Early prediction of sepsis in intensive care patients using the machine learning algorithm NAVOY® Sepsis, a prospective randomized clinical validation study

Development and Validation of a Machine Learning Model for Early Prediction of Sepsis Onset in Hospital Inpatients from All Departments

Background: With 11 million sepsis-related deaths worldwide, the development of tools for early prediction of sepsis onset in hospitalized patients is a global health priority. We developed a machine learning algorithm, capable of detecting the early onset of sepsis in all hospital departments. Methods: Predictors of sepsis from 45,127 patients from all departments of Valenciennes Hospital (France) were retrospectively collected for training. The binary classifier SEPSI Score for sepsis prediction was constructed using a gradient boosted trees approach, and assessed on the study dataset of 5270 patient stays, including 121 sepsis cases (2.3%). Finally, the performance of the model and its ability to detect early sepsis onset were evaluated and compared with existing sepsis scoring systems. Results: The mean positive predictive value of the SEPSI Score was 0.610 compared to 0.174 for the SOFA (Sepsis-related Organ Failure Assessment) score. The mean area under the precision-recall curve was 0.738 for SEPSI Score versus 0.174 for the most efficient score (SOFA). High sensitivity (0.845) and specificity (0.987) were also reported for SEPSI Score. The model was more accurate than all tested scores, up to 3 h before sepsis onset. Half of sepsis cases were detected by the model at least 48 h before their medically confirmed onset. Conclusions: The SEPSI Score model accurately predicted the early onset of sepsis, with performance exceeding existing scoring systems. It could be a valuable predictive tool in all hospital departments, allowing early management of sepsis patients. Its impact on associated morbidity-mortality needs to be further assessed.

Assessing the performance of chat generative pretrained transformer (ChatGPT) in answering chronic kidney disease-related questions

BACKGROUND

Chatbots produced by artificial intelligence are frequently used in health information today. We aimed to investigate the reliability and reproducibility of the answers given by Chat Generative Pretrained Transformer (ChatGPT), one of the most used chatbots, to frequently asked questions related to chronic kidney failure.

METHODS

We reviewed frequently asked questions related to chronic kidney disease (CKD) from social media platforms and Internet. The questions were asked to ChatGPT, and the answers were scored from 1 to 4 by two experienced nephrologists.

RESULTS

Eighty-five frequently asked questions about chronic renal failure were examined and 60 of them were included in the study after exclusion criteria. Fifty-one (85%) of the questions received 1 point, 7 (11.7%) received 2 points and 2 (3.3%) received 3 points. The similarity rates of the answers to the repeated questions were between 80% and 100%.

CONCLUSION

ChatGPT has provided reliable responses with high reproducibility to inquiries related to CKD.

Advances and Challenges in Sepsis Management: Modern Tools and Future Directions

Sepsis, a critical condition marked by systemic inflammation, profoundly impacts both innate and adaptive immunity, often resulting in lymphopenia. This immune alteration can spare regulatory T cells (Tregs) but significantly affects other lymphocyte subsets, leading to diminished effector functions, altered cytokine profiles, and metabolic changes. The complexity of sepsis stems not only from its pathophysiology but also from the heterogeneity of patient responses, posing significant challenges in developing universally effective therapies. This review emphasizes the importance of phenotyping in sepsis to enhance patient-specific diagnostic and therapeutic strategies. Phenotyping immune cells, which categorizes patients based on clinical and immunological characteristics, is pivotal for tailoring treatment approaches. Flow cytometry emerges as a crucial tool in this endeavor, offering rapid, low cost and detailed analysis of immune cell populations and their functional states. Indeed, this technology facilitates the understanding of immune dysfunctions in sepsis and contributes to the identification of novel biomarkers. Our review underscores the potential of integrating flow cytometry with omics data, machine learning and clinical observations to refine sepsis management, highlighting the shift towards personalized medicine in critical care. This approach could lead to more precise interventions, improving outcomes in this heterogeneously affected patient population.

Artificial Intelligence for Mechanical Ventilation: A Transformative Shift in Critical Care

With the large volume of data coming from implemented technologies and monitoring systems, intensive care units (ICUs) represent a key area for artificial intelligence (AI) application. Despite the last decade has been marked by studies focused on the use of AI in medicine, its application in mechanical ventilation management is still limited. Optimizing mechanical ventilation is a complex and high-stake intervention, which requires a deep understanding of respiratory pathophysiology. Therefore, this complex task might be supported by AI and machine learning. Most of the studies already published involve the use of AI to predict outcomes for mechanically ventilated patients, including the need for intubation, the respiratory complications, and the weaning readiness and success. In conclusion, the application of AI for the management of mechanical ventilation is still at an early stage and requires a cautious and much less enthusiastic approach. Future research should be focused on AI progressive introduction in the everyday management of mechanically ventilated patients, with the aim to explore the great potentiality of this tool.