Early Prediction of Positive Hospital-Acquired MRSA Screening using Deep Learning on Vital Signs Time Series
Bibliographic record
Abstract
Methicillin-Resistant Staphylococcus Aureus (MRSA) is a major cause of Hospital-Acquired Infections (HAIs), leading to increased morbidity, mortality, and healthcare costs. Early detection is critical for timely intervention, yet current diagnostic methods rely on laboratory testing, which can delay necessary treatments. This study proposes a deep learning-based approach to predict positive MRSA screening outcomes using only time-series vital signs data. Utilizing the MIMIC-IV database, we developed a Bidirectional Long Short-Term Memory (BiLSTM) model trained on six key vital signs: body temperature, heart rate, systolic and diastolic blood pressure, respiratory rate, and oxygen saturation. The model was evaluated across different prediction windows and lookback periods to assess its ability to detect positive MRSA screening before the laboratory confirmation. Results show that a 1-day prediction window achieved an F1-score of 89.19% and an Area Under Receiver Operating Characteristic (AUROC) of 0.96, outperforming the models with 3-day prediction window, which attained an F1-score of 82.67% and an AUROC of 0.93. Compared to recent related studies on the same dataset, this study achieved an overall higher performance. The findings indicate that recent fluctuations in vital signs hold predictive value for early MRSA detection. This approach offers a non-invasive, real-time solution to assist infection control practitioners in proactively mitigating MRSA transmission risks. Using readily available physiological data, this study demonstrates the potential of AI-driven early warning systems in healthcare settings, improving patient outcomes and resource allocation. Future work will focus on integrating additional clinical parameters and enhancing model generalizability across diverse healthcare environments.Clinical relevance - This study introduces a rapid, AI-driven method for predicting positive MRSA screening using only vital signs, enabling early intervention before laboratory confirmation. Implementing such a system in clinical practice could enhance infection control strategies, reduce HAIs, and improve patient safety.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".