Identifying Modifiable Predictors of Patient Outcomes After Intracerebral Hemorrhage with Machine Learning.

BACKGROUND/OBJECTIVE: Demonstrating a benefit of acute treatment to patients with intracerebral hemorrhage (ICH) requires identifying which patients have a potentially modifiable outcome, where treatment could favorably shift a patient's expected outcome. A decision rule for which patients have a modifiable outcome could improve the targeting of treatments. We sought to determine which patients with ICH have a modifiable outcome. METHODS: Patients with ICH were prospectively identified at two institutions. Data on hematoma volumes, medication histories, and other variables of interest were collected. ICH outcomes were evaluated using the modified Rankin Scale (mRS), assessed at 14 days and 3 months after ICH, with "good outcome" defined as 0-3 (independence or better) and "poor outcome" defined as 4-6 (dependence or worse). Supervised machine learning models identified the best predictors of good versus poor outcomes at Institution 1. Models were validated using repeated fivefold cross-validation as well as testing on the entirely independent sample at Institution 2. Model fit was assessed with area under the ROC curve (AUC). RESULTS: Model performance at Institution 1 was strong for both 14-day (AUC of 0.79 [0.77, 0.81] for decision tree, 0.85 [0.84, 0.87] for random forest) and 3 month (AUC of 0.75 [0.73, 0.77] for decision tree, 0.82 [0.80, 0.84] for random forest) outcomes. Independent predictors of functional outcome selected by the algorithms as important included hematoma volume at hospital admission, hematoma expansion, intraventricular hemorrhage, overall ICH Score, and Glasgow Coma Scale. Hematoma expansion was the only potentially modifiable independent predictor of outcome and was compatible with "good" or "poor" outcome in a subset of patients with low hematoma volumes, good Glasgow Coma scale and premorbid modified Rankin Scale scores. Models trained on harmonized data also predicted patient outcomes well at Institution 2 using decision tree (AUC 0.69 [0.63, 0.75]) and random forests (AUC 0.78 [0.72, 0.84]). CONCLUSIONS: Patient outcomes are predictable to a high level in patients with ICH, and hematoma expansion is the sole-modifiable predictor of these outcomes across two outcome types and modeling approaches. According to decision tree analyses predicting outcome at 3 months, patients with a high Glasgow Coma Scale score, less than 44.5 mL hematoma volume at admission, and relatively low premorbid modified Rankin Score in particular have a modifiable outcome and appear to be candidates for future interventions to improve outcomes after ICH.

Retinal Detachment and Laser Retinopexy Rates During the COVID-19 Pandemic.

Purpose: At the start of March 2020, the COVID-19 pandemic placed an unprecedented burden on the healthcare system. Throughout much of the United States, shelter-in-place orders were imposed to reduce transmission. A consequence of this crisis, risk mitigation orders, and patient fear of exposure may have led to underutilization of emergency services. We aimed to quantify 2 emergent interventions in ophthalmology, specifically acute laser retinopexy procedures and retinal detachment repair, to determine whether these procedures decreased during the start of the pandemic. Methods: All retinal detachment surgeries and laser retinopexy procedures were identified using Current Procedural Terminology codes. Rate data during the study period (March 1 through May 31, 2020) was compared to historical data from the year prior (March 2019 through May 2019; epoch 1) as well as the immediate 3 months prior to the study period (December 2019 through February 2020; epoch 2). Results: Combined procedures fell by 38.5% (P = .01) and 36.0% (P = .02) when compared to epoch 1 and epoch 2, respectively. The rate of laser retinopexy procedures fell by 45.5% (P = .02) and 33.0% (P = .14) when compared to epoch 1 and epoch 2, respectively. The rate of retinal detachment repair fell by 29.4% (P = .24) and 38.0% (P = .07) when compared to epoch 1 and epoch 2, respectively. Conclusions: Procedures fell during the study period, suggesting underutilization of emergent ophthalmology care. It is necessary for ophthalmologists to emphasize the need to seek care for concerning symptoms.

Trajectories of Big Five Personality Traits: A Coordinated Analysis of 16 Longitudinal Samples.

This study assessed change in self-reported Big Five personality traits. We conducted a coordinated integrative data analysis using data from 16 longitudinal samples, comprising a total sample of over 60 000 participants. We coordinated models across multiple datasets and fit identical multi-level growth models to assess and compare the extent of trait change over time. Quadratic change was assessed in a subset of samples with four or more measurement occasions. Across studies, the linear trajectory models revealed declines in conscientiousness, extraversion, and openness. Non-linear models suggested late-life increases in neuroticism. Meta-analytic summaries indicated that the fixed effects of personality change are somewhat heterogeneous and that the variability in trait change is partially explained by sample age, country of origin, and personality measurement method. We also found mixed evidence for predictors of change, specifically for sex and baseline age. This study demonstrates the importance of coordinated conceptual replications for accelerating the accumulation of robust and reliable findings in the lifespan developmental psychological sciences.

The I3 Model: a metatheoretical framework for understanding aggression.

The I3 Model is a general-purpose metatheory. It posits that three orthogonal processes influence the likelihood and intensity of a given behavior, including aggressive behavior. Instigation encompasses immediate environmental stimuli (e.g., provocation) that normatively afford an aggressive response. Impellance encompasses situational or dispositional qualities (e.g., trait aggressiveness) that influence how strongly the instigator produces a proclivity to enact that response. Inhibition encompasses situational or dispositional qualities (e.g., alcohol intoxication) that influence how strongly the proclivity is overridden rather than manifesting in aggressive behavior. Extant evidence supports Perfect Storm Theory-a theoretical perspective derived from the I3 Model-which posits that aggression is especially likely, and especially intense, to the extent that instigation and impellance are strong and inhibition is weak.