Scores based on neutrophil percentage and lactate dehydrogenase with or without oxygen saturation predict hospital mortality risk in severe COVID-19 patients

Abstract Background Risk scores are needed to predict the risk of death in severe coronavirus disease 2019 (COVID-19) patients in the context of rapid disease progression. Methods Using data from China (training dataset, n = 96), prediction models were developed by logistic regression and then risk scores were established. Leave-one-out cross validation was used for internal validation and data from Iran (test dataset, n = 43) was used for external validation. Results A NSL model (area under the curve (AUC) 0.932) and a NL model (AUC 0.903) were developed based on neutrophil percentage and lactate dehydrogenase with and without oxygen saturation (SaO2) using the training dataset. AUCs of the NSL and NL models in the test dataset were 0.910 and 0.871, respectively. The risk scoring systems corresponding to these two models were established. The AUCs of the NSL and NL scores in the training dataset were 0.928 and 0.901, respectively. At the optimal cut-off value of NSL score, the sensitivity and specificity were 94% and 82%, respectively. The sensitivity and specificity of NL score were 94% and 75%, respectively. Conclusions These scores may be used to predict the risk of death in severe COVID-19 patients and the NL score could be used in regions where patients' SaO2 cannot be tested.

Download Full-text

Scores based on neutrophil percentage and lactate dehydrogenase with or without oxygen saturation predict the risk of hospital mortality in severe COVID-19 patients

10.21203/rs.3.rs-73731/v1 ◽

2020 ◽

Author(s):

Xiude Fan ◽

Bin Zhu ◽

Masoud Nouri-Vaskeh ◽

Chunguo Jiang ◽

Xiaokai Feng ◽

...

Keyword(s):

Lactate Dehydrogenase ◽

Oxygen Saturation ◽

Prediction Models ◽

External Validation ◽

Risk Scores ◽

Training Dataset ◽

Test Dataset ◽

Risk Of Death ◽

Neutrophil Percentage ◽

Risk Scoring

Abstract Background. Risk scores are urgently needed to assist clinicians in predicting the risk of death in severe patients with SARS-CoV-2 infection in the context of millions of people infected, rapid disease progression, and shortage of medical resources.Method. A total of 139 severe patients with SARS-CoV-2 from China and Iran were included. Using data from China (training dataset, n = 96), prediction models were developed based on logistic regression models, nomogram and risk scoring system for simplification. Leave-one-out cross validation was used for internal validation and data from Iran (test dataset, n = 43) for external validation. Results. The NSL model (Area under the curve (AUC) 0.932) and NL model (AUC 0.903) were developed based on neutrophil percentage (NE), lactate dehydrogenase (LDH) with or without oxygen saturation (SaO2) using the training dataset. Compared with the training dataset, the predictability of NSL model (AUC 0.910) and NL model (AUC 0.871) were similar in the test dataset. The risk scoring systems corresponding to these two models were established for clinical application. The AUCs of the NSL and NL scores were 0.928 and 0.901 in the training dataset, respectively. At the optimal cut-off value of NSL score, the sensitivity was 94% and specificity was 82%. In addition, for NL score, the sensitivity and specificity were 94% and 75%, respectively.Conclusion. NSL and NL score are straightforward means for clinicians to predict the risk of death in severe patients. NL score could be used in selected regions where patients’ SaO2 cannot be tested.

Download Full-text

Genetic co-expression networks contribute to creating predictive model and exploring novel biomarkers for the prognosis of breast cancer

Scientific Reports ◽

10.1038/s41598-021-84995-z ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Chi-Ming Chu ◽

Huan-Ming Hsu ◽

Chi-Wen Chang ◽

Yuan-Kuei Li ◽

Yu-Jia Chang ◽

...

Keyword(s):

Breast Cancer ◽

Prediction Models ◽

Reference Model ◽

External Validation ◽

Risk Scores ◽

Consistent Finding ◽

Hazard Ratios ◽

Genetic Predictors ◽

Novel Biomarkers ◽

Cox Proportional Hazard Regression

AbstractGenetic co-expression network (GCN) analysis augments the understanding of breast cancer (BC). We aimed to propose GCN-based modeling for BC relapse-free survival (RFS) prediction and to discover novel biomarkers. We used GCN and Cox proportional hazard regression to create various prediction models using mRNA microarray of 920 tumors and conduct external validation using independent data of 1056 tumors. GCNs of 34 identified candidate genes were plotted in various sizes. Compared to the reference model, the genetic predictors selected from bigger GCNs composed better prediction models. The prediction accuracy and AUC of 3 ~ 15-year RFS are 71.0–81.4% and 74.6–78% respectively (rfm, ACC 63.2–65.5%, AUC 61.9–74.9%). The hazard ratios of risk scores of developing relapse ranged from 1.89 ~ 3.32 (p < 10–8) over all models under the control of the node status. External validation showed the consistent finding. We found top 12 co-expressed genes are relative new or novel biomarkers that have not been explored in BC prognosis or other cancers until this decade. GCN-based modeling creates better prediction models and facilitates novel genes exploration on BC prognosis.

Download Full-text

Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients

Scientific Reports ◽

10.1038/s41598-021-81844-x ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Espen Jimenez-Solem ◽

Tonny S. Petersen ◽

Casper Hansen ◽

Christian Hansen ◽

Christina Lioma ◽

...

Keyword(s):

Prediction Models ◽

Severe Disease ◽

External Validation ◽

Area Under The Curve ◽

Predictive Performance ◽

Mortality Prediction ◽

Icu Admission ◽

Risk Of Death ◽

Online Risk ◽

The United Kingdom

AbstractPatients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that machine learning (ML) models could be used to predict risks at different stages of management and thereby provide insights into drivers and prognostic markers of disease progression and death. From a cohort of approx. 2.6 million citizens in Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further analysis. SARS-CoV-2 positive cases from the United Kingdom Biobank was used for external validation. The ML models predicted the risk of death (Receiver Operation Characteristics—Area Under the Curve, ROC-AUC) of 0.906 at diagnosis, 0.818, at hospital admission and 0.721 at Intensive Care Unit (ICU) admission. Similar metrics were achieved for predicted risks of hospital and ICU admission and use of mechanical ventilation. Common risk factors, included age, body mass index and hypertension, although the top risk features shifted towards markers of shock and organ dysfunction in ICU patients. The external validation indicated fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission. ML may be used to identify drivers of progression to more severe disease and for prognostication patients in patients with COVID-19. We provide access to an online risk calculator based on these findings.

Download Full-text

Cluster-Based Smartphone Predictive Analytics for Application Usage and Next Location Prediction

International Journal of Business Intelligence Research ◽

10.4018/ijbir.2018070104 ◽

2018 ◽

Vol 9 (2) ◽

pp. 64-80

Author(s):

Xiaoling Lu ◽

Bharatendra Rai ◽

Yan Zhong ◽

Yuzhu Li

Keyword(s):

Prediction Models ◽

Predictive Analytics ◽

User Behavior ◽

Training Dataset ◽

Location Prediction ◽

Behavior Prediction ◽

Test Dataset ◽

Smartphone Sensors ◽

Using Data ◽

Prediction Approach

Prediction of app usage and location of smartphone users is an interesting problem and active area of research. Several smartphone sensors such as GPS, accelerometer, gyroscope, microphone, camera and Bluetooth make it easier to capture user behavior data and use it for appropriate analysis. However, differences in user behavior and increasing number of apps have made such prediction a challenging problem. In this article, a prediction approach that takes smartphone user behavior into consideration is proposed. The proposed approach is illustrated using data from over 30000 users from a leading IT company in China by first converting data in to recency, frequency, and monetary variables and then performing cluster analysis to capture user behavior. Prediction models are then developed for each cluster using a training dataset and their performance is assessed using a test dataset. The study involves ten different categories of apps and four different regions in Beijing. The proposed app usage prediction and next location prediction approach has provided interesting results.

Download Full-text

Development and external validation of 1- and 2-year mortality prediction models in cystic fibrosis

European Respiratory Journal ◽

10.1183/13993003.00224-2019 ◽

2019 ◽

Vol 54 (3) ◽

pp. 1900224 ◽

Cited By ~ 3

Author(s):

Sanja Stanojevic ◽

Jenna Sykes ◽

Anne L. Stephenson ◽

Shawn D. Aaron ◽

George A. Whitmore

Keyword(s):

Cystic Fibrosis ◽

Health Status ◽

Prediction Models ◽

Risk Model ◽

External Validation ◽

Registry Data ◽

Receiver Operating Curve ◽

Clinical Tool ◽

Risk Of Death ◽

The Uk

IntroductionWe aimed to develop a clinical tool for predicting 1- and 2-year risk of death for patients with cystic fibrosis (CF). The model considers patients' overall health status as well as risk of intermittent shock events in calculating the risk of death.MethodsCanadian CF Registry data from 1982 to 2015 were used to develop a predictive risk model using threshold regression. A 2-year risk of death estimated conditional probability of surviving the second year given survival for the first year. UK CF Registry data from 2007 to 2013 were used to externally validate the model.ResultsThe combined effect of CF chronic health status and CF intermittent shock risk provided a simple clinical scoring tool for assessing 1-year and 2-year risk of death for an individual CF patient. At a threshold risk of death of ≥20%, the 1-year model had a sensitivity of 74% and specificity of 96%. The area under the receiver operating curve (AUC) for the 2-year mortality model was significantly greater than the AUC for a model that predicted survival based on forced expiratory volume in 1 s <30% predicted (AUC 0.95 versus 0.68 respectively, p<0.001). The Canadian-derived model validated well with the UK data and correctly identified 79% of deaths and 95% of survivors in a single year in the UK.ConclusionsThe prediction models provide an accurate risk of death over a 1- and 2-year time horizon. The models performed equally well when validated in an independent UK CF population.

Download Full-text

Can computed tomography-based radiomics potentially discriminate between anterior mediastinal cysts and type B1 and B2 thymomas?

BioMedical Engineering OnLine ◽

10.1186/s12938-020-00833-9 ◽

2020 ◽

Vol 19 (1) ◽

Author(s):

Lulu Liu ◽

Fangxiao Lu ◽

Peipei Pang ◽

Guoliang Shao

Keyword(s):

Computed Tomography ◽

Sensitivity And Specificity ◽

Texture Features ◽

Training Dataset ◽

Features Selection ◽

Clinical Factors ◽

Combined Model ◽

Test Dataset ◽

Enhanced Ct ◽

Mediastinal Cysts

Abstract Background Anterior mediastinal cysts (AMC) are often misdiagnosed as thymomas and undergo surgical resection, which caused unnecessary treatment and medical resource waste. The purpose of this study is to explore potential possibility of computed tomography (CT)-based radiomics for the diagnosis of AMC and type B1 and B2 thymomas. Methods A group of 188 patients with pathologically confirmed AMC (106 cases misdiagnosed as thymomas in CT) and thymomas (82 cases) and underwent routine chest CT from January 2010 to December 2018 were retrospectively analyzed. The lesions were manually delineated using ITK-SNAP software, and radiomics features were performed using the artificial intelligence kit (AK) software. A total of 180 tumour texture features were extracted from enhanced CT and unenhanced CT, respectively. The general test, correlation analysis, and LASSO were used to features selection and then the radiomics signature (radscore) was obtained. The combined model including radscore and independent clinical factors was developed. The model performances were evaluated on discrimination, calibration curve. Results Two radscore models were constructed from the unenhanced and enhanced phases based on the selected four and three features, respectively. The AUC, sensitivity, and specificity of the enhanced radscore model were 0.928, 89.3%, and 83.8% in the training dataset and 0.899, 84.6%, and 87.5% in the test dataset (higher than the unenhanced radscore model). The combined model of enhanced CT including radiomics features and independent clinical factors yielded an AUC, sensitivity and specificity of 0.941, 82.1%, and 94.6% in the training dataset and 0.938, 92.3%, and 87.5% in the test dataset (higher than the unenhanced combined model and enhanced radscore model). Conclusions The study suggested the possibility that the combined model in enhanced CT provided a potential tool to facilitate the differential diagnosis of AMC and type B1 and B2 thymomas.

Download Full-text

External validation of risk prediction models for incident colorectal cancer using UK Biobank

British Journal of Cancer ◽

10.1038/bjc.2017.463 ◽

2018 ◽

Vol 118 (5) ◽

pp. 750-759 ◽

Cited By ~ 15

Author(s):

J A Usher-Smith ◽

A Harshfield ◽

C L Saunders ◽

S J Sharp ◽

J Emery ◽

...

Keyword(s):

Colorectal Cancer ◽

Prediction Models ◽

Characteristic Curve ◽

External Validation ◽

Risk Scores ◽

Prior History ◽

Uk Biobank ◽

Risk Models ◽

Potential Health ◽

Men And Women

Abstract Background: This study aimed to compare and externally validate risk scores developed to predict incident colorectal cancer (CRC) that include variables routinely available or easily obtainable via self-completed questionnaire. Methods: External validation of fourteen risk models from a previous systematic review in 373 112 men and women within the UK Biobank cohort with 5-year follow-up, no prior history of CRC and data for incidence of CRC through linkage to national cancer registries. Results: There were 1719 (0.46%) cases of incident CRC. The performance of the risk models varied substantially. In men, the QCancer10 model and models by Tao, Driver and Ma all had an area under the receiver operating characteristic curve (AUC) between 0.67 and 0.70. Discrimination was lower in women: the QCancer10, Wells, Tao, Guesmi and Ma models were the best performing with AUCs between 0.63 and 0.66. Assessment of calibration was possible for six models in men and women. All would require country-specific recalibration if estimates of absolute risks were to be given to individuals. Conclusions: Several risk models based on easily obtainable data have relatively good discrimination in a UK population. Modelling studies are now required to estimate the potential health benefits and cost-effectiveness of implementing stratified risk-based CRC screening.

Download Full-text

DEVELOPING AND VALIDATING COVID-19 ADVERSE OUTCOME RISK PREDICTION MODELS FROM A BI-NATIONAL EUROPEAN COHORT OF 5594 PATIENTS

10.1101/2020.10.06.20207209 ◽

2020 ◽

Author(s):

Espen Jimenez-Solem ◽

Tonny S Petersen ◽

Casper Hansen ◽

Christian Hansen ◽

Christina Lioma ◽

...

Keyword(s):

Hospital Admission ◽

Organ Dysfunction ◽

Prediction Models ◽

Severe Disease ◽

External Validation ◽

Manuscript Preparation ◽

Design Data ◽

Prognostic Features ◽

Icu Admission ◽

Risk Of Death

ABSTRACTBackgroundPatients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that Machine Learning (ML) models could be used to predict risks at different stages of management (at diagnosis, hospital admission and ICU admission) and thereby provide insights into drivers and prognostic markers of disease progression and death.MethodsFrom a cohort of approx. 2.6 million citizens in the two regions of Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further analysis. A cohort of SARS- CoV-2 positive cases from the United Kingdom Biobank was used for external validation.FindingsThe ML models predicted the risk of death (Receiver Operation Characteristics – Area Under the Curve, ROC-AUC) of 0.904 at diagnosis, 0.818, at hospital admission and 0.723 at Intensive Care Unit (ICU) admission. Similar metrics were achieved for predicted risks of hospital and ICU admission and use of mechanical ventilation. We identified some common risk factors, including age, body mass index (BMI) and hypertension as driving factors, although the top risk features shifted towards markers of shock and organ dysfunction in ICU patients. The external validation indicated fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission.InterpretationML may be used to identify drivers of progression to more severe disease and for prognostication patients in patients with COVID-19. Prognostic features included age, BMI and hypertension, although markers of shock and organ dysfunction became more important in more severe cases.We provide access to an online risk calculator based on these findings.FundingThe study was funded by grants from the Novo Nordisk Foundation to MS (#NNF20SA0062879 and #NNF19OC0055183) and MN (#NNF20SA0062879). The foundation took no part in project design, data handling and manuscript preparation.

Download Full-text

Development of Sex-Stratified Prediction Models for Recurrent Venous Thromboembolism: A Danish Nationwide Cohort Study

Thrombosis and Haemostasis ◽

10.1055/s-0040-1708877 ◽

2020 ◽

Vol 120 (05) ◽

pp. 805-814 ◽

Cited By ~ 1

Author(s):

Ida Ehlers Albertsen ◽

Mette Søgaard ◽

Samuel Zachary Goldhaber ◽

Gregory Piazza ◽

Flemming Skjøth ◽

...

Keyword(s):

Venous Thromboembolism ◽

Treatment Duration ◽

Prediction Models ◽

Cox Regression ◽

External Validation ◽

Risk Scores ◽

Major Surgery ◽

Anticoagulant Treatment ◽

Cox Regression Analysis ◽

Recurrent Venous Thromboembolism

Abstract Objective To optimize decision making for anticoagulant treatment duration after incident venous thromboembolism, we derived and internally validated two clinically applicable sex-specific prediction models for venous thromboembolism recurrence, discarding the traditional categorization of provoked and unprovoked venous thromboembolism. Methods This study was based on data from Danish nationwide registries. We identified all routine care in- and outpatients with completed anticoagulant treatment for incident venous thromboembolism from 2012 through 2017. The outcome was recurrent venous thromboembolism within 2 years. Risk scores were derived using Cox regression analysis and a backward selection process on a set of 24 potential predictors. Performance was assessed through calibration and discrimination using bootstrap techniques to internally validate the scores. Results The study included 11,519 patients. Risk scores under the joint acronym AIM-SHA-RP were developed. Age, Incident pulmonary embolism, and recent Major surgery were predictors for both sexes; Statin treatment, Heart disease and Antiplatelet treatment were predictors specifically for men, while chronic Renal disease and recent Pneumonia or sepsis were predictors specifically for women. The risk scores were well calibrated and identified a low- (< 5%), intermediate- (5–10%), and high-risk (> 10%) group for both sexes. Generally, discriminative capacities, as measured by the c-statistic, were limited. Conclusion We developed two clinically applicable risk scores to estimate the risk of recurrent venous thromboembolism after completed anticoagulant treatment. The risk scores can potentially guide treatment duration of anticoagulation after incident venous thromboembolism but require further external validation before implemented in clinical practice.

Download Full-text

Predicting Disease in Transition Dairy Cattle Based on Behaviors Measured Before Calving

Animals ◽

10.3390/ani10060928 ◽

2020 ◽

Vol 10 (6) ◽

pp. 928

Author(s):

Mohammad W. Sahar ◽

Annabelle Beaver ◽

Marina A. G. von Keyserlingk ◽

Daniel M. Weary

Keyword(s):

Dairy Cattle ◽

Sensitivity And Specificity ◽

Roc Curve ◽

Predictive Value ◽

Predictive Ability ◽

Training Dataset ◽

Test Dataset ◽

Increased Risk ◽

High Prevalence ◽

Random Method

Dairy cattle are particularly susceptible to metritis, hyperketonemia (HYK), and mastitis in the weeks after calving. These high-prevalence transition diseases adversely affect animal welfare, milk production, and profitability. Our aim was to use prepartum behavior to predict which cows have an increased risk of developing these conditions after calving. The behavior of 213 multiparous and 105 primiparous Holsteins was recorded for approximately three weeks before calving by an electronic feeding system. Cows were also monitored for signs of metritis, HYK, and mastitis in the weeks after calving. The data were split using a stratified random method: we used 70% of our data (hereafter referred to as the “training” dataset) to develop the model and the remaining 30% of data (i.e., the “test” dataset) to assess the model’s predictive ability. Separate models were developed for primiparous and multiparous animals. The area under the receiver operating characteristic (ROC) curve using the test dataset for multiparous cows was 0.83, sensitivity and specificity were 73% and 80%, positive predictive value (PPV) was 73%, and negative predictive value (NPV) was 80%. The area under the ROC curve using the test dataset for primiparous cows was 0.86, sensitivity and specificity were 71% and 84%, PPV was 77%, and NPV was 80%. We conclude that prepartum behavior can be used to predict cows at risk of metritis, HYK, and mastitis after calving.

Download Full-text