Profile and outcome of patients with ground-level falls

Field Measures Are All You Need: Predicting Need for Surgery in Elderly Ground-Level Fall Patients via Machine Learning

BACKGROUND

As ground-level falls (GLFs) are a significant cause of mortality in elderly patients, field triage plays an essential role in patient outcomes. This research investigates how machine learning algorithms can supplement traditional t-tests to recognize statistically significant patterns in medical data and to aid clinical guidelines.

METHODS

This is a retrospective study using data from 715 GLF patients over 75 years old. We first calculated P-values for each recorded factor to determine the factor's significance in contributing to a need for surgery (P < .05 is significant). We then utilized the XGBoost machine learning method to rank contributing factors. We applied SHapley Additive exPlanations (SHAP) values to interpret the feature importance and provide clinical guidance via decision trees.

RESULTS

The three most significant P-values when comparing patients with and without surgery are as follows: Glasgow Coma Scale (GCS) (P < .001), no comorbidities (P < .001), and transfer-in (P = .019). The XGBoost algorithm determined that GCS and systolic blood pressure contribute most strongly. The prediction accuracy of these XGBoost results based on the test/train split was 90.3%.

DISCUSSION

When compared to P-values, XGBoost provides more robust, detailed results regarding the factors that suggest a need for surgery. This demonstrates the clinical applicability of machine learning algorithms. Paramedics can use resulting decision trees to inform medical decision-making in real time. XGBoost's generalizability power increases with more data and can be tuned to prospectively assist individual hospitals.

Unintentional falls among children in rural Ghana and associated factors: a cluster-randomized, population-based household survey

INTRODUCTION

falls contribute to almost one-fifth of injury-related deaths. The majority of these occur in low- and middle-income countries. The impact of fall injury in low- and middle-income countries is greater in younger individuals. We aimed to determine the epidemiology of falls among rural Ghanaian children.

METHODS

from March to May, 2018, we conducted a cluster-randomized household survey of caregivers in a rural Ghanaian sub-district, regarding household child falls and their severity. We utilized a previously validated survey tool for household child injury. Associations between household child falls and previously described predictors of household child injury were examined with multivariable logistic regression. These included age and gender of the child, household socioeconomic status, caregiver education, employment status, and their beliefs on why household child injuries occur.

RESULTS

three hundred and fifty-seven caregivers of 1,016 children were surveyed. One hundred and sixty-four children under 18 years had sustained a household fall within the past six months, giving a household child fall prevalence of 16% (95% C.I, 14%-19%). Mean age was 4.4 years; 59% were males. Ground level falls were more common (80%). Severity was mostly moderate (86%). Most caregivers believed household child injuries occurred due to lack of supervision (85%) or unsafe environment (75%); only 2% believed it occurred because of fate. Girls had reduced odds of household falls (adjusted O.R 0.6; 95% C.I 0.4-0.9). Five to nine year-old and 15-17 year-old children had reduced odds of household falls (adjusted O.R 0.4; 95% C.I 0.2-0.7 and 0.1; 95% C.I 0.02-0.3, respectively) compared to 1-4 year-olds. Caregiver engagement in non-salary paying work was associated with increased odds of household child falls (adjusted O.R 2.2; 95% C.I 1.0-4.7) compared to unemployed caregivers. There was no association between household child falls and caregiver education, socioeconomic status and beliefs about why household child injuries occurred.

CONCLUSION

the prevalence of household child falls in rural Ghana was 16%. This study confirms the need to improve supervision of all children to reduce household falls, especially younger children and particularly boys. Majority of caregivers also acknowledge the role of improper child supervision and unsafe environments in household child falls. These beliefs should be reinforced and emphasized in campaigns to prevent household child falls in rural communities.

Visual function and mobility after multifocal versus monofocal intraocular lens implantation

Clinical relevance: Mobility and fall risk may be important considerations in choosing between intraocular lenses.Background: Fall risk in older adults increases when wearing multifocal spectacles, but little is known about mobility among individuals with different types of intraocular lenses. This study compared visual function, fall risk and balance control following bilateral implantation of monofocal or multifocal intraocular lenses.Methods: This was a non-randomised, cross-sectional study involving adults with bilateral intraocular lenses. Participants completed questionnaires concerning physical functioning, fall history and balance-related confidence. Binocular visual acuity, contrast sensitivity (Pelli-Robson chart and computerized testing), depth perception and glare sensitivity were assessed. Physical performance measures included the Sensory Organization Test, preferred gait speed, Dynamic Gait Index and wayfinding in a virtual environment.Results: Fifteen participants (mean ± standard deviation, 67.1 ± 6.8 years) had monofocal intraocular lenses and 14 participants (68.1 ± 6.1 years) had multifocal intraocular lenses. Contrast sensitivity in the monofocal group was significantly better than that in the multifocal group (p = 0.02) at intermediate and high spatial frequencies. Contrast sensitivity of the monofocal group also was less affected by glare than the contrast sensitivity of the multifocal group, at an intermediate spatial frequency (p = 0.02). However, the multifocal group had significantly better Dynamic Gait Index scores (p = 0.04), even after controlling for perceived physical function.Conclusions: The participants with monofocal intraocular lenses generally had better contrast sensitivity than did those with multifocal intraocular lenses. However, the scores on a mobility test that is associated with fall risk were worse for those with monofocal lenses.