A Machine Learning-Based Fall Risk Assessment Model for Inpatients

Construction of an Early Risk Prediction Model for Type 2 Diabetic Peripheral Neuropathy Based on Random Forest

Diabetic peripheral neuropathy is a major cause of disability and death in the later stages of diabetes. A retrospective chart review was performed using a hospital-based electronic medical record database to identify 1020 patients who met the criteria. The objective of this study was to explore and analyze the early risk factors for peripheral neuropathy in patients with type 2 diabetes, even in the absence of specific clinical symptoms or signs. Finally, the random forest algorithm was used to rank the influencing factors and construct a predictive model, and then the model performance was evaluated. Logistic regression analysis revealed that vitamin D plays a crucial protective role in preventing diabetic peripheral neuropathy. The top three risk factors with significant contributions to the model in the random forest algorithm eigenvalue ranking were glycosylated hemoglobin, disease duration, and vitamin D. The areas under the receiver operating characteristic curve of the model ware 0.90. The accuracy, precision, specificity, and sensitivity were 0.85, 0.83, 0.92, and 0.71, respectively. The predictive model, which is based on the random forest algorithm, is intended to support clinical decision-making by healthcare professionals and help them target timely interventions to key factors in early diabetic peripheral neuropathy.

Computerization of risk prediction scale: strategy for safety and quality of care

OBJECTIVE

To describe the development of computerization of risk prediction scales used by nursing in the AGHUse® system.

METHOD

An experience report of technological production at a university hospital, which followed the phases of conception, detailing, construction and prototyping.

RESULTS

Different scales were computerized, with emphasis on the Braden and Braden Q, which assess the risk of pressure injuries, and the Severo-Almeida-Kuchenbecker, which assesses the risk of falls. The process of computerization and implementation took place through registration of the scales in the software, application of them in care practice, integration and visualization of their scores with the other functionalities of the electronic medical record.

FINAL CONSIDERATIONS

The functionalities developed in the computerization of risk prediction scales favored its operation, reflecting positively on nursing practice and patient safety.

Can the Electronic Health Record Predict Risk of Falls in Hospitalized Patients by Using Artificial Intelligence? A Meta-analysis

Because of an aging population worldwide, the increasing prevalence of falls and their consequent injuries are becoming a safety, health, and social-care issue among elderly people. We conducted a meta-analysis to investigate the benchmark of prediction power when using the EHR with artificial intelligence to predict risk of falls in hospitalized patients. The CHARMS guideline was used in this meta-analysis. We searched PubMed, Cochrane, and EMBASE. The pooled sensitivity and specificity were calculated, and the summary receiver operating curve was formed to investigate the predictive power of artificial intelligence models. The PROBAST table was used to assess the quality of the selected studies. A total of 132 846 patients were included in this meta-analysis. The pooled area under the curve of the collected research was estimated to be 0.78. The pooled sensitivity was 0.63 (95% confidence interval, 0.52-0.72), whereas the pooled specificity was 0.82 (95% confidence interval, 0.73-0.88). The quality of our selected studies was high, with most of them being evaluated with low risk of bias and low concern for applicability. Our study demonstrates that using the EHR with artificial intelligence to predict the risk of falls among hospitalized patients is feasible. Future clinical applications are anticipated.

A model for predicting fall risks of hospitalized elderly in Taiwan-A machine learning approach based on both electronic health records and comprehensive geriatric assessment

Backgrounds

Falls are currently one of the important safety issues of elderly inpatients. Falls can lead to their injury, reduced mobility and comorbidity. In hospitals, it may cause medical disputes and staff guilty feelings and anxiety. We aimed to predict fall risks among hospitalized elderly patients using an approach of artificial intelligence.

Materials and methods

Our working hypothesis was that if hospitalized elderly patients have multiple risk factors, their incidence of falls is higher. Artificial intelligence was then used to predict the incidence of falls of these patients. We enrolled those elderly patients aged >65 years old and were admitted to the geriatric ward during 2018 and 2019, at a single medical center in central Taiwan. We collected 21 physiological and clinical data of these patients from their electronic health records (EHR) with their comprehensive geriatric assessment (CGA). Data included demographic information, vital signs, visual ability, hearing ability, previous medication, and activity of daily living. We separated data from a total of 1,101 patients into 3 datasets: (a) training dataset, (b) testing dataset and (c) validation dataset. To predict incidence of falls, we applied 6 models: (a) Deep neural network (DNN), (b) machine learning algorithm extreme Gradient Boosting (XGBoost), (c) Light Gradient Boosting Machine (LightGBM), (d) Random Forest, (e) Stochastic Gradient Descent (SGD) and (f) logistic regression.

Results

From modeling data of 1,101 elderly patients, we found that machine learning algorithm XGBoost, LightGBM, Random forest, SGD and logistic regression were successfully trained. Finally, machine learning algorithm XGBoost achieved 73.2% accuracy.

Conclusion

This is the first machine-learning based study using both EHR and CGA to predict fall risks of elderly. Multiple risk factors of falls in hospitalized elderly patients can be put into a machine learning model to predict future falls for early planned actions. Future studies should be focused on the model fitting and accuracy of data analysis.