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

Background: Timely 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. Methods: Linked 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. Results: The 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. Conclusions: It 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.

Constructing Inpatient Pressure Injury Prediction Models Using Machine Learning Techniques.

The incidence rate of pressure injury is a critical nursing quality indicator in clinic care; consequently, factors causing pressure injury are diverse and complex. The early prevention of pressure injury and monitoring of these complex high-risk factors are critical to reduce the patients' pain, prevent further surgical treatment, avoid prolonged hospital stay, decrease the risk of wound infection, and lower associated medical costs and expenses. Although a number of risk assessment scales of pressure injury have been adopted in various countries, their criteria are set for specific populations, which may not be suitable for the medical care systems of other countries. This study constructs three prediction models of inpatient pressure injury using machine learning techniques, including decision tree, logistic regression, and random forest. A total of 11 838 inpatient records were collected, and 30 sets of training samples were adopted for data analysis in the experiment. The experimental results and evaluations of the models suggest that the prediction model built using random forest had most favorable classification performance of 0.845. The critical risk factors for pressure injury identified in this study were skin integrity, systolic blood pressure, expression ability, capillary refill time, and level of consciousness.

Developing and psychometric testing of a short-form problem areas in diabetes scale in chinese patients.

BACKGROUND: The 20-item Problem Areas in Diabetes (PAID) scale is widely used to measure diabetes-related emotional distress. The short-form PAID scale is helpful for the rapid screening of diabetes-related emotional distress in clinical settings. PURPOSE: This study developed and examined the psychometric properties of a short-form Chinese-version PAID (SF-PAID-C) scale. METHODS: The Chinese-version 20-item PAID (PAID-C) scale was administered to 855 patients with type 2 diabetes mellitus. Item analysis, exploratory factor analysis, and confirmatoryfactoranalysis were then applied to develop the SF-PAID-C and evaluate its construct validity. The correlations between SF-PAID-C and the latest HbA1c close to the measurement of PAID-C (baseline HbA1c) 3 months and 12 months later were used to examine the concurrent and predictive validity of the SF-PAID-C. Receiver operating characteristic curve analysis was used to examine the sensitivity and specificity of the SF-PAID-C. Cronbach's alpha was used to assess internal consistency. Test-retest on 24 patients was used to examine the stability of the SF-PAID-C. RESULTS: An 8-item SF-PAID-C was developed. The SF-PAID-C significantly correlated with the PAID-C (r = .941, p < .001), baseline HbA1c (r = .148, p < .001), 3-month HbA1c (r = .147, p < .001), and 12-month HbA1c (r = .142, p < .001). The sensitivity and specificity of the SF-PAID-C were 93.2% and 94.2%, respectively. The Cronbach's α and test-retest reliability of the SF-PAID-C were .85 and .93, respectively. CONCLUSIONS/IMPLICATIONS FOR PRACTICE: The SF-PAID-C is a reliable and valid scale that can be used to screen for diabetes-related emotional problem in Chinese patients with type 2 diabetes mellitus in clinical settings.