Hugo Armando Guillen-Ramirez

Objectives: Infections following healthcare-associated interventions drive patient morbidity and mortality, making early detection essential. Traditional predictive models utilize preoperative surgical characteristics. This study evaluated whether integrating postoperative laboratory values and their kinetics could improve outcome prediction. Materials and Methods: 91,794 surgical cases were extracted from electronic health records (EHR) and analyzed to predict bacterial infection as the endpoint. The endpoint was documented in the EHR as ICD-10 by a professional coding team. Variables were grouped as preoperative, intraoperative, or postoperative. Strategic imputation was used for postoperative missing laboratory values. Procedure-agnostic prediction models were built incorporating both static and kinetic properties of laboratory values. Results: The integration of kinetics of laboratory values into a machine learning predictor achieved a recall, precision and ROC AUC at postoperative day 2 of 0.71, 0.69, and 0.83, respectively. Moreover, infection detection outperformed clinician-based decision-making, as reflected by the postoperative timing of antibiotic administration. The analysis identified previously unknown, informative combinations of routine markers from hepatic, renal, and bone marrow functions that predict outcome. Discussion: Dynamic modelling of postoperative laboratory values enhanced the timeliness and accuracy of infection detection compared with static or preoperative-only models. The integration of explainable machine learning supports clinical interpretation and highlights the contribution of multiple organ systems to postoperative infection risk. Conclusion: A surgery-independent workflow integrating time-series values from laboratory parameters to enhance baseline predictors of infection. This interpretable approach is generalizable across procedures and has the potential to optimize patient outcomes and resource use in surgical care.

Infections after surgery remain a leading cause of morbidity and mortality, yet reliable risk stratification at the end of surgery is limited. Intraoperative vital signs are continuously recorded in modern operating rooms but remain an underexploited source of real-time prognostic information. We developed and validated a machine-learning model integrating intraoperative vital-sign dynamics to predict postoperative infections immediately at the end of surgery. We extracted arterial blood pressure, heart rate, oxygen saturation, temperature, and end-tidal CO2 time-series from a clinical data warehouse, transforming these signals into interpretable summary, trend, and distributional descriptors. Using routine data from 10,719 surgical procedures, models incorporating interpretable intraoperative time-series features achieved an AUROC of 0.88 (95% CI, 0.85–0.91) for infection prediction at the end of surgery, significantly outperforming models based on preoperative variables alone. Model predictions were calibrated across major procedure clusters and interpretable through SHAP-based feature attribution. Our results demonstrate that intraoperative time-series data encode signatures of cumulative surgical and physiological stress, revealing early and clinically actionable signals of postoperative infection risk and enable an explainable machine-learning framework for perioperative monitoring systems.

Cross-lingual information retrieval limits global exchange of data because of the high diversity in the methods to classify, document and encode medical procedures. Traditional keyword-based or single-language systems are not able to align data from surgical and interventional procedures, especially from non-English healthcare systems. This study aims to develop a pipeline for cross-lingual retrieval and integration of medical procedures data. MAP-CARE is a novel framework that leverages Large Language Models (LLMs) for translating and transforming medical procedures into a unified multilingual embedding space. Semantic embeddings are used to enhance retrieval accuracy and interoperability across languages and healthcare systems. MAP-CARE demonstrated high accuracy in the translation and mapping of clinical terms. Its cross-language translation performance proved robust, achieving up to Acc@5 = 0.90 in translating procedure classification codes across English, German, French, and Italian. The cross-classification mapping workflow also showed high accuracy in aligning two different national procedure classifications, with exact and near matches exceeding 53.8% at the most granular level. MAP-CARE offers a flexible, scalable, and robust solution for the multilingual and cross-system integration of medical procedural data. Its innovative use of large language models combined with semantic embeddings sets a new standard for the accessibility and utility of multilingual medical information. The framework is designed for easy extension from a terminology file in CSV format and is publicly available.