Prediction and risk assessment of sepsis-associated encephalopathy in ICU based on interpretable machine learning
Problem
Sepsis-associated encephalopathy is a dangerous complication of sepsis in ICU patients with high mortality, and clinicians lacked a tool to predict which patients would develop it.
Why it matters
SAE is associated with high mortality and poor long-term prognosis, so early prediction could guide ICU care.
What the AI did
Six machine learning classifiers with Bayesian-optimized hyperparameters were trained to predict SAE occurrence after ICU admission; physicians evaluated the model outputs for interpretability.
Results
not stated in source
Impact
Evidence supports development of a prediction model; clinical adoption or outcome improvement is not stated.
Record
| Venue | Scientific Reports |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Lu Xiao, Hongyu Kang, Dawei Zhou, Qin Li |
| Citations | 30 (OpenAlex, at import time) |
| References | 25 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41598-022-27134-6 |
| Open access | gold |
| Keywords | sepsis, encephalopathy, machine learning, ICU, prediction, interpretability |
Importance rating
significant — thousands to millions affected
Abstract states SAE is a major sepsis complication associated with high mortality and poor long-term prognosis; prediction could guide ICU care, but no scale given.