ArticleCommunications medicine2024
Applying a transformer architecture to intraoperative temporal dynamics improves the prediction of postoperative delirium.
Article in Communications medicine, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 14 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
14 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Machine Learning-Based prediction models for postoperative delirium: a systematic review and Meta-Analysis.BMC psychiatry · 2025Pooled it
- Benchmarking imputation methods on real-world clinical time series with simulated spatio-temporal missingness.Nature communications · 2026Article
- A hierarchical clinical fusion transformer model for personalized opioid treatment: Development and validation in diabetic surgical patients.medRxiv : the preprint server for health sciences · 2026Article
- A dynamic risk prediction framework for Alzheimer's disease and related dementias with interpretability.NPJ digital medicine · 2026Article
- Integrating large language models for enhanced predictive analytics in healthcare.NPJ digital medicine · 2026Article
- Multi-output LSTM-based prediction of postoperative delirium: integrating baseline and perioperative data for enhanced risk stratification in older spine surgery patients.BioData mining · 2026Article
- Predicting postoperative delirium after lung cancer resection: the utility of synthetic data and LIME algorithm for model interpretation.Scientific reports · 2026Article
- Multimodal data for predictive medicine: algorithmic fusion of clinical data in anesthesiology and intensive care.Frontiers in medicine · 2026Article
- Large language models in emergency and critical care medicine: a comprehensive review of applications, challenges, and future directions.Burns & trauma · 2026Review
- Fusion of clinical magnet resonance images and electronic health records promotes multimodal predictions of postoperative delirium.Scientific reports · 2025Article
- Natural language processing techniques to detect delirium in hospitalized patients from clinical notes: a systematic review.NPJ digital medicine · 2025Article
- Development of a deep learning-based prediction model for postoperative delirium using intraoperative electroencephalogram in adults.NPJ digital medicine · 2025Article
- A large language model for delirium prediction in the intensive care unit using structured electronic health records.Scientific reports · 2025Article
- Explainable machine learning for predicting ICU mortality in myocardial infarction patients using pseudo-dynamic data.Scientific reports · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
7 authors.
Funding
Abstract
backgroundPatients who experienced postoperative delirium (POD) are at higher risk of poor outcomes like dementia or death. Previous machine learning models predicting POD mostly relied on time-aggregated features. We aimed to assess the potential of temporal patterns in clinical parameters during surgeries to predict POD.
methodsLong short-term memory (LSTM) and transformer models, directly consuming time series, were compared to multi-layer perceptrons (MLPs) trained on time-aggregated features. We also fitted hybrid models, fusing either LSTM or transformer models with MLPs. Univariate Spearman's rank correlations and linear mixed-effect models establish the importance of individual features that we compared to transformers' attention weights.
resultsBest performance is achieved by a transformer architecture ingesting 30 min of intraoperative parameter sequences. Systolic invasive blood pressure and given opioids mark the most important input variables, in line with univariate feature importances.
conclusionsIntraoperative temporal dynamics of clinical parameters, exploited by a transformer architecture named TRAPOD, are critical for the accurate prediction of POD.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.