Development and validation of a dynamic inpatient risk prediction model for clinically significant hypokalemia using electronic health record data

Prediction of in-hospital hypokalemia using machine learning and first hospitalization day records in patients with traumatic brain injury

AIMS

Hypokalemia is a common complication following traumatic brain injury, which may complicate treatment and lead to unfavorable outcomes. Identifying patients at risk of hypokalemia on the first day of admission helps to implement prophylactic treatment, reduce complications, and improve prognosis.

METHODS

This multicenter retrospective study was performed between January 2017 and December 2020 using the electronic medical records of patients admitted due to traumatic brain injury. A propensity score matching approach was adopted with a ratio of 1:1 to overcome overfitting and data imbalance during subgroup analyses. Five machine learning algorithms were applied to generate a best-performed prediction model for in-hospital hypokalemia. The internal fivefold cross-validation and external validation were performed to demonstrate the interpretability and generalizability.

RESULTS

A total of 4445 TBI patients were recruited for analysis and model generation. Hypokalemia occurred in 46.55% of recruited patients and the incidences of mild, moderate, and severe hypokalemia were 32.06%, 12.69%, and 1.80%, respectively. Hypokalemia was associated with increased mortality, while severe hypokalemia cast greater impacts. The logistic regression algorithm had the best performance in predicting decreased serum potassium and moderate-to-severe hypokalemia, with an AUC of 0.73 ± 0.011 and 0.74 ± 0.019, respectively. The prediction model was further verified using two external datasets, including our previous published data and the open-assessed Medical Information Mart for Intensive Care database. Linearized calibration curves showed no statistical difference (p > 0.05) with perfect predictions.

CONCLUSIONS

The occurrence of hypokalemia following traumatic brain injury can be predicted by first hospitalization day records and machine learning algorithms. The logistic regression algorithm showed an optimal predicting performance verified by both internal and external validation.

Using machine learning to investigate the relationship between domains of functioning and functional mobility in older adults

Previous studies have shown that functional mobility, along with other physical functions, decreases with advanced age. However, it is still unclear which domains of functioning (body structures, body functions, and activities) are most closely related to functional mobility. This study used machine learning classification to predict the rankings of Timed Up and Go tests based on the results of four assessments (soft lean mass, FEV1/FVC, knee extension torque, and one-leg standing time). We tested whether assessment results for each level could predict functional mobility assessments in older adults. Using support vector machines for machine learning classification, we verified that the four assessments of each level could classify functional mobility. Knee extension torque (from the body function domain) was the most closely related assessment. Naturally, the classification accuracy rate increased with a larger number of assessments as explanatory variables. However, knee extension torque remained the highest of all assessments. This extended to all combinations (of 2-3 assessments) that included knee extension torque. This suggests that resistance training may help protect individuals suffering from age-related declines in functional mobility.

Deep learning prediction of falls among nursing home residents with Alzheimer's disease

AIM

This study aimed to use a convolutional neural network (CNN) to investigate the associations between the time of falling and multiple complicating factors, including age, dementia severity, lower extremity strength and physical function, among nursing home residents with Alzheimer's disease.

METHODS

A total of 42 people with Alzheimer's disease were enrolled. We evaluated falling events from nursing home admission (baseline) to 300 days later. We assessed the knee extension strength and Functional Independence Measure locomotion item and carried out the Mini-Mental State Examination at baseline. To predict falling, participants were categorized into three classes: those who fell within the first 150 (or 300) days from baseline or those who did not experience a fall within the study period. For each class, 1000 bootstrap datasets were generated using 42 actual sample datasets, and were used to propose a CNN algorithm and cross-validate the algorithm.

RESULTS

Eight (19.0%), 11 (26.2%) and 31 participants (73.8%) fell within 150 or 300 days after the baseline assessment or did not fall until 300 days or later, respectively. The highest accuracy rate of the CNN classification was 0.647 in the factor combination extracted from the Mini-Mental State Examination score, knee extension strength and Functional Independence Measure locomotion item score.

CONCLUSIONS

A CNN based on multiple complicating factors could predict the time of falling in nursing home residents with Alzheimer's disease. Geriatr Gerontol Int 2020; ••: ••-••.

Machine-learning prediction of self-care activity by grip strengths of both hands in poststroke hemiplegia

To investigate the relationships between grip strengths and self-care activities in stroke patients using a non-linear support vector machine (SVM).Overall, 177 inpatients with poststroke hemiparesis were enrolled. Their grip strengths were measured using the Jamar dynamometer on the first day of rehabilitation training. Self-care activities were assessed by therapists using Functional Independence Measure (FIM), including items for eating, grooming, dressing the upper body, dressing the lower body, and bathing at the time of discharge. When each FIM item score was ≥6 points, the subject was considered independent. One thousand bootstrap grip strength datasets for each independence and dependence in self-care activities were generated from the actual grip strength. Thereafter, we randomly assigned the total bootstrap datasets to 90% training and 10% testing datasets and inputted the bootstrap training data into a non-linear SVM. After training, we used the SVM algorithm to predict a testing dataset for cross-validation. This validation procedure was repeated 10 times.The SVM with grip strengths more accurately predicted independence or dependence in self-care activities than the chance level (mean ± standard deviation of accuracy rate: eating, 0.71 ± 0.04, P < .0001; grooming, 0.77 ± 0.03, P < .0001; upper-body dressing, 0.75 ± 0.03, P < .0001; lower-body dressing, 0.72 ± 0.05, P < .0001; bathing, 0.68 ± 0.03, P < .0001).Non-linear SVM based on grip strengths can prospectively predict self-care activities.