A risk stratification scoring system for new-onset atrial fibrillation after ischemic stroke

et al. 2021

JPM

Self Cite

Background: The objective is to study whether the cardiovascular protective effects of colchicines could be applied to non-cardiogenic ischemic stroke (IS) patients. Patients and Methods: Non-cardiogenic IS patients were identified from the National Health Insurance Research Database. Eligible patients were divided into chronic and non-chronic use categories based on their long-term status of colchicine use. The non-chronic use category was subdivided into (1) non-user and (2) new user groups while the chronic use category was divided into (3) former user and (4) long-term user groups according to the patient’s recent status of colchicine use. Inverse probability of treatment weights for propensity scores was used to balance the baseline characteristics. The primary outcome was recurrent IS, which was compared within the non-chronic use and chronic use categories. Results: In the non-chronic use category, the number of patients was 355,498 and 912 in the non-user and new user groups, respectively. In the chronic use category, the number of patients was 4737 and 4354 in the former user and long-term user groups, respectively. In the non-chronic use category, patients in the new user group had a marginally lower risk of recurrent IS at 6-months (subdistribution hazard ratio [SHR], 0.95; 95% confidence interval [CI], 0.94–0.97) and 2-years (SHR, 0.92; 95% CI, 0.91–0.93) follow up. In the chronic use category, patients in the long-term user group also had a marginally lower risk of recurrent IS at 6-months (SHR, 0.87; 95% CI, 0.86–0.88) and 2-years (SHR, 0.87; 95% CI, 0.86–0.88) follow up. The effect of colchicine on the reduced risk of recurrent IS was more favorable in patients who also used statins. Conclusions: Recent colchicine use in acute non-cardiogenic IS patients is associated with marginal fewer incidences of recurrent IS. Patients with concurrent statin use may have more profound protective effects.

Section: Methodsmentioning

confidence: 98%

Colchicine Use and Risks of Stroke Recurrence in Acute Non-Cardiogenic Ischemic Stroke Patients: A Population-Based Cohort Study

Liu

Lin

et al. 2021

JPM

Self Cite

“…Their C-indices were below the accepted 0.7 threshold necessary to have clinical relevance at the individual patient level. Previous studies have shown that the C-indices of the CHADS 2 score ranged from 0.536 to 0.700 (12,18,19,22,36,37) and those of the CHA 2 DS 2 -VASc score varied between 0.578 and 0.706 (15,18,19,22,36,37), whereas the HATCH score attained C-indices of 0.612 and 0.653 (22). Only the C 2 HEST score achieved a C-index of 0.734 in the external validation cohort (15).…”

Section: Performance Of Risk Scores For Atrial Fibrillation Detected ...mentioning

confidence: 93%

Validation of Risk Scores for Predicting Atrial Fibrillation Detected After Stroke Based on an Electronic Medical Record Algorithm: A Registry-Claims-Electronic Medical Record Linked Data Study

Hsieh

Kao

Front. Cardiovasc. Med.

et al. 2022

BackgroundPoststroke atrial fibrillation (AF) screening aids decisions regarding the optimal secondary prevention strategies in patients with acute ischemic stroke (AIS). We used an electronic medical record (EMR) algorithm to identify AF in a cohort of AIS patients, which were used to validate eight risk scores for predicting AF detected after stroke (AFDAS).MethodsWe used linked data between a hospital stroke registry and a deidentified database including EMRs and administrative claims data. EMR algorithms were constructed to identify AF using diagnostic and medication codes as well as free clinical text. Based on the optimal EMR algorithm, the incidence rate of AFDAS was estimated. The predictive performance of 8 risk scores including AS5F, C2HEST, CHADS2, CHA2DS2-VASc, CHASE-LESS, HATCH, HAVOC, and Re-CHARGE-AF scores, were compared using the C-index, net reclassification improvement, integrated discrimination improvement, calibration curve, and decision curve analysis.ResultsThe algorithm that defines AF as any positive mention of AF-related keywords in electrocardiography or echocardiography reports, or presence of diagnostic codes of AF was used to identify AF. Among the 5,412 AIS patients without known AF at stroke admission, the incidence rate of AFDAS was 84.5 per 1,000 person-year. The CHASE-LESS and AS5F scores were well calibrated and showed comparable C-indices (0.741 versus 0.730, p = 0.223), which were significantly higher than the other risk scores.ConclusionThe CHASE-LESS and AS5F scores demonstrated adequate discrimination and calibration for predicting AFDAS. Both simple risk scores may help select patients for intensive AF monitoring.

“…Many studies have investigated prediction models for NDAF in the general population (25,42,43) or in selected patient groups such as those with stroke or TIA (18,21,22,31,44,45). Owing to the different characteristics of at-risk populations, it is arguable whether the relationships between the predictors and NDAF are similar across patient groups.…”

Section: Important Predictors Of Newly Detected Atrial Fibrillationmentioning

confidence: 99%

Automated risk assessment of newly detected atrial fibrillation poststroke from electronic health record data using machine learning and natural language processing

Front. Cardiovasc. Med.

Sung²,

Pan³

et al. 2022

BackgroundTimely detection of atrial fibrillation (AF) after stroke is highly clinically relevant, aiding decisions on the optimal strategies for secondary prevention of stroke. In the context of limited medical resources, it is crucial to set the right priorities of extended heart rhythm monitoring by stratifying patients into different risk groups likely to have newly detected AF (NDAF). This study aimed to develop an electronic health record (EHR)-based machine learning model to assess the risk of NDAF in an early stage after stroke.MethodsLinked data between a hospital stroke registry and a deidentified research-based database including EHRs and administrative claims data was used. Demographic features, physiological measurements, routine laboratory results, and clinical free text were extracted from EHRs. The extreme gradient boosting algorithm was used to build the prediction model. The prediction performance was evaluated by the C-index and was compared to that of the AS5F and CHASE-LESS scores.ResultsThe study population consisted of a training set of 4,064 and a temporal test set of 1,492 patients. During a median follow-up of 10.2 months, the incidence rate of NDAF was 87.0 per 1,000 person-year in the test set. On the test set, the model based on both structured and unstructured data achieved a C-index of 0.840, which was significantly higher than those of the AS5F (0.779, p = 0.023) and CHASE-LESS (0.768, p = 0.005) scores.ConclusionsIt is feasible to build a machine learning model to assess the risk of NDAF based on EHR data available at the time of hospital admission. Inclusion of information derived from clinical free text can significantly improve the model performance and may outperform risk scores developed using traditional statistical methods. Further studies are needed to assess the clinical usefulness of the prediction model.