Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0785
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-08-16T06:22:24.957109Z
status: published
lens: g_space
sector: labor
headline: Moral distress risk profiling in ICU nurses: A cross-sectional study
dek: BackgroundMoral distress is common among ICU nurses and has been linked to burnout, diminished care quality, and turnover. Which factors matter most - and how they combine to shape individual risk - remains poorly characterised.Research objectiveTo identify factors associated with moral distress in ICU nurses and develop a parsimonious, exploratory risk-profiling model.Research designMulticentre cross-sectional survey with machine learning analysis.Participants and research contextA total of 318 registered nurse…
gain_title: A gradient boosting machine trained on survey data from 318 ICU nurses predicted high moral distress with high discrimination using six predictors, preserving accuracy after feature reduction.
problem_title: (none)
trace_subject: (none)
gain_reading: A gradient boosting machine trained on survey data from 318 ICU nurses predicted high moral distress with high discrimination using six predictors, preserving accuracy after feature reduction.
gain_evidence: Gradient boosting machine (GBM) achieved the best balanced performance among all models (F1 = 0.767) | High moral distress was present in 28.6% of participants
problem_reading: (none)
problem_evidence: (none)
quick_read: In a multicentre cross-sectional study of 318 ICU nurses in China, researchers developed a machine learning risk-profiling model for moral distress, which was present in 28.6% of participants. A gradient boosting machine achieved the best balanced performance and, after SHAP-guided reduction, retained full accuracy with six predictors: monthly night shifts, financial responsibility role, psychological resilience, sleep quality, nurse-to-patient ratio, and weekly working hours.

The result matters because it points to modifiable work-organization factors that could inform future interventions for nurse burnout and care quality, but the authors frame the model as exploratory. By the August 2026 publication date, performance was reported only on an internal test set with AUC 0.907, and external validation, generalizability beyond Chinese tertiary ICUs, and actual impact on distress or turnover remain untested.
limitation: Exploratory model lacks external validation and is not ready for clinical application, with findings limited to the sampled Chinese tertiary ICU context.
tag: Evidence-backed gain
key_points: Multicentre cross-sectional survey of 318 registered ICU nurses in China between January and June 2025 using validated moral distress, resilience, and sleep scales. | LASSO selected 12 predictors from 29 variables; 11 algorithms compared with GBM best balanced performance and SHAP guiding reduction to six features. | Six predictors in order of importance were monthly night shifts, financial responsibility role, psychological resilience, sleep quality, nurse-to-patient ratio, and weekly working hours. | Model was well-calibrated with Hosmer-Lemeshow p = 0.220 and Brier score = 0.097 and showed net clinical benefit in decision curve analysis.
rundown: Researchers recruited 318 registered nurses from ICUs of multiple tertiary hospitals across China between January and June 2025, splitting data into training n=223 and test n=95, and administered the Chinese-validated Moral Distress Assessment in Professional Practice Scale, Connor-Davidson Resilience Scale, and Pittsburgh Sleep Quality Index.

After LASSO regression selected 12 predictors from 29 variables, 11 machine learning algorithms were compared; SHAP analysis guided reduction to six features while preserving discriminative accuracy, with night shift frequency showing a nonlinear relationship with risk.
sources:
- peer_reviewed | Nursing Ethics | https://doi.org/10.1177/09697330261474090 | 2026-08-13
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

6635ae4d0e62521472eb7956a25a41aacc24ef1e6ccfb1a1d607b2be712f0d25

previous

0000000000000000000000000000000000000000000000000000000000000000