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

2019 ◽  
Vol 54 (3) ◽  
pp. 1900224 ◽  
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.

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

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.

scholarly journals Development and validation of prediction models to estimate risk of primary total hip and knee replacements using data from the UK: two prospective open cohorts using the UK Clinical Practice Research Datalink

2018 ◽  
Vol 78 (1) ◽  
pp. 91-99 ◽  
Author(s):  
Dahai Yu ◽  
Kelvin P Jordan ◽  
Kym I E Snell ◽  
Richard D Riley ◽  
John Bedson ◽  
...  
Keyword(s):  
Clinical Practice ◽  
Large Scale ◽  
Prediction Models ◽  
Cox Proportional Hazards ◽  
Practice Research ◽  
Clinical Practice Research Datalink ◽  
Total Hip ◽  
Risk Of Death ◽  
Geographical Regions ◽  
The Uk

ObjectivesThe ability to efficiently and accurately predict future risk of primary total hip and knee replacement (THR/TKR) in earlier stages of osteoarthritis (OA) has potentially important applications. We aimed to develop and validate two models to estimate an individual’s risk of primary THR and TKR in patients newly presenting to primary care.MethodsWe identified two cohorts of patients aged ≥40 years newly consulting hip pain/OA and knee pain/OA in the Clinical Practice Research Datalink. Candidate predictors were identified by systematic review, novel hypothesis-free ‘Record-Wide Association Study’ with replication, and panel consensus. Cox proportional hazards models accounting for competing risk of death were applied to derive risk algorithms for THR and TKR. Internal–external cross-validation (IECV) was then applied over geographical regions to validate two models.Results45 predictors for THR and 53 for TKR were identified, reviewed and selected by the panel. 301 052 and 416 030 patients newly consulting between 1992 and 2015 were identified in the hip and knee cohorts, respectively (median follow-up 6 years). The resultant model C-statistics is 0.73 (0.72, 0.73) and 0.79 (0.78, 0.79) for THR (with 20 predictors) and TKR model (with 24 predictors), respectively. The IECV C-statistics ranged between 0.70–0.74 (THR model) and 0.76–0.82 (TKR model); the IECV calibration slope ranged between 0.93–1.07 (THR model) and 0.92–1.12 (TKR model).ConclusionsTwo prediction models with good discrimination and calibration that estimate individuals’ risk of THR and TKR have been developed and validated in large-scale, nationally representative data, and are readily automated in electronic patient records.

scholarly journals Comparison of prognostic models to predict the occurrence of colorectal cancer in asymptomatic individuals: a systematic literature review and external validation in the EPIC and UK Biobank prospective cohort studies

Gut ◽  
2018 ◽  
Vol 68 (4) ◽  
pp. 672-683 ◽  
Author(s):  
Todd Smith ◽  
David C Muller ◽  
Karel G M Moons ◽  
Amanda J Cross ◽  
Mattias Johansson ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Systematic Review ◽  
Prediction Models ◽  
Large Population ◽  
External Validation ◽  
Population Based ◽  
Prognostic Models ◽  
Uk Biobank ◽  
Asymptomatic Individuals ◽  
The Uk

ObjectiveTo systematically identify and validate published colorectal cancer risk prediction models that do not require invasive testing in two large population-based prospective cohorts.DesignModels were identified through an update of a published systematic review and validated in the European Prospective Investigation into Cancer and Nutrition (EPIC) and the UK Biobank. The performance of the models to predict the occurrence of colorectal cancer within 5 or 10 years after study enrolment was assessed by discrimination (C-statistic) and calibration (plots of observed vs predicted probability).ResultsThe systematic review and its update identified 16 models from 8 publications (8 colorectal, 5 colon and 3 rectal). The number of participants included in each model validation ranged from 41 587 to 396 515, and the number of cases ranged from 115 to 1781. Eligible and ineligible participants across the models were largely comparable. Calibration of the models, where assessable, was very good and further improved by recalibration. The C-statistics of the models were largely similar between validation cohorts with the highest values achieved being 0.70 (95% CI 0.68 to 0.72) in the UK Biobank and 0.71 (95% CI 0.67 to 0.74) in EPIC.ConclusionSeveral of these non-invasive models exhibited good calibration and discrimination within both external validation populations and are therefore potentially suitable candidates for the facilitation of risk stratification in population-based colorectal screening programmes. Future work should both evaluate this potential, through modelling and impact studies, and ascertain if further enhancement in their performance can be obtained.

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

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.

scholarly journals A Prediction Model for Severe AKI in Critically Ill Adults That Incorporates Clinical and Biomarker Data

2019 ◽  
Vol 14 (4) ◽  
pp. 506-514 ◽  
Author(s):  
Pavan Kumar Bhatraju ◽  
Leila R. Zelnick ◽  
Ronit Katz ◽  
Carmen Mikacenic ◽  
Susanna Kosamo ◽  
...  
Keyword(s):  
Critically Ill ◽  
Critically Ill Patients ◽  
Prediction Models ◽  
Risk Model ◽  
External Validation ◽  
Variable Model ◽  
Internal Validation ◽  
Predictive Values ◽  
Derivation Cohort ◽  
C Statistic

Background and objectivesCritically ill patients with worsening AKI are at high risk for poor outcomes. Predicting which patients will experience progression of AKI remains elusive. We sought to develop and validate a risk model for predicting severe AKI within 72 hours after intensive care unit admission.Design, setting, participants, & measurementsWe applied least absolute shrinkage and selection operator regression methodology to two prospectively enrolled, critically ill cohorts of patients who met criteria for the systemic inflammatory response syndrome, enrolled within 24–48 hours after hospital admission. The risk models were derived and internally validated in 1075 patients and externally validated in 262 patients. Demographics and laboratory and plasma biomarkers of inflammation or endothelial dysfunction were used in the prediction models. Severe AKI was defined as Kidney Disease Improving Global Outcomes (KDIGO) stage 2 or 3.ResultsSevere AKI developed in 62 (8%) patients in the derivation, 26 (8%) patients in the internal validation, and 15 (6%) patients in the external validation cohorts. In the derivation cohort, a three-variable model (age, cirrhosis, and soluble TNF receptor-1 concentrations [ACT]) had a c-statistic of 0.95 (95% confidence interval [95% CI], 0.91 to 0.97). The ACT model performed well in the internal (c-statistic, 0.90; 95% CI, 0.82 to 0.96) and external (c-statistic, 0.93; 95% CI, 0.89 to 0.97) validation cohorts. The ACT model had moderate positive predictive values (0.50–0.95) and high negative predictive values (0.94–0.95) for severe AKI in all three cohorts.ConclusionsACT is a simple, robust model that could be applied to improve risk prognostication and better target clinical trial enrollment in critically ill patients with AKI.

scholarly journals Kidney Failure Prediction Models: A Comprehensive External Validation Study in Patients with Advanced CKD

2021 ◽  
pp. ASN.2020071077
Author(s):  
Chava L. Ramspek ◽  
Marie Evans ◽  
Christoph Wanner ◽  
Christiane Drechsler ◽  
Nicholas C. Chesnaye ◽  
...  
Keyword(s):  
Kidney Failure ◽  
Prediction Models ◽  
External Validation ◽  
Model Performance ◽  
Time Frame ◽  
Competing Risk ◽  
Multicenter Cohort Study ◽  
Risk Equation ◽  
Risk Of Death ◽  
Competing Events

BackgroundVarious prediction models have been developed to predict the risk of kidney failure in patients with CKD. However, guideline-recommended models have yet to be compared head to head, their validation in patients with advanced CKD is lacking, and most do not account for competing risks.MethodsTo externally validate 11 existing models of kidney failure, taking the competing risk of death into account, we included patients with advanced CKD from two large cohorts: the European Quality Study (EQUAL), an ongoing European prospective, multicenter cohort study of older patients with advanced CKD, and the Swedish Renal Registry (SRR), an ongoing registry of nephrology-referred patients with CKD in Sweden. The outcome of the models was kidney failure (defined as RRT-treated ESKD). We assessed model performance with discrimination and calibration.ResultsThe study included 1580 patients from EQUAL and 13,489 patients from SRR. The average c statistic over the 11 validated models was 0.74 in EQUAL and 0.80 in SRR, compared with 0.89 in previous validations. Most models with longer prediction horizons overestimated the risk of kidney failure considerably. The 5-year Kidney Failure Risk Equation (KFRE) overpredicted risk by 10%–18%. The four- and eight-variable 2-year KFRE and the 4-year Grams model showed excellent calibration and good discrimination in both cohorts.ConclusionsSome existing models can accurately predict kidney failure in patients with advanced CKD. KFRE performed well for a shorter time frame (2 years), despite not accounting for competing events. Models predicting over a longer time frame (5 years) overestimated risk because of the competing risk of death. The Grams model, which accounts for the latter, is suitable for longer-term predictions (4 years).

scholarly journals A 5-mRNA-Based Prognostic Signature of Survival in Lung Adenocarcinoma

2021 ◽  
Author(s):  
qianlin xia ◽  
Weimo Yu ◽  
Qiuyue Li ◽  
Jin Wang ◽  
Yuzhen Du
Keyword(s):  
Regression Analysis ◽  
Lung Adenocarcinoma ◽  
Prediction Models ◽  
Risk Model ◽  
Cox Regression ◽  
External Validation ◽  
Assessment Tools ◽  
Normal Lung ◽  
Survival Prognosis ◽  
Cox Regression Analysis

Abstract Background: Lung adenocarcinoma (LUAD) is the most common non-small cell lung cancer, with an increasing incidence and poor prognosis. To evaluate the prognosis of LUAD patients and optimize treatment, effective clinical research prediction models are urgently needed. Methods : In this study, we thoroughly mined LUAD genomic data from GEO (GSE43458, GSE32863, and GSE27262) and TCGA datasets, including 698 LUAD and 172 healthy (or adjacent normal) lung tissue samples. Single-factor Cox and LASSO regression analyses were used to screen DEGs related to patient prognosis, and multivariate Cox regression analysis was applied to establish the risk score equation and construct the survival prognosis model. Receiver operating characteristic (ROC) curve and Kaplan-Meier (KM) survival analyses with clinically independent prognostic parameters were performed to verify the predictive power of the model and further establish a prognostic nomogram. Results: A total of 380 DEGs were identified in LUAD tissues through GEO and TCGA datasets, and 5 DEGs (TCN1, CENPF, MAOB, CRTAC1 and PLEK2) were screened out by multivariate Cox regression analysis, indicating that the prognostic risk model could be used as an independent prognostic factor (HR = 1.520, P < 0.001). Internal and external validation of the model confirmed that the prediction model had good sensitivity and specificity (AUC = 0.754, 0.737). Combining genetic models and clinical prognostic factors, nomograms can also predict overall survival more effectively. Conclusion: A 5-mRNA-based model was constructed to predict the prognosis of lung adenocarcinoma, which may provide clinicians with reliable prognostic assessment tools and help clinical treatment decisions.

External Validation of Risk Prediction Models to Improve Selection of Patients for Carotid Endarterectomy

Stroke ◽  
2021 ◽  
Author(s):  
Michiel H.F. Poorthuis ◽  
Reinier A.R. Herings ◽  
Kirsten Dansey ◽  
Johanna A.A. Damen ◽  
Jacoba P. Greving ◽  
...  
Keyword(s):  
Carotid Endarterectomy ◽  
Prediction Models ◽  
Risk Model ◽  
External Validation ◽  
The United States ◽  
Net Benefit ◽  
Improvement Program ◽  
C Statistic ◽  
Asymptomatic Patients ◽  
Number Of Patients

Background and Purpose: The net benefit of carotid endarterectomy (CEA) is determined partly by the risk of procedural stroke or death. Current guidelines recommend CEA if 30-day risks are <6% for symptomatic stenosis and <3% for asymptomatic stenosis. We aimed to identify prediction models for procedural stroke or death after CEA and to externally validate these models in a large registry of patients from the United States. Methods: We conducted a systematic search in MEDLINE and EMBASE for prediction models of procedural outcomes after CEA. We validated these models with data from patients who underwent CEA in the American College of Surgeons National Surgical Quality Improvement Program (2011–2017). We assessed discrimination using C statistics and calibration graphically. We determined the number of patients with predicted risks that exceeded recommended thresholds of procedural risks to perform CEA. Results: After screening 788 reports, 15 studies describing 17 prediction models were included. Nine were developed in populations including both asymptomatic and symptomatic patients, 2 in symptomatic and 5 in asymptomatic populations. In the external validation cohort of 26 293 patients who underwent CEA, 702 (2.7%) developed a stroke or died within 30-days. C statistics varied between 0.52 and 0.64 using all patients, between 0.51 and 0.59 using symptomatic patients, and between 0.49 to 0.58 using asymptomatic patients. The Ontario Carotid Endarterectomy Registry model that included symptomatic status, diabetes, heart failure, and contralateral occlusion as predictors, had C statistic of 0.64 and the best concordance between predicted and observed risks. This model identified 4.5% of symptomatic and 2.1% of asymptomatic patients with procedural risks that exceeded recommended thresholds. Conclusions: Of the 17 externally validated prediction models, the Ontario Carotid Endarterectomy Registry risk model had most reliable predictions of procedural stroke or death after CEA and can inform patients about procedural hazards and help focus CEA toward patients who would benefit most from it.

scholarly journals Independent, external validation of clinical prediction rules for the identification of extended-spectrum β-lactamase-producing Enterobacterales, University Hospital Basel, Switzerland, January 2010 to December 2016

2020 ◽  
Vol 25 (26) ◽  
Author(s):  
Isabelle Vock ◽  
Lisandra Aguilar-Bultet ◽  
Adrian Egli ◽  
Pranita D Tamma ◽  
Sarah Tschudin-Sutter
Keyword(s):  
Prediction Models ◽  
Bacterial Species ◽  
External Validation ◽  
High Specificity ◽  
University Hospital ◽  
Receiver Operating Curve ◽  
Retrospective Case ◽  
Predictive Values ◽  
Extended Spectrum ◽  
Low Sensitivity

Background Algorithms for predicting infection with extended-spectrum β-lactamase-producing Enterobacterales (ESBL-PE) on hospital admission or in patients with bacteraemia have been proposed, aiming to optimise empiric treatment decisions. Aim We sought to confirm external validity and transferability of two published prediction models as well as their integral components. Methods We performed a retrospective case–control study at University Hospital Basel, Switzerland. Consecutive patients with ESBL-producing Escherichia coli or Klebsiella pneumoniae isolated from blood samples between 1 January 2010 and 31 December 2016 were included. For each case, three non-ESBL-producing controls matching for date of detection and bacterial species were identified. The main outcome measure was the ability to accurately predict infection with ESBL-PE by measures of discrimination and calibration. Results Overall, 376 patients (94 patients, 282 controls) were analysed. Performance measures for prediction of ESBL-PE infection of both prediction models indicate adequate measures of calibration, but poor discrimination (area under receiver-operating curve: 0.627 and 0.651). History of ESBL-PE colonisation or infection was the single most predictive independent risk factor for ESBL-PE infection with high specificity (97%), low sensitivity (34%) and balanced positive and negative predictive values (80% and 82%). Conclusions Applying published prediction models to institutions these were not derived from, may result in substantial misclassification of patients considered as being at risk, potentially leading to wrong allocation of antibiotic treatment, negatively affecting patient outcomes and overall resistance rates in the long term. Future prediction models need to address differences in local epidemiology by allowing for customisation according to different settings.

Sign in / Sign up

Export Citation Format

Share Document