scholarly journals Learning Data-Driven Patient Risk Stratification Models for Clostridium difficile

2014 ◽  
Vol 1 (2) ◽  
Author(s):  
Jenna Wiens ◽  
Wayne N. Campbell ◽  
Ella S. Franklin ◽  
John V. Guttag ◽  
Eric Horvitz
Keyword(s):  
Risk Factors ◽  
Clostridium Difficile ◽  
Risk Stratification ◽  
Characteristic Curve ◽  
Data Driven ◽  
First Year ◽  
High Risk Population ◽  
Urban Hospital ◽  
Small Set ◽  
Validation Set

Abstract Background.  Although many risk factors are well known, Clostridium difficile infection (CDI) continues to be a significant problem throughout the world. The purpose of this study was to develop and validate a data-driven, hospital-specific risk stratification procedure for estimating the probability that an inpatient will test positive for C difficile. Methods.  We consider electronic medical record (EMR) data from patients admitted for ≥24 hours to a large urban hospital in the U.S. between April 2011 and April 2013. Predictive models were constructed using L2-regularized logistic regression and data from the first year. The number of observational variables considered varied from a small set of well known risk factors readily available to a physician to over 10 000 variables automatically extracted from the EMR. Each model was evaluated on holdout admission data from the following year. A total of 34 846 admissions with 372 cases of CDI was used to train the model. Results.  Applied to the separate validation set of 34 722 admissions with 355 cases of CDI, the model that made use of the additional EMR data yielded an area under the receiver operating characteristic curve (AUROC) of 0.81 (95% confidence interval [CI], .79–.83), and it significantly outperformed the model that considered only the small set of known clinical risk factors, AUROC of 0.71 (95% CI, .69–.75). Conclusions.  Automated risk stratification of patients based on the contents of their EMRs can be used to accurately ide.jpegy a high-risk population of patients. The proposed method holds promise for enabling the selective allocation of interventions aimed at reducing the rate of CDI.

scholarly journals A data-driven approach to predict daily risk of Clostridium difficile infection at two large academic health centers

2017 ◽  
Vol 4 (suppl_1) ◽  
pp. S403-S404
Author(s):  
Maggie Makar ◽  
Jeeheh Oh ◽  
Christopher Fusco ◽  
Joseph Marchesani ◽  
Robert McCaffrey ◽  
...  
Keyword(s):  
Risk Factors ◽  
Clostridium Difficile ◽  
Risk Stratification ◽  
Clostridium Difficile Infection ◽  
Prediction Models ◽  
The United States ◽  
Data Driven ◽  
Discriminative Performance ◽  
Adult Inpatient ◽  
Data Driven Approach

Abstract Background An estimated 293,300 healthcare-associated cases of Clostridium difficile infection (CDI) occur annually in the United States. Prior research on risk-prediction models for CDI have focused on a small number of risk factors with the goal of developing a model that works well across hospitals. We hypothesize that risk factors are, in part, hospital-specific. We applied a generalizable machine learning approach to discovering, or “learning”, hospital-specific risk-stratification models using electronic health record (EHR) data collected during the course of patient care from the Massachusetts General Hospital (MGH) and the University of Michigan Health System (UM). Methods We utilized EHR data from 115,958 adult inpatient admissions from 2012–2014 (MGH) and 258,050 adult inpatient admissions from 2010–2016 (UM) (Fig 1). We extracted patient demographics, admission details, patient history, and daily hospitalization details, resulting in 2,964 and 4,739 features in the MGH and UM models, respectively. We used L2 regularized logistic regression to learn the models and measured the discriminative performance of the models on a year of held-out data from each hospital. Results The MGH and UM models achieved AUROCs of 0.74 (CI: 0.73–0.75) and 0.77 (CI: 0.75–0.80), respectively. The relative importance of risk factors varied significantly across hospitals. In particular, in-hospital locations appeared in the set of top risk factors at one hospital and in the set of protective factors at the other. On average, both models were able to predict CDI five days in advance of clinical diagnosis (Fig 2). Conclusion We used EHR data to generate a daily estimate of the risk of CDI for each inpatient hospitalization. We applied a generalizable data-driven approach to existing data from two large institutions with different patient populations and different data formats and content. In contrast to approaches that focus on learning models that apply generally across hospitals, our proposed approach yields risk stratification models tailored to an institution’s EHR system and patient population. In turn, these hospital-specific models could allow for earlier and more accurate identification of high-risk patients. Disclosures All authors: No reported disclosures.

Development and Validation of a Nomogram for Predicting Bladder Calculi Risk in Patients With Benign Prostatic Hyperplasia

2021 ◽  
Author(s):  
Euxu Xie ◽  
Xuelian Gu ◽  
Chen Ma ◽  
Li Guo ◽  
Man Li ◽  
...  
Keyword(s):  
Risk Factors ◽  
Benign Prostatic Hyperplasia ◽  
Characteristic Curve ◽  
Prostatic Hyperplasia ◽  
Calibration Plot ◽  
Lasso Regression ◽  
Net Benefit ◽  
Bladder Calculi ◽  
Validation Set ◽  
Selection Operator

Abstract Objective To develop and validate a nomogram for predicting bladder calculi risk in patients with benign prostatic hyperplasia (BPH).Methods A total of 368 patients who underwent transurethral resection of the prostate (TURP) and had histologically proven BPH from January 2018 to January 2021 were retrospectively collected. Eligible patients were randomly assigned to the training and validation datasets. Least absolute shrinkage and selection operator (LASSO) regression was used to select the optimal risk factors. A prediction model was established based on the selected characteristics. The performance of the nomogram was assessed by calibration plots and the area under the receiver operating characteristic curve (AUROC). Furthermore, decision curve analysis (DCA) was used to determine the net benefit rate of of the nomogram. Results Among 368 patients who met the inclusion criteria, older age, a history of diabetes and hyperuricemia, longer intravesical prostatic protrusion (IPP)and larger prostatic urethral angulation (PUA) were independent risk factors for bladder calculi in patients with BPH. These factors were used to develop a nomogram, which had a good identification ability in predicting the risk of bladder calculi in patients, with AUROCs of 0.911 (95% CI: 0.876–0.945) in the training set and 0.884 (95% CI: 0.820–0.948) in the validation set. The calibration plot showed that the model had good calibration. Moreover, DCA indicated that the model had a goodclinical benefit. Conclusion We developed and internally validated the first nomogram to date to help physicians assess the risk of bladder calculi in patients with BPH, which may help physicians improve individual interventions and make better clinical decisions.

scholarly journals A model for predicting carotid instability plaque in high risk group of stroke individuals

2019 ◽  
Author(s):  
Junxiong Yin ◽  
Chuanyong Yu ◽  
Hongxing Liu ◽  
Mingyang Du ◽  
Feng Sun ◽  
...  
Keyword(s):  
Risk Factors ◽  
High Risk ◽  
Predictive Model ◽  
Doppler Ultrasound ◽  
Scoring System ◽  
Risk Group ◽  
High Risk Group ◽  
High Risk Population ◽  
Auc Value ◽  
Validation Set

Abstract Objective: To establish a predictive model of carotid vulnerable plaque through systematic screening of high-risk population for stroke.Patients and methods: All community residents who participated in the screening of stroke high-risk population by the China National Stroke Screening and Prevention Project (CNSSPP). A total of 19 risk factors were analyzed. Individuals were randomly divided into Derivation Set group and Validation Set group. According to carotid ultrasonography, the derivation set group patients were divided into instability plaque group and non-instability plaque group. Univariate and multivariable logistic regression were taken for risk factors. A predictive model scoring system were established by the coefficient. The AUC value of both derivation and validation set group were used to verify the effectiveness of the model.Results: A total of 2841 high-risk stroke patients were enrolled in this study, 266 (9.4%) patients were found instability plaque. According to the results of Doppler ultrasound, Derivation Set group were divided into instability plaque group (174 cases) and non-instability plaque group (1720 cases). The independent risk factors for carotid instability plaque were: male (OR 1.966, 95%CI 1.406-2.749)，older age (50-59, OR 6.012, 95%CI 1.410-25.629; 60-69, OR 13.915, 95%CI 3.381-57.267;≥70, OR 31.267, 95%CI 7.472-130.83) , married(OR 1.780, 95%CI 1.186-2.672)，LDL-c(OR 2.015, 95%CI 1.443-2.814), and HDL-C(OR 2.130, 95%CI 1.360-3.338). A predictive scoring system was created, range 0-10. The cut-off value of prediction model score is 6.5. The AUC value of derivation and validation set group were 0.738 and 0.737.Conclusion：For a high risk group of stroke individual, We provide a model that could distinguishing those who have a high probability of having carotid instability plaque. When resident’s predictive model score exceeds 6.5, the incidence of carotid instability plaque is high, carotid artery Doppler ultrasound would be checked immediately. This model can be helpful in the primary prevention of stroke.

scholarly journals Development and validation of an International Prognostic Score of thrombosis in World Health Organization–essential thrombocythemia (IPSET-thrombosis)

Blood ◽  
2012 ◽  
Vol 120 (26) ◽  
pp. 5128-5133 ◽  
Author(s):  
Tiziano Barbui ◽  
Guido Finazzi ◽  
Alessandra Carobbio ◽  
Juergen Thiele ◽  
Francesco Passamonti ◽  
...  
Keyword(s):  
Risk Factors ◽  
Cardiovascular Risk ◽  
High Risk ◽  
Risk Stratification ◽  
Prognostic Model ◽  
Low Risk ◽  
World Health ◽  
Intermediate Risk ◽  
Validation Set ◽  
Health Organization

Abstract Accurate prediction of thrombosis in essential thrombocythemia (ET) provides the platform for prospective studies exploring preventive measures. Current risk stratification for thrombosis in ET is 2-tiered and considers low- and high-risk categories based on the respective absence or presence of either age > 60 years or history of thrombosis. In an international study of 891 patients with World Health Organization (WHO)–defined ET, we identified additional independent risk factors including cardiovascular risk factors and JAK2V617F. Accordingly, we assigned risk scores based on multivariable analysis–derived hazard ratios (HRs) to age > 60 years (HR = 1.5; 1 point), thrombosis history (HR = 1.9; 2 points), cardiovascular risk factors (HR = 1.6; 1 point), and JAK2V617F (HR = 2.0; 2 points) and subsequently devised a 3-tiered prognostic model (low-risk = < 2 points; intermediate-risk = 2 points; and high-risk = > 2 points) using a training set of 535 patients and validated the results in the remaining cohort (n = 356; internal validation set) and in an external validation set (n = 329). Considering all 3 cohorts (n = 1220), the 3-tiered new prognostic model (low-risk n = 474 vs intermediate-risk n = 471 vs high-risk n = 275), with a respective thrombosis risk of 1.03% of patients/y versus 2.35% of patients/y versus 3.56% of patients/y, outperformed the 2-tiered (low-risk 0.95% of patients/y vs high-risk 2.86% of patients/y) conventional risk stratification in predicting future vascular events.

Brachial-ankle pulse wave velocity and SCORE in primary hypertension patients

2019 ◽  
pp. 41-47
Author(s):  
Thi Van Trang Luong ◽  
Anh Tien Hoang
Keyword(s):  
Risk Factors ◽  
Cardiovascular Risk ◽  
Risk Stratification ◽  
Risk Score ◽  
Characteristic Curve ◽  
Primary Hypertension ◽  
Risk Scores ◽  
Cardiovascular Risks ◽  
Atherosclerotic Risk Factors ◽  
Score Risk

Background: Hypertension is still an important health problem that cause many serious cardiovascular risks. So screening these risks is extremely essential for primary hypertension patients. Aim: This study was conducted to evaluate baPWV and SCORE risk score in primary hypertension patients, then determine the association between baPWV and SCORE as well as conventional atherosclerotic risk factors in screening cardiovascular risk in hypertension patients. Methods: baPWV and SCORE were measured in a descriptive cross-sectional study in total of 107 primary hypertension patients (43 males and 64 females, age 30 to 74 years). Results: Analysis demonstrated that baPWV was associated with both Framingham and SCORE risk scores, independently from conventional atherosclerotic risk factors. The receiver-operator characteristic curve demonstrated that a baPWV of 25.06 m/s is useful for discriminating primary hypertension patients with high risk stratification by SCORE. Logistic regression analysis demonstrated that a baPWV>25,06 m/s is an independent variable for the risk stratification by SCORE. Conclusion: baPWV that was significantly correlated with SCORE, has potential as a marker of evaluating cardiovascular risk in primary hypertension patients. Key words: Hypertension, primary hypertension, baPWV and SCORE risk score

scholarly journals A model for predicting carotid instability plaque in high risk group of stroke individuals

2019 ◽  
Author(s):  
Junxiong Yin ◽  
Chuanyong Yu ◽  
Hongxing Liu ◽  
Mingyang Du ◽  
Feng Sun ◽  
...  
Keyword(s):  
Risk Factors ◽  
High Risk ◽  
Predictive Model ◽  
Doppler Ultrasound ◽  
Scoring System ◽  
Risk Group ◽  
High Risk Group ◽  
High Risk Population ◽  
Auc Value ◽  
Validation Set

Abstract Background: Atherosclerosis is the main risk factor of cerebral vascular disease. Previous studies published several predictive models of asymptomatic carotid stenosis , yet they were ignored that people with lower levels of stenosis (＜50% or carotid instability plaque) who may benefit from early risk reducing medications, such as statins, antiplatelet drugs. Thus, this study determined to establish a predictive model of carotid vulnerable plaque through systematic screening of high-risk population for stroke. Methods: All community residents who participated in the screening of stroke high-risk population by the China National Stroke Screening and Prevention Project(CNSSPP). A total of 19 risk factors were analyzed. Individuals were randomly divided into Derivation-Set group and Validation-Set group. According to carotid ultrasonography, the derivation set group patients were divided into instability plaque group and non-instability plaque group. Univariate and multivariable logistic regression were taken for risk factors. A predictive model scoring system were established by the coefficient. The Area under curve (AUC) value of both derivation and validation set group were used to verify the effectiveness of the model. Results: A total of 2841 high risk stroke patients were enrolled in this study, 266(9.4%) patients were found instability plaque. According to the results of Doppler ultrasound, Derivation Set group were divided into instability plaque group (174 cases) and non-instability plaque group (1720 cases). The independent risk factors for carotid instability plaque were: male (OR 1.966, 95%CI 1.406-2.749)，older age (50-59, OR 6.012, 95%CI 1.410-25.629; 60-69, OR 13.915, 95%CI 3.381-57.267;≥70, OR 31.267, 95%CI 7.472-130.83) , married(OR 1.780, 95%CI 1.186-2.672)，LDL-c(OR 2.015, 95%CI 1.443-2.814), and HDL-C(OR 2.130, 95%CI 1.360-3.338). A predictive scoring system was created, range 0-10. The cut-off value of prediction model score is 6.5. The AUC value of derivation and validation set group were 0.738 and 0.737. Conclusions:For a high risk group of stroke individual, We provide a model that could distinguishing those who have a high probability of having carotid instability plaque. When resident’s predictive model score exceeds 6.5, the incidence of carotid instability plaque is high, carotid artery Doppler ultrasound would be checked immediately. This model can be helpful in the primary prevention of stroke.

Leukocytosis and Risk Stratification Assessment in Essential Thrombocythemia

2008 ◽  
Vol 26 (16) ◽  
pp. 2732-2736 ◽  
Author(s):  
Alessandra Carobbio ◽  
Elisabetta Antonioli ◽  
Paola Guglielmelli ◽  
Alessandro M. Vannucchi ◽  
Federica Delaini ◽  
...  
Keyword(s):  
Risk Factors ◽  
High Risk ◽  
Risk Stratification ◽  
Essential Thrombocythemia ◽  
Characteristic Curve ◽  
Risk Category ◽  
Vascular Events ◽  
Thrombotic Risk ◽  
C Statistic ◽  
Asymptomatic Patients

Purpose Established risk factors for thrombosis in essential thrombocythemia (ET) include age and previous vascular events. We aimed to refine this risk stratification by adding baseline leukocytosis. Patients and Methods We enrolled 657 patients with ET followed for a median of 4.5 years who developed 72 major thrombosis. Cox proportional hazard model was performed to analyze the thrombotic risk and to discriminate ET patients with or without thrombosis, multivariable C statistic index was used. We searched for leukocytes cutoff with the best sensitivity and specificity by a receiver operating characteristic curve. Results Results confirmed that age and prior events are independent risk factors for thrombosis and showed a gradient between baseline leukocytosis and thrombosis. On the contrary, no significant association was found either for JAK2V617F allele burden and for other laboratory parameters, including platelet number. In the model with conventional risk factors alone, C statistic ratio for total thrombosis was 0.63 and when leukocytosis was added, the change was small (C = 0.67). In contrast, in younger and asymptomatic patients (low-risk category), C statistic value indicated an high risk for thrombosis in patients with leukocytosis, similar to that calculated in conventionally defined high-risk group (C = 0.65). The best leukocyte cutoff values for predicting the events was found to be 9.4 (× 109/L). Conclusion We suggest to include baseline leukocytosis in the risk stratification of ET patients enrolled in clinical trials.

Sign in / Sign up

Export Citation Format

Share Document