Dynamic treatment regime in critical ill patients with high risk of antibiotic drug resistance, a cohort study
Liu, Y.
Show abstract
Antibiotic resistance threatens modern medicine, especially in critical care. This retrospective observational cohort study, based on MIMIC-IV v2.0 database, included 2,532 ICU admissions with high - risk antibiotic resistance. We aimed to find the optimal strategy for using high - risk resisted antibiotics in critical ill patients by constructing a dynamic treatment regime (DTR) model with DWSurv method. The results showed that the DTR optimal models suggestion differed from clinical practice. Clinical practice showed a sharp decline in high - risk resistance antibiotic administration, while the model suggested treatment with gaps in 7 days. Survival analysis indicated that the DTR model had a lower mortality rate. The more the clinical practice disobeyed the models recommendation, the higher the 28 - day mortality (adjusted HR = 1.21, 95%CI: 1.12 - 1.30, P<0.001). This study suggests that the DTR model might offer a new perspective on personalized antibiotic administration, but its clinical application remains to be further explored.
Matching journals
The top 11 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Development of a Risk Prediction Model for Sepsis-Related Delirium Based on Multiple Machine Learning Approaches and an Online Calculator 95%
- Medium-term impacts of the waves of the COVID-19 epidemic on treatments for non-COVID-19 patients in intensive care units: a retrospective cohort study in Japan 95%
- Clinical pattern of antibiotic overuse and misuse in primary healthcare hospitals in the southwest of China 94%
Similar papers in this journal
- Machine Learning-based Clinical Decision Support for Infection Risk Prediction 92%
- Exploration of the link between COVID-19 and gastric cancer from the perspective of bioinformatics and systems biology 92%
- A Predictive Nomogram for In-ICU Deterioration of Stage 1 Pressure Injuries: A Retrospective Study 92%
Similar papers in this journal
- Species-specific bacterial detector for fast pathogen diagnosis of severe pneumonia patients in the intensive care unit 93%
- Data-driven methodology for discovery and response to pulmonary symptomology in hypertension through AI and machine learning: Application to COVID-19 related pharmacovigilance 92%
- A survey of optimal strategy for signature-based drug repositioning and an application to liver cancer 91%
Similar papers in this journal
Similar papers in this journal
- A Novel Triage Tool of Artificial Intelligence-Assisted Diagnosis Aid System for Suspected COVID-19 Pneumonia in Fever Clinics 95%
- Nosocomial Infections Among Patients with COVID-19, SARS and MERS: A Rapid Review and Meta-Analysis 90%
- Supportive Care for Patient with Respiratory Diseases: An Umbrella Review 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.