
Support Vector ◽  
Supplementary File ◽  
Feature Subset ◽  
Lipid Molecule ◽  
Bee Colony

Background: Glycation is a nonenzymatic post-translational modification process by attaching a sugar molecule to a protein or lipid molecule. It may impair the function and change the characteristic of the proteins which may lead to some metabolic diseases. In order to understand the underlying molecular mechanisms of glycation, computational prediction methods have been developed because of their convenience and high speed. However, a more effective computational tool is still a challenging task in computational biology. Methods: In this study, we showed an accurate identification tool named ABC-Gly for predicting lysine glycation sites. At first, we utilized three informative features, including position-specific amino acid propensity, secondary structure and the composition of k-spaced amino acid pairs to encode the peptides. Moreover, to sufficiently exploit discriminative features thus can improve the prediction and generalization ability of the model, we developed a two-step feature selection, which combined the Fisher score and an improved binary artificial bee colony algorithm based on support vector machine. Finally, based on the optimal feature subset, we constructed the effective model by using Support Vector Machine on the training dataset. Results: The performance of the proposed predictor ABC-Gly was measured with the sensitivity of 76.43%, the specificity of 91.10%, the balanced accuracy of 83.76%, the area under the receiver-operating characteristic curve (AUC) of 0.9313, a Matthew’s Correlation Coefficient (MCC) of 0.6861 by 10-fold cross-validation on training dataset, and a balanced accuracy of 59.05% on independent dataset. Compared to the state-of-the-art predictors on the training dataset, the proposed predictor achieved significant improvement in the AUC of 0.156 and MCC of 0.336. Conclusion: The detailed analysis results indicated that our predictor may serve as a powerful complementary tool to other existing methods for predicting protein lysine glycation. The source code and datasets of the ABC-Gly were provided in the Supplementary File 1.

scholarly journals CanAssist Breast Impacting Clinical Treatment Decisions in Early-Stage HR+ Breast Cancer Patients: Indian Scenario

2019 ◽  
Author(s):  
Satish Sankaran ◽  
Jyoti Bajpai Dikshit ◽  
Chandra Prakash SV ◽  
SE Mallikarjuna ◽  
SP Somashekhar ◽  
...  
Keyword(s):  
High Risk ◽  
Early Stage ◽  
Risk Groups ◽  
Treatment Decisions ◽  
Low Risk ◽  
Not Given ◽  
Breast Cancer Patients ◽  
Number Of Patients ◽  
Risk Of Cancer ◽  
The Impact

AbstractCanAssist Breast (CAB) has thus far been validated on a retrospective cohort of 1123 patients who are mostly Indians. Distant metastasis–free survival (DMFS) of more than 95% was observed with significant separation (P < 0.0001) between low-risk and high-risk groups. In this study, we demonstrate the usefulness of CAB in guiding physicians to assess risk of cancer recurrence and to make informed treatment decisions for patients. Of more than 500 patients who have undergone CAB test, detailed analysis of 455 patients who were treated based on CAB-based risk predictions by more than 140 doctors across India is presented here. Majority of patients tested had node negative, T2, and grade 2 disease. Age and luminal subtypes did not affect the performance of CAB. On comparison with Adjuvant! Online (AOL), CAB categorized twice the number of patients into low risk indicating potential of overtreatment by AOL-based risk categorization. We assessed the impact of CAB testing on treatment decisions for 254 patients and observed that 92% low-risk patients were not given chemotherapy. Overall, we observed that 88% patients were either given or not given chemotherapy based on whether they were stratified as high risk or low risk for distant recurrence respectively. Based on these results, we conclude that CAB has been accepted by physicians to make treatment planning and provides a cost-effective alternative to other similar multigene prognostic tests currently available.

Comparison of the Prognoses of FIGO Stage I to Stage II Adenosquamous Carcinoma and Adenocarcinoma of the Uterine Cervix Treated With Radical Hysterectomy

2012 ◽  
Vol 22 (8) ◽  
pp. 1389-1397 ◽  
Author(s):  
Seiji Mabuchi ◽  
Mika Okazawa ◽  
Yasuto Kinose ◽  
Koji Matsuo ◽  
Masateru Fujiwara ◽  
...  
Keyword(s):  
Risk Factors ◽  
Cervical Cancer ◽  
High Risk ◽  
Uterine Cervix ◽  
Radical Hysterectomy ◽  
Adenosquamous Carcinoma ◽  
Early Stage ◽  
Univariate Analysis ◽  
Low Risk ◽  
Histological Subtype

ObjectivesTo evaluate the significance of adenosquamous carcinoma (ASC) compared with adenocarcinoma (AC) in the survival of surgically treated early-stage cervical cancer.MethodsWe retrospectively reviewed the medical records of 163 patients with International Federation of Gynecology and Obstetrics stage IA2 to stage IIB cervical cancer who had been treated with radical hysterectomy with or without adjuvant radiotherapy between January 1998 and December 2008. The patients were classified according to the following: (1) histological subtype (ASC group or AC group) and (2) pathological risk factors (low-risk or intermediate/high-risk group). Survival was evaluated using the Kaplan-Meier method and compared using the log-rank test. Multivariate analysis of progression-free survival (PFS) was performed using the Cox proportional hazards regression model to investigate the prognostic significance of histological subtype.ResultsClinicopathological characteristics were similar between the ASC and AC histology groups. Patients with the ASC histology displayed a PFS rate similar to that of the patients with the AC histology in both the low-risk and intermediate/high-risk groups. Neither the recurrence rate nor the pattern of recurrence differed between the ASC group and the AC group. Univariate analysis revealed that patients with pelvic lymph node metastasis and parametrial invasion achieved significantly shorter PFS than those without these risk factors.ConclusionsCharacteristics of the patients and the tumors as well as survival outcomes of ASC were comparable to adenocarcinoma of early-stage uterine cervix treated with radical hysterectomy. Our results in part support that the management of ASC could be the same as the one of AC of the uterine cervix.

Identification of Molecular Biomarkers and Pathways for Risk Stratification in Human Papilloma Virus-Associated Cancers

2021 ◽  
Author(s):  
Eun Jung Kwon ◽  
Hye Ran Lee ◽  
Ju Ho Lee ◽  
Mihyang Ha ◽  
Yun Hak Kim ◽  
...  
Keyword(s):  
High Risk ◽  
Risk Stratification ◽  
Expression Patterns ◽  
Risk Groups ◽  
Molecular Biomarkers ◽  
Low Risk ◽  
Receptor Interaction ◽  
Prognostic Impact ◽  
Tumor Microenvironments ◽  
Cell Immunity

Abstract Background: Human papillomavirus (HPV) is the major cause of cervical cancer (CC) etiology; its contribution to head and neck cancer (HNC) incidence is steadily increasing. As individual patients’ response to the treatment of HPV-associated cancer is variable, there is a pressing need for the identification of biomarkers for risk stratification that can help determine the intensity of treatment. Methods: We have previously reported a novel prognostic and predictive indicator (HPPI) scoring system in HPV-associated cancers regardless of the anatomical locations by analyzing the TCGA and GEO databases. In this study, we comprehensively investigated the association of group-specific expression patterns of common differentially expressed genes (DEGs) between high-risk and low-risk groups in HPV-associated CC and HNC, identifying a molecular biomarkers and pathways for the risk stratification. Results: Among the identified 174 DEGs, expression of the genes associated with extracellular matrix (ECM)-receptor interaction pathway (ITGA5, ITGB1, LAMB1, LAMC1) were increased in high-risk groups in both HPV-associated CC and HNC while expression of the genes associated with the T-cell immunity (CD3D, CD3E, CD8B, LCK, and ZAP70) were decreased vise versa. The individual genes showed statistically significant prognostic impact on HPV-associated cancers but not on HPV-negative cancers. The expression levels of identified genes were similar between HPV-negative and HPV-associated high-risk groups with distinct expression patterns only in HPV-associated low-risk groups. Each group of genes showed negative correlations, and distinct patterns of immune cell infiltration in tumor microenvironments. Conclusion: These results identify molecular biomarkers and pathways for risk stratification in HPV-associated cancers regardless of anatomical locations. The identified targets are selectively working in only HPV-associated cancers, but not in HPV-negative cancers indicating possibility of the selective targets governing HPV-infective tumor microenvironments.

Sign in / Sign up

Export Citation Format

Share Document