Dataset Information

Development and validation of a multivariate predictive model for rheumatoid arthritis mortality using a machine learning approach.

ABSTRACT: We developed and independently validated a rheumatoid arthritis (RA) mortality prediction model using the machine learning method Random Survival Forests (RSF). Two independent cohorts from Madrid (Spain) were used: the Hospital Clínico San Carlos RA Cohort (HCSC-RAC; training; 1,461 patients), and the Hospital Universitario de La Princesa Early Arthritis Register Longitudinal study (PEARL; validation; 280 patients). Demographic and clinical-related variables collected during the first two years after disease diagnosis were used. 148 and 21 patients from HCSC-RAC and PEARL died during a median follow-up time of 4.3 and 5.0 years, respectively. Age at diagnosis, median erythrocyte sedimentation rate, and number of hospital admissions showed the higher predictive capacity. Prediction errors in the training and validation cohorts were 0.187 and 0.233, respectively. A survival tree identified five mortality risk groups using the predicted ensemble mortality. After 1 and 7 years of follow-up, time-dependent specificity and sensitivity in the validation cohort were 0.79-0.80 and 0.43-0.48, respectively, using the cut-off value dividing the two lower risk categories. Calibration curves showed overestimation of the mortality risk in the validation cohort. In conclusion, we were able to develop a clinical prediction model for RA mortality using RSF, providing evidence for further work on external validation.

SUBMITTER: Lezcano-Valverde JM

PROVIDER: S-EPMC5579234 | biostudies-literature | 2017 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and validation of a multivariate predictive model for rheumatoid arthritis mortality using a machine learning approach.

Lezcano-Valverde José M JM Salazar Fernando F León Leticia L Toledano Esther E Jover Juan A JA Fernandez-Gutierrez Benjamín B Soudah Eduardo E González-Álvaro Isidoro I Abasolo Lydia L Rodriguez-Rodriguez Luis L

Scientific reports 20170831 1

We developed and independently validated a rheumatoid arthritis (RA) mortality prediction model using the machine learning method Random Survival Forests (RSF). Two independent cohorts from Madrid (Spain) were used: the Hospital Clínico San Carlos RA Cohort (HCSC-RAC; training; 1,461 patients), and the Hospital Universitario de La Princesa Early Arthritis Register Longitudinal study (PEARL; validation; 280 patients). Demographic and clinical-related variables collected during the first two years ...[more]

PMID: 28860558

Similar Datasets

Project description:BackgroundFinancial codes are often used to extract diagnoses from electronic health records. This approach is prone to false positives. Alternatively, queries are constructed, but these are highly center and language specific. A tantalizing alternative is the automatic identification of patients by employing machine learning on format-free text entries.ObjectiveThe aim of this study was to develop an easily implementable workflow that builds a machine learning algorithm capable of accurately identifying patients with rheumatoid arthritis from format-free text fields in electronic health records.MethodsTwo electronic health record data sets were employed: Leiden (n=3000) and Erlangen (n=4771). Using a portion of the Leiden data (n=2000), we compared 6 different machine learning methods and a naïve word-matching algorithm using 10-fold cross-validation. Performances were compared using the area under the receiver operating characteristic curve (AUROC) and the area under the precision recall curve (AUPRC), and F1 score was used as the primary criterion for selecting the best method to build a classifying algorithm. We selected the optimal threshold of positive predictive value for case identification based on the output of the best method in the training data. This validation workflow was subsequently applied to a portion of the Erlangen data (n=4293). For testing, the best performing methods were applied to remaining data (Leiden n=1000; Erlangen n=478) for an unbiased evaluation.ResultsFor the Leiden data set, the word-matching algorithm demonstrated mixed performance (AUROC 0.90; AUPRC 0.33; F1 score 0.55), and 4 methods significantly outperformed word-matching, with support vector machines performing best (AUROC 0.98; AUPRC 0.88; F1 score 0.83). Applying this support vector machine classifier to the test data resulted in a similarly high performance (F1 score 0.81; positive predictive value [PPV] 0.94), and with this method, we could identify 2873 patients with rheumatoid arthritis in less than 7 seconds out of the complete collection of 23,300 patients in the Leiden electronic health record system. For the Erlangen data set, gradient boosting performed best (AUROC 0.94; AUPRC 0.85; F1 score 0.82) in the training set, and applied to the test data, resulted once again in good results (F1 score 0.67; PPV 0.97).ConclusionsWe demonstrate that machine learning methods can extract the records of patients with rheumatoid arthritis from electronic health record data with high precision, allowing research on very large populations for limited costs. Our approach is language and center independent and could be applied to any type of diagnosis. We have developed our pipeline into a universally applicable and easy-to-implement workflow to equip centers with their own high-performing algorithm. This allows the creation of observational studies of unprecedented size covering different countries for low cost from already available data in electronic health record systems.

Project description:BackgroundSarcopenia is linked to an unfavorable prognosis in individuals with rheumatoid arthritis (RA). Early identification and treatment of sarcopenia are clinically significant. This study aimed to create and validate a nomogram for predicting sarcopenia risk in RA patients, providing clinicians with a reliable tool for the early identification of high-risk patients.MethodsPatients with RA diagnosed between August 2022 and January 2024 were included and randomized into training and validation sets in a 7:3 ratio. Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis and multifactorial logistic regression analysis were used to screen the risk variables for RA-associated muscle loss and to create an RA sarcopenia risk score. The predictive performance and clinical utility of the risk model were evaluated by plotting the receiver operating characteristic curve and calculating the area under the curve (AUC), along with the calibration curve and clinical decision curve (DCA).ResultsA total of 480 patients with RA were included in the study (90% female, with the largest number in the 45-59 age group, about 50%). In this study, four variables (body mass index, disease duration, hemoglobin, and grip strength) were included to construct a nomogram for predicting RA sarcopenia. The training and validation set AUCs were 0.915 (95% CI: 0.8795-0.9498) and 0.907 (95% CI: 0.8552-0.9597), respectively, proving that the predictive model was well discriminated. The calibration curve showed that the predicted values of the model were basically in line with the actual values, demonstrating good calibration. The DCA indicated that almost the entire range of patients with RA can benefit from this novel prediction model, suggesting good clinical utility.ConclusionThis study developed and validated a nomogram prediction model to predict the risk of sarcopenia in RA patients. The model can assist clinicians in enhancing their ability to screen for RA sarcopenia, assess patient prognosis, make early decisions, and improve the quality of life for RA patients.

Project description:Clinical predictors of mortality in systemic sclerosis (SSc) are diversely reported due to different healthcare conditions and populations. A simple predictive model for early mortality among patients with SSc is needed as a precise referral tool for general practitioners. We aimed to develop and validate a simple predictive model for predicting mortality among patients with SSc. Prognostic research with a historical cohort study design was conducted between January 1, 2013, and December 31, 2020, in adult SSc patients attending the Scleroderma Clinic at a university hospital in Thailand. The data were extracted from the Scleroderma Registry Database. Early mortality was defined as dying within 5 years after the onset of SSc. Deep learning algorithms with Adam optimizer and different machine learning algorithms (including Logistic Regression, Decision tree, AdaBoost, Random Forest, Gradient Boosting, XGBoost, and Autoencoder neural network) were used to classify SSc mortality. In addition, the model's performance was evaluated using the area under the receiver operating characteristic curve (auROC) and its 95% confidence interval (CI) and values in the confusion matrix. The predictive model development included 528 SSc patients, 343 (65.0%) were females and 374 (70.8%) had dcSSc. Ninety-five died within 5 years after disease onset. The final 2 models with the highest predictive performance comprise the modified Rodnan skin score (mRSS) and the WHO-FC ≥ II for Model 1 and mRSS and WHO-FC ≥ III for Model 2. Model 1 provided the highest predictive performance, followed by Model 2. After internal validation, the accuracy and auROC were good. The specificity was high in Models 1 and 2 (84.8%, 89.8%, and 98.8% in model 1 vs. 84.8%, 85.6%, and 98.8% in model 2). This simplified machine learning model for predicting early mortality among patients with SSc could guide early referrals to specialists and help rheumatologists with close monitoring and management planning. External validation across multi-SSc clinics should be considered for further study.

Project description:BackgroundEchocardiography (echo) based machine learning (ML) models may be useful in identifying patients at high-risk of all-cause mortality.MethodsWe developed ML models (ResNet deep learning using echo videos and CatBoost gradient boosting using echo measurements) to predict 1-year, 3-year, and 5-year mortality. Models were trained on the Mackay dataset, Taiwan (6083 echos, 3626 patients) and validated in the Alberta HEART dataset, Canada (997 echos, 595 patients). We examined the performance of the models overall, and in subgroups (healthy controls, at risk of heart failure (HF), HF with reduced ejection fraction (HFrEF) and HF with preserved ejection fraction (HFpEF)). We compared the models' performance to the MAGGIC risk score, and examined the correlation between the models' predicted probability of death and baseline quality of life as measured by the Kansas City Cardiomyopathy Questionnaire (KCCQ).FindingsMortality rates at 1-, 3- and 5-years were 14.9%, 28.6%, and 42.5% in the Mackay cohort, and 3.0%, 10.3%, and 18.7%, in the Alberta HEART cohort. The ResNet and CatBoost models achieved area under the receiver-operating curve (AUROC) between 85% and 92% in internal validation. In external validation, the AUROCs for the ResNet (82%, 82%, and 78%) were significantly better than CatBoost (78%, 73%, and 75%), for 1-, 3- and 5-year mortality prediction respectively, with better or comparable performance to the MAGGIC score. ResNet models predicted higher probability of death in the HFpEF and HFrEF (30%-50%) subgroups than in controls and at risk patients (5%-20%). The predicted probabilities of death correlated with KCCQ scores (all p < 0.05).InterpretationEcho-based ML models to predict mortality had good internal and external validity, were generalizable, correlated with patients' quality of life, and are comparable to an established HF risk score. These models can be leveraged for automated risk stratification at point-of-care.FundingFunding for Alberta HEART was provided by an Alberta Innovates - Health Solutions Interdisciplinary Team Grant no. AHFMRITG 200801018. P.K. holds a Canadian Institutes of Health Research (CIHR) Sex and Gender Science Chair and a Heart & Stroke Foundation Chair in Cardiovascular Research. A.V. and V.S. received funding from the Mitacs Globalink Research Internship.

Dataset Information

Development and validation of a multivariate predictive model for rheumatoid arthritis mortality using a machine learning approach.

Publications

Development and validation of a multivariate predictive model for rheumatoid arthritis mortality using a machine learning approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets