BMC Medical Informatics and Decision Making最新文献

Background: Early identification of septic patients who will require vasopressor support could provide a critical window for hemodynamic optimisation, yet current bedside cues often appear only when shock is imminent.

Objective: We aimed to develop and validate an interpretable electronic health record (EHR)-based machine-learning model that predicts vasopressor initiation several hours before therapy in intensive care unit (ICU) patients with sepsis.

Methods: We conducted a retrospective study using the MIMIC-IV v2.2 database (2008-2019). We screened adult Sepsis-3 ICU stays and labeled the patients who commenced continuous vasopressor infusions 6 to 48 hours after admission as cases; we defined controls as sepsis patients with ICU stays ≥48 hours and no vasopressor exposure. We performed one to one nearest neighbour matching on age, sex, Charlson index, SOFA score with the cardiovascular component removed, weight, and early lactate/hematocrit availability to minimise confounding. We engineered demographic, physiological, and laboratory features measured from -6 to -2 hours relative to vasopressor initiation (or a matched time point) under multiple parameter combinations. We trained seven algorithms with Monte Carlo cross validation and evaluated performance on an independent validation set. We assessed model interpretability with Shapley values.

Results: We analyzed 1,539 cases and 1,431 controls; the independent validation set comprised 751 stays (~25%). A Random Forest classifier achieved an area under the receiver operating characteristic (AUROC) of 0.75 (95% CI, 0.72-0.79), a sensitivity of 0.74 (95% CI, 0.69-0.78), a specificity of 0.65 (95% CI, 0.60-0.70), a precision of 0.70 (95% CI, 0.66-0.74) and a F1 score of 0.72 (95% CI, 0.68-0.75) at the Youden's index threshold. The model outperformed simple surrogates-mean blood pressure (AUROC, 0.68; 95% CI, 0.64-0.72) and modified shock index (AUROC, 0.65; 95% CI, 0.62-0.69)-and a reproduced bidirectional LSTM (AUROC, 0.73; 95% CI, 0.70-0.77). Key predictors included declining mean blood pressure at - 2 to -4 hours, elevated lactate ( > 2.5 mmol/L), and hematocrit outside 30-37%. Model alerts would occur two to four hours before vasopressor initiation, providing actionable lead time for clinicians.

Conclusions: This proof-of-concept study shows that routinely collected ICU data can predict impending vasopressor initiation with clinically interpretable outputs. However, these findings reflect internal validation only and should be interpreted with caution. External validation on multi-center retrospective cohorts, followed by silent-mode prospective evaluation, is warranted to confirm generalisability and to assess the real-world impact on time-to-vasopressor, fluid balance, and patient outcomes.

Introduction: Electronic prescribing, allows physicians to send prescriptions digitally to pharmacies and laboratories. This process streamlines patient care and ensures equitable access to medical services for all patients. This study aims to do the usability evaluation of Social Security electronic prescription system (SSEPS) and Health Insurance electronic prescription system (HIEPS) using insights from users and experts.

Methods: This research is a descriptive cross-sectional study conducted in 2024. Three experts evaluated two electronic prescribing systems using Nielsen's Heuristic evaluation principles, rating issues on a 0-4 severity scale. The usability evaluation, conducted with fifty users via the Persian SUS, showed that the translated instrument was highly reliable (α = 0.79). Expert and user feedback were compared across 2 systems using SPSS to identify usability improvements.

Results: Based on heuristic evaluation, HIEPS demonstrates better consistency, but significant improvements in error prevention and user control remain priorities for both systems. Usability testing using the SUS revealed a slightly higher average score for the SSEPS (70.73) than the HIEPS (69.21). The significant P-value indicates this difference reflects a real distinction in perceived usability between the two systems.

Conclusion: E-prescription systems, despite their widespread use, continue to face usability issues that risk patient safety, reduce efficiency, and impact user satisfaction and hospital finances. Combining user and expert evaluations is more effective in identifying these issues than using a single method. Annual usability assessments and updates are recommended to address these challenges and improve system performance.

Sepsis, a critical infection-induced inflammatory condition, poses substantial global health challenges, demanding timely detection for effective intervention. This article explores the application of machine learning (ML) and deep learning (DL) in predicting sepsis using electronic health record (EHR) to enhance patient outcomes. A comprehensive search across PubMed, IEEE Xplore, Google Scholar, and Scopus yielded 39 studies meeting stringent inclusion criteria. Predominantly retrospective (n = 34) and geographically diverse, these studies, spanning North America (n=19), Asia (n=13), Europe (n=6), and Australia (n=1), exhibited varied datasets, sepsis definitions, and prevalence rates, necessitating data augmentation strategies. Heterogeneous parameter usage, diverse model distribution, and inconsistent quality assessments were identified. Despite differences, longitudinal data showcased the potential of early sepsis prediction. The review outlines the challenges posed by disparate funding and article quality correlation, emphasizing the need for standardized evaluation metrics. In conclusion, this systematic review highlights the promising role of ML/DL methodologies in sepsis detection and early prediction through EHR, underscoring the imperative for standardized approaches and comprehensive quality assessments.

Background: Metastasis significantly influences prognosis in thyroid cancer, especially in papillary thyroid carcinoma. With the rise of artificial intelligence (AI) in medical diagnostics, machine learning (ML) and deep learning (DL) models are being increasingly explored for their ability to enhance the early detection of metastatic spread. This systematic review and meta-analysis aimed to evaluate the diagnostic performance of ML and DL algorithms in detecting metastasis in thyroid cancer.

Method: We conducted a comprehensive search of scientific databases, including PubMed, IEEE, Scopus, and Web of Science, covering literature up to July 1st, 2025. This review included studies published in English that used diagnostic models for metastasis in adults with thyroid cancer. Key metrics analyzed were the area under the receiver operating characteristic curve (AUC-ROC) sensitivity, specificity, and the diagnostic odds ratio (DOR) with a 95% confidence interval (CI). Heterogeneity was quantified using I² statistics, and subgroup and moderator analyses were conducted to identify sources of variability. Risk of bias was assessed using the PROBAST tool. Bias risk and concerns were evaluated using the PROBAST checklist. This study was registered with PROSPERO (CRD42024622930).

Results: Thirty-five studies encompassing 162 estimates were included. The pooled sensitivity was 0.747 (95% CI: 0.715-0.775) and specificity was 0.746 (95% CI: 0.706-0.783). The pooled DOR was 9.45 (95% CI: 7.27-12.28), indicating a strong association between AI predictions and actual metastatic status. The overall AUC-ROC was 0.818. Subgroup analysis demonstrated particularly high accuracy in models targeting distant metastasis. ML models showed slightly higher discriminative ability compared to DL models, and robust performance was observed across a variety of cancer subtypes and input data sources. Moderator analysis further confirmed the stability and adaptability of these models under different clinical and technical settings.

Conclusion: ML and DL algorithms demonstrate favorable diagnostic performance in identifying metastasis in thyroid cancer and may serve as supportive tools in clinical decision-making. Their consistent results across different metastasis types and technical settings highlight their potential to complement existing diagnostic approaches. These findings encourage further exploration and refinement of AI-based methods for integration into routine oncologic practice.