Development and Validation of a Machine Learning Model to Estimate Bacterial Sepsis Among Immunocompromised Recipients of Stem Cell Transplant

Sepsis death risk factor score based on systemic inflammatory response syndrome, quick sequential organ failure assessment, and comorbidities

OBJECTIVE

In this study, we aimed to evaluate the death risk factors of patients included in the sepsis protocol bundle, using clinical data from qSOFA, SIRS, and comorbidities, as well as development of a mortality risk score.

DESIGN

This retrospective cohort study was conducted between 2016 and 2021.

SETTING

Two university hospitals in Brazil.

PARTICIPANTS

Patients with sepsis.

INTERVENTIONS

Several clinical and laboratory data were collected focused on SIRS, qSOFA, and comorbidities.

MAIN VARIABLE OF INTEREST

In-hospital mortality was the primary outcome variable. A mortality risk score was developed after logistic regression analysis.

RESULTS

A total of 1,808 patients were included with a death rate of 36%. Ten variables remained independent factors related to death in multivariate analysis: temperature ≥38 °C (odds ratio [OR] = 0.65), previous sepsis (OR = 1.42), qSOFA ≥ 2 (OR = 1.43), leukocytes >12,000 or <4,000 cells/mm3 (OR = 1.61), encephalic vascular accident (OR = 1.88), age >60 years (OR = 1.93), cancer (OR = 2.2), length of hospital stay before sepsis >7 days (OR = 2.22,), dialysis (OR = 2.51), and cirrhosis (OR = 3.97). Considering the equation of the binary regression logistic analysis, the score presented an area under curve of 0.668, is not a potential model for death prediction.

CONCLUSIONS

Several risk factors are independently associated with mortality, allowing the development of a prediction score based on qSOFA, SIRS, and comorbidities data, however, the performance of this score is low.

Improving management of febrile neutropenia in oncology patients: the role of artificial intelligence and machine learning

INTRODUCTION

Artificial intelligence (AI) and machine learning (ML) have the potential to revolutionize the management of febrile neutropenia (FN) and drive progress toward personalized medicine.

AREAS COVERED

In this review, we detail how the collection of a large number of high-quality data can be used to conduct precise mathematical studies with ML and AI. We explain the foundations of these techniques, covering the fundamentals of supervised and unsupervised learning, as well as the most important challenges, e.g. data quality, 'black box' model interpretation and overfitting. To conclude, we provide detailed examples of how AI and ML have been used to enhance predictions of chemotherapy-induced FN, detection of bloodstream infections (BSIs) and multidrug-resistant (MDR) bacteria, and anticipation of severe complications and mortality.

EXPERT OPINION

There is promising potential of implementing accurate AI and ML models whilst managing FN. However, their integration as viable clinical tools poses challenges, including technical and implementation barriers. Improving global accessibility, fostering interdisciplinary collaboration, and addressing ethical and security considerations are essential. By overcoming these challenges, we could transform personalized care for patients with FN.

Prognostic Factors and Outcomes in Patients With Septic Shock After Allogeneic Hematopoietic Stem Cell Transplantation

Septic shock remains a potentially life-threatening complication among allogeneic hematopoietic stem cell transplant (allo-HSCT) recipients. There is a paucity of information on the clinical characteristics, outcome and prognostic factors of septic shock patients after allo-HSCT. We aimed to describe the clinical characteristics of septic shock after allo-HSCT and its associated health outcomes and to evaluate the role of patient demographics, transplantation-related laboratory and clinical variables associated with the short-term mortality of septic shock after allo-HSCT. We retrospectively studied 242 septic shock patients from 6105 consecutive patients allografted between 2007 and 2021. We assessed 29 risk factors as candidate predictors and used multivariable logistic regression to establish clinical model. The primary outcome was 28-day mortality. The median age of the subjects was 34 (IQR 24 to 45) years. A total of 148 patients (61.2%) had positive blood cultures. Gram-negative bacilli accounted for 61.5% of the positive isolates, gram-positive cocci accounted for 12.2%, and fungi accounted for 6.1%. Coinfections were found in 30 (20.3%) patients. Escherichia coli was the dominant isolated pathogen (31.1%), followed by Pseudomonas spp. (12.8%) and Klebsiella pneumoniae (10.1%). With a median follow-up of 34 (IQR: 2 to 528) days, a total of 142 (58.7%) patients died, of whom 118 (48.8%) died within the first 28 days after septic shock diagnosis, 131 (54.1%) died within 90 days, and 141 (58.3%) died within 1 year. A large majority of deaths (83.1% [118/142]) occurred within 28 days of septic shock diagnosis. Finally, 6 independent predictive variables of 28-day mortality were identified by multivariable logistic regression: time of septic shock, albumin, bilirubin, PaO2/FiO2, lactate, and sepsis-induced coagulopathy. Patients with late onset shock had higher 28-day mortality rates (64.6% versus 25.5%, P < .001) and more ICU admission (32.6% versus 7.1%, P < .001) than those with early onset shock. We highlight the poor survival outcomes in patients who develop septic shock, emphasizing the need for increasing awareness regarding septic shock after allo-HSCT. The information from the current study may help to assist clinicians in identifying high-risk patients.

Risk Management and Patient Safety in the Artificial Intelligence Era: A Systematic Review

BACKGROUND

Healthcare systems represent complex organizations within which multiple factors (physical environment, human factor, technological devices, quality of care) interconnect to form a dense network whose imbalance is potentially able to compromise patient safety. In this scenario, the need for hospitals to expand reactive and proactive clinical risk management programs is easily understood, and artificial intelligence fits well in this context. This systematic review aims to investigate the state of the art regarding the impact of AI on clinical risk management processes. To simplify the analysis of the review outcomes and to motivate future standardized comparisons with any subsequent studies, the findings of the present review will be grouped according to the possibility of applying AI in the prevention of the different incident type groups as defined by the ICPS.

MATERIALS AND METHODS

On 3 November 2023, a systematic review of the literature according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines was carried out using the SCOPUS and Medline (via PubMed) databases. A total of 297 articles were identified. After the selection process, 36 articles were included in the present systematic review.

RESULTS AND DISCUSSION

The studies included in this review allowed for the identification of three main "incident type" domains: clinical process, healthcare-associated infection, and medication. Another relevant application of AI in clinical risk management concerns the topic of incident reporting.

CONCLUSIONS

This review highlighted that AI can be applied transversely in various clinical contexts to enhance patient safety and facilitate the identification of errors. It appears to be a promising tool to improve clinical risk management, although its use requires human supervision and cannot completely replace human skills. To facilitate the analysis of the present review outcome and to enable comparison with future systematic reviews, it was deemed useful to refer to a pre-existing taxonomy for the identification of adverse events. However, the results of the present study highlighted the usefulness of AI not only for risk prevention in clinical practice, but also in improving the use of an essential risk identification tool, which is incident reporting. For this reason, the taxonomy of the areas of application of AI to clinical risk processes should include an additional class relating to risk identification and analysis tools. For this purpose, it was considered convenient to use ICPS classification.

Longitudinal clinical data improve survival prediction after hematopoietic cell transplantation using machine learning

ABSTRACT

Serial prognostic evaluation after allogeneic hematopoietic cell transplantation (allo-HCT) might help identify patients at high risk of lethal organ dysfunction. Current prediction algorithms based on models that do not incorporate changes to patients' clinical condition after allo-HCT have limited predictive ability. We developed and validated a robust risk-prediction algorithm to predict short- and long-term survival after allo-HCT in pediatric patients that includes baseline biological variables and changes in the patients' clinical status after allo-HCT. The model was developed using clinical data from children and young adults treated at a single academic quaternary-care referral center. The model was created using a randomly split training data set (70% of the cohort), internally validated (remaining 30% of the cohort) and then externally validated on patient data from another tertiary-care referral center. Repeated clinical measurements performed from 30 days before allo-HCT to 30 days afterwards were extracted from the electronic medical record and incorporated into the model to predict survival at 100 days, 1 year, and 2 years after allo-HCT. Naïve-Bayes machine learning models incorporating longitudinal data were significantly better than models constructed from baseline variables alone at predicting whether patients would be alive or deceased at the given time points. This proof-of-concept study demonstrates that unlike traditional prognostic tools that use fixed variables for risk assessment, incorporating dynamic variability using clinical and laboratory data improves the prediction of mortality in patients undergoing allo-HCT.

Prediction of Multiple Clinical Complications in Cancer Patients to Ensure Hospital Preparedness and Improved Cancer Care

Reliable and rapid medical diagnosis is the cornerstone for improving the survival rate and quality of life of cancer patients. The problem of clinical decision-making pertaining to the management of patients with hematologic cancer is multifaceted and intricate due to the risk of therapy-induced myelosuppression, multiple infections, and febrile neutropenia (FN). Myelosuppression due to treatment increases the risk of sepsis and mortality in hematological cancer patients with febrile neutropenia. A high prevalence of multidrug-resistant organisms is also noted in such patients, which implies that these patients are left with limited or no-treatment options amidst severe health complications. Hence, early screening of patients for such organisms in their bodies is vital to enable hospital preparedness, curtail the spread to other weak patients in hospitals, and limit community outbreaks. Even though predictive models for sepsis and mortality exist, no model has been suggested for the prediction of multidrug-resistant organisms in hematological cancer patients with febrile neutropenia. Hence, for predicting three critical clinical complications, such as sepsis, the presence of multidrug-resistant organisms, and mortality, from the data available from medical records, we used 1166 febrile neutropenia episodes reported in 513 patients. The XGboost algorithm is suggested from 10-fold cross-validation on 6 candidate models. Other highlights are (1) a novel set of easily available features for the prediction of the aforementioned clinical complications and (2) the use of data augmentation methods and model-scoring-based hyperparameter tuning to address the problem of class disproportionality, a common challenge in medical datasets and often the reason behind poor event prediction rate of various predictive models reported so far. The proposed model depicts improved recall and AUC (area under the curve) for sepsis (recall = 98%, AUC = 0.85), multidrug-resistant organism (recall = 96%, AUC = 0.91), and mortality (recall = 86%, AUC = 0.88) prediction. Our results encourage the need to popularize artificial intelligence-based devices to support clinical decision-making.

Development and assessment of novel machine learning models to predict medication non-adherence risks in type 2 diabetics

Background

Medication adherence is the main determinant of effective management of type 2 diabetes, yet there is no gold standard method available to screen patients with high-risk non-adherence. Developing machine learning models to predict high-risk non-adherence in patients with T2D could optimize management.

Methods

This cross-sectional study was carried out on patients with T2D at the Sichuan Provincial People's Hospital from April 2018 to December 2019 who were examined for HbA1c on the day of the survey. Demographic and clinical characteristics were extracted from the questionnaire and electronic medical records. The sample was randomly divided into a training dataset and a test dataset with a radio of 8:2 after data preprocessing. Four imputing methods, five sampling methods, three screening methods, and 18 machine learning algorithms were used to groom data and develop and validate models. Bootstrapping was performed to generate the validation set for external validation and univariate analysis. Models were compared on the basis of predictive performance metrics. Finally, we validated the sample size on the best model.

Results

This study included 980 patients with T2D, of whom 184 (18.8%) were defined as medication non-adherence. The results indicated that the model used modified random forest as the imputation method, random under sampler as the sampling method, Boruta as the feature screening method and the ensemble algorithms and had the best performance. The area under the receiver operating characteristic curve (AUC), F1 score, and area under the precision-recall curve (AUPRC) of the best model, among a total of 1,080 trained models, were 0.8369, 0.7912, and 0.9574, respectively. Age, present fasting blood glucose (FBG) values, present HbA1c values, present random blood glucose (RBG) values, and body mass index (BMI) were the most significant contributors associated with risks of medication adherence.

Conclusion

We found that machine learning methods could be used to predict the risk of non-adherence in patients with T2D. The proposed model was well performed to identify patients with T2D with non-adherence and could help improve individualized T2D management.

Bring it on: Top five antimicrobial stewardship challenges in transplant infectious diseases and practical strategies to address them

Antimicrobial therapies are essential tools for transplant recipients who are at high risk for infectious complications. However, judicious use of antimicrobials is critical to preventing the development of antimicrobial resistance. Treatment of multidrug-resistant organisms is challenging and potentially leads to therapies with higher toxicities, intravenous access, and intensive drug monitoring for interactions. Antimicrobial stewardship programs are crucial in the prevention of antimicrobial resistance, though balancing these strategies with the need for early and frequent antibiotic therapy in these immunocompromised patients can be challenging. In this review, we summarize 5 frequently encountered transplant infectious disease stewardship challenges, and we suggest strategies to improve practices for each clinical syndrome. These 5 challenging areas are: asymptomatic bacteriuria in kidney transplant recipients, febrile neutropenia in hematopoietic stem cell transplantation, antifungal prophylaxis in liver and lung transplantation, treatment of left-ventricular assist device infections, and Clostridioides difficile infection in solid-organ and hematopoietic stem-cell transplant recipients. Common themes contributing to these challenges include limited data specific to transplant patients, shortcomings in diagnostic testing, and uncertainties in pharmacotherapy.

Artificial intelligence model comparison for risk factor analysis of patent ductus arteriosus in nationwide very low birth weight infants cohort

Despite the many comorbidities and high mortality rate in preterm infants with patent ductus arteriosus (PDA), therapeutic strategies vary depending on the clinical setting, and most studies of the related risk factors are based on small sample populations. We aimed to compare the performance of artificial intelligence (AI) analysis with that of conventional analysis to identify risk factors associated with symptomatic PDA (sPDA) in very low birth weight infants. This nationwide cohort study included 8369 very low birth weight (VLBW) infants. The participants were divided into an sPDA group and an asymptomatic PDA or spontaneously close PDA (nPDA) group. The sPDA group was further divided into treated and untreated subgroups. A total of 47 perinatal risk factors were collected and analyzed. Multiple logistic regression was used as a standard analytic tool, and five AI algorithms were used to identify the factors associated with sPDA. Combining a large database of risk factors from nationwide registries and AI techniques achieved higher accuracy and better performance of the PDA prediction tasks, and the ensemble methods showed the best performances.