Dataset Information

Predicting 6-year mortality risk in patients with type 2 diabetes.

ABSTRACT: OBJECTIVE: The objective of this study was to create a tool that predicts the risk of mortality in patients with type 2 diabetes. RESEARCH DESIGN AND METHODS: This study was based on a cohort of 33,067 patients with type 2 diabetes identified in the Cleveland Clinic electronic health record (EHR) who were initially prescribed a single oral hypoglycemic agent between 1998 and 2006. Mortality was determined in the EHR and the Social Security Death Index. A Cox proportional hazards regression model was created using medication class and 20 other predictor variables chosen for their association with mortality. A prediction tool was created using the Cox model coefficients. The tool was internally validated using repeated, random subsets of the cohort, which were not used to create the prediction model. RESULTS: Follow-up in the cohort ranged from 1 day to 8.2 years (median 28.6 months), and 3,661 deaths were observed. The prediction tool had a concordance index (i.e., c statistic) of 0.752. CONCLUSIONS: We successfully created a tool that accurately predicts mortality risk in patients with type 2 diabetes. The incorporation of medications into mortality predictions in patients with type 2 diabetes should improve treatment decisions.

SUBMITTER: Wells BJ

PROVIDER: S-EPMC2584185 | biostudies-literature | 2008 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting 6-year mortality risk in patients with type 2 diabetes.

Wells Brian J BJ Jain Anil A Arrigain Susana S Yu Changhong C Rosenkrans Wayne A WA Kattan Michael W MW

Diabetes care 20080922 12

<h4>Objective</h4>The objective of this study was to create a tool that predicts the risk of mortality in patients with type 2 diabetes.<h4>Research design and methods</h4>This study was based on a cohort of 33,067 patients with type 2 diabetes identified in the Cleveland Clinic electronic health record (EHR) who were initially prescribed a single oral hypoglycemic agent between 1998 and 2006. Mortality was determined in the EHR and the Social Security Death Index. A Cox proportional hazards reg ...[more]

PMID: 18809629

Similar Datasets

Project description:In an era of increasing need for precision medicine, machine learning has shown promise in making accurate acute myocardial infarction outcome predictions. The accurate assessment of high-risk patients is a crucial component of clinical practice. Type 2 diabetes mellitus (T2DM) complicates ST-segment elevation myocardial infarction (STEMI), and currently, there is no practical method for predicting or monitoring patient prognosis. The objective of the study was to compare the ability of machine learning models to predict in-hospital mortality among STEMI patients with T2DM. We compared six machine learning models, including random forest (RF), CatBoost classifier (CatBoost), naive Bayes (NB), extreme gradient boosting (XGBoost), gradient boosting classifier (GBC), and logistic regression (LR), with the Global Registry of Acute Coronary Events (GRACE) risk score. From January 2016 to January 2020, we enrolled patients aged > 18 years with STEMI and T2DM at the Affiliated Hospital of Zunyi Medical University. Overall, 438 patients were enrolled in the study [median age, 62 years; male, 312 (71%); death, 42 (9.5%]). All patients underwent emergency percutaneous coronary intervention (PCI), and 306 patients with STEMI who underwent PCI were enrolled as the training cohort. Six machine learning algorithms were used to establish the best-fit risk model. An additional 132 patients were recruited as a test cohort to validate the model. The ability of the GRACE score and six algorithm models to predict in-hospital mortality was evaluated. Seven models, including the GRACE risk model, showed an area under the curve (AUC) between 0.73 and 0.91. Among all models, with an accuracy of 0.93, AUC of 0.92, precision of 0.79, and F1 value of 0.57, the CatBoost model demonstrated the best predictive performance. A machine learning algorithm, such as the CatBoost model, may prove clinically beneficial and assist clinicians in tailoring precise management of STEMI patients and predicting in-hospital mortality complicated by T2DM.

Project description:AimsThe aim of this study was to assess the performance of these main scores in predicting prognosis in patients with heart failure (HF).Methods and resultsA total of 2008 patients who were admitted to the Fourth People's Hospital of Zigong, Sichuan, from December 2016 to June 2019 and diagnosed with HF were included in the study. We compared the prognostic predictive performance of Seattle Heart Failure Model (SHFM), Meta-Analysis Global Group in Chronic Heart Failure (MAGGIC-HF) risk score, Get With the Guidelines-Heart Failure programme (GWTG-HF), Acute Study of Clinical Effectiveness of Nesiritide in Decompensated Heart Failure (ASCEND) risk scores, the Acute Decompensated Heart Failure National Registry (ADHERE) model, Barcelona Bio-Heart Failure (BCN-Bio-HF) risk calculator, and Gruppo Italiano per lo Studio della Streptochinasi nell'Infarto Miocardico-Heart Failure (GISSI-HF) for the endpoints. The primary endpoint was 1 year all-cause mortality and the secondary endpoint was the incidence of 28 day readmission post-discharge. At 1 year follow-up, 44 (2.21%) patients with HF died. Discrimination analyses showed that all risk scores performed reasonably well in predicting 1 year mortality, with areas under the receiver operating characteristic curve (AUCs) fluctuating between 0.757 and 0.822. GISSI-HF showed the best discrimination with the AUC of 0.822 (0.768-0.876), followed by MAGGIC-HF, BCN-Bio-HF, ASCEND, SHFM, GWTG-HF, and ADHERE with AUCs of 0.819 (0.756-0.883), 0.812 (0.758-0.865), 0.802 (0.742-0.862), 0.787 (0.725-0.849), 0.762 (0.684-0.840), and 0.757 (0.681-0.833), respectively. All risk scores were similarly predictive of 28 day emergency readmissions, with AUCs fluctuating between 0.609 and 0.680. Overestimation of mortality occurred in all scores except the ASCEND. The risk scores remained with good prognostic discrimination in patients with biventricular HF and in the subgroup of patients taking angiotensin-converting enzyme inhibitor/angiotensin II receptor blocker.ConclusionsCurrently assessed risk scores have limited clinical utility, with fair accuracy and calibration in assessing patients' 1 year risk of death and poor accuracy in assessing patients' risk of readmission. There is a need to incorporate more patient-level information, use more advanced technologies, and develop models for different subgroups of patients to achieve more practical, innovative, and accurate risk assessment tools.

Dataset Information

Predicting 6-year mortality risk in patients with type 2 diabetes.

Publications

Predicting 6-year mortality risk in patients with type 2 diabetes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets