Risk Factors for Meibomian Gland Disease Assessed by Meibography

Purpose

To elucidate risk factors for meibomian gland disease (MGD) and understand associated changes in meibography and in relation to ocular surface disease.

Patients and Methods

As part of the standard workup for ocular surface disease at a tertiary academic center, 203 patients received an ocular history and lifestyle questionnaire. The questionnaire included detailed inquiries about ocular health and lifestyle, including makeup use, cosmetic eyelid procedures, screen time, and contact lens habits. Subjects also took the standardized patient evaluation of eye dryness (SPEED) II questionnaire. Meibomian gland (MG) dropout and structural changes were evaluated on meibography and scored by three independent graders using meiboscores. Statistical analysis was conducted to identify significant risk factors associated with MG loss.

Results

This retrospective, cross-sectional study included 189 patients (378 eyes) with high-quality images for grading, and the average age was 67 years (77% female). Patients older than 45 years had significantly more dropout than younger patients (p < 0.01). Self-reported eye makeup use did not significantly impact MG loss. Patients with a history of blepharoplasty trended toward higher meiboscores, but the difference was not statistically significant. Self-reported screen time did not affect meiboscores. Contact lens use over 20 years was associated with significant MG loss (p < 0.05). SPEED II scores had no relationship to meiboscores (p = 0.75).

Conclusion

Older age is a significant risk factor for MG loss. Any contact lens use over 20 years also impacted MG dropout. Highlighting the incongruence of symptoms to signs, SPEED II scores showed no relationship to the structural integrity of MGs.

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.