Eyal Klang - research works

Among 19,501 visits (15,273 patients), 13,682 (70.2%) were treated.

A post-treatment pain score appeared at any time for 77.1% (95% CI, 76.4 to 77.8), but within 2 hours of the analgesic for only 47.9% and within 1 hour for 27.5%.

Completeness was similar across headache strata and comparator painful presentations.

In an independent ED (MC-MED, a different EHR), the score-selection effect replicated: relief rose from 71.1% (first) to 80.6% (last) and 83.4% (lowest).

For each patient we streamed one 24-minute window near 24 hours after return of spontaneous circulation, computed the algorithmic burst-suppression ratio on a 5-second grid, and derived non-saturated occupancy, within-window stability, and short-horizon forecastability.

Main results The burst-suppression ratio occupied a non-saturated band (0.10 to 0.90) for a median of 0.250 of monitored time (95% CI 0.200 to 0.306) and sat toward suppression (median operating level 0.824).

Confounding by indication was addressed with propensity overlap weighting; associations are reported as adjusted risk ratios (RRs) with bootstrap 95% CIs and E-values.

Results Among 13,285 treated adults (10,799 MIMIC-IV-ED; 2,486 MC-MED), opioid recipients were older and higher-acuity than dopamine-antagonist recipients (index admission 38.1% vs 16.4%).

In the MIMIC-IV-ED discharged primary-contrast population, overlap weighting reduced the maximum standardized mean difference from 0.35 to 0.002; pooled and site-specific balance diagnostics are provided in the Supplement.

In MIMIC-IV-ED, the cumulative all-cause return incidence by treatment class separated by day 3 and persisted through 30 days.

Abstract Objective A calibration-derived score has been related to online P300-speller accuracy in the same session, always within the cohort measured.

Pooled estimation error was 0.098 (95% CI 0.091 to 0.107) against a benchmark of 0.146.

A protocol proxy for the stopping rule, median time per selection, reduced the between-cohort slope variance by 66%.

The four ALS cohorts alone gave an uncorrected between-cohort slope spread of 0.223, against 0.560 overall.

Eighteen studies covered rheumatoid arthritis (n=3), ankylosing spondylitis/axial spondyloarthritis (n=7), psoriatic arthritis (n=2), gout (n=1), juvenile idiopathic arthritis (n=1), and multiple diseases (n=4).

Most diseases and tasks were represented by only one to a few studies, and the evidence base remains earlystage and uneven across conditions.

Guideline concordance ranged from 48% to 96%.

When compared with real clinical data, agreement was poor (Cohen and Fleiss κ ≈ 0).

Differences were attenuated when vignettes contained clearer diagnostic information.

Other effects were smaller, including increased neuroimaging recommendations for low-income descriptors (+4.0 pp; 95% CI 2.1-5.8).

ConclusionLLM clinical recommendations varied by sociodemographic descriptors, particularly under diagnostic uncertainty.