Diagnostic performance of machine learning models using cell population data for the detection of sepsis: a comparative study

Glucocorticoid therapy for sepsis in the AI era: a survey on current and future approaches

Sepsis, a life-threatening medical condition, manifests as new or worsening organ failures due to a dysregulated host response to infection. Many patients with sepsis have manifested a hyperinflammatory phenotype leading to the identification of inflammatory modulation by corticosteroids as a key treatment modality. However, the optimal use of corticosteroids in sepsis treatment remains a contentious subject, necessitating a deeper understanding of their physiological and pharmacological effects. Our study conducts a comprehensive review of randomized controlled trials (RCTs) focusing on traditional corticosteroid treatment in sepsis, alongside an analysis of evolving clinical guidelines. Additionally, we explore the emerging role of artificial intelligence (AI) in medicine, particularly in diagnosing, prognosticating, and treating sepsis. AI's advanced data processing capabilities reveal new avenues for enhancing corticosteroid therapeutic strategies in sepsis. The integration of AI in sepsis treatment has the potential to address existing gaps in knowledge, especially in the application of corticosteroids. Our findings suggest that combining corticosteroid therapy with AI-driven insights could lead to more personalized and effective sepsis treatments. This approach holds promise for improving clinical outcomes and presents a significant advancement in the management of this complex and often fatal condition.

Machine learning-based clinical decision support using laboratory data

Artificial intelligence (AI) and machine learning (ML) are becoming vital in laboratory medicine and the broader context of healthcare. In this review article, we summarized the development of ML models and how they contribute to clinical laboratory workflow and improve patient outcomes. The process of ML model development involves data collection, data cleansing, feature engineering, model development, and optimization. These models, once finalized, are subjected to thorough performance assessments and validations. Recently, due to the complexity inherent in model development, automated ML tools were also introduced to streamline the process, enabling non-experts to create models. Clinical Decision Support Systems (CDSS) use ML techniques on large datasets to aid healthcare professionals in test result interpretation. They are revolutionizing laboratory medicine, enabling labs to work more efficiently with less human supervision across pre-analytical, analytical, and post-analytical phases. Despite contributions of the ML tools at all analytical phases, their integration presents challenges like potential model uncertainties, black-box algorithms, and deskilling of professionals. Additionally, acquiring diverse datasets is hard, and models' complexity can limit clinical use. In conclusion, ML-based CDSS in healthcare can greatly enhance clinical decision-making. However, successful adoption demands collaboration among professionals and stakeholders, utilizing hybrid intelligence, external validation, and performance assessments.

Detection of blasts using flags and cell population data rules on Beckman Coulter DxH 900 hematology analyzer in patients with hematologic diseases

OBJECTIVES

White blood cell (WBC)-related flags are essential for detecting abnormal cells including blasts in automated hematology analyzers (AHAs). Cell population data (CPD) may characterize each WBC population, and customized CPD rules can be also useful for detecting blasts. We evaluated the performance of WBC-related flags, customized CPD rules, and their combination for detecting blasts on the Beckman Coulter DxH 900 AHA (DxH 900, Beckman Coulter, Miami, Florida, USA).

METHODS

In a total of 239 samples from patients with hematologic diseases, complete blood count on DxH 900 and manual slide review (MSR) were conducted. The sensitivity, specificity, and efficiency of the five WBC-related flags, nine customized CPD rules, and their combination were evaluated for detecting blasts, in comparison with MSR.

RESULTS

Blasts were detected by MSR in 40 out of 239 (16.7 %) samples. The combination of flags and CPD rules showed the highest sensitivity compared with each of flags and CPD rules for detecting blasts (97.5 vs. 72.5 % vs. 92.5 %). Compared with any flag, the combination of flags and CPD rules significantly reduced false-negative samples from 11 to one for detecting blasts (27.5 vs. 2.5 %, p=0.002).

CONCLUSIONS

This is the first study that evaluated the performance of both flags and CPD rules on DxH 900. The customized CPD rules as well as the combination of flags and CPD rules outperformed WBC-related flags for detecting blasts on DxH 900. The customized CPD rules can play a complementary role for improving the capability of blast detection on DxH 900.

Machine learning algorithms in sepsis

Sepsis remains a significant global health challenge due to its high mortality and morbidity, compounded by the difficulty of early detection given its variable clinical manifestations. The integration of machine learning (ML) into laboratory medicine for timely sepsis identification and outcome forecasting is an emerging field of interest. This comprehensive review assesses the current body of research on ML applications for sepsis within the realm of laboratory diagnostics, detailing both their strengths and shortcomings. An extensive literature search was performed by two independent investigators across PubMed and Scopus databases, employing the keywords "Sepsis," "Machine Learning," and "Laboratory" without publication date limitations, culminating in January 2023. Each selected study was meticulously evaluated for various aspects, including its design, intent (diagnostic or prognostic), clinical environment, demographics, sepsis criteria, data gathering period, and the scope and nature of features, in addition to the ML methodologies and their validation procedures. Out of 135 articles reviewed, 39 fulfilled the criteria for inclusion. Among these, the majority (30 studies) were focused on devising ML algorithms for diagnosis, fewer (8 studies) on prognosis, and one study addressed both aspects. The dissemination of these studies across an array of journals reflects the interdisciplinary engagement in the development of ML algorithms for sepsis. This analysis highlights the promising role of ML in the early diagnosis of sepsis while drawing attention to the need for uniformity in validating models and defining features, crucial steps for ensuring the reliability and practicality of ML in clinical setting.

The unfolded protein response pathway as a possible link in the pathogenesis of COVID-19 and sepsis

The global impact of the COVID-19 pandemic has been substantial. Emerging evidence underscores a strong clinical connection between COVID-19 and sepsis. Numerous studies have identified the unfolded protein response (UPR) pathway as a crucial pathogenic pathway for both COVID-19 and sepsis, but it remains to be investigated whether this signaling pathway operates as a common pathogenic mechanism for both COVID-19 and sepsis. In this study, single-cell RNA-seq data and transcriptome data for COVID-19 and sepsis cases were downloaded from GEO (Gene Expression Omnibus). By analyzing the single-cell transcriptome data, we identified B cells as the critical cell subset and the UPR pathway as the critical signaling pathway. Based on the transcriptome data, a machine learning diagnostic model was then constructed using the interleaved genes of B-cell-related and UPR-pathway-related genes. We validated the diagnostic model using both internal and external datasets and found the accuracy and stability of this model to be extremely strong. Even after integrating our algorithmic model with the patient's clinical status, it continued to yield identical results, further emphasizing the reliability of this model. This study provides a novel molecular perspective on the pathogenesis of sepsis and COVID-19 at the single-cell level and suggests that these two diseases may share a common mechanism.

Association of serum phosphate and changes in serum phosphate with 28-day mortality in septic shock from MIMIC-IV database

This study aimed to investigate the relationship between serum phosphate levels, changes in serum phosphate levels, and 28-day mortality in patients with septic shock. In this retrospective study, data were collected from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database between 2008 and 2019. Patients were divided into three groups according to the tertiles of serum phosphate levels. Kaplan-Meier curves and log-rank test analyses were used for survival analysis. Multivariate logistic regression, and restricted cubic spline (RCS) curve were used to explore the association between serum phosphate, delta serum phosphate levels and 28-day mortality. In total, 3296 patients with septic shock were included in the study, and the 28-day mortality was 30.0%. Serum phosphate levels were significantly higher in the non-survivor group than in the survivor group. The Kaplan-Meier curves showed significant differences among the three groups. Multivariate logistic regression analysis and the RCS curve showed that serum phosphate levels were independently and positively associated with the 28-day mortality of septic shock. Non-survivors had higher delta serum phosphate levels than survivors. Survival analysis showed that patients with higher delta serum phosphate levels had higher 28-day mortality. A non-linear relationship was detected between delta serum phosphate and 28-day mortality with a point of inflection at - 0.3 mg/dL. Serum phosphate levels were positively and independently associated with 28-day mortality in septic shock. Delta serum phosphate level was a high-risk factor for patients with septic shock.